初始化
This commit is contained in:
4
tools/core/__init__.py
Normal file
4
tools/core/__init__.py
Normal file
@@ -0,0 +1,4 @@
|
||||
"""
|
||||
核心功能模块
|
||||
包含独立的功能脚本，可以在独立进程中运行
|
||||
"""
|
||||
0
tools/core/acid_stats/__init__.py
Normal file
0
tools/core/acid_stats/__init__.py
Normal file
610
tools/core/acid_stats/土地利用类型酸化统计表.py
Normal file
610
tools/core/acid_stats/土地利用类型酸化统计表.py
Normal file
@@ -0,0 +1,610 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
import os
|
||||
import arcpy
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
from collections import OrderedDict
|
||||
from openpyxl import Workbook
|
||||
from openpyxl.styles import Font
|
||||
from openpyxl.utils import get_column_letter
|
||||
from tools.config.arcgis_field_cal_code import codeblock_cal_shfj, codeblock_dltb_ejdl, codeblock_dltb_yjdl
|
||||
from tools.core.utils.excel_utils import ExcelStyleUtils
|
||||
|
||||
|
||||
yjdl_order = ["耕地", "园地", "林地", "草地", "其他"]
|
||||
ejdl_order = ["水田", "旱地", "水浇地", "果园", "茶园", "橡胶园", "其他园地"]
|
||||
|
||||
# --- 2. 辅助函数 ---
|
||||
# 等级计算
|
||||
def get_acidification_degree(delta_ph):
|
||||
"""根据ΔpH值判断酸化程度"""
|
||||
if pd.isna(delta_ph) or delta_ph == 0:
|
||||
return "-"
|
||||
# 请根据您的实际分级标准调整这里的阈值
|
||||
if delta_ph > 1.0:
|
||||
return "重度酸化"
|
||||
elif 0.5 < delta_ph <= 1.0:
|
||||
return "中度酸化"
|
||||
elif 0.3 < delta_ph <= 0.5:
|
||||
return "轻度酸化"
|
||||
elif -0.3 <= delta_ph <= 0.3:
|
||||
return "未酸化"
|
||||
else: # dPH < -0.3
|
||||
return "碱化"
|
||||
|
||||
# --- 3. 数据处理与分析 均值---
|
||||
def process_data_for_table5_3(gdb_path, mean_table_name, sample_table_name):
|
||||
"""
|
||||
【最终版 v2】: 增加对制图样点数的处理，以支持加权平均计算。
|
||||
"""
|
||||
print("【最终版 v2】开始处理数据...")
|
||||
|
||||
def clean_df(df, columns):
|
||||
# ... (此函数不变)
|
||||
for col in columns:
|
||||
df[col] = df[col].astype(str).str.strip()
|
||||
df.replace(['<Null>', 'None', '', '<空>'], np.nan, inplace=True)
|
||||
df.dropna(subset=columns, inplace=True)
|
||||
return df
|
||||
|
||||
# --- a. 处理样点数据，计算“样点均值” ---
|
||||
print("--> 步骤1: 计算样点均值...")
|
||||
sample_table_path = os.path.join(gdb_path, sample_table_name)
|
||||
sample_fields = ['YJDL', 'EJDL', 'dPH']
|
||||
df_samples = pd.DataFrame(arcpy.da.TableToNumPyArray(sample_table_path, sample_fields,'dPH>0.3', skip_nulls=False))
|
||||
df_samples = clean_df(df_samples, ['YJDL', 'EJDL'])
|
||||
|
||||
# 按 YJDL, EJDL 分组，计算 dPH 的均值
|
||||
df_sample_means = df_samples.groupby(['YJDL', 'EJDL'])['dPH'].mean().reset_index()
|
||||
df_sample_means.rename(columns={'dPH': '样点均值'}, inplace=True)
|
||||
print("样点均值计算完成。")
|
||||
|
||||
# --- b. 处理制图数据，获取“制图均值”和“制图样点数” ---
|
||||
print("--> 步骤2: 获取制图均值和样点数...")
|
||||
mean_table_path = os.path.join(gdb_path, mean_table_name)
|
||||
# **【核心修改】: 增加读取 COUNT 字段**
|
||||
mean_fields = ['YJDL', 'EJDL', 'MEAN', 'COUNT']
|
||||
df_map_data = pd.DataFrame(arcpy.da.TableToNumPyArray(mean_table_path, mean_fields, skip_nulls=False))
|
||||
df_map_data = clean_df(df_map_data, ['YJDL', 'EJDL'])
|
||||
df_map_data.rename(columns={'MEAN': '制图均值', 'COUNT': '制图样点数'}, inplace=True)
|
||||
print("制图数据获取完成。")
|
||||
|
||||
# --- c. 合并数据 ---
|
||||
print("--> 步骤3: 合并数据...")
|
||||
df_skeleton = pd.concat([
|
||||
df_sample_means[['YJDL', 'EJDL']],
|
||||
df_map_data[['YJDL', 'EJDL']]
|
||||
]).drop_duplicates().reset_index(drop=True)
|
||||
|
||||
df_final = pd.merge(df_skeleton, df_sample_means, on=['YJDL', 'EJDL'], how='left')
|
||||
# **【核心修改】: 合并整个 df_map_data，而不仅仅是均值列**
|
||||
df_final = pd.merge(df_final, df_map_data, on=['YJDL', 'EJDL'], how='left')
|
||||
|
||||
# --- d. 计算酸化程度 ---
|
||||
print("--> 步骤4: 计算酸化程度...")
|
||||
# **【核心修改】: 在计算酸化程度之前，先过滤掉不展示的行**
|
||||
# 我们只对 dPH 在酸化范围内 ( > 0.3) 的数据感兴趣
|
||||
# 但为了计算合计，我们需要保留所有数据，所以这一步只计算，不删除
|
||||
df_final['酸化程度_样本'] = df_final['样点均值'].apply(get_acidification_degree)
|
||||
df_final['酸化程度_制图'] = df_final['制图均值'].apply(get_acidification_degree)
|
||||
|
||||
# (可选) 按“一级地类”和“二级地类”排序
|
||||
in_ejdl_order = ejdl_order + [x for x in df_final['EJDL'].unique() if x not in ejdl_order]
|
||||
df_final["YJDL"] = pd.Categorical(df_final['YJDL'], categories=yjdl_order, ordered=True)
|
||||
df_final["EJDL"] = pd.Categorical(df_final['EJDL'], categories=in_ejdl_order, ordered=True)
|
||||
df_final.sort_values(['YJDL', 'EJDL'], inplace=True)
|
||||
|
||||
print("数据处理流程完成！")
|
||||
return df_final
|
||||
|
||||
|
||||
# --- 4. Excel 制表 均值---
|
||||
def write_to_excel_table5_3(df, output_path):
|
||||
"""
|
||||
将处理好的数据写入格式化的 Excel 文件。
|
||||
"""
|
||||
if df.empty:
|
||||
print("警告: 没有数据可以写入 Excel。")
|
||||
return
|
||||
|
||||
print(f"开始生成 Excel 报告到 '{output_path}'...")
|
||||
wb = Workbook()
|
||||
ws = wb.create_sheet("Mysheet", 0)
|
||||
ws.title = "不同土地利用类型pH变化统计"
|
||||
|
||||
# --- b. 绘制表头 ---
|
||||
ws.merge_cells('A1:B1'); ws['A1'] = '土地利用类型'
|
||||
ws.merge_cells('C1:F1'); ws['C1'] = 'ΔpH'
|
||||
|
||||
ws['A2'] = '一级'
|
||||
ws['B2'] = '二级'
|
||||
ws['C2'] = '样点均值'
|
||||
ws['D2'] = '酸化程度'
|
||||
ws['E2'] = '制图均值'
|
||||
ws['F2'] = '酸化程度'
|
||||
|
||||
# --- c. 填充数据 ---
|
||||
current_row = 3
|
||||
|
||||
# **【核心修改】: 先对整个DataFrame进行过滤，只保留需要展示的行**
|
||||
# 只有当“样点酸化程度”或“制图酸化程度”不为“未酸化”、“碱化”或“-”时，才展示该行
|
||||
acid_levels_to_show = ["轻度酸化", "中度酸化", "重度酸化"]
|
||||
df_to_write = df[
|
||||
df['酸化程度_样本'].isin(acid_levels_to_show) |
|
||||
df['酸化程度_制图'].isin(acid_levels_to_show)
|
||||
].copy() # 使用 .copy() 避免 SettingWithCopyWarning
|
||||
|
||||
for yl, group_yl_df in df_to_write.groupby('YJDL', sort=False, observed=False):
|
||||
|
||||
print(f"正在写入一级地类: {yl}...")
|
||||
yl_start_row = current_row
|
||||
|
||||
# 遍历该一级地类下的所有“二级地类”
|
||||
for _, row_data in group_yl_df.iterrows():
|
||||
ws.cell(row=current_row, column=2).value = row_data['EJDL']
|
||||
|
||||
# 填充样点数据
|
||||
sample_mean = row_data.get('样点均值')
|
||||
if pd.notna(sample_mean):
|
||||
ws.cell(row=current_row, column=3).value = f"{sample_mean:.2f}" if sample_mean > 0.3 else "-"
|
||||
ws.cell(row=current_row, column=4).value = row_data.get('酸化程度_样本', '-') if sample_mean > 0.3 else "-"
|
||||
else:
|
||||
ws.cell(row=current_row, column=3).value = "-"
|
||||
ws.cell(row=current_row, column=4).value = "-"
|
||||
|
||||
# 填充制图数据
|
||||
map_mean = row_data.get('制图均值')
|
||||
if pd.notna(map_mean):
|
||||
ws.cell(row=current_row, column=5).value = f"{map_mean:.2f}" if map_mean > 0.3 else "-"
|
||||
ws.cell(row=current_row, column=6).value = row_data.get('酸化程度_制图', '-') if map_mean > 0.3 else "-"
|
||||
else:
|
||||
ws.cell(row=current_row, column=5).value = "-"
|
||||
ws.cell(row=current_row, column=6).value = "-"
|
||||
|
||||
current_row += 1
|
||||
|
||||
# 计算并写入“合计”行
|
||||
if ws.cell(row=current_row-1, column=2).value in ["林地", "草地", "其他"]:
|
||||
ws.merge_cells(start_row=yl_start_row, start_column=1, end_row=yl_start_row, end_column=2)
|
||||
ws.cell(row=yl_start_row, column=1).value = yl
|
||||
continue
|
||||
|
||||
ws.cell(row=current_row, column=2).value = '合计'
|
||||
|
||||
# 计算合计行的均值 (均值的均值)
|
||||
total_sample_mean = group_yl_df['样点均值'].mean()
|
||||
|
||||
if pd.notna(total_sample_mean):
|
||||
ws.cell(row=current_row, column=3).value = f"{total_sample_mean:.2f}"
|
||||
ws.cell(row=current_row, column=4).value = get_acidification_degree(total_sample_mean)
|
||||
else:
|
||||
ws.cell(row=current_row, column=3).value = "-"
|
||||
ws.cell(row=current_row, column=4).value = "-"
|
||||
|
||||
# b. **【核心修正】: 计算合计行的“制图均值”(加权平均)**
|
||||
# 准备加权平均的分子和分母
|
||||
weighted_sum = 0
|
||||
total_count = 0
|
||||
|
||||
# 遍历当前一级地类分组中的每一行
|
||||
for _, row in group_yl_df.iterrows():
|
||||
mean_val = row.get('制图均值')
|
||||
count_val = row.get('制图样点数')
|
||||
|
||||
# 只有当均值和样点数都存在且有效时，才参与计算
|
||||
if pd.notna(mean_val) and pd.notna(count_val) and count_val > 0:
|
||||
weighted_sum += mean_val * count_val # Σ (mean * count)
|
||||
total_count += count_val # Σ (count)
|
||||
|
||||
# 计算加权平均值
|
||||
weighted_avg = (weighted_sum / total_count) if total_count > 0 else 0
|
||||
|
||||
if weighted_avg > 0:
|
||||
ws.cell(row=current_row, column=5).value = f"{weighted_avg:.2f}"
|
||||
ws.cell(row=current_row, column=6).value = get_acidification_degree(weighted_avg)
|
||||
else:
|
||||
ws.cell(row=current_row, column=5).value = "-"
|
||||
ws.cell(row=current_row, column=6).value = "-"
|
||||
|
||||
# 合并“一级地类”单元格
|
||||
if yl_start_row <= current_row:
|
||||
ws.merge_cells(start_row=yl_start_row, start_column=1, end_row=current_row, end_column=1)
|
||||
ws.cell(row=yl_start_row, column=1).value = yl
|
||||
|
||||
current_row += 1
|
||||
|
||||
# --- a. 定义样式 ---
|
||||
header_font = Font(name='等线', size=11, bold=True)
|
||||
|
||||
# --- d. 应用样式和调整列宽 ---
|
||||
max_col_letter = get_column_letter(ws.max_column)
|
||||
if current_row > 1: # 确保有数据才应用样式
|
||||
ExcelStyleUtils.set_style(ws, f'A1:{max_col_letter}{current_row-1}')
|
||||
ExcelStyleUtils.set_style(ws, f'A1:{max_col_letter}2', header_font)
|
||||
|
||||
print("正在自动调整列宽...")
|
||||
|
||||
# 自动调整列宽
|
||||
ExcelStyleUtils.auto_adjust_column_width(ws)
|
||||
|
||||
# --- e. 保存文件 ---
|
||||
wb.save(output_path)
|
||||
print("Excel 报告生成成功！")
|
||||
|
||||
|
||||
# --- 2. 数据处理与分析 (使用 Pandas) ---
|
||||
def process_data_for_table5_4(gdb_path, area_table_name, sample_table_name, target_area_dict):
|
||||
"""
|
||||
【最终修正版 v2】: 先建立统一的层级结构，再分别合并统计结果。
|
||||
"""
|
||||
print("【最终修正版 v2】开始处理数据...")
|
||||
|
||||
def clean_df(df, columns):
|
||||
# ... (此函数不变)
|
||||
for col in columns:
|
||||
df[col] = df[col].astype(str).str.strip()
|
||||
df.replace(['<Null>', 'None', '', '<空>'], np.nan, inplace=True)
|
||||
df.dropna(subset=columns, inplace=True)
|
||||
return df
|
||||
|
||||
# --- a. 从两个表中提取并建立唯一的 (YJDL, EJDL) 层级结构 "骨架" ---
|
||||
print("--> 步骤1: 建立统一的层级结构...")
|
||||
sample_table_path = os.path.join(gdb_path, sample_table_name)
|
||||
area_table_path = os.path.join(gdb_path, area_table_name)
|
||||
|
||||
df_samples_raw = pd.DataFrame(arcpy.da.TableToNumPyArray(sample_table_path, ['YJDL', 'EJDL'], skip_nulls=False))
|
||||
df_area_raw = pd.DataFrame(arcpy.da.TableToNumPyArray(area_table_path, ['YJDL', 'EJDL'], skip_nulls=False))
|
||||
|
||||
# 清理并合并两个表中的 (YJDL, EJDL) 组合
|
||||
df_samples_raw = clean_df(df_samples_raw, ['YJDL', 'EJDL'])
|
||||
df_area_raw = clean_df(df_area_raw, ['YJDL', 'EJDL'])
|
||||
|
||||
# 使用 concat 连接两个DataFrame，然后用 drop_duplicates 去除重复的组合
|
||||
df_skeleton = pd.concat([df_samples_raw, df_area_raw]).drop_duplicates().reset_index(drop=True)
|
||||
|
||||
if df_skeleton.empty:
|
||||
print("警告: 无法从源数据中建立任何有效的 (YJDL, EJDL) 层级结构。")
|
||||
return pd.DataFrame(), {}
|
||||
print(f"已建立包含 {len(df_skeleton)} 个唯一土壤类型的层级结构。")
|
||||
|
||||
# --- b. 独立统计样点数据 ---
|
||||
print("--> 步骤2: 独立统计样点数据...")
|
||||
df_samples = pd.DataFrame(arcpy.da.TableToNumPyArray(sample_table_path, ['EJDL', 'YJDL', 'dPH'], skip_nulls=False))
|
||||
df_samples = clean_df(df_samples, ['YJDL', 'EJDL'])
|
||||
|
||||
if not df_samples.empty:
|
||||
# ... (统计逻辑不变)
|
||||
bins = [-np.inf, -0.3, 0.3, 0.5, 1.0, np.inf]
|
||||
labels = ["碱化", "未酸化", "轻度酸化", "中度酸化", "重度酸化"]
|
||||
df_samples['SHFJ'] = pd.cut(df_samples['dPH'], bins=bins, labels=labels, right=True)
|
||||
sample_counts = df_samples.groupby(['YJDL', 'EJDL', 'SHFJ'], observed=False).size().reset_index(name='样点数')
|
||||
ts_total_samples = sample_counts.groupby(['YJDL', 'EJDL'])['样点数'].transform('sum')
|
||||
sample_counts['样点占比'] = (sample_counts['样点数'] / ts_total_samples) * 100
|
||||
df_sample_stats = sample_counts.pivot_table(
|
||||
index=['YJDL', 'EJDL'], columns='SHFJ', values=['样点数', '样点占比'], fill_value=0, observed=False
|
||||
).reset_index()
|
||||
df_sample_stats.columns = [f'{col[0]}_{col[1]}'.strip('_') if col[1] else col[0] for col in df_sample_stats.columns]
|
||||
|
||||
# 将样点统计结果合并到骨架上
|
||||
df_final = pd.merge(df_skeleton, df_sample_stats, on=['YJDL', 'EJDL'], how='left')
|
||||
else:
|
||||
df_final = df_skeleton.copy()
|
||||
|
||||
# --- c. 独立统计面积数据 ---
|
||||
print("--> 步骤3: 独立统计面积数据...")
|
||||
df_area = pd.DataFrame(arcpy.da.TableToNumPyArray(area_table_path, ['EJDL', 'YJDL', 'SHFJ', 'AREA'], skip_nulls=False))
|
||||
df_area = clean_df(df_area, ['YJDL', 'EJDL'])
|
||||
|
||||
if not df_area.empty:
|
||||
# 计算平差系数
|
||||
landuse_types = {'耕地':'01', '园地':'02', '林地':'03', '草地':'04', '其他':'12'}
|
||||
|
||||
df_area['AREA_MU'] = df_area['AREA'] * 0.0015
|
||||
yjdl_area = df_area.groupby(['YJDL'])['AREA_MU'].sum().reset_index()
|
||||
yjdl_area.columns = ['YJDL', 'ORIGINAL_TOTAL_MU']
|
||||
|
||||
adjustment_factors = []
|
||||
for _, row in yjdl_area.iterrows():
|
||||
yjdl = row['YJDL']
|
||||
original_total = row['ORIGINAL_TOTAL_MU']
|
||||
target_total = target_area_dict.get(landuse_types[yjdl], original_total) # 如果没有指定，就用原始面积
|
||||
|
||||
adjustment_factor = target_total / original_total
|
||||
|
||||
adjustment_factors.append({
|
||||
'YJDL': yjdl,
|
||||
'原始总面积_亩': original_total,
|
||||
'目标总面积_亩': target_total,
|
||||
'平差系数': adjustment_factor
|
||||
})
|
||||
|
||||
factor_df = pd.DataFrame(adjustment_factors)
|
||||
|
||||
# 4. 对每个二级地类应用平差系数
|
||||
# 合并原始数据和平差系数
|
||||
df_with_factors = df_area.merge(factor_df[['YJDL', '平差系数']], on='YJDL')
|
||||
|
||||
df_with_factors['制图面积_亩'] = df_with_factors['AREA_MU'] * df_with_factors['平差系数']
|
||||
ts_total_area = df_with_factors.groupby(['YJDL', 'EJDL'])['制图面积_亩'].transform('sum')
|
||||
df_with_factors['面积占比'] = (df_with_factors['制图面积_亩'] / ts_total_area) * 100
|
||||
df_area_stats = df_with_factors.pivot_table(
|
||||
index=['YJDL', 'EJDL'], columns='SHFJ', values=['制图面积_亩', '面积占比'], fill_value=0
|
||||
).reset_index()
|
||||
df_area_stats.columns = [f'{col[0]}_{col[1]}'.strip('_') if col[1] else col[0] for col in df_area_stats.columns]
|
||||
|
||||
# 将面积统计结果合并到 df_final 上
|
||||
# 注意，这里我们合并到已经包含样点数据的 df_final 上
|
||||
df_final = pd.merge(df_final, df_area_stats, on=['YJDL', 'EJDL'], how='left')
|
||||
|
||||
# --- d. 最后清理和构建映射 ---
|
||||
df_final.fillna(0, inplace=True)
|
||||
|
||||
print("--> 步骤4: 自动构建层级结构...")
|
||||
dynamic_soil_mapping = df_final.groupby('YJDL')['EJDL'].unique().apply(list).to_dict()
|
||||
dynamic_soil_mapping = OrderedDict(sorted(dynamic_soil_mapping.items(),key=lambda item: yjdl_order.index(item[0])))
|
||||
in_ejdl_order = ejdl_order + [x for x in df_final['EJDL'].unique() if x not in ejdl_order]
|
||||
for yl in dynamic_soil_mapping:
|
||||
# dynamic_soil_mapping[yl].sort()
|
||||
dynamic_soil_mapping[yl] = sorted( dynamic_soil_mapping[yl], key=lambda x: in_ejdl_order.index(x))
|
||||
|
||||
print("数据处理流程完成！")
|
||||
return df_final, dynamic_soil_mapping
|
||||
|
||||
|
||||
# --- 3. Excel 制表 面积---
|
||||
def write_to_excel_table5_4(df, soil_mapping, output_path):
|
||||
"""
|
||||
【最终修正版】: 将处理好的数据写入格式化的 Excel 文件。
|
||||
"""
|
||||
if df.empty:
|
||||
print("警告: 没有数据可以写入 Excel，将创建一个空的报告。")
|
||||
return
|
||||
|
||||
print(f"开始生成 Excel 报告到 '{output_path}'...")
|
||||
wb = Workbook()
|
||||
ws = wb.create_sheet("Mysheet", 0)
|
||||
ws.title = "不同类型土壤酸化程度统计"
|
||||
|
||||
# --- b. 绘制表头 (不变) ---
|
||||
ws.merge_cells('A1:B1'); ws['A1'] = '土地利用类型'
|
||||
ws['A2'] = '一级'
|
||||
ws['B2'] = '二级'
|
||||
|
||||
acid_levels = ['轻度酸化', '中度酸化', '重度酸化']
|
||||
all_possible_levels = ['碱化', '未酸化', '轻度酸化', '中度酸化', '重度酸化']
|
||||
acid_level_headers = ['轻度酸化(0.3<ΔpH≤0.5)', '中度酸化(0.5<ΔpH≤1.0)', '重度酸化(ΔpH>1.0)']
|
||||
|
||||
col_start = 3
|
||||
for header in acid_level_headers:
|
||||
ws.merge_cells(start_row=1, start_column=col_start, end_row=1, end_column=col_start + 3)
|
||||
ws.cell(row=1, column=col_start).value = header
|
||||
ws.cell(row=2, column=col_start).value = '样点数/个'
|
||||
ws.cell(row=2, column=col_start + 1).value = '占比/%'
|
||||
ws.cell(row=2, column=col_start + 2).value = '制图面积/亩'
|
||||
ws.cell(row=2, column=col_start + 3).value = '占比/%'
|
||||
col_start += 4
|
||||
|
||||
# --- c. 填充数据 (完全重构的逻辑) ---
|
||||
current_row = 3
|
||||
|
||||
# 使用 .groupby('YJDL', sort=False) 来保证我们之前设置的排序顺序
|
||||
for yl, ts_list in soil_mapping.items():
|
||||
|
||||
# **【关键】** group_yl 是一个只包含当前一级地类数据的子DataFrame
|
||||
# 我们可以安全地在这个子DataFrame上进行迭代和计算
|
||||
|
||||
print(f"正在写入一级地类: {yl}...")
|
||||
yl_start_row = current_row
|
||||
|
||||
# 筛选出当前一级地类的所有数据
|
||||
group_yl_df = df[df['YJDL'] == yl]
|
||||
|
||||
# 1. 遍历该一级地类下的所有“二级地类”并写入数据
|
||||
for ts in ts_list:
|
||||
ws.cell(row=current_row, column=2).value = ts
|
||||
|
||||
# 在子集中查找当前二级地类的数据行
|
||||
row_data = group_yl_df[group_yl_df['EJDL'] == ts]
|
||||
|
||||
# --- 填充单元格的逻辑开始 ---
|
||||
|
||||
col_start = 3 # 从第 C 列开始填充
|
||||
|
||||
# 检查是否找到了该土属的数据
|
||||
if not row_data.empty:
|
||||
# 如果找到了数据 (row_data 不为空)，我们就获取这一行的数据
|
||||
# .iloc[0] 获取第一行（也是唯一一行）的数据，作为一个 Series 对象
|
||||
data_series = row_data.iloc[0]
|
||||
|
||||
# 遍历每一个酸化等级，填充对应的四列数据
|
||||
for level in acid_levels:
|
||||
# 1. 构建要从 data_series 中查找的列名
|
||||
sample_col = f'样点数_{level}'
|
||||
sample_pct_col = f'样点占比_{level}'
|
||||
area_col = f'制图面积_亩_{level}'
|
||||
area_pct_col = f'面积占比_{level}'
|
||||
|
||||
# 2. 从 data_series 中安全地获取值
|
||||
# 使用 .get(key, default_value) 的好处是，如果列名不存在，它会返回默认值(0)，而不会报错
|
||||
sample_val = data_series.get(sample_col, 0)
|
||||
sample_pct_val = data_series.get(sample_pct_col, 0)
|
||||
area_val = data_series.get(area_col, 0)
|
||||
area_pct_val = data_series.get(area_pct_col, 0)
|
||||
|
||||
# 3. 将获取到的值填入单元格
|
||||
# - 对于数值，我们判断它是否大于0。如果是，就填入数值；否则，填入 "-"
|
||||
# - 对于样点数，我们将其转为整数
|
||||
# - 对于占比和面积，我们保留两位小数
|
||||
|
||||
# 样点数/个
|
||||
ws.cell(row=current_row, column=col_start).value = int(sample_val) if sample_val > 0 else "-"
|
||||
# 占比/%
|
||||
ws.cell(row=current_row, column=col_start + 1).value = f"{sample_pct_val:.2f}%" if sample_val > 0 else "-"
|
||||
# 制图面积/万亩
|
||||
ws.cell(row=current_row, column=col_start + 2).value = f"{area_val:.0f}" if area_val > 0 else "-"
|
||||
# 占比/%
|
||||
ws.cell(row=current_row, column=col_start + 3).value = f"{area_pct_val:.2f}%" if area_val > 0 else "-"
|
||||
|
||||
# 移动到下一个酸化等级的起始列
|
||||
col_start += 4
|
||||
else:
|
||||
# 如果没有找到该土属的数据 (row_data 为空)
|
||||
# 这意味着该土属在源数据中不存在任何样点或面积信息
|
||||
# 我们将整行所有统计单元格都填充为 "-"
|
||||
|
||||
# acid_levels 列表包含3个等级，每个等级4列，总共12列
|
||||
for _ in range(len(acid_levels) * 4):
|
||||
ws.cell(row=current_row, column=col_start).value = "-"
|
||||
col_start += 1
|
||||
|
||||
# --- 填充单元格的逻辑结束 ---
|
||||
|
||||
# 完成一行填充后，行号加1，为下一行做准备
|
||||
current_row += 1
|
||||
|
||||
# 2. 计算并写入这个一级地类的“合计”行
|
||||
if ws.cell(row=current_row-1, column=2).value in ["林地","草地", "其他"]:
|
||||
ws.merge_cells(start_row=yl_start_row, start_column=1, end_row=yl_start_row, end_column=2)
|
||||
ws.cell(row=yl_start_row, column=1).value = yl
|
||||
continue
|
||||
|
||||
ws.cell(row=current_row, column=2).value = '合计'
|
||||
|
||||
# 计算总样点数和总面积，仅针对当前 group_yl
|
||||
yl_grand_total_samples = 0
|
||||
for lvl in all_possible_levels:
|
||||
if f'样点数_{lvl}' in group_yl_df:
|
||||
yl_grand_total_samples += group_yl_df[f'样点数_{lvl}'].sum()
|
||||
|
||||
yl_grand_total_area = 0
|
||||
for lvl in all_possible_levels:
|
||||
if f'制图面积_亩_{lvl}' in group_yl_df:
|
||||
yl_grand_total_area += group_yl_df[f'制图面积_亩_{lvl}'].sum()
|
||||
|
||||
col_start = 3
|
||||
for level in acid_levels:
|
||||
sample_sum = group_yl_df.get(f'样点数_{level}', 0).sum()
|
||||
col_name = f'制图面积_亩_{level}'
|
||||
area_sum = group_yl_df[col_name].sum() if col_name in group_yl_df else 0
|
||||
# area_sum = group_yl_df.get(f'制图面积_亩_{level}', 0).sum()
|
||||
|
||||
sample_perc = (sample_sum / yl_grand_total_samples * 100) if yl_grand_total_samples > 0 else 0
|
||||
area_perc = (area_sum / yl_grand_total_area * 100) if yl_grand_total_area > 0 else 0
|
||||
|
||||
ws.cell(row=current_row, column=col_start).value = int(sample_sum) if sample_sum > 0 else "-"
|
||||
ws.cell(row=current_row, column=col_start + 1).value = f"{sample_perc:.2f}%" if sample_sum > 0 else "-"
|
||||
ws.cell(row=current_row, column=col_start + 2).value = f"{area_sum:.0f}" if area_sum > 0 else "-"
|
||||
ws.cell(row=current_row, column=col_start + 3).value = f"{area_perc:.2f}%" if area_sum > 0 else "-"
|
||||
col_start += 4
|
||||
|
||||
# 3. 合并“一级地类”单元格
|
||||
if yl_start_row <= current_row:
|
||||
ws.merge_cells(start_row=yl_start_row, start_column=1, end_row=current_row, end_column=1)
|
||||
ws.cell(row=yl_start_row, column=1).value = yl
|
||||
|
||||
current_row += 1
|
||||
|
||||
# --- a. 定义样式 (不变) ---
|
||||
header_font = Font(name='等线', size=11, bold=True)
|
||||
|
||||
# --- d. 应用样式和调整列宽 (最终健壮版) ---
|
||||
max_col_letter = get_column_letter(ws.max_column)
|
||||
if current_row > 1: # 确保有数据才应用样式
|
||||
ExcelStyleUtils.set_style(ws, f'A1:{max_col_letter}{current_row-1}')
|
||||
ExcelStyleUtils.set_style(ws, f'A1:{max_col_letter}2', header_font)
|
||||
|
||||
print("正在自动调整列宽...")
|
||||
# 调整列宽
|
||||
ExcelStyleUtils.auto_adjust_column_width(ws)
|
||||
|
||||
# --- e. 保存文件 ---
|
||||
wb.save(output_path)
|
||||
print("Excel 报告生成成功！")
|
||||
|
||||
|
||||
def main(gdb_path:str, ph_features:str,dltb_class_feature:str, shph_tif:str, output_path:str,target_areas_dict:dict):
|
||||
try:
|
||||
# --- 1. 用户配置 ---
|
||||
# 输出配置
|
||||
output_excel_path = os.path.join(output_path, "土地利用类型酸化统计表.xlsx") # 生成的Excel报告文件路径
|
||||
|
||||
# 设置工作空间和变量
|
||||
arcpy.env.workspace = gdb_path
|
||||
arcpy.env.overwriteOutput = True
|
||||
|
||||
sample_table_name = "历史样点PH信息_Table" # 图2: 样点信息表名
|
||||
in_zone_feature = dltb_class_feature # 地类图斑
|
||||
in_class_feature = ph_features # 已重分类好的酸化PH图层
|
||||
in_value_raster = shph_tif # 赋值栅格,酸化PH栅格
|
||||
out_table_area = r"土地利用类型_酸化面积表" # 输出的面积统计表名
|
||||
out_table_mean = r"土地利用类型_酸化均值表" # 输出的均值表名
|
||||
|
||||
print("开始处理数据...")
|
||||
|
||||
if not arcpy.Exists(out_table_area):
|
||||
# 判断输入表是否存在SHFJ字段
|
||||
try:
|
||||
if not arcpy.ListFields(in_zone_feature, "EJDL"):
|
||||
arcpy.management.CalculateField(in_zone_feature, "EJDL", "calculate_ejdl(!DLBM!,!DLMC!)", "PYTHON3", codeblock_dltb_ejdl)
|
||||
arcpy.management.CalculateField(in_zone_feature, "YJDL", "calculate_yjdl(!DLBM!)", "PYTHON3", codeblock_dltb_yjdl)
|
||||
if not arcpy.ListFields(in_class_feature, "SHFJ"):
|
||||
arcpy.management.CalculateField(in_class_feature, "SHFJ", "calculate_shfj(!gridcode!)", "PYTHON3", codeblock_cal_shfj)
|
||||
except Exception as e:
|
||||
print(f"计算SHFJ字段时发生错误: {e}")
|
||||
|
||||
# 拿到地类图斑的坐标系
|
||||
desc = arcpy.Describe(in_zone_feature)
|
||||
spatial_ref = desc.spatialReference
|
||||
|
||||
# 1.用arcpy.analysis.TabulateIntersection进行交集制表,面积使用地类图斑投影坐标系下面积
|
||||
with arcpy.EnvManager(outputCoordinateSystem=spatial_ref):
|
||||
arcpy.analysis.TabulateIntersection(
|
||||
in_zone_feature,
|
||||
["YJDL", "EJDL"],
|
||||
in_class_feature,
|
||||
out_table_area,
|
||||
"SHFJ",
|
||||
out_units="SQUARE_METERS",
|
||||
)
|
||||
|
||||
if not arcpy.Exists(out_table_mean):
|
||||
# 判断输入表是否存在YJDL_EJDL字段
|
||||
if not arcpy.ListFields(in_zone_feature, "YJDL_EJDL"):
|
||||
# 如果不存在，则添加该字段
|
||||
arcpy.management.AddField(in_zone_feature, "YJDL_EJDL", "TEXT")
|
||||
# 计算YJDL_EJDL字段的值
|
||||
arcpy.management.CalculateField(in_zone_feature,"YJDL_EJDL","!YJDL! + '_' + !EJDL!","PYTHON3")
|
||||
|
||||
# 2.用arcpy.sa.ZonalStatisticsAsTable进行区域统计
|
||||
mean_table = arcpy.sa.ZonalStatisticsAsTable(
|
||||
in_zone_feature, "YJDL_EJDL", in_value_raster, out_table_mean, "DATA", "MEAN"
|
||||
)
|
||||
# 2.1 添加土壤类型字段并计算
|
||||
arcpy.management.AddFields(
|
||||
out_table_mean,
|
||||
[["YJDL", "TEXT"],["EJDL", "TEXT"]],
|
||||
)
|
||||
arcpy.management.CalculateField(mean_table, "YJDL", "!YJDL_EJDL!.split('_')[0]", "PYTHON3")
|
||||
arcpy.management.CalculateField(mean_table, "EJDL", "!YJDL_EJDL!.split('_')[1]", "PYTHON3")
|
||||
|
||||
# 生成表5.4的面积统计Excel报告
|
||||
final_dataframe, soil_structure = process_data_for_table5_4(gdb_path, out_table_area, sample_table_name,target_areas_dict)
|
||||
write_to_excel_table5_4(final_dataframe, soil_structure, output_excel_path)
|
||||
|
||||
# 生成表5.3的均值统计Excel报告
|
||||
final_mean_dataframe = process_data_for_table5_3(gdb_path, out_table_mean, sample_table_name)
|
||||
write_to_excel_table5_3(final_mean_dataframe, output_excel_path.replace(".xlsx", "_mean.xlsx"))
|
||||
|
||||
except Exception as e:
|
||||
print(f"\n处理过程中发生严重错误: {e}")
|
||||
import traceback
|
||||
|
||||
traceback.print_exc()
|
||||
finally:
|
||||
import gc
|
||||
gc.collect()
|
||||
|
||||
# --- 4. 主程序入口 ---
|
||||
# if __name__ == "__main__":
|
||||
# main()
|
||||
629
tools/core/acid_stats/土壤类型图酸化统计表.py
Normal file
629
tools/core/acid_stats/土壤类型图酸化统计表.py
Normal file
@@ -0,0 +1,629 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
import os
|
||||
import arcpy
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
from openpyxl import Workbook
|
||||
from openpyxl.styles import Font
|
||||
from openpyxl.utils import get_column_letter
|
||||
from tools.config.arcgis_field_cal_code import codeblock_cal_shfj
|
||||
from tools.core.utils.excel_utils import ExcelStyleUtils
|
||||
from tools.config.custom_sort import yl_order, ts_order
|
||||
|
||||
# --- 2. 辅助函数 ---
|
||||
# 获取要素类各酸化等级面积
|
||||
def get_acid_area_by_group(target_area_df):
|
||||
try:
|
||||
# 转为numpy数组供pandas统计使用
|
||||
df = target_area_df.copy()
|
||||
area_by_group = df.groupby("SHFJ")["AREA_MU"].sum()
|
||||
|
||||
for key in area_by_group.keys():
|
||||
area_by_group[key] = area_by_group[key]
|
||||
|
||||
return area_by_group.to_dict()
|
||||
|
||||
except Exception as e:
|
||||
print(f"计算面积时出错: {str(e)}")
|
||||
return None
|
||||
|
||||
def apply_adjustment_by_each_level(df, target_area_dict):
|
||||
"""
|
||||
对DataFrame中的面积数据按每一个酸化等级独立进行平差。
|
||||
|
||||
参数:
|
||||
df (pd.DataFrame): 包含面积统计的DataFrame。
|
||||
target_area_dict (dict): 每个酸化等级的目标总面积字典。
|
||||
例如: {'轻度酸化': 10000.0, '中度酸化': 8000.0, ...}
|
||||
"""
|
||||
print("\n开始按每个酸化等级独立进行平差...")
|
||||
df_adjusted = df.copy()
|
||||
|
||||
for level, target_area in target_area_dict.items():
|
||||
col_name = f'制图面积_亩_{level}'
|
||||
adjusted_col_name = f'平差后面积_亩_{level}'
|
||||
|
||||
if col_name not in df.columns:
|
||||
print(f"警告: 未找到列 '{col_name}'，跳过该等级平差。")
|
||||
if adjusted_col_name not in df_adjusted.columns:
|
||||
df_adjusted[adjusted_col_name] = 0 # 创建一个空列
|
||||
continue
|
||||
|
||||
# a. 计算该等级的实际总面积
|
||||
actual_area = df_adjusted[col_name].sum()
|
||||
|
||||
if actual_area > 0:
|
||||
# b. 计算误差
|
||||
error = target_area - actual_area
|
||||
print(f"等级 '{level}': 目标面积={target_area:.2f}, 实际面积={actual_area:.2f}, 误差={error:.2f}")
|
||||
|
||||
# c. 按比例分配误差
|
||||
adjustment = error * (df_adjusted[col_name] / actual_area)
|
||||
df_adjusted[adjusted_col_name] = df_adjusted[col_name] + adjustment
|
||||
df_adjusted[adjusted_col_name] = df_adjusted[adjusted_col_name].clip(lower=0)
|
||||
else:
|
||||
df_adjusted[adjusted_col_name] = df_adjusted[col_name]
|
||||
|
||||
print("按每个酸化等级独立平差完成。")
|
||||
return df_adjusted
|
||||
|
||||
# 获取酸化程度
|
||||
def get_acidification_degree(delta_ph):
|
||||
"""根据ΔpH值判断酸化程度"""
|
||||
if pd.isna(delta_ph) or delta_ph == 0:
|
||||
return "-"
|
||||
# 请根据您的实际分级标准调整这里的阈值
|
||||
if delta_ph > 1.0:
|
||||
return "重度酸化"
|
||||
elif 0.5 < delta_ph <= 1.0:
|
||||
return "中度酸化"
|
||||
elif 0.3 < delta_ph <= 0.5:
|
||||
return "轻度酸化"
|
||||
elif -0.3 <= delta_ph <= 0.3:
|
||||
return "未酸化"
|
||||
else: # dPH < -0.3
|
||||
return "碱化"
|
||||
|
||||
# --- 3. 数据处理与分析 均值表---
|
||||
def process_data_for_table5_5(gdb_path, mean_table_name, sample_table_name):
|
||||
"""
|
||||
【最终版 v2】: 增加对制图样点数的处理，以支持加权平均计算。
|
||||
"""
|
||||
print("【最终版 v2】开始处理数据...")
|
||||
|
||||
def clean_df(df, columns):
|
||||
for col in columns:
|
||||
df[col] = df[col].astype(str).str.strip()
|
||||
df.replace(['<Null>', 'None', '', '<空>'], np.nan, inplace=True)
|
||||
df.dropna(subset=columns, inplace=True)
|
||||
return df
|
||||
|
||||
# --- a. 处理样点数据，计算“样点均值” ---
|
||||
print("--> 步骤1: 计算样点均值...")
|
||||
sample_table_path = os.path.join(gdb_path, sample_table_name)
|
||||
sample_fields = ['YL', 'TS', 'dPH']
|
||||
df_samples = pd.DataFrame(arcpy.da.TableToNumPyArray(sample_table_path, sample_fields, 'dPH>0.3', skip_nulls=False))
|
||||
df_samples = clean_df(df_samples, ['YL', 'TS'])
|
||||
|
||||
# 按 YL, TS 分组，计算 dPH 的均值
|
||||
df_sample_means = df_samples.groupby(['YL', 'TS'])['dPH'].mean().reset_index()
|
||||
df_sample_means.rename(columns={'dPH': '样点均值'}, inplace=True)
|
||||
print("样点均值计算完成。")
|
||||
|
||||
# --- b. 处理制图数据，获取“制图均值”和“制图样点数” ---
|
||||
print("--> 步骤2: 获取制图均值和样点数...")
|
||||
mean_table_path = os.path.join(gdb_path, mean_table_name)
|
||||
mean_fields = ['YL', 'TS', 'MEAN', 'COUNT']
|
||||
df_map_data = pd.DataFrame(arcpy.da.TableToNumPyArray(mean_table_path, mean_fields, skip_nulls=False))
|
||||
df_map_data = clean_df(df_map_data, ['YL', 'TS'])
|
||||
df_map_data.rename(columns={'MEAN': '制图均值', 'COUNT': '制图样点数'}, inplace=True)
|
||||
print("制图数据获取完成。")
|
||||
|
||||
# --- c. 合并数据 ---
|
||||
print("--> 步骤3: 合并数据...")
|
||||
df_skeleton = pd.concat([
|
||||
df_sample_means[['YL', 'TS']],
|
||||
df_map_data[['YL', 'TS']]
|
||||
]).drop_duplicates().reset_index(drop=True)
|
||||
|
||||
df_final = pd.merge(df_skeleton, df_sample_means, on=['YL', 'TS'], how='left')
|
||||
# **【核心修改】: 合并整个 df_map_data，而不仅仅是均值列**
|
||||
df_final = pd.merge(df_final, df_map_data, on=['YL', 'TS'], how='left')
|
||||
|
||||
# --- d. 计算酸化程度 ---
|
||||
print("--> 步骤4: 计算酸化程度...")
|
||||
# **【核心修改】: 在计算酸化程度之前，先过滤掉不展示的行**
|
||||
# 我们只对 dPH 在酸化范围内 ( > 0.3) 的数据感兴趣
|
||||
# 但为了计算合计，我们需要保留所有数据，所以这一步只计算，不删除
|
||||
df_final['酸化程度_样本'] = df_final['样点均值'].apply(get_acidification_degree)
|
||||
df_final['酸化程度_制图'] = df_final['制图均值'].apply(get_acidification_degree)
|
||||
|
||||
# (可选) 按“亚类”和“土属”排序
|
||||
in_yl_order = yl_order + [x for x in df_final['YL'].unique() if x not in yl_order]
|
||||
in_ts_order = ts_order + [x for x in df_final['TS'].unique() if x not in ts_order]
|
||||
df_final["YL"] = pd.Categorical(df_final['YL'], categories=in_yl_order, ordered=True)
|
||||
df_final["TS"] = pd.Categorical(df_final['TS'], categories=in_ts_order, ordered=True)
|
||||
df_final.sort_values(['YL', 'TS'], inplace=True)
|
||||
|
||||
print("数据处理流程完成！")
|
||||
return df_final
|
||||
|
||||
|
||||
# --- 4. Excel 制表 均值表---
|
||||
def write_to_excel_table5_5(df, output_path):
|
||||
"""
|
||||
将处理好的数据写入格式化的 Excel 文件。
|
||||
"""
|
||||
if df.empty:
|
||||
print("警告: 没有数据可以写入 Excel。")
|
||||
return
|
||||
|
||||
print(f"开始生成 Excel 报告到 '{output_path}'...")
|
||||
wb = Workbook()
|
||||
ws = wb.create_sheet("Mysheet", 0)
|
||||
ws.title = "不同类型土壤pH变化统计"
|
||||
|
||||
# --- b. 绘制表头 ---
|
||||
ws.merge_cells('A1:A2'); ws['A1'] = '亚类'
|
||||
ws.merge_cells('B1:B2'); ws['B1'] = '土属'
|
||||
ws.merge_cells('C1:F1'); ws['C1'] = 'ΔpH'
|
||||
|
||||
ws['C2'] = '样点均值'
|
||||
ws['D2'] = '酸化程度'
|
||||
ws['E2'] = '制图均值'
|
||||
ws['F2'] = '酸化程度'
|
||||
|
||||
# --- c. 填充数据 ---
|
||||
current_row = 3
|
||||
|
||||
# **【核心修改】: 先对整个DataFrame进行过滤，只保留需要展示的行**
|
||||
# 只有当“样点酸化程度”或“制图酸化程度”不为“未酸化”、“碱化”或“-”时，才展示该行
|
||||
acid_levels_to_show = ["轻度酸化", "中度酸化", "重度酸化"]
|
||||
df_to_write = df[
|
||||
df['酸化程度_样本'].isin(acid_levels_to_show) |
|
||||
df['酸化程度_制图'].isin(acid_levels_to_show)
|
||||
].copy() # 使用 .copy() 避免 SettingWithCopyWarning
|
||||
|
||||
for yl, group_yl_df in df_to_write.groupby('YL', observed=True, sort=False):
|
||||
|
||||
print(f"正在写入亚类: {yl}...")
|
||||
yl_start_row = current_row
|
||||
|
||||
# 遍历该亚类下的所有“土属”
|
||||
for _, row_data in group_yl_df.iterrows():
|
||||
ws.cell(row=current_row, column=2).value = row_data['TS']
|
||||
|
||||
# 填充样点数据
|
||||
sample_mean = row_data.get('样点均值')
|
||||
if pd.notna(sample_mean):
|
||||
ws.cell(row=current_row, column=3).value = f"{sample_mean:.2f}" if sample_mean > 0.3 else "-"
|
||||
ws.cell(row=current_row, column=4).value = row_data.get('酸化程度_样本', '-') if sample_mean > 0.3 else "-"
|
||||
else:
|
||||
ws.cell(row=current_row, column=3).value = "-"
|
||||
ws.cell(row=current_row, column=4).value = "-"
|
||||
|
||||
# 填充制图数据
|
||||
map_mean = row_data.get('制图均值')
|
||||
if pd.notna(map_mean):
|
||||
ws.cell(row=current_row, column=5).value = f"{map_mean:.2f}" if map_mean > 0.3 else "-"
|
||||
ws.cell(row=current_row, column=6).value = row_data.get('酸化程度_制图', '-') if map_mean > 0.3 else "-"
|
||||
else:
|
||||
ws.cell(row=current_row, column=5).value = "-"
|
||||
ws.cell(row=current_row, column=6).value = "-"
|
||||
|
||||
current_row += 1
|
||||
|
||||
# 计算并写入“合计”行
|
||||
ws.cell(row=current_row, column=2).value = '合计'
|
||||
|
||||
# 计算合计行的均值 (均值的均值)
|
||||
total_sample_mean = group_yl_df['样点均值'].mean()
|
||||
|
||||
if pd.notna(total_sample_mean):
|
||||
ws.cell(row=current_row, column=3).value = f"{total_sample_mean:.2f}"
|
||||
ws.cell(row=current_row, column=4).value = get_acidification_degree(total_sample_mean)
|
||||
else:
|
||||
ws.cell(row=current_row, column=3).value = "-"
|
||||
ws.cell(row=current_row, column=4).value = "-"
|
||||
|
||||
# b. **【核心修正】: 计算合计行的“制图均值”(加权平均)**
|
||||
# 准备加权平均的分子和分母
|
||||
weighted_sum = 0
|
||||
total_count = 0
|
||||
|
||||
# 遍历当前亚类分组中的每一行
|
||||
for _, row in group_yl_df.iterrows():
|
||||
mean_val = row.get('制图均值')
|
||||
count_val = row.get('制图样点数')
|
||||
|
||||
# 只有当均值和样点数都存在且有效时，才参与计算
|
||||
if pd.notna(mean_val) and pd.notna(count_val) and count_val > 0:
|
||||
weighted_sum += mean_val * count_val # Σ (mean * count)
|
||||
total_count += count_val # Σ (count)
|
||||
|
||||
# 计算加权平均值
|
||||
weighted_avg = (weighted_sum / total_count) if total_count > 0 else 0
|
||||
|
||||
if weighted_avg > 0:
|
||||
ws.cell(row=current_row, column=5).value = f"{weighted_avg:.2f}"
|
||||
ws.cell(row=current_row, column=6).value = get_acidification_degree(weighted_avg)
|
||||
else:
|
||||
ws.cell(row=current_row, column=5).value = "-"
|
||||
ws.cell(row=current_row, column=6).value = "-"
|
||||
|
||||
# 合并“亚类”单元格
|
||||
if yl_start_row <= current_row:
|
||||
ws.merge_cells(start_row=yl_start_row, start_column=1, end_row=current_row, end_column=1)
|
||||
ws.cell(row=yl_start_row, column=1).value = yl
|
||||
|
||||
current_row += 1
|
||||
|
||||
# --- a. 定义样式 ---
|
||||
header_font = Font(name='等线', size=11, bold=True)
|
||||
|
||||
# --- d. 应用样式和调整列宽 (最终健壮版) ---
|
||||
max_col_letter = get_column_letter(ws.max_column)
|
||||
if current_row > 1: # 确保有数据才应用样式
|
||||
ExcelStyleUtils.set_style(ws, f'A1:{max_col_letter}{current_row-1}')
|
||||
ExcelStyleUtils.set_style(ws, f'A1:{max_col_letter}2', header_font)
|
||||
|
||||
print("正在自动调整列宽...")
|
||||
|
||||
# 自动调整列宽
|
||||
ExcelStyleUtils.auto_adjust_column_width(ws)
|
||||
|
||||
# --- e. 保存文件 ---
|
||||
wb.save(output_path)
|
||||
print("Excel 报告生成成功！")
|
||||
|
||||
|
||||
# --- 2. 数据处理与分析 (面积统计表) ---
|
||||
def process_data_final(gdb_path, area_table_name, sample_table_name):
|
||||
"""
|
||||
【最终修正版 v2】: 先建立统一的层级结构，再分别合并统计结果。
|
||||
"""
|
||||
print("【最终修正版 v2】开始处理数据...")
|
||||
|
||||
def clean_df(df, columns):
|
||||
# ... (此函数不变)
|
||||
for col in columns:
|
||||
df[col] = df[col].astype(str).str.strip()
|
||||
df.replace(['<Null>', 'None', '', '<空>'], np.nan, inplace=True)
|
||||
df.dropna(subset=columns, inplace=True)
|
||||
return df
|
||||
|
||||
# --- a. 从两个表中提取并建立唯一的 (YL, TS) 层级结构 "骨架" ---
|
||||
print("--> 步骤1: 建立统一的层级结构...")
|
||||
sample_table_path = os.path.join(gdb_path, sample_table_name)
|
||||
area_table_path = os.path.join(gdb_path, area_table_name)
|
||||
|
||||
df_samples_raw = pd.DataFrame(arcpy.da.TableToNumPyArray(sample_table_path, ['YL', 'TS'], skip_nulls=False))
|
||||
df_area_raw = pd.DataFrame(arcpy.da.TableToNumPyArray(area_table_path, ['YL', 'TS'], skip_nulls=False))
|
||||
|
||||
# 清理并合并两个表中的 (YL, TS) 组合
|
||||
df_samples_raw = clean_df(df_samples_raw, ['YL', 'TS'])
|
||||
df_area_raw = clean_df(df_area_raw, ['YL', 'TS'])
|
||||
|
||||
# 使用 concat 连接两个DataFrame，然后用 drop_duplicates 去除重复的组合
|
||||
df_skeleton = pd.concat([df_samples_raw, df_area_raw]).drop_duplicates().reset_index(drop=True)
|
||||
|
||||
if df_skeleton.empty:
|
||||
print("警告: 无法从源数据中建立任何有效的 (YL, TS) 层级结构。")
|
||||
return pd.DataFrame(), {}
|
||||
print(f"已建立包含 {len(df_skeleton)} 个唯一土壤类型的层级结构。")
|
||||
|
||||
# --- b. 独立统计样点数据 ---
|
||||
print("--> 步骤2: 独立统计样点数据...")
|
||||
df_samples = pd.DataFrame(arcpy.da.TableToNumPyArray(sample_table_path, ['TS', 'YL', 'dPH'], skip_nulls=False))
|
||||
df_samples = clean_df(df_samples, ['YL', 'TS'])
|
||||
|
||||
if not df_samples.empty:
|
||||
bins = [-np.inf, -0.3, 0.3, 0.5, 1.0, np.inf]
|
||||
labels = ["碱化", "未酸化", "轻度酸化", "中度酸化", "重度酸化"]
|
||||
df_samples['SHFJ'] = pd.cut(df_samples['dPH'], bins=bins, labels=labels, right=True)
|
||||
sample_counts = df_samples.groupby(['YL', 'TS', 'SHFJ'], observed=False).size().reset_index(name='样点数')
|
||||
ts_total_samples = sample_counts.groupby(['YL', 'TS'])['样点数'].transform('sum')
|
||||
sample_counts['样点占比'] = (sample_counts['样点数'] / ts_total_samples) * 100
|
||||
df_sample_stats = sample_counts.pivot_table(
|
||||
index=['YL', 'TS'], columns='SHFJ', values=['样点数', '样点占比'], fill_value=0, observed=False
|
||||
).reset_index()
|
||||
df_sample_stats.columns = [f'{col[0]}_{col[1]}'.strip('_') if col[1] else col[0] for col in df_sample_stats.columns]
|
||||
|
||||
# 将样点统计结果合并到骨架上
|
||||
df_final = pd.merge(df_skeleton, df_sample_stats, on=['YL', 'TS'], how='left')
|
||||
else:
|
||||
df_final = df_skeleton.copy()
|
||||
|
||||
# --- c. 独立统计面积数据 ---
|
||||
print("--> 步骤3: 独立统计面积数据...")
|
||||
df_area = pd.DataFrame(arcpy.da.TableToNumPyArray(area_table_path, ['TS', 'YL', 'SHFJ', 'AREA'], skip_nulls=False))
|
||||
df_area = clean_df(df_area, ['YL', 'TS'])
|
||||
|
||||
if not df_area.empty:
|
||||
df_area['制图面积_亩'] = df_area['AREA'] * 0.0015
|
||||
ts_total_area = df_area.groupby(['YL', 'TS'])['制图面积_亩'].transform('sum')
|
||||
df_area['面积占比'] = (df_area['制图面积_亩'] / ts_total_area) * 100
|
||||
df_area_stats = df_area.pivot_table(
|
||||
index=['YL', 'TS'], columns='SHFJ', values=['制图面积_亩', '面积占比'], fill_value=0
|
||||
).reset_index()
|
||||
df_area_stats.columns = [f'{col[0]}_{col[1]}'.strip('_') if col[1] else col[0] for col in df_area_stats.columns]
|
||||
|
||||
# 将面积统计结果合并到 df_final 上
|
||||
# 注意，这里我们合并到已经包含样点数据的 df_final 上
|
||||
df_final = pd.merge(df_final, df_area_stats, on=['YL', 'TS'], how='left')
|
||||
|
||||
# --- d. 最后清理和构建映射 ---
|
||||
df_final.fillna(0, inplace=True)
|
||||
|
||||
print("--> 步骤4: 自动构建层级结构...")
|
||||
in_yl_order = yl_order + [x for x in df_final['YL'].unique() if x not in yl_order]
|
||||
in_ts_order = ts_order + [x for x in df_final['TS'].unique() if x not in ts_order]
|
||||
df_final["YL"] = pd.Categorical(df_final['YL'], categories=in_yl_order, ordered=True)
|
||||
df_final["TS"] = pd.Categorical(df_final['TS'], categories=in_ts_order, ordered=True)
|
||||
df_final.sort_values(['YL', 'TS'], inplace=True)
|
||||
dynamic_soil_mapping = df_final.groupby('YL', observed=True)['TS'].unique().apply(list).to_dict()
|
||||
# for yl in dynamic_soil_mapping:
|
||||
# dynamic_soil_mapping[yl].sort()
|
||||
|
||||
print("数据处理流程完成！")
|
||||
return df_final, dynamic_soil_mapping
|
||||
|
||||
|
||||
# --- 3. Excel 制表 面积统计表 ---
|
||||
def write_to_excel(df, soil_mapping, output_path):
|
||||
"""
|
||||
【最终修正版】: 将处理好的数据写入格式化的 Excel 文件。
|
||||
"""
|
||||
if df.empty:
|
||||
print("警告: 没有数据可以写入 Excel，将创建一个空的报告。")
|
||||
return
|
||||
|
||||
print(f"开始生成 Excel 报告到 '{output_path}'...")
|
||||
wb = Workbook()
|
||||
ws = wb.create_sheet("Mysheet", 0)
|
||||
ws.title = "不同类型土壤酸化程度统计"
|
||||
|
||||
# --- b. 绘制表头 (不变) ---
|
||||
ws.merge_cells('A1:A2'); ws['A1'] = '亚类'
|
||||
ws.merge_cells('B1:B2'); ws['B1'] = '土属'
|
||||
|
||||
acid_levels = ['轻度酸化', '中度酸化', '重度酸化']
|
||||
all_possible_levels = ['碱化', '未酸化', '轻度酸化', '中度酸化', '重度酸化']
|
||||
acid_level_headers = ['轻度酸化(0.3<ΔpH≤0.5)', '中度酸化(0.5<ΔpH≤1.0)', '重度酸化(ΔpH>1.0)']
|
||||
|
||||
col_start = 3
|
||||
for header in acid_level_headers:
|
||||
ws.merge_cells(start_row=1, start_column=col_start, end_row=1, end_column=col_start + 3)
|
||||
ws.cell(row=1, column=col_start).value = header
|
||||
ws.cell(row=2, column=col_start).value = '样点数/个'
|
||||
ws.cell(row=2, column=col_start + 1).value = '占比/%'
|
||||
ws.cell(row=2, column=col_start + 2).value = '制图面积/亩'
|
||||
ws.cell(row=2, column=col_start + 3).value = '占比/%'
|
||||
col_start += 4
|
||||
|
||||
# --- c. 填充数据 (完全重构的逻辑) ---
|
||||
current_row = 3
|
||||
|
||||
# 使用 .groupby('YL', sort=False) 来保证我们之前设置的排序顺序
|
||||
for yl, ts_list in soil_mapping.items():
|
||||
|
||||
# **【关键】** group_yl 是一个只包含当前亚类数据的子DataFrame
|
||||
# 我们可以安全地在这个子DataFrame上进行迭代和计算
|
||||
|
||||
print(f"正在写入亚类: {yl}...")
|
||||
yl_start_row = current_row
|
||||
|
||||
# 筛选出当前亚类的所有数据
|
||||
group_yl_df = df[df['YL'] == yl]
|
||||
|
||||
# 1. 遍历该亚类下的所有“土属”并写入数据
|
||||
for ts in ts_list:
|
||||
ws.cell(row=current_row, column=2).value = ts
|
||||
|
||||
# 在子集中查找当前土属的数据行
|
||||
row_data = group_yl_df[group_yl_df['TS'] == ts]
|
||||
|
||||
# --- 填充单元格的逻辑开始 ---
|
||||
|
||||
col_start = 3 # 从第 C 列开始填充
|
||||
|
||||
# 检查是否找到了该土属的数据
|
||||
if not row_data.empty:
|
||||
# 如果找到了数据 (row_data 不为空)，我们就获取这一行的数据
|
||||
# .iloc[0] 获取第一行（也是唯一一行）的数据，作为一个 Series 对象
|
||||
data_series = row_data.iloc[0]
|
||||
|
||||
# 遍历每一个酸化等级，填充对应的四列数据
|
||||
for level in acid_levels:
|
||||
# 1. 构建要从 data_series 中查找的列名
|
||||
sample_col = f'样点数_{level}'
|
||||
sample_pct_col = f'样点占比_{level}'
|
||||
area_col = f'平差后面积_亩_{level}'
|
||||
area_pct_col = f'面积占比_{level}'
|
||||
|
||||
# 2. 从 data_series 中安全地获取值
|
||||
# 使用 .get(key, default_value) 的好处是，如果列名不存在，它会返回默认值(0)，而不会报错
|
||||
sample_val = data_series.get(sample_col, 0)
|
||||
sample_pct_val = data_series.get(sample_pct_col, 0)
|
||||
area_val = data_series.get(area_col, 0)
|
||||
area_pct_val = data_series.get(area_pct_col, 0)
|
||||
|
||||
# 3. 将获取到的值填入单元格
|
||||
# - 对于数值，我们判断它是否大于0。如果是，就填入数值；否则，填入 "-"
|
||||
# - 对于样点数，我们将其转为整数
|
||||
# - 对于占比和面积，我们保留两位小数
|
||||
|
||||
# 样点数/个
|
||||
ws.cell(row=current_row, column=col_start).value = int(sample_val) if sample_val > 0 else "-"
|
||||
# 占比/%
|
||||
ws.cell(row=current_row, column=col_start + 1).value = f"{sample_pct_val:.2f}%" if sample_val > 0 else "-"
|
||||
# 制图面积/亩
|
||||
ws.cell(row=current_row, column=col_start + 2).number_format = "0.00"
|
||||
ws.cell(row=current_row, column=col_start + 2).value = f"{area_val:.0f}" if area_val > 0 else "-"
|
||||
# 占比/%
|
||||
ws.cell(row=current_row, column=col_start + 3).value = f"{area_pct_val:.2f}%" if area_val > 0 else "-"
|
||||
|
||||
# 移动到下一个酸化等级的起始列
|
||||
col_start += 4
|
||||
else:
|
||||
# 如果没有找到该土属的数据 (row_data 为空)
|
||||
# 这意味着该土属在源数据中不存在任何样点或面积信息
|
||||
# 我们将整行所有统计单元格都填充为 "-"
|
||||
|
||||
# acid_levels 列表包含3个等级，每个等级4列，总共12列
|
||||
for _ in range(len(acid_levels) * 4):
|
||||
ws.cell(row=current_row, column=col_start).value = "-"
|
||||
col_start += 1
|
||||
|
||||
# --- 填充单元格的逻辑结束 ---
|
||||
|
||||
# 完成一行填充后，行号加1，为下一行做准备
|
||||
current_row += 1
|
||||
|
||||
# 2. 计算并写入这个亚类的“合计”行
|
||||
ws.cell(row=current_row, column=2).value = '合计'
|
||||
|
||||
# 计算总样点数和总面积，仅针对当前 group_yl
|
||||
yl_grand_total_samples = 0
|
||||
for lvl in all_possible_levels:
|
||||
if f'样点数_{lvl}' in group_yl_df:
|
||||
yl_grand_total_samples += group_yl_df[f'样点数_{lvl}'].sum()
|
||||
|
||||
yl_grand_total_area = 0
|
||||
for lvl in all_possible_levels:
|
||||
if f'制图面积_亩_{lvl}' in group_yl_df:
|
||||
yl_grand_total_area += group_yl_df[f'制图面积_亩_{lvl}'].sum()
|
||||
|
||||
col_start = 3
|
||||
for level in acid_levels:
|
||||
sample_sum = group_yl_df.get(f'样点数_{level}', 0).sum()
|
||||
col_name = f'制图面积_亩_{level}'
|
||||
area_sum = group_yl_df[col_name].sum() if col_name in group_yl_df else 0
|
||||
# area_sum = group_yl_df.get(f'平差后面积_亩_{level}', 0).sum()
|
||||
|
||||
sample_perc = (sample_sum / yl_grand_total_samples * 100) if yl_grand_total_samples > 0 else 0
|
||||
area_perc = (area_sum / yl_grand_total_area * 100) if yl_grand_total_area > 0 else 0
|
||||
|
||||
ws.cell(row=current_row, column=col_start).value = int(sample_sum) if sample_sum > 0 else "-"
|
||||
ws.cell(row=current_row, column=col_start + 1).value = f"{sample_perc:.2f}%" if sample_sum > 0 else "-"
|
||||
ws.cell(row=current_row, column=col_start + 2).value = f"{area_sum:.0f}" if area_sum > 0 else "-"
|
||||
ws.cell(row=current_row, column=col_start + 3).value = f"{area_perc:.2f}%" if area_sum > 0 else "-"
|
||||
col_start += 4
|
||||
|
||||
# 3. 合并“亚类”单元格
|
||||
if yl_start_row <= current_row:
|
||||
ws.merge_cells(start_row=yl_start_row, start_column=1, end_row=current_row, end_column=1)
|
||||
ws.cell(row=yl_start_row, column=1).value = yl
|
||||
|
||||
current_row += 1
|
||||
|
||||
# --- a. 定义样式 (不变) ---
|
||||
header_font = Font(name='等线', size=11, bold=True)
|
||||
|
||||
# d. 应用样式和调整列宽
|
||||
max_col = 2 + len(acid_levels) * 4
|
||||
if current_row > 1: # 确保有数据才应用样式
|
||||
ExcelStyleUtils.set_style(ws, f'A1:{get_column_letter(max_col)}{current_row-1}')
|
||||
ExcelStyleUtils.set_style(ws, f'A1:{get_column_letter(max_col)}2', header_font)
|
||||
|
||||
# 调整列宽
|
||||
ExcelStyleUtils.auto_adjust_column_width(ws)
|
||||
|
||||
# --- e. 保存文件 ---
|
||||
wb.save(output_path)
|
||||
print("Excel 报告生成成功！")
|
||||
|
||||
|
||||
def main(gdb_path, trlx_polygon, sh_ph_polygon, ph_raster, output_path, target_areas_df):
|
||||
try:
|
||||
# --- 1. 用户配置 ---
|
||||
sample_table_name = "历史样点PH信息_Table" # 图2: 样点信息表名
|
||||
|
||||
# 输出配置
|
||||
output_excel_path = os.path.join(output_path, "土壤类型酸化统计表.xlsx") # 生成的Excel报告文件路径
|
||||
|
||||
# 设置工作空间和变量
|
||||
arcpy.env.workspace = gdb_path
|
||||
arcpy.env.overwriteOutput = True
|
||||
|
||||
in_zone_feature = trlx_polygon # 土壤类型图
|
||||
# in_class_feature = sh_ph_polygon # 已重分类好的酸化PH图层
|
||||
in_class_feature = "最小面积统计单元"
|
||||
in_value_raster = ph_raster # 酸化PH栅格
|
||||
dltb_ph_statstable = "土地利用类型_酸化面积表" # 土壤类型_酸化面积表（gdb table）
|
||||
out_table_area = r"土壤类型_酸化面积表" # 输出的交集表名
|
||||
out_table_mean = r"土壤类型_酸化均值表" # 输出的均值表名
|
||||
|
||||
print("开始处理数据...")
|
||||
|
||||
if not arcpy.Exists(out_table_area):
|
||||
# 判断输入表是否存在SHFJ字段
|
||||
try:
|
||||
arcpy.management.CalculateField(in_class_feature, "SHFJ", "calculate_shfj(!gridcode!)", "PYTHON3", codeblock_cal_shfj)
|
||||
except Exception as e:
|
||||
print(f"计算SHFJ字段时发生错误: {e}")
|
||||
|
||||
# 1.用arcpy.analysis.TabulateIntersection进行交集制表
|
||||
arcpy.analysis.TabulateIntersection(
|
||||
in_zone_feature,
|
||||
["TS", "YL"],
|
||||
in_class_feature,
|
||||
out_table_area,
|
||||
"SHFJ",
|
||||
out_units="SQUARE_METERS",
|
||||
)
|
||||
|
||||
if not arcpy.Exists(out_table_mean):
|
||||
# 判断输入表是否存在YL_TS字段
|
||||
if not arcpy.ListFields(in_zone_feature, "YL_TS"):
|
||||
# 如果不存在，则添加该字段
|
||||
arcpy.management.AddField(in_zone_feature, "YL_TS", "TEXT")
|
||||
# 计算YL_TS字段的值
|
||||
arcpy.management.CalculateField(in_zone_feature,"YL_TS","!YL! + '_' + !TS!","PYTHON3")
|
||||
|
||||
# 2.用arcpy.sa.ZonalStatisticsAsTable进行区域统计
|
||||
mean_table = arcpy.sa.ZonalStatisticsAsTable(
|
||||
in_zone_feature, "YL_TS", in_value_raster, out_table_mean, "DATA", "MEAN"
|
||||
)
|
||||
# 2.1 添加土壤类型字段并计算
|
||||
arcpy.management.AddFields(
|
||||
out_table_mean,
|
||||
[["YL", "TEXT"],["TS", "TEXT"]],
|
||||
)
|
||||
arcpy.management.CalculateField(mean_table, "YL", "!YL_TS!.split('_')[0]", "PYTHON3")
|
||||
arcpy.management.CalculateField(mean_table, "TS", "!YL_TS!.split('_')[1]", "PYTHON3")
|
||||
|
||||
|
||||
# 生成表5.4的面积统计Excel报告
|
||||
final_dataframe, soil_structure = process_data_final(gdb_path, out_table_area, sample_table_name)
|
||||
|
||||
# 统计地类图斑酸化总面积亩
|
||||
each_acid_area = get_acid_area_by_group(target_areas_df)
|
||||
print(f"容县土壤类型图斑总 acid 总面积（亩）：{each_acid_area}")
|
||||
# 执行平差计算
|
||||
if each_acid_area:
|
||||
adjusted_dataframe = apply_adjustment_by_each_level(final_dataframe, each_acid_area)
|
||||
print("使用平差值进行修正！")
|
||||
write_to_excel(adjusted_dataframe, soil_structure, output_excel_path)
|
||||
else:
|
||||
print("未使用平差值进行修正！")
|
||||
write_to_excel(final_dataframe, soil_structure, output_excel_path)
|
||||
|
||||
# 生成表5.4的均值统计Excel报告
|
||||
final_mean_dataframe = process_data_for_table5_5(gdb_path, out_table_mean, sample_table_name)
|
||||
write_to_excel_table5_5(final_mean_dataframe, output_excel_path.replace(".xlsx", "_mean.xlsx"))
|
||||
# adjusted_dataframe.to_csv(output_excel_path.replace(".xlsx", "_adjusted.csv"), index=False)
|
||||
|
||||
|
||||
except Exception as e:
|
||||
print(f"\n处理过程中发生严重错误: {e}")
|
||||
import traceback
|
||||
|
||||
traceback.print_exc()
|
||||
finally:
|
||||
import gc
|
||||
gc.collect()
|
||||
|
||||
# --- 4. 主程序入口 ---
|
||||
# if __name__ == "__main__":
|
||||
# main()
|
||||
167
tools/core/acid_stats/空间连接.py
Normal file
167
tools/core/acid_stats/空间连接.py
Normal file
@@ -0,0 +1,167 @@
|
||||
|
||||
# -*- coding: utf-8 -*-
|
||||
import sys
|
||||
import arcpy
|
||||
from pathlib import Path
|
||||
|
||||
sys.path.append(str(Path(__file__).parent))
|
||||
from tools.config.arcgis_field_cal_code import codeblock_dltb_ejdl, codeblock_dltb_yjdl
|
||||
|
||||
def export_to_points(ph_points, dltb_features, trlx_features, xzq_features, assign_raster, workspace):
|
||||
# --- 1. 设置工作空间和变量 ---
|
||||
# 请根据您的实际情况修改以下路径
|
||||
arcpy.env.workspace = workspace
|
||||
arcpy.env.overwriteOutput = True
|
||||
|
||||
# 输入的要素类
|
||||
input_features = ph_points # 历史样点PH数据
|
||||
join_features_list = [trlx_features,xzq_features,dltb_features] # 连接图层 (规划分区)
|
||||
|
||||
# 输出的要素类
|
||||
final_output_fc = "历史样点PH信息_Table"
|
||||
|
||||
# --- 3. 主处理逻辑 ---
|
||||
try:
|
||||
print("开始处理赋值样点PH信息...")
|
||||
target_features = f"in_memory/temp_sample_raster"
|
||||
# 将栅格数据提取至历史PH样点
|
||||
arcpy.sa.ExtractValuesToPoints(
|
||||
in_point_features=input_features,
|
||||
in_raster=assign_raster,
|
||||
out_point_features=target_features,
|
||||
interpolate_values="NONE",
|
||||
add_attributes="VALUE_ONLY"
|
||||
)
|
||||
|
||||
print("开始计算地类一二级类别...")
|
||||
# 计算地类图斑一级、二级类别
|
||||
try:
|
||||
arcpy.management.CalculateField(dltb_features, "EJDL", "calculate_ejdl(!DLBM!,!DLMC!)", "PYTHON3", codeblock_dltb_ejdl)
|
||||
arcpy.management.CalculateField(dltb_features, "YJDL", "calculate_yjdl(!DLBM!)", "PYTHON3", codeblock_dltb_yjdl)
|
||||
arcpy.management.CalculateField(dltb_features, "YJDLBM", "!DLBM![:2]", "PYTHON3")
|
||||
|
||||
raster_path = Path(assign_raster)
|
||||
# if "二普" in raster_path.stem or "测土" in raster_path.stem:
|
||||
arcpy.management.CalculateField(target_features, "dPH", "!RASTERVALU!-!PH!", "PYTHON3", field_type="DOUBLE")
|
||||
# else:
|
||||
# arcpy.management.CalculateField(target_features, "dPH", "!PH!-!RASTERVALU!", "PYTHON3", field_type="DOUBLE")
|
||||
except Exception as e:
|
||||
print(e)
|
||||
|
||||
# --- 2. 定义要保留的字段 ---
|
||||
# 这是一个非常清晰的配置方式：指定每个图层要保留的字段列表
|
||||
fields_to_keep = {
|
||||
target_features: ["PH", "RASTERVALU", "dPH"],
|
||||
trlx_features: ["YL", "TS"],
|
||||
xzq_features: ["XZQMC"],
|
||||
dltb_features: ["YJDL", "EJDL"]
|
||||
}
|
||||
|
||||
print("开始配置字段映射...")
|
||||
|
||||
# 初始化当前的目标图层，最开始是原始的目标图层
|
||||
current_target = target_features
|
||||
|
||||
# 存储所有中间生成的临时文件，以便最后清理
|
||||
temp_outputs = []
|
||||
|
||||
temp_outputs.append(target_features)
|
||||
|
||||
# 获取目标图层的所有字段，以便在后续迭代中保留
|
||||
retained_fields = fields_to_keep.get(target_features, [])
|
||||
|
||||
|
||||
# 迭代处理每一个连接图层
|
||||
for i, join_features in enumerate(join_features_list):
|
||||
print(f"\n--- 开始处理第 {i+1} 个连接图层: {join_features} ---")
|
||||
|
||||
# 检查连接图层是否存在
|
||||
if not arcpy.Exists(join_features):
|
||||
print(f"警告: 连接图层 '{join_features}' 不存在，将跳过此连接。")
|
||||
continue
|
||||
|
||||
# --- 配置 FieldMappings ---
|
||||
field_mappings = arcpy.FieldMappings()
|
||||
|
||||
# a. 保留已经存在于 current_target 中的字段
|
||||
# 这些字段是在之前的迭代中保留下来的
|
||||
for field_name in retained_fields:
|
||||
try:
|
||||
field_map = arcpy.FieldMap()
|
||||
field_map.addInputField(current_target, field_name)
|
||||
field_mappings.addFieldMap(field_map)
|
||||
except Exception:
|
||||
# 如果字段在之前的某个步骤中未能成功添加，这里会捕获异常
|
||||
print(f"注意: 在图层 '{current_target}' 中未找到字段 '{field_name}'，可能在之前的步骤中已被跳过。")
|
||||
|
||||
|
||||
# b. 从当前的 join_features 中添加新字段
|
||||
fields_from_current_join = fields_to_keep.get(join_features, [])
|
||||
for field_name in fields_from_current_join:
|
||||
try:
|
||||
field_map = arcpy.FieldMap()
|
||||
field_map.addInputField(join_features, field_name)
|
||||
field_map.mergeRule = "First" # 对所有连接字段使用 "First" 规则
|
||||
field_mappings.addFieldMap(field_map)
|
||||
except Exception as e:
|
||||
print(f"警告: 添加字段 '{field_name}' (来自 '{join_features}') 时出错，将跳过。错误信息: {e}")
|
||||
|
||||
# 如果本次迭代没有有效的字段映射，则跳过
|
||||
if field_mappings.fieldCount == 0:
|
||||
print(f"警告: 对于连接图层 '{join_features}' 没有有效的字段可以添加，跳过此连接。")
|
||||
continue
|
||||
|
||||
# 定义本次连接的临时输出名
|
||||
# 使用 in_memory 工作空间可以提高性能
|
||||
temp_output = f"in_memory/temp_join_{i}"
|
||||
temp_outputs.append(temp_output)
|
||||
|
||||
print(f"执行空间连接: '{current_target}' + '{join_features}' -> '{temp_output}'")
|
||||
|
||||
# 执行空间连接
|
||||
arcpy.analysis.SpatialJoin(
|
||||
target_features=current_target,
|
||||
join_features=join_features,
|
||||
out_feature_class=temp_output,
|
||||
join_operation="JOIN_ONE_TO_ONE",
|
||||
join_type="KEEP_ALL",
|
||||
field_mapping=field_mappings,
|
||||
match_option="INTERSECT"
|
||||
)
|
||||
|
||||
# 更新 current_target 为本次操作的输出，以便下一次迭代使用
|
||||
current_target = temp_output
|
||||
|
||||
# 更新已保留字段列表，为下一次迭代做准备
|
||||
retained_fields.extend(fields_from_current_join)
|
||||
print(f"连接成功。目前已保留的字段: {retained_fields}")
|
||||
|
||||
# --- 4. 保存最终结果并清理 ---
|
||||
|
||||
# 将最后一个临时输出复制或重命名为最终结果
|
||||
if arcpy.Exists(current_target):
|
||||
print(f"\n所有连接完成。将最终结果 '{current_target}' 保存为 '{final_output_fc}'...")
|
||||
# arcpy.management.CopyFeatures(current_target, final_output_fc)
|
||||
arcpy.conversion.ExportTable(current_target, final_output_fc)
|
||||
print("最终结果已保存。")
|
||||
|
||||
# 验证输出字段
|
||||
output_fields = [f.name for f in arcpy.ListFields(final_output_fc)]
|
||||
print(f"最终输出的字段为: {output_fields}")
|
||||
else:
|
||||
print("警告: 没有任何连接操作成功执行，未生成最终输出。")
|
||||
|
||||
except arcpy.ExecuteError:
|
||||
print("\n--- ArcPy 执行错误 ---")
|
||||
print(arcpy.GetMessages(2))
|
||||
except Exception as e:
|
||||
print(f"\n--- 发生未预料的错误 ---")
|
||||
print(e)
|
||||
finally:
|
||||
# 清理所有中间生成的临时文件
|
||||
print("\n开始清理临时文件...")
|
||||
for temp_file in temp_outputs:
|
||||
if arcpy.Exists(temp_file):
|
||||
arcpy.management.Delete(temp_file)
|
||||
print(f"已删除临时文件: {temp_file}")
|
||||
print("清理完成。")
|
||||
641
tools/core/acid_stats/行政区划酸化统计表.py
Normal file
641
tools/core/acid_stats/行政区划酸化统计表.py
Normal file
@@ -0,0 +1,641 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
import os
|
||||
import arcpy
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
from openpyxl import Workbook
|
||||
from openpyxl.styles import Font
|
||||
from openpyxl.utils import get_column_letter
|
||||
from tools.config.arcgis_field_cal_code import codeblock_cal_shfj
|
||||
from tools.core.utils.excel_utils import ExcelStyleUtils
|
||||
|
||||
|
||||
|
||||
yjdl_order = ["耕地", "园地", "林地", "草地", "其他"]
|
||||
ejdl_order = ["水田", "旱地", "水浇地", "果园", "茶园", "橡胶园", "其他园地"]
|
||||
|
||||
# --- 2. 辅助函数 ---
|
||||
# 等级计算
|
||||
def get_acidification_degree(delta_ph):
|
||||
"""根据ΔpH值判断酸化程度"""
|
||||
if pd.isna(delta_ph) or delta_ph == 0:
|
||||
return "-"
|
||||
# 请根据您的实际分级标准调整这里的阈值
|
||||
if delta_ph > 1.0:
|
||||
return "重度酸化"
|
||||
elif 0.5 < delta_ph <= 1.0:
|
||||
return "中度酸化"
|
||||
elif 0.3 < delta_ph <= 0.5:
|
||||
return "轻度酸化"
|
||||
elif 0.1 < delta_ph <= 0.3:
|
||||
return "弱酸化"
|
||||
else: # dPH < -0.3
|
||||
return "其他"
|
||||
|
||||
# --- 3. 数据处理与分析 均值---
|
||||
def process_data_for_table5_7(gdb_path, mean_table_name, sample_table_name):
|
||||
"""
|
||||
【最终版 v2】: 增加对制图样点数的处理，以支持加权平均计算。
|
||||
"""
|
||||
print("开始处理数据...")
|
||||
|
||||
def clean_df(df, columns):
|
||||
for col in columns:
|
||||
df[col] = df[col].astype(str).str.strip()
|
||||
df.replace(['<Null>', 'None', '', '<空>'], np.nan, inplace=True)
|
||||
df.dropna(subset=columns, inplace=True)
|
||||
return df
|
||||
|
||||
# --- a. 处理样点数据，计算“样点均值” ---
|
||||
print("--> 步骤1: 计算样点均值...")
|
||||
sample_table_path = os.path.join(gdb_path, sample_table_name)
|
||||
sample_fields = ['XZQMC','YJDL','EJDL', 'dPH']
|
||||
df_samples = pd.DataFrame(arcpy.da.TableToNumPyArray(sample_table_path, sample_fields, 'dPH>0.3', skip_nulls=False))
|
||||
df_samples = clean_df(df_samples, ['XZQMC','YJDL', 'EJDL'])
|
||||
|
||||
# 按 YJDL, EJDL 分组，计算 dPH 的均值
|
||||
df_sample_means = df_samples.groupby(['XZQMC'])['dPH'].mean().reset_index()
|
||||
df_sample_means.rename(columns={'dPH': '样点均值'}, inplace=True)
|
||||
print("样点均值计算完成。")
|
||||
|
||||
# --- b. 处理制图数据，获取“制图均值”和“制图样点数” ---
|
||||
print("--> 步骤2: 获取制图均值和样点数...")
|
||||
mean_table_path = os.path.join(gdb_path, mean_table_name)
|
||||
mean_fields = ['XZQMC', 'MEAN', 'COUNT']
|
||||
df_map_data = pd.DataFrame(arcpy.da.TableToNumPyArray(mean_table_path, mean_fields, skip_nulls=False))
|
||||
df_map_data = clean_df(df_map_data, ['XZQMC'])
|
||||
df_map_data.rename(columns={'MEAN': '制图均值', 'COUNT': '制图样点数'}, inplace=True)
|
||||
print("制图数据获取完成。")
|
||||
|
||||
# --- c. 合并数据 ---
|
||||
print("--> 步骤3: 合并数据...")
|
||||
df_skeleton = pd.concat([
|
||||
df_sample_means[['XZQMC']],
|
||||
df_map_data[['XZQMC']]
|
||||
]).drop_duplicates().reset_index(drop=True)
|
||||
|
||||
df_final = pd.merge(df_skeleton, df_sample_means, on=['XZQMC'], how='left')
|
||||
# **【核心修改】: 合并整个 df_map_data，而不仅仅是均值列**
|
||||
df_final = pd.merge(df_final, df_map_data, on=['XZQMC'], how='left')
|
||||
|
||||
# --- d. 计算酸化程度 ---
|
||||
print("--> 步骤4: 计算酸化程度...")
|
||||
# **【核心修改】: 在计算酸化程度之前，先过滤掉不展示的行**
|
||||
# 我们只对 dPH 在酸化范围内 ( > 0.3) 的数据感兴趣
|
||||
# 但为了计算合计，我们需要保留所有数据，所以这一步只计算，不删除
|
||||
df_final['酸化程度_样本'] = df_final['样点均值'].apply(get_acidification_degree)
|
||||
df_final['酸化程度_制图'] = df_final['制图均值'].apply(get_acidification_degree)
|
||||
|
||||
df_final.sort_values(['XZQMC'], inplace=True)
|
||||
|
||||
print("数据处理流程完成！")
|
||||
return df_final
|
||||
|
||||
|
||||
# --- 4. Excel 制表 均值---
|
||||
def write_to_excel_table5_7(df, output_path):
|
||||
"""
|
||||
将处理好的数据写入格式化的 Excel 文件。
|
||||
"""
|
||||
if df.empty:
|
||||
print("警告: 没有数据可以写入 Excel。")
|
||||
return
|
||||
|
||||
print(f"开始生成 Excel 报告到 '{output_path}'...")
|
||||
wb = Workbook()
|
||||
ws = wb.create_sheet("Mysheet", 0)
|
||||
ws.title = "不同土地利用类型pH变化统计"
|
||||
|
||||
# --- b. 绘制表头 ---
|
||||
ws.merge_cells('A1:A2'); ws['A1'] = '乡镇/街道'
|
||||
ws.merge_cells('B1:E1'); ws['B1'] = 'ΔpH'
|
||||
|
||||
ws['B2'] = '样点均值'
|
||||
ws['C2'] = '酸化程度'
|
||||
ws['D2'] = '制图均值'
|
||||
ws['E2'] = '酸化程度'
|
||||
|
||||
# --- c. 填充数据 ---
|
||||
current_row = 3
|
||||
|
||||
# **【核心修改】: 先对整个DataFrame进行过滤，只保留需要展示的行**
|
||||
acid_levels_to_show = ["弱酸化", "轻度酸化", "中度酸化", "重度酸化", "其他"]
|
||||
df_to_write = df[
|
||||
df['酸化程度_样本'].isin(acid_levels_to_show) | df['酸化程度_制图'].isin(acid_levels_to_show)
|
||||
].copy() # 使用 .copy() 避免 SettingWithCopyWarning
|
||||
|
||||
for _, row_data in df_to_write.iterrows():
|
||||
|
||||
print(f"正在写入一级地类...")
|
||||
|
||||
# 写入数据”
|
||||
ws.cell(row=current_row, column=1).value = row_data['XZQMC']
|
||||
|
||||
# 填充样点数据
|
||||
sample_mean = row_data.get('样点均值')
|
||||
if pd.notna(sample_mean):
|
||||
ws.cell(row=current_row, column=2).value = f"{sample_mean:.2f}" if sample_mean > 0.3 else "-"
|
||||
ws.cell(row=current_row, column=3).value = row_data.get('酸化程度_样本', '-') if sample_mean > 0.3 else "-"
|
||||
else:
|
||||
ws.cell(row=current_row, column=2).value = "-"
|
||||
ws.cell(row=current_row, column=3).value = "-"
|
||||
|
||||
# 填充制图数据
|
||||
map_mean = row_data.get('制图均值')
|
||||
if pd.notna(map_mean):
|
||||
ws.cell(row=current_row, column=4).value = f"{map_mean:.2f}" if map_mean > 0.3 else "-"
|
||||
ws.cell(row=current_row, column=5).value = row_data.get('酸化程度_制图', '-') if map_mean > 0.3 else "-"
|
||||
else:
|
||||
ws.cell(row=current_row, column=4).value = "-"
|
||||
ws.cell(row=current_row, column=5).value = "-"
|
||||
|
||||
current_row += 1
|
||||
|
||||
# --- a. 定义样式 ---
|
||||
header_font = Font(name='等线', size=11, bold=True)
|
||||
|
||||
# --- d. 应用样式和调整列宽 ---
|
||||
max_col_letter = get_column_letter(ws.max_column)
|
||||
if current_row > 1: # 确保有数据才应用样式
|
||||
ExcelStyleUtils.set_style(ws, f'A1:{max_col_letter}{current_row-1}')
|
||||
ExcelStyleUtils.set_style(ws, f'A1:{max_col_letter}2', header_font)
|
||||
|
||||
print("正在自动调整列宽...")
|
||||
|
||||
# 设置列宽
|
||||
ExcelStyleUtils.auto_adjust_column_width(ws)
|
||||
|
||||
# --- e. 保存文件 ---
|
||||
wb.save(output_path)
|
||||
print("Excel 报告生成成功！")
|
||||
|
||||
|
||||
# --- 2. 数据处理与分析 面积 各乡镇---
|
||||
def process_data_for_table5_4(gdb_path, area_table_name, target_area_dict):
|
||||
"""
|
||||
【最终修正版 v2】: 先建立统一的层级结构，再分别合并统计结果。
|
||||
"""
|
||||
print("【最终修正版 v2】开始处理数据...")
|
||||
|
||||
def clean_df(df, columns):
|
||||
for col in columns:
|
||||
df[col] = df[col].astype(str).str.strip()
|
||||
df.replace(['<Null>', 'None', '', '<空>'], np.nan, inplace=True)
|
||||
df.dropna(subset=columns, inplace=True)
|
||||
return df
|
||||
|
||||
# --- a. 独立统计面积数据 ---
|
||||
print("--> 步骤1: 独立统计面积数据...")
|
||||
area_table_path = os.path.join(gdb_path, area_table_name)
|
||||
df_area = pd.DataFrame(arcpy.da.TableToNumPyArray(area_table_path, ['XZQMC', 'SHFJ', 'AREA'], skip_nulls=False))
|
||||
df_area = clean_df(df_area, ['XZQMC'])
|
||||
|
||||
df_final = pd.DataFrame()
|
||||
if not df_area.empty:
|
||||
# 计算平差系数
|
||||
target_shfj_areas = target_area_dict.groupby(['SHFJ'])['AREA_MU'].sum().reset_index()
|
||||
original_shfj_areas = df_area.groupby(['SHFJ'])['AREA'].sum().reset_index()
|
||||
original_shfj_areas['AREA_MU'] = original_shfj_areas['AREA'] * 0.0015
|
||||
|
||||
adjustment_factors = []
|
||||
for index, row in original_shfj_areas.iterrows():
|
||||
shfj = row['SHFJ']
|
||||
area_mu = row['AREA_MU']
|
||||
adjustment_factor = target_shfj_areas[target_shfj_areas['SHFJ'] == shfj]['AREA_MU'].values[0] / area_mu
|
||||
adjustment_factors.append({
|
||||
'SHFJ': shfj,
|
||||
'平差系数':adjustment_factor
|
||||
})
|
||||
|
||||
|
||||
factor_df = pd.DataFrame(adjustment_factors)
|
||||
|
||||
df_sh_area = df_area.merge(factor_df[['SHFJ', '平差系数']], on='SHFJ')
|
||||
|
||||
df_sh_area['制图面积_亩'] = df_sh_area['AREA'] * 0.0015 * df_sh_area['平差系数']
|
||||
ts_total_area = df_sh_area.groupby(['XZQMC'])['制图面积_亩'].transform('sum')
|
||||
df_sh_area['面积占比'] = (df_sh_area['制图面积_亩'] / ts_total_area) * 100
|
||||
df_area_stats = df_sh_area.pivot_table(
|
||||
index=['XZQMC'], columns='SHFJ', values=['制图面积_亩', '面积占比'], fill_value=0
|
||||
).reset_index()
|
||||
df_area_stats.columns = [f'{col[0]}_{col[1]}'.strip('_') if col[1] else col[0] for col in df_area_stats.columns]
|
||||
|
||||
df_final = df_area_stats
|
||||
|
||||
print("--> 步骤2: 计算酸化面积合计...")
|
||||
|
||||
# 定义属于酸化类别的面积列
|
||||
acidic_area_cols = [
|
||||
'制图面积_亩_轻度酸化',
|
||||
'制图面积_亩_中度酸化',
|
||||
'制图面积_亩_重度酸化'
|
||||
]
|
||||
|
||||
# 确保这些列存在于DataFrame中，不存在的列用0代替
|
||||
for col in acidic_area_cols:
|
||||
if col not in df_final.columns:
|
||||
df_final[col] = 0
|
||||
|
||||
# 将这三列相加，得到合计值
|
||||
df_final['酸化面积合计_亩'] = df_final[acidic_area_cols].sum(axis=1)
|
||||
|
||||
# --- d. 最后清理和构建映射 ---
|
||||
df_final.fillna(0, inplace=True)
|
||||
|
||||
print("数据处理流程完成！")
|
||||
return df_final
|
||||
|
||||
# --- 3. Excel 制表 面积---
|
||||
def write_to_excel_table5_4(df, output_path):
|
||||
"""
|
||||
【最终修正版】: 将处理好的数据写入格式化的 Excel 文件。
|
||||
"""
|
||||
if df.empty:
|
||||
print("警告: 没有数据可以写入 Excel，将创建一个空的报告。")
|
||||
wb = Workbook()
|
||||
ws = wb.create_sheet("Mysheet", 0)
|
||||
ws.title = "不同乡镇酸化面积统计"
|
||||
ws['A1'] = "没有有效的统计数据。"
|
||||
wb.save(output_path)
|
||||
return
|
||||
|
||||
print(f"开始生成 Excel 报告到 '{output_path}'...")
|
||||
wb = Workbook()
|
||||
ws = wb.create_sheet("Mysheet", 0)
|
||||
ws.title = "不同乡镇酸化面积统计"
|
||||
|
||||
# --- b. 绘制表头 (不变) ---
|
||||
ws.merge_cells('A1:A2'); ws['A1'] = '乡镇/街道'
|
||||
|
||||
acid_levels = ['弱酸化', '轻度酸化', '中度酸化', '重度酸化', '其他']
|
||||
# acid_level_headers = ['0.1<ΔpH≤0.3', '0.3<ΔpH≤0.5', '0.5<ΔpH≤1.0', 'ΔpH>1.0', '其他']
|
||||
# all_possible_levels = ['碱化', '未酸化', '轻度酸化', '中度酸化', '重度酸化']
|
||||
acid_level_headers = ['弱酸化(0.1<ΔpH≤0.3)','轻度酸化(0.3<ΔpH≤0.5)', '中度酸化(0.5<ΔpH≤1.0)', '重度酸化(ΔpH>1.0)', '其他(未酸化)']
|
||||
|
||||
col_start = 2
|
||||
for header in acid_level_headers:
|
||||
ws.merge_cells(start_row=1, start_column=col_start, end_row=1, end_column=col_start + 1)
|
||||
ws.cell(row=1, column=col_start).value = header
|
||||
ws.cell(row=2, column=col_start).value = '面积/亩'
|
||||
ws.cell(row=2, column=col_start + 1).value = '占比/%'
|
||||
col_start += 2
|
||||
|
||||
# 增加合计列的表头**
|
||||
total_col = col_start # 记录合计列的列号
|
||||
ws.merge_cells(start_row=1, start_column=total_col, end_row=2, end_column=total_col)
|
||||
ws.cell(row=1, column=total_col).value = '酸化面积合计'
|
||||
|
||||
# --- c. 填充数据 (完全重构的逻辑) ---
|
||||
current_row = 3
|
||||
|
||||
# **【核心修改】: 不再需要 group_yl_df，直接遍历整个 df**
|
||||
# 假设 df 已经按 XZQMC 排序（如果需要的话）
|
||||
df_sorted = df.sort_values('XZQMC').reset_index(drop=True)
|
||||
|
||||
for index, row_data in df_sorted.iterrows():
|
||||
ws.cell(row=current_row, column=1).value = row_data['XZQMC']
|
||||
|
||||
col_start = 2
|
||||
for level in acid_levels:
|
||||
area_col = f'制图面积_亩_{level}'
|
||||
area_pct_col = f'面积占比_{level}'
|
||||
area_val = row_data.get(area_col, 0)
|
||||
area_pct_val = row_data.get(area_pct_col, 0)
|
||||
|
||||
ws.cell(row=current_row, column=col_start).value = f"{area_val:.0f}" if area_val > 0 else "-"
|
||||
ws.cell(row=current_row, column=col_start + 1).value = f"{area_pct_val:.2f}%" if area_val > 0 else "-"
|
||||
col_start += 2
|
||||
|
||||
# **【核心修改】: 填充酸化面积合计列的值**
|
||||
total_area_val = row_data.get('酸化面积合计_亩', 0)
|
||||
ws.cell(row=current_row, column=total_col).value = f"{total_area_val:.0f}" if total_area_val > 0 else "-"
|
||||
|
||||
current_row += 1
|
||||
|
||||
# **(可选) 增加一个所有乡镇的“总合计”行**
|
||||
# print("--> 计算并写入总合计行...")
|
||||
# ws.cell(row=current_row, column=1).value = '总合计'
|
||||
|
||||
# col_start = 2
|
||||
# for level in acid_levels:
|
||||
# area_col = f'制图面积_亩_{level}'
|
||||
# area_sum = df_sorted.get(area_col, 0).sum()
|
||||
# # 总合计行的占比是相对于所有乡镇的总面积
|
||||
# grand_total_area = df_sorted[[f'制图面积_亩_{lvl}' for lvl in all_possible_levels if f'制图面积_亩_{lvl}' in df_sorted]].sum().sum()
|
||||
# area_perc = (area_sum / grand_total_area * 100) if grand_total_area > 0 else 0
|
||||
|
||||
# ws.cell(row=current_row, column=col_start).value = f"{area_sum:.2f}" if area_sum > 0 else "-"
|
||||
# ws.cell(row=current_row, column=col_start + 1).value = f"{area_perc:.2f}" if area_sum > 0 else "-"
|
||||
# col_start += 2
|
||||
|
||||
# grand_total_acidic_area = df_sorted['酸化面积合计_亩'].sum()
|
||||
# ws.cell(row=current_row, column=total_col).value = f"{grand_total_acidic_area:.2f}" if grand_total_acidic_area > 0 else "-"
|
||||
# current_row += 1
|
||||
|
||||
# --- a. 定义样式 (不变) ---
|
||||
header_font = Font(name='等线', size=11, bold=True)
|
||||
|
||||
# --- d. 应用样式和调整列宽 (最终健壮版) ---
|
||||
max_col_letter = get_column_letter(ws.max_column)
|
||||
if current_row > 1: # 确保有数据才应用样式
|
||||
ExcelStyleUtils.set_style(ws, f'A1:{max_col_letter}{current_row-1}')
|
||||
ExcelStyleUtils.set_style(ws, f'A1:{max_col_letter}2', header_font)
|
||||
|
||||
print("正在自动调整列宽...")
|
||||
# 设置列宽
|
||||
ExcelStyleUtils.auto_adjust_column_width(ws)
|
||||
|
||||
# --- e. 保存文件 ---
|
||||
wb.save(output_path)
|
||||
print("Excel 报告生成成功！")
|
||||
|
||||
# 步骤5.3: 生成表5.3 - 总表数据处理
|
||||
def process_data_for_table5_2(gdb_path, area_table_name, sample_table_name, target_area_dict:pd.DataFrame):
|
||||
def clean_df(df, columns):
|
||||
for col in columns:
|
||||
df[col] = df[col].astype(str).str.strip()
|
||||
df.replace(['<Null>', 'None', '', '<空>'], np.nan, inplace=True)
|
||||
df.dropna(subset=columns, inplace=True)
|
||||
return df
|
||||
|
||||
# --- a. 从两个表中提取并建立唯一的 (YJDL, EJDL) 层级结构 "骨架" ---
|
||||
print("--> 步骤1: 建立统一的层级结构...")
|
||||
sample_table_path = os.path.join(gdb_path, sample_table_name)
|
||||
area_table_path = os.path.join(gdb_path, area_table_name)
|
||||
|
||||
|
||||
# --- b. 独立统计样点数据 ---
|
||||
print("--> 步骤2: 独立统计样点数据...")
|
||||
df_samples = pd.DataFrame(arcpy.da.TableToNumPyArray(sample_table_path, ['XZQMC', 'dPH'], skip_nulls=False))
|
||||
df_samples = clean_df(df_samples, ['XZQMC'])
|
||||
|
||||
if not df_samples.empty:
|
||||
bins = [-np.inf, 0.1, 0.3, 0.5, 1.0, np.inf]
|
||||
labels = ["其他", "弱酸化", "轻度酸化", "中度酸化", "重度酸化"]
|
||||
df_samples['SHFJ'] = pd.cut(df_samples['dPH'], bins=bins, labels=labels, right=True)
|
||||
sample_counts = df_samples.groupby(['SHFJ'], observed=False).size().reset_index(name='样点数')
|
||||
sample_counts = sample_counts.merge(df_samples.groupby(['SHFJ'], observed=False)['dPH'].mean(), on='SHFJ')
|
||||
ts_total_samples = sample_counts['样点数'].sum()
|
||||
sample_counts['样点占比'] = (sample_counts['样点数'] / ts_total_samples) * 100
|
||||
# print(sample_counts)
|
||||
|
||||
# --- c. 独立统计面积数据 ---
|
||||
print("--> 步骤3: 独立统计面积数据...")
|
||||
df_area = pd.DataFrame(arcpy.da.TableToNumPyArray(area_table_path, ['XZQMC', 'SHFJ', 'AREA'], skip_nulls=False))
|
||||
df_area = clean_df(df_area, ['XZQMC'])
|
||||
|
||||
if not df_area.empty:
|
||||
# 计算平差系数
|
||||
target_shfj_areas = target_area_dict.groupby(['SHFJ'])['AREA_MU'].sum().reset_index()
|
||||
original_shfj_areas = df_area.groupby(['SHFJ'])['AREA'].sum().reset_index()
|
||||
original_shfj_areas['AREA_MU'] = original_shfj_areas['AREA'] * 0.0015
|
||||
|
||||
adjustment_factors = []
|
||||
for index, row in original_shfj_areas.iterrows():
|
||||
shfj = row['SHFJ']
|
||||
area_mu = row['AREA_MU']
|
||||
adjustment_factor = target_shfj_areas[target_shfj_areas['SHFJ'] == shfj]['AREA_MU'].values[0] / area_mu
|
||||
adjustment_factors.append({
|
||||
'SHFJ': shfj,
|
||||
'平差系数':adjustment_factor
|
||||
})
|
||||
|
||||
|
||||
factor_df = pd.DataFrame(adjustment_factors)
|
||||
|
||||
df_sh_area = df_area.merge(factor_df[['SHFJ', '平差系数']], on='SHFJ')
|
||||
|
||||
df_sh_area['制图面积_亩'] = df_sh_area['AREA'] * 0.0015 * df_sh_area['平差系数']
|
||||
df_area_counts = df_sh_area.groupby(['SHFJ'], observed=False)[['制图面积_亩']].sum()
|
||||
ts_total_area = df_area_counts['制图面积_亩'].sum()
|
||||
df_area_counts['面积占比'] = (df_area_counts['制图面积_亩'] / ts_total_area) * 100
|
||||
|
||||
df_final = pd.merge(sample_counts, df_area_counts, on=['SHFJ'], how='left')
|
||||
|
||||
# # --- d. 最后清理和构建映射 ---
|
||||
df_final.fillna(0, inplace=True)
|
||||
|
||||
return df_final
|
||||
|
||||
# --- 3. Excel 制表 总表---
|
||||
def write_to_excel_table5_2(df, df_mean, output_path):
|
||||
"""
|
||||
【最终修正版】: 将处理好的数据写入格式化的 Excel 文件。
|
||||
"""
|
||||
if df.empty:
|
||||
print("警告: 没有数据可以写入 Excel，将创建一个空的报告。")
|
||||
wb = Workbook()
|
||||
ws = wb.create_sheet("Mysheet", 0)
|
||||
ws['A1'] = "没有有效的统计数据。"
|
||||
wb.save(output_path)
|
||||
return
|
||||
|
||||
print(f"开始生成 Excel 报告到 '{output_path}'...")
|
||||
wb = Workbook()
|
||||
ws = wb.create_sheet("Mysheet", 0)
|
||||
ws.title = "行政区酸化程度等级分布及占比"
|
||||
|
||||
# --- b. 绘制表头 (不变) ---
|
||||
ws.merge_cells('A1:B1'); ws['A1'] = '酸化程度'
|
||||
ws.merge_cells('C1:D1'); ws['C1'] = '样点统计'
|
||||
ws.merge_cells('E1:F1'); ws['E1'] = '制图统计'
|
||||
ws.merge_cells('A8:B8'); ws['A8'] = '总计'
|
||||
ws.merge_cells('A9:B9'); ws['A9'] = '全县酸化样点ΔpH 均值'
|
||||
ws.merge_cells('A10:B10'); ws['A10'] = '全县酸化制图ΔpH 均值'
|
||||
|
||||
ws['A2'] = '分级'; ws['B2'] = '值域'
|
||||
ws['C2'] = '数量/个'; ws['D2'] = '占比'
|
||||
ws['E2'] = '面积/亩'; ws['F2'] = '占比'
|
||||
|
||||
acid_levels = ['弱酸化', '轻度酸化', '中度酸化', '重度酸化', '其他']
|
||||
acid_level_headers = ['0.1<ΔpH≤0.3', '0.3<ΔpH≤0.5', '0.5<ΔpH≤1.0', 'ΔpH>1.0', '未酸化']
|
||||
|
||||
# --- c. 填充数据 ---
|
||||
current_row = 3
|
||||
|
||||
# 1. 遍历该一级地类下的所有“二级地类”并写入数据
|
||||
for index,level in enumerate(acid_levels):
|
||||
ws.cell(row=current_row, column=1).value = level
|
||||
ws.cell(row=current_row, column=2).value = acid_level_headers[index]
|
||||
|
||||
# 在子集中查找当前二级地类的数据行
|
||||
row_data = df[df['SHFJ'] == level]
|
||||
|
||||
# --- 填充单元格的逻辑开始 ---
|
||||
col_start = 3 # 从第 C 列开始填充
|
||||
|
||||
# 检查是否找到了该土属的数据
|
||||
if not row_data.empty:
|
||||
data_series = row_data.iloc[0]
|
||||
|
||||
# 1. 构建要从 data_series 中查找的列名
|
||||
sample_col = f'样点数'
|
||||
sample_pct_col = f'样点占比'
|
||||
area_col = f'制图面积_亩'
|
||||
area_pct_col = f'面积占比'
|
||||
|
||||
# 2. 从 data_series 中安全地获取值
|
||||
sample_val = data_series.get(sample_col, 0)
|
||||
sample_pct_val = data_series.get(sample_pct_col, 0)
|
||||
area_val = data_series.get(area_col, 0)
|
||||
area_pct_val = data_series.get(area_pct_col, 0)
|
||||
|
||||
|
||||
# 3. 将获取到的值填入单元格
|
||||
ws.cell(row=current_row, column=col_start).value = f"{sample_val:.0f}" if sample_val > 0 else "-"
|
||||
# 占比/%
|
||||
ws.cell(row=current_row, column=col_start + 1).value = f"{sample_pct_val:.2f}%" if sample_val > 0 else "-"
|
||||
# 制图面积/亩
|
||||
ws.cell(row=current_row, column=col_start + 2).value = f"{area_val:.0f}" if area_val > 0 else "-"
|
||||
# 占比/%
|
||||
ws.cell(row=current_row, column=col_start + 3).value = f"{area_pct_val:.2f}%" if area_val > 0 else "-"
|
||||
|
||||
# 移动到下一个酸化等级的起始列
|
||||
col_start += 2
|
||||
else:
|
||||
for _ in range(4):
|
||||
ws.cell(row=current_row, column=col_start).value = "-"
|
||||
col_start += 1
|
||||
|
||||
current_row += 1
|
||||
|
||||
# 合计单元格填充
|
||||
mask = df["SHFJ"].isin(acid_levels)
|
||||
df_acid = df[mask]
|
||||
weighted_avg = (df_acid["dPH"] * df_acid["样点数"]).sum() / df_acid["样点数"].sum()
|
||||
|
||||
mean_msk = df_mean["酸化程度_制图"].isin(acid_levels)
|
||||
df_mean_acid = df_mean[mean_msk]
|
||||
weighted_mean = (df_mean_acid["制图均值"] * df_mean_acid["制图样点数"]).sum() / df_mean_acid["制图样点数"].sum()
|
||||
|
||||
ws.merge_cells('C9:F9')
|
||||
ws.merge_cells('C10:F10')
|
||||
ws['C8'] = df[df['SHFJ'].isin(acid_levels)]['样点数'].sum()
|
||||
ws['D8'] = f"{df[df['SHFJ'].isin(acid_levels)]['样点占比'].sum():.2f}%"
|
||||
ws['E8'] = f"{df[df['SHFJ'].isin(acid_levels)]['制图面积_亩'].sum():.0f}"
|
||||
ws['F8'] = f"{df[df['SHFJ'].isin(acid_levels)]['面积占比'].sum():.2f}%"
|
||||
ws['C9'] = f"{weighted_avg:.2f}" # type: ignore
|
||||
ws['C10'] = f"{weighted_mean:.2f}"
|
||||
|
||||
# --- a. 定义样式 (不变) ---
|
||||
header_font = Font(name='宋体', size=11)
|
||||
|
||||
# --- d. 应用样式和调整列宽 (最终健壮版) ---
|
||||
if current_row > 1: # 确保有数据才应用样式
|
||||
ExcelStyleUtils.set_style(ws, f'A1:F10')
|
||||
ExcelStyleUtils.set_style(ws, f'A1:F2', header_font)
|
||||
|
||||
print("正在自动调整列宽...")
|
||||
|
||||
# 设置列宽
|
||||
ExcelStyleUtils.auto_adjust_column_width(ws)
|
||||
|
||||
# --- e. 保存文件 ---
|
||||
wb.save(output_path)
|
||||
print("Excel 报告生成成功！")
|
||||
|
||||
|
||||
def main(gdb_path, xzq_features, ph_features, dltb_features, sh_ph_tif, output_path,target_areas_dict:dict):
|
||||
try:
|
||||
# --- 1. 用户配置 ---
|
||||
# 输出配置
|
||||
output_excel_path = os.path.join(output_path,"乡镇街道酸化统计表.xlsx") # 生成的Excel报告文件路径
|
||||
|
||||
# 设置工作空间和变量
|
||||
arcpy.env.workspace = gdb_path
|
||||
arcpy.env.overwriteOutput = True
|
||||
|
||||
sample_table_name = "历史样点PH信息_Table" # 图2: 样点信息表名
|
||||
in_zone_feature = xzq_features # 规划分区图层
|
||||
in_class_feature = ph_features # 已重分类好的酸化PH图层
|
||||
dltb_class_feature = dltb_features
|
||||
in_value_raster = sh_ph_tif # 赋值栅格
|
||||
out_feature_class = "最小面积统计单元"
|
||||
out_table_area = r"行政区划_酸化面积表" # 输出的交集表名
|
||||
out_table_mean = r"行政区划_酸化均值表" # 输出的均值表名
|
||||
|
||||
print("开始处理数据...")
|
||||
|
||||
if not arcpy.Exists(out_feature_class):
|
||||
# 判断输入表是否存在SHFJ字段
|
||||
try:
|
||||
arcpy.management.CalculateField(in_class_feature, "SHFJ", "calculate_shfj(!gridcode!)", "PYTHON3", codeblock_cal_shfj)
|
||||
except Exception as e:
|
||||
print(f"计算SHFJ字段时发生错误: {e}")
|
||||
|
||||
arcpy.analysis.Intersect(
|
||||
in_features=[dltb_class_feature, in_class_feature],
|
||||
out_feature_class=out_feature_class,
|
||||
join_attributes="ALL",
|
||||
output_type="INPUT"
|
||||
)
|
||||
|
||||
if not arcpy.Exists(out_table_area):
|
||||
# 1.用arcpy.analysis.TabulateIntersection进行交集制表
|
||||
arcpy.analysis.TabulateIntersection(
|
||||
in_zone_feature,
|
||||
["XZQMC"],
|
||||
out_feature_class,
|
||||
out_table_area,
|
||||
"SHFJ",
|
||||
out_units="SQUARE_METERS",
|
||||
)
|
||||
|
||||
if not arcpy.Exists(out_table_mean):
|
||||
# 2.用arcpy.sa.ZonalStatisticsAsTable进行区域统计
|
||||
arcpy.sa.ZonalStatisticsAsTable(
|
||||
in_zone_feature, "XZQMC", in_value_raster, out_table_mean, "DATA", "MEAN"
|
||||
)
|
||||
|
||||
# 计算按地类平差后的各酸化等级面积
|
||||
if arcpy.Exists(out_feature_class):
|
||||
df = pd.DataFrame(arcpy.da.TableToNumPyArray(out_feature_class, ["YJDL", "SHFJ", "Shape_Area"]))
|
||||
df_area = df.groupby(["YJDL", "SHFJ"]).agg({"Shape_Area": "sum"}).reset_index()
|
||||
|
||||
yjdl_area = df_area.groupby(['YJDL'])['Shape_Area'].sum().reset_index()
|
||||
|
||||
landuse_types = {'耕地':'01', '园地':'02', '林地':'03', '草地':'04', '其他':'12'}
|
||||
adjustment_factors = []
|
||||
for _, row in yjdl_area.iterrows():
|
||||
yjdl = row['YJDL']
|
||||
original_total = row['Shape_Area'] * 0.0015
|
||||
target_total = target_areas_dict.get(landuse_types[yjdl], original_total)
|
||||
adjustment_factor = target_total / original_total
|
||||
|
||||
adjustment_factors.append({
|
||||
'YJDL': yjdl,
|
||||
'平差系数': adjustment_factor
|
||||
})
|
||||
|
||||
factor_df = pd.DataFrame(adjustment_factors)
|
||||
|
||||
df_with_factors = df_area.merge(factor_df[['YJDL', '平差系数']], on='YJDL')
|
||||
df_with_factors['AREA_MU'] = df_with_factors['Shape_Area'] * df_with_factors['平差系数'] * 0.0015
|
||||
|
||||
# print(df_with_factors)
|
||||
|
||||
# 生成表5.4的面积统计Excel报告
|
||||
final_area_dataframe = process_data_for_table5_4(gdb_path, out_table_area, df_with_factors)
|
||||
write_to_excel_table5_4(final_area_dataframe, output_excel_path)
|
||||
|
||||
# 生成表5.3的均值统计Excel报告
|
||||
final_mean_dataframe = process_data_for_table5_7(gdb_path, out_table_mean, sample_table_name)
|
||||
write_to_excel_table5_7(final_mean_dataframe, output_excel_path.replace(".xlsx", "_mean.xlsx"))
|
||||
|
||||
# 生成总表5.2的统计Excel报告
|
||||
final_dataframe = process_data_for_table5_2(gdb_path, out_table_area, sample_table_name, df_with_factors)
|
||||
write_to_excel_table5_2(final_dataframe, final_mean_dataframe, output_excel_path.replace(".xlsx", "_total.xlsx"))
|
||||
|
||||
return df_with_factors
|
||||
except Exception as e:
|
||||
print(f"\n处理过程中发生严重错误: {e}")
|
||||
import traceback
|
||||
|
||||
traceback.print_exc()
|
||||
finally:
|
||||
import gc
|
||||
gc.collect()
|
||||
|
||||
# --- 4. 主程序入口 ---
|
||||
# if __name__ == "__main__":
|
||||
# main()
|
||||
167
tools/core/export_excel_to_jpg_v1.py
Normal file
167
tools/core/export_excel_to_jpg_v1.py
Normal file
@@ -0,0 +1,167 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
"""
|
||||
输入重分类后栅格转面要素类、乡镇边界面要素类、地类图斑要素类；
|
||||
按一级地类统计土壤属性面积 和 按乡镇统计土壤属性面积；
|
||||
将统计结果导出为Excel表格；
|
||||
将Excel表格转换为jpg图片；
|
||||
"""
|
||||
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
import sys
|
||||
import traceback
|
||||
import argparse
|
||||
import win32com.client as win32
|
||||
import pythoncom
|
||||
import time
|
||||
|
||||
sys.path.append(str(Path(__file__).parent))
|
||||
|
||||
def parse_arguments():
|
||||
"""解析命令行参数"""
|
||||
parser = argparse.ArgumentParser(description="将Excel表格转换为jpg图片")
|
||||
parser.add_argument("--settings_path", required=True, help="配置文件路径")
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
if args.settings_path:
|
||||
with open(args.settings_path, 'r', encoding="utf-8") as settings_file:
|
||||
settings = json.load(settings_file)
|
||||
area_stat_settings = settings.get("area_stat_settings", {})
|
||||
else:
|
||||
print_status("错误: 未找到有效配置文件")
|
||||
sys.exit(1)
|
||||
|
||||
return area_stat_settings
|
||||
def print_status(message):
|
||||
"""
|
||||
输出状态信息到标准输出，用于 GUI 实时显示
|
||||
格式: STATUS: <message>
|
||||
"""
|
||||
print(f"STATUS:{message}")
|
||||
sys.stdout.flush() # 确保立即输出
|
||||
|
||||
def print_result(success, output_path="", error_message=""):
|
||||
"""
|
||||
输出最终结果到标准输出，用于 GUI 判断任务状态和获取结果
|
||||
格式: RESULT:True|<output_path>|
|
||||
格式: RESULT:False||<error_message>
|
||||
"""
|
||||
if success:
|
||||
print(f"RESULT:True|{output_path}|")
|
||||
else:
|
||||
# 在错误信息中替换换行符，避免干扰解析
|
||||
cleaned_error_message = error_message.replace('\n', ' ').replace('\r', '')
|
||||
print(f"RESULT:False||{cleaned_error_message}")
|
||||
sys.stdout.flush() # 确保立即输出
|
||||
|
||||
def export_excel_to_image(excel_path, sheet_name, output_path, range_address=None):
|
||||
|
||||
# 检查 Excel 文件是否存在
|
||||
if not os.path.exists(excel_path):
|
||||
print(f"错误: Excel 文件 '{excel_path}' 不存在。请检查路径。")
|
||||
return
|
||||
|
||||
# 确保输出目录存在
|
||||
os.makedirs(os.path.dirname(output_path), exist_ok=True)
|
||||
|
||||
# 初始化 COM 库
|
||||
pythoncom.CoInitialize()
|
||||
|
||||
try:
|
||||
# 1. 获取 Excel 应用程序对象
|
||||
excel = win32.Dispatch("Excel.Application")
|
||||
excel.Visible = False # 不显示 Excel 窗口
|
||||
excel.DisplayAlerts = False # 不显示任何警告或提示框
|
||||
|
||||
# 2. 打开工作簿
|
||||
workbook_obj = excel.Workbooks.Open(excel_path)
|
||||
|
||||
# 3. 选择工作表
|
||||
try:
|
||||
sheet = workbook_obj.Sheets(sheet_name)
|
||||
except Exception:
|
||||
print(f"错误: 工作簿 '{os.path.basename(excel_path)}' 中找不到工作表 '{sheet_name}'。")
|
||||
# 尝试选择第一个工作表作为备用
|
||||
if workbook_obj.Sheets.Count > 0:
|
||||
sheet = workbook_obj.Sheets(1)
|
||||
print(f"改为导出第一个工作表 '{sheet.Name}'。")
|
||||
else:
|
||||
raise ValueError("工作簿中没有可用的工作表。")
|
||||
|
||||
# 4. 选择要复制的区域
|
||||
if range_address:
|
||||
try:
|
||||
range_obj = sheet.Range(range_address)
|
||||
except Exception:
|
||||
print(f"警告: 指定的导出范围 '{range_address}' 无效或不存在，将导出 UsedRange。")
|
||||
range_obj = sheet.UsedRange
|
||||
else:
|
||||
range_obj = sheet.UsedRange
|
||||
|
||||
# 选中区域（确保焦点）
|
||||
range_obj.Select()
|
||||
|
||||
# 5. 将选定区域复制为图片
|
||||
range_obj.CopyPicture(Format=1, Appearance=2) # xlBitmap = 1, xlScreen = 2
|
||||
|
||||
# 6. 临时创建ChartObject在当前工作表
|
||||
chart_width = range_obj.Width * (300/72) # 将点转换为厘米
|
||||
chart_height = range_obj.Height * (300/65) # 将点转换为厘米
|
||||
temp_chart_obj = sheet.ChartObjects().Add(0, 0, chart_width, chart_height).Chart
|
||||
|
||||
temp_chart_obj.Paste()
|
||||
|
||||
# 7. 导出图表为图片文件
|
||||
temp_chart_obj.Export(output_path, FilterName="JPG")
|
||||
print(f"图片已成功导出到 '{output_path}'。")
|
||||
|
||||
# 8. 删除临时图表对象
|
||||
sheet.ChartObjects(sheet.ChartObjects().Count).Delete()
|
||||
|
||||
# 9. 关闭工作簿，不保存更改
|
||||
workbook_obj.Close(False)
|
||||
|
||||
except Exception as e:
|
||||
print(f"处理 Excel 时发生错误: {e}")
|
||||
print("请确保已安装 Microsoft Excel 应用程序，并且 Excel 文件路径、工作表名称正确。")
|
||||
finally:
|
||||
# 确保 Excel 应用程序被关闭
|
||||
if excel:
|
||||
try:
|
||||
excel.Quit()
|
||||
except Exception as e:
|
||||
print(f"关闭 Excel 应用程序时发生错误: {e}")
|
||||
|
||||
# 释放 COM 对象
|
||||
pythoncom.CoUninitialize()
|
||||
|
||||
def main():
|
||||
|
||||
params = None
|
||||
try:
|
||||
# 1. 解析参数
|
||||
params = parse_arguments()
|
||||
|
||||
output_path = params["batch_output_folder"]
|
||||
|
||||
for excel_file in os.listdir(output_path):
|
||||
time.sleep(1.5)
|
||||
if excel_file.endswith(".xlsx"):
|
||||
excel_file_path = os.path.join(output_path, excel_file)
|
||||
output_jpg_path = os.path.join(output_path, excel_file.replace(".xlsx", ".jpg"))
|
||||
export_excel_to_image(excel_file_path, "综合统计表", output_jpg_path)
|
||||
print_status(f"已处理文件: {excel_file}")
|
||||
|
||||
except Exception as e:
|
||||
error_msg = f"主函数错误: {str(e)}\n{traceback.format_exc()}"
|
||||
print_status(error_msg)
|
||||
print_result(False, error_message=error_msg)
|
||||
finally:
|
||||
sys.exit(0)
|
||||
|
||||
if __name__ == '__main__':
|
||||
print_status("开始执行")
|
||||
main()
|
||||
310
tools/core/export_layout.py
Normal file
310
tools/core/export_layout.py
Normal file
@@ -0,0 +1,310 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
"""
|
||||
导出布局脚本
|
||||
此脚本可以独立运行，用于导出布局，不依赖于PyQt6线程
|
||||
"""
|
||||
|
||||
import os
|
||||
import sys
|
||||
import json
|
||||
import arcpy
|
||||
import argparse
|
||||
|
||||
|
||||
def log(message):
|
||||
"""日志输出函数"""
|
||||
print(message)
|
||||
sys.stdout.flush() # 确保立即输出
|
||||
|
||||
def parse_arguments():
|
||||
"""解析命令行参数"""
|
||||
parser = argparse.ArgumentParser(description='导出布局')
|
||||
parser.add_argument('--mode', choices=['single', 'batch'], default='single', help='导出模式')
|
||||
parser.add_argument('--aprx_file_list', help='ArcGIS Pro工程文件路径')
|
||||
parser.add_argument('--input_aprx_folder', help='批量模式下的工程文件夹路径')
|
||||
parser.add_argument('--output_image_path', required=True, help='输出路径')
|
||||
parser.add_argument('--export_format', default='PDF', help='导出格式')
|
||||
parser.add_argument('--resolution', type=int, default=300, help='分辨率(DPI)')
|
||||
parser.add_argument('--use_multiprocessing', action='store_true', help='是否使用多进程')
|
||||
parser.add_argument('--process_count', type=int, default=2, help='进程数')
|
||||
parser.add_argument('--image_force_regenerate', help='输出文件名')
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
# 处理图层列表参数（从JSON字符串转换为列表）
|
||||
try:
|
||||
# 尝试将字符串解析为JSON
|
||||
if args.aprx_file_list.startswith('[') and args.aprx_file_list.endswith(']'):
|
||||
args.aprx_file_list = json.loads(args.aprx_file_list)
|
||||
else:
|
||||
# 如果不是JSON格式，则假定是单个图层或逗号分隔的列表
|
||||
if ',' in args.aprx_file_list:
|
||||
cleaned = args.aprx_file_list.strip("[]")
|
||||
args.aprx_file_list = [aprx_file_list.strip() for aprx_file_list in cleaned.split(',')]
|
||||
else:
|
||||
args.aprx_file_list = [args.aprx_file_list]
|
||||
except json.JSONDecodeError:
|
||||
args.aprx_file_list = [args.aprx_file_list]
|
||||
|
||||
return args
|
||||
|
||||
def get_file_extension(format_name):
|
||||
"""根据格式名称获取文件扩展名"""
|
||||
format_dict = {
|
||||
"PDF": ".pdf",
|
||||
"PNG": ".png",
|
||||
"JPG": ".jpg",
|
||||
"JPEG": ".jpg",
|
||||
"TIFF": ".tif",
|
||||
"EPS": ".eps",
|
||||
"SVG": ".svg",
|
||||
"AI": ".ai"
|
||||
}
|
||||
|
||||
return format_dict.get(format_name.upper(), ".pdf")
|
||||
|
||||
|
||||
def export_layout(params):
|
||||
"""导出布局"""
|
||||
aprx = None
|
||||
try:
|
||||
# 获取参数
|
||||
log(f"开始导出布局...")
|
||||
aprx_path = params['aprx_path']
|
||||
output_folder = params['output_path']
|
||||
export_format = params.get('export_format', 'PDF')
|
||||
resolution = params.get('resolution', 300)
|
||||
output_name = params.get('output_name', '')
|
||||
|
||||
# 确保输出文件夹存在
|
||||
if not os.path.exists(output_folder):
|
||||
os.makedirs(output_folder)
|
||||
|
||||
# 打开地图文档
|
||||
try:
|
||||
log(f"打开地图文档: {aprx_path}")
|
||||
aprx = arcpy.mp.ArcGISProject(aprx_path) # type: ignore
|
||||
except Exception as e:
|
||||
raise Exception(f"无法打开地图文档: {str(e)}")
|
||||
|
||||
# 获取布局
|
||||
layouts = aprx.listLayouts()
|
||||
if not layouts:
|
||||
raise Exception("地图文档中没有布局")
|
||||
|
||||
# 如果未指定输出名称，则使用地图文档名称
|
||||
if not output_name:
|
||||
output_name = os.path.splitext(os.path.basename(aprx_path))[0]
|
||||
|
||||
# 获取文件扩展名
|
||||
file_ext = get_file_extension(export_format)
|
||||
|
||||
# 导出每个布局
|
||||
exported_files = []
|
||||
for layout in layouts:
|
||||
layout_name = layout.name
|
||||
output_file = os.path.join(output_folder, f"{output_name}{file_ext}")
|
||||
log(f"导出布局 {layout_name} 到 {output_file}")
|
||||
|
||||
try:
|
||||
if export_format.upper() == "PDF":
|
||||
# 导出PDF
|
||||
layout.exportToPDF(output_file, resolution=resolution)
|
||||
elif export_format.upper() in ["PNG", "JPG", "JPEG", "TIFF"]:
|
||||
# 导出栅格图像
|
||||
layout.exportToJPEG(output_file, resolution=resolution,jpeg_quality=85) if export_format.upper() in ["JPG", "JPEG"] else None
|
||||
layout.exportToPNG(output_file, resolution=resolution) if export_format.upper() == "PNG" else None
|
||||
layout.exportToTIFF(output_file, resolution=resolution) if export_format.upper() == "TIFF" else None
|
||||
elif export_format.upper() in ["EPS", "SVG"]:
|
||||
# 导出矢量图像
|
||||
layout.exportToEPS(output_file, resolution=resolution) if export_format.upper() == "EPS" else None
|
||||
layout.exportToSVG(output_file, resolution=resolution) if export_format.upper() == "SVG" else None
|
||||
else:
|
||||
# 默认导出PDF
|
||||
layout.exportToPDF(output_file, resolution=resolution)
|
||||
|
||||
exported_files.append(output_file)
|
||||
log(f"成功导出布局 {layout_name} 到 {output_file}")
|
||||
except Exception as e:
|
||||
log(f"导出布局 {layout_name} 失败: {str(e)}")
|
||||
|
||||
return {
|
||||
'exported_files': exported_files,
|
||||
'count': len(exported_files)
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
log(f"导出布局失败: {str(e)}")
|
||||
raise
|
||||
finally:
|
||||
# 释放资源
|
||||
if aprx:
|
||||
del aprx
|
||||
arcpy.management.ClearWorkspaceCache()
|
||||
|
||||
|
||||
def batch_export_layout(params):
|
||||
"""批量导出布局"""
|
||||
try:
|
||||
# 获取参数
|
||||
log(f"开始批量导出布局...")
|
||||
aprx_files = params['aprx_files']
|
||||
output_folder = params['output_path']
|
||||
export_format = params.get('export_format', 'PDF')
|
||||
resolution = params.get('resolution', 300)
|
||||
|
||||
# 确保输出文件夹存在
|
||||
if not os.path.exists(output_folder):
|
||||
os.makedirs(output_folder)
|
||||
|
||||
# 记录导出结果
|
||||
all_exported_files = []
|
||||
success_count = 0
|
||||
failed_count = 0
|
||||
|
||||
# 逐个处理aprx文件
|
||||
for aprx_path in aprx_files:
|
||||
try:
|
||||
file_name = os.path.splitext(os.path.basename(aprx_path))[0]
|
||||
log(f"\n处理文件: {file_name}")
|
||||
|
||||
# 准备参数
|
||||
export_params = {
|
||||
'aprx_path': aprx_path,
|
||||
'output_path': output_folder,
|
||||
'export_format': export_format,
|
||||
'resolution': resolution,
|
||||
'output_name': file_name
|
||||
}
|
||||
|
||||
# 调用导出布局函数
|
||||
result = export_layout(export_params)
|
||||
all_exported_files.extend(result['exported_files'])
|
||||
success_count += result['count']
|
||||
|
||||
log(f"文件 {file_name} 处理完成")
|
||||
except Exception as e:
|
||||
log(f"处理文件 {os.path.basename(aprx_path)} 失败: {str(e)}")
|
||||
failed_count += 1
|
||||
|
||||
# 返回结果
|
||||
log(f"\n批量导出完成")
|
||||
log(f"成功: {success_count} 个布局")
|
||||
log(f"失败: {failed_count} 个文件")
|
||||
|
||||
return {
|
||||
'exported_files': all_exported_files,
|
||||
'count': success_count,
|
||||
'success_count': success_count,
|
||||
'failed_count': failed_count
|
||||
}
|
||||
|
||||
except Exception as e:
|
||||
log(f"批量导出布局失败: {str(e)}")
|
||||
raise
|
||||
|
||||
|
||||
def export_worker(aprx_path, output_path, export_format, resolution):
|
||||
"""子进程专用工作函数（保持最小化参数）"""
|
||||
try:
|
||||
# 每个子进程独立初始化ArcPy环境
|
||||
import arcpy
|
||||
arcpy.env.overwriteOutput = True
|
||||
|
||||
result = export_layout({
|
||||
'aprx_path': aprx_path,
|
||||
'output_path': output_path,
|
||||
'export_format': export_format,
|
||||
'resolution': resolution
|
||||
})
|
||||
return (True, aprx_path, result)
|
||||
except Exception as e:
|
||||
return (False, aprx_path, str(e))
|
||||
|
||||
|
||||
def main():
|
||||
"""主函数"""
|
||||
|
||||
try:
|
||||
args = parse_arguments()
|
||||
|
||||
if len(args.aprx_file_list) == 1:
|
||||
aprx_file = args.aprx_file_list[0]
|
||||
if not os.path.exists(aprx_file):
|
||||
log(f"所选文件{aprx_file}不存在，请确认")
|
||||
return 1
|
||||
|
||||
# 准备参数
|
||||
params = {
|
||||
'aprx_path': aprx_file,
|
||||
'output_path': args.output_image_path,
|
||||
'export_format': args.export_format,
|
||||
'resolution': args.resolution
|
||||
}
|
||||
|
||||
# 调用导出函数
|
||||
result = export_layout(params)
|
||||
log(f"导出完成，成功导出 {result['count']} 个布局")
|
||||
|
||||
elif len(args.aprx_file_list) >1:
|
||||
if not args.input_aprx_folder:
|
||||
log("批量导出模式需要指定aprx_folder参数")
|
||||
return 1
|
||||
|
||||
# 查找所有aprx文件
|
||||
aprx_files = []
|
||||
valied_files = []
|
||||
failed_files = []
|
||||
|
||||
for file in args.aprx_file_list:
|
||||
if not os.path.exists(file) and file.lower().endswith('.aprx'):
|
||||
failed_files.append(os.path.basename(file))
|
||||
continue
|
||||
aprx_files.append(file)
|
||||
valied_files.append(os.path.basename(file))
|
||||
|
||||
if not aprx_files:
|
||||
log(f"在指定文件夹中未找到aprx文件: {args.input_aprx_folder}")
|
||||
return 1
|
||||
|
||||
log(f"找到 {len(valied_files)} 个有效aprx文件: {', '.join(valied_files)}\n")
|
||||
log(f"{len(failed_files)} 个无效文件: {', '.join(failed_files)}")
|
||||
|
||||
if args.use_multiprocessing and args.process_count > 1 and len(aprx_files)>1:
|
||||
from multiprocessing import Pool
|
||||
tasks = [(aprx_file, args.output_image_path, args.export_format, args.resolution) for aprx_file in aprx_files]
|
||||
with Pool(min(int(args.process_count), len(tasks))) as p:
|
||||
results = p.starmap(export_worker, tasks)
|
||||
|
||||
for success, aprx_path, result in results:
|
||||
if success:
|
||||
log(f"成功导出布局 {aprx_path} 到 {result['exported_files']}") # type: ignore
|
||||
else:
|
||||
log(f"导出布局 {aprx_path} 失败: {result}")
|
||||
return 0
|
||||
|
||||
else:
|
||||
# 准备参数
|
||||
params = {
|
||||
'aprx_files': aprx_files,
|
||||
'output_path': args.output_image_path,
|
||||
'export_format': args.export_format,
|
||||
'resolution': args.resolution
|
||||
}
|
||||
|
||||
# 调用批量导出函数
|
||||
result = batch_export_layout(params)
|
||||
log(f"批量导出完成，成功导出 {result['count']} 个布局")
|
||||
return 0
|
||||
else:
|
||||
log("请选择要处理的aprx文件")
|
||||
return 0
|
||||
except Exception as e:
|
||||
log(f"导出失败: {str(e)}")
|
||||
return 1
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
572
tools/core/export_map_v1.py
Normal file
572
tools/core/export_map_v1.py
Normal file
@@ -0,0 +1,572 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
"""
|
||||
导出地图脚本
|
||||
此脚本可以独立运行，用于导出地图，支持批量导出
|
||||
"""
|
||||
|
||||
import os
|
||||
import sys
|
||||
import json
|
||||
import time
|
||||
import arcpy
|
||||
import argparse
|
||||
from pathlib import Path
|
||||
from collections import defaultdict
|
||||
|
||||
sys.path.append(str(Path(__file__).parent))
|
||||
from utils import common_utils
|
||||
|
||||
|
||||
def parse_arguments():
|
||||
"""解析命令行参数"""
|
||||
parser = argparse.ArgumentParser(description="导出地图工具")
|
||||
parser.add_argument("--config_file", required=True, help="配置文件路径")
|
||||
parser.add_argument("--county_name", required=True, help="区县名称")
|
||||
parser.add_argument("--polygon_list", required=True, help="要导出的图层列表，JSON格式字符串")
|
||||
parser.add_argument("--template_aprx_file", required=True, help="模板文件路径")
|
||||
parser.add_argument("--output_path", required=True, help="输出路径")
|
||||
parser.add_argument("--data_source_path", required=True, help="数据源路径")
|
||||
parser.add_argument("--symbol_path", required=True, help="符号文件路径")
|
||||
parser.add_argument("--force_regenerate", action="store_true", help="强制重新生成工程文件")
|
||||
parser.add_argument("--pic_path", required=True, help="图片输入路径")
|
||||
|
||||
# 解析参数
|
||||
args = parser.parse_args()
|
||||
|
||||
# 处理图层列表参数（从JSON字符串转换为列表）
|
||||
try:
|
||||
# 尝试将字符串解析为JSON
|
||||
if args.polygon_list.startswith('[') and args.polygon_list.endswith(']'):
|
||||
args.polygon_list = json.loads(args.polygon_list)
|
||||
else:
|
||||
# 如果不是JSON格式，则假定是单个图层或逗号分隔的列表
|
||||
if ',' in args.polygon_list:
|
||||
cleaned = args.polygon_list.strip("[]")
|
||||
args.polygon_list = [layer.strip() for layer in cleaned.split(',')]
|
||||
else:
|
||||
args.polygon_list = [args.polygon_list]
|
||||
except json.JSONDecodeError:
|
||||
args.polygon_list = [args.polygon_list]
|
||||
|
||||
return args
|
||||
|
||||
def print_status(message):
|
||||
"""
|
||||
输出状态信息到标准输出，用于 GUI 实时显示
|
||||
格式: STATUS: <message>
|
||||
"""
|
||||
print(f"STATUS:{message}")
|
||||
sys.stdout.flush() # 确保立即输出
|
||||
|
||||
def print_result(success, output_path="", error_message=""):
|
||||
"""
|
||||
输出最终结果到标准输出，用于 GUI 判断任务状态和获取结果
|
||||
格式: RESULT:True|<output_path>|
|
||||
格式: RESULT:False||<error_message>
|
||||
"""
|
||||
if success:
|
||||
print(f"RESULT:True|{output_path}|")
|
||||
else:
|
||||
# 在错误信息中替换换行符，避免干扰解析
|
||||
cleaned_error_message = error_message.replace('\n', ' ').replace('\r', '')
|
||||
print(f"RESULT:False||{cleaned_error_message}")
|
||||
sys.stdout.flush() # 确保立即输出
|
||||
|
||||
def log_arcpy_message(message):
|
||||
"""输出 ArcPy 产生的 geoprocessing 消息"""
|
||||
# 可以在这里进一步处理或过滤 ArcPy 消息
|
||||
if message.type == 'Message':
|
||||
print_status(f"ArcPy消息: {message.message}")
|
||||
elif message.type == 'Warning':
|
||||
print_status(f"ArcPy警告: {message.message}")
|
||||
elif message.type == 'Error':
|
||||
# 对于错误，也可以记录到标准错误
|
||||
print_status(f"ArcPy错误: {message.message}")
|
||||
sys.stderr.write(f"ArcPyError:{message.message}\n")
|
||||
sys.stderr.flush()
|
||||
|
||||
def area_statistics_by_field(layer, field_name="GRIDCODE", area_unit="HECTARES"):
|
||||
"""计算要素的面积统计信息"""
|
||||
area_stats = defaultdict(float, {1: 0.00, 2: 0.00, 3: 0.00, 4: 0.00, 5: 0.00})
|
||||
try:
|
||||
# 检查图层是否有效
|
||||
if not layer or not layer.isFeatureLayer:
|
||||
raise ValueError("输入图层无效或不是要素图层")
|
||||
|
||||
# 检查字段是否存在
|
||||
if field_name not in [f.name for f in arcpy.ListFields(layer)]:
|
||||
raise ValueError(f"字段 '{field_name}' 在图层中不存在")
|
||||
|
||||
# 判断坐标系类型
|
||||
desc = arcpy.Describe(layer.dataSource)
|
||||
is_geographic = desc.spatialReference.type == "Geographic"
|
||||
if is_geographic:
|
||||
print_status("图层坐标系为地理坐标系，计算面积可能不准确")
|
||||
|
||||
# 创建游标遍历要素
|
||||
with arcpy.da.SearchCursor(layer, ["SHAPE@", field_name]) as cursor:
|
||||
for row in cursor:
|
||||
geometry = row[0]
|
||||
value = row[1]
|
||||
|
||||
# 计算面积
|
||||
area = geometry.getArea("GEODESIC" if is_geographic else "PLANAR", area_unit)
|
||||
|
||||
# 根据分类进行统计
|
||||
if value in area_stats:
|
||||
area_stats[value] += area
|
||||
else:
|
||||
area_stats[value] = area
|
||||
|
||||
return area_stats
|
||||
|
||||
except Exception as e:
|
||||
raise Exception(f"计算面积统计信息失败: {str(e)}")
|
||||
|
||||
def update_text_elements(layout, config_data, county_name):
|
||||
"""更新布局中的文本元素"""
|
||||
|
||||
# 更新标题和其他文本元素
|
||||
for element_name, element_content in config_data.items():
|
||||
if element_name == "项目名称":
|
||||
new_text = element_content.replace('{区县占位符}', county_name)
|
||||
text_element = layout.listElements("TEXT_ELEMENT", element_name)[0]
|
||||
text_element.text = new_text
|
||||
if element_name == "分析方法":
|
||||
text_element = layout.listElements("TEXT_ELEMENT", element_name)[0]
|
||||
text_element.text = element_content
|
||||
|
||||
print_status(f"文本元素更新成功")
|
||||
|
||||
def update_data_source(layer, layer_name, new_data_source):
|
||||
"""更新图层数据源"""
|
||||
try:
|
||||
# 确保路径分隔符正确
|
||||
new_data_source = os.path.normpath(new_data_source)
|
||||
layer_path = os.path.join(new_data_source, layer_name)
|
||||
|
||||
# 检查数据源是否存在
|
||||
if not arcpy.Exists(layer_path):
|
||||
raise ValueError(f"数据源不存在: {layer_path}")
|
||||
|
||||
# 更新数据源
|
||||
cp = layer.connectionProperties
|
||||
cp["connection_info"]["database"] = new_data_source
|
||||
cp["dataset"] = layer_name
|
||||
cp["workspace_factory"] = "File Geodatabase"
|
||||
|
||||
layer.updateConnectionProperties(layer.connectionProperties, cp)
|
||||
|
||||
print_status(f"数据源更新成功")
|
||||
|
||||
except Exception as e:
|
||||
print_status(f"更新数据源失败: {str(e)}")
|
||||
raise
|
||||
|
||||
def update_symbol_system(layer, layer_name, symbol_path):
|
||||
"""
|
||||
更新符号系统
|
||||
1.ApplySymbologyFromLayer循环更新不起作用，还没找到原因
|
||||
2.替代方案： lf = arcpy.mp.LayerFile(symbol_file)
|
||||
layer.symbology = lf.listLayers()[0].symbology
|
||||
"""
|
||||
try:
|
||||
# 获取符号文件
|
||||
if os.path.isfile(symbol_path) and symbol_path.endswith('.lyr'):
|
||||
symbol_file = symbol_path
|
||||
|
||||
elif os.path.isdir(symbol_path):
|
||||
symbol_file = None
|
||||
for file in os.listdir(symbol_path):
|
||||
if (file.endswith('.lyr') or file.endswith('.lyrx')) and layer_name in file:
|
||||
symbol_file = os.path.join(symbol_path, file)
|
||||
break
|
||||
|
||||
if not symbol_file:
|
||||
raise FileNotFoundError(f"符号系统中未找到匹配 {layer_name} 的.lyr文件")
|
||||
else:
|
||||
raise FileNotFoundError("符号系统路径必须是有效的.lyr文件或文件夹")
|
||||
|
||||
# 更新符号系统
|
||||
lf = arcpy.mp.LayerFile(symbol_file) # type: ignore
|
||||
layer.symbology = lf.listLayers()[0].symbology
|
||||
# arcpy.management.ApplySymbologyFromLayer(layer, symbol_file, update_symbology="MAINTAIN")
|
||||
print_status(f"符号系统更新成功")
|
||||
|
||||
except Exception as e:
|
||||
print_status(f"更新符号系统失败: {str(e)}")
|
||||
|
||||
# 添加注记
|
||||
def add_annotation(map_scale, map_obj, label_layer,layer_name, new_data_source):
|
||||
"""
|
||||
标注转注记
|
||||
标注存在缓存机制和layer.name绑定，需修改layer.name
|
||||
"""
|
||||
try:
|
||||
# 检查图层是否为空
|
||||
if label_layer is None:
|
||||
print_status(f"图层对象为空，无法进行标注转注记")
|
||||
return
|
||||
|
||||
# 转换为注记
|
||||
anno_layer_name = f"{layer_name}_GDBAnno"
|
||||
output_anno = os.path.join(new_data_source, anno_layer_name)
|
||||
|
||||
try:
|
||||
# 1. 从地图中移除所有相关图层
|
||||
for lyr in map_obj.listLayers("*GDBAnno"):
|
||||
map_obj.removeLayer(lyr)
|
||||
|
||||
label_layer.showLabels = False
|
||||
|
||||
# 将新生成的注记图层添加到地图中
|
||||
if arcpy.Exists(output_anno):
|
||||
new_anno_layer = map_obj.addDataFromPath(output_anno)
|
||||
map_obj.moveLayer(label_layer, new_anno_layer)
|
||||
print_status(f" 成功添加注记图层: {new_anno_layer.name}")
|
||||
else:
|
||||
raise FileNotFoundError(f"注记图层不存在: {output_anno}")
|
||||
|
||||
except Exception as e:
|
||||
print_status(f"执行标注转注记工具时出错: {str(e)}")
|
||||
raise Exception(f"执行标注转注记工具时出错: {str(e)}")
|
||||
|
||||
except Exception as e:
|
||||
print_status(f"标注转注记失败: {str(e)}")
|
||||
# 打印详细错误信息
|
||||
import traceback
|
||||
print_status(traceback.format_exc())
|
||||
|
||||
def label_to_annotation(map_scale, map_obj, label_layer,layer_name, new_data_source):
|
||||
"""
|
||||
标注转注记
|
||||
标注存在缓存机制和layer.name绑定，需修改layer.name
|
||||
"""
|
||||
try:
|
||||
# 检查图层是否为空
|
||||
if label_layer is None:
|
||||
print_status(f"图层对象为空，无法进行标注转注记")
|
||||
return
|
||||
|
||||
# 尝试开启标注
|
||||
if label_layer.supports("SHOWLABELS"):
|
||||
try:
|
||||
label_layer.showLabels = True
|
||||
except Exception as e:
|
||||
print_status(f"启用标注失败: {str(e)}")
|
||||
|
||||
# 转换为注记
|
||||
anno_layer_name = f"{layer_name}_GDBAnno"
|
||||
output_anno = os.path.join(new_data_source, anno_layer_name)
|
||||
|
||||
try:
|
||||
# 1. 从地图中移除所有相关图层
|
||||
for lyr in map_obj.listLayers("*GDBAnno"):
|
||||
map_obj.removeLayer(lyr)
|
||||
if arcpy.Exists(output_anno):
|
||||
# 2. 强制释放工作空间锁
|
||||
arcpy.management.ClearWorkspaceCache(new_data_source)
|
||||
|
||||
# 3. 带重试机制的要素类删除
|
||||
max_retries = 5
|
||||
for attempt in range(max_retries):
|
||||
try:
|
||||
arcpy.management.Delete(output_anno)
|
||||
except arcpy.ExecuteError as e:
|
||||
if "000464" in str(e) and attempt < max_retries - 1:
|
||||
time.sleep((attempt + 1) * 3)
|
||||
arcpy.management.ClearWorkspaceCache(new_data_source)
|
||||
continue
|
||||
raise
|
||||
|
||||
# 4. 最终存在性检查
|
||||
if arcpy.Exists(output_anno):
|
||||
raise RuntimeError("无法彻底删除旧注记要素类")
|
||||
except Exception as e:
|
||||
raise Exception(f"清除旧注记失败，{str(e)}")
|
||||
|
||||
try:
|
||||
# 使用ConvertLabelsToAnnotation工具
|
||||
arcpy.cartography.ConvertLabelsToAnnotation(
|
||||
input_map=map_obj,
|
||||
conversion_scale=map_scale,
|
||||
output_geodatabase=new_data_source,
|
||||
anno_suffix="_GDBAnno",
|
||||
extent="DEFAULT",
|
||||
output_group_layer=f"{layer_name}GDBAnno",
|
||||
which_layers="SINGLE_LAYER",
|
||||
single_layer=label_layer
|
||||
)
|
||||
print_status(f"标注转注记成功")
|
||||
# 关闭原始标注显示（可选）
|
||||
label_layer.showLabels = False
|
||||
|
||||
# 将新生成的注记图层添加到地图中
|
||||
if arcpy.Exists(output_anno):
|
||||
new_anno_layer = map_obj.addDataFromPath(output_anno)
|
||||
map_obj.moveLayer(label_layer, new_anno_layer)
|
||||
print_status(f" 成功添加注记图层: {new_anno_layer.name}")
|
||||
else:
|
||||
raise FileNotFoundError(f"注记图层不存在: {output_anno}")
|
||||
|
||||
except Exception as e:
|
||||
print_status(f"执行标注转注记工具时出错: {str(e)}")
|
||||
raise Exception(f"执行标注转注记工具时出错: {str(e)}")
|
||||
|
||||
except Exception as e:
|
||||
print_status(f"标注转注记失败: {str(e)}")
|
||||
# 打印详细错误信息
|
||||
import traceback
|
||||
print_status(traceback.format_exc())
|
||||
|
||||
def export_map(params):
|
||||
"""导出地图"""
|
||||
start_time = time.time()
|
||||
aprx = None
|
||||
try:
|
||||
# 获取参数
|
||||
export_config = params['export_config']
|
||||
county_name = params['county_name']
|
||||
template_aprx_file = params['template_aprx_file']
|
||||
output_path = params['output_path']
|
||||
data_source_path = params['data_source_path']
|
||||
symbol_path = params['symbol_path']
|
||||
force_regenerate = params.get('force_regenerate', False) # 是否强制重新生成工程文件
|
||||
polygon_list = params['polygon_list']
|
||||
pic_path = params.get('pic_path', None)
|
||||
|
||||
# 结果记录
|
||||
success_count = 0
|
||||
|
||||
# 确保输出文件夹存在
|
||||
if not os.path.exists(output_path):
|
||||
os.makedirs(output_path)
|
||||
|
||||
# 创建工作空间
|
||||
workspace_path = os.path.join(output_path, f"{county_name}_工作空间")
|
||||
if not os.path.exists(workspace_path) or force_regenerate:
|
||||
if os.path.exists(workspace_path):
|
||||
print_status(f"强制重新生成，删除现有工作空间：{workspace_path}")
|
||||
# 删除旧工作空间（可能需要arcpy函数）
|
||||
|
||||
os.makedirs(workspace_path, exist_ok=True)
|
||||
print_status(f"创建工作空间：{workspace_path}")
|
||||
|
||||
# 工程模板不存在则返回
|
||||
if not arcpy.Exists(template_aprx_file):
|
||||
raise Exception("模板文件不存在")
|
||||
|
||||
# 设置工作空间
|
||||
orginal_workspace = arcpy.env.workspace
|
||||
arcpy.env.workspace = workspace_path
|
||||
|
||||
aprx = arcpy.mp.ArcGISProject(template_aprx_file) # type: ignore
|
||||
|
||||
# 获取指定布局
|
||||
target_layout = None
|
||||
layout_name = "属性图模板"
|
||||
target_layout = aprx.listLayouts(layout_name)[0]
|
||||
if not target_layout:
|
||||
raise Exception(f"未找到布局: {layout_name}")
|
||||
|
||||
# 获取当前地图比例尺
|
||||
map_frame = target_layout.listElements("MAPFRAME_ELEMENT", "地图框")[0]
|
||||
# if isinstance(map_frame, arcpy.mp.MapFrame):
|
||||
map_scale = map_frame.camera.scale
|
||||
# else:
|
||||
# raise Exception("地图框元素不存在")
|
||||
|
||||
# 获取指定地图
|
||||
target_map = None
|
||||
map_name = "土壤属性图层"
|
||||
target_map = aprx.listMaps(map_name)[0]
|
||||
if not target_map:
|
||||
raise Exception(f"未找到地图: {map_name}")
|
||||
|
||||
# 获取指定图层
|
||||
target_layer = None
|
||||
target_layer_name = "属性图"
|
||||
try:
|
||||
target_layer = target_map.listLayers(target_layer_name)[0]
|
||||
if not target_layer:
|
||||
raise Exception(f"未找到图层: {target_layer_name}")
|
||||
except Exception as e:
|
||||
raise Exception(f"错误信息: {str(e)}")
|
||||
|
||||
# 循环处理每个图层
|
||||
for layer_name in polygon_list:
|
||||
print_status(f"===== 开始处理要素: {layer_name} =====")
|
||||
|
||||
config_key = common_utils.get_config_key(layer_name)
|
||||
|
||||
try:
|
||||
# 更新图层名
|
||||
target_layer.name = config_key
|
||||
|
||||
# 获取图层配置
|
||||
single_export_config = export_config.get(config_key, {})
|
||||
if not single_export_config:
|
||||
print_status(f"警告: 未找到 {layer_name} 的配置信息, 将处理下一个")
|
||||
continue
|
||||
|
||||
# 生成输出文件名和路径
|
||||
temp_file_name = single_export_config['项目名称'].split('\n')[1]
|
||||
file_name = temp_file_name.replace('{区县占位符}', county_name)
|
||||
output_path = os.path.join(workspace_path, f"{file_name}.aprx")
|
||||
|
||||
# 检查工程文件是否已存在
|
||||
if os.path.exists(output_path) and not force_regenerate:
|
||||
print_status(f"工程文件已存在: {file_name}.aprx, 将直接使用")
|
||||
success_count += 1
|
||||
continue
|
||||
|
||||
# 检查数据源是否存在
|
||||
data_layer_path = os.path.join(data_source_path, layer_name)
|
||||
if not arcpy.Exists(data_layer_path):
|
||||
print_status(f"警告: 数据源不存在: {layer_name}要素，跳过此图层")
|
||||
continue
|
||||
|
||||
# 更新数据源
|
||||
if data_source_path:
|
||||
try:
|
||||
update_data_source(target_layer, layer_name, data_source_path)
|
||||
except Exception as e:
|
||||
print_status(f"更新数据源时出错: {str(e)}，跳过此图层")
|
||||
continue
|
||||
|
||||
# 更新符号系统
|
||||
if os.path.exists(symbol_path):
|
||||
try:
|
||||
update_symbol_system(target_layer, config_key, symbol_path)
|
||||
except Exception as e:
|
||||
print_status(f"更新符号系统时出错: {str(e)}，但将继续处理")
|
||||
|
||||
# 更新文本元素
|
||||
if target_layout:
|
||||
try:
|
||||
update_text_elements(target_layout, single_export_config, county_name)
|
||||
except Exception as e:
|
||||
print_status(f"更新文本元素时出错: {str(e)}，但将继续处理")
|
||||
|
||||
# 替换图片
|
||||
try:
|
||||
for pic in os.listdir(pic_path):
|
||||
if pic.endswith(".jpg") and pic.startswith(config_key):
|
||||
pic_file = os.path.join(pic_path, pic)
|
||||
break
|
||||
pic_element = target_layout.listElements("PICTURE_ELEMENT", "统计图片")[0]
|
||||
# if isinstance(pic_element, arcpy.mp.PictureElement):
|
||||
pic_element.sourceImage = pic_file
|
||||
print_status(f"图片替换成功,{pic_file}")
|
||||
# else:
|
||||
# print_status(f"未找到统计图片元素，无法替换图片")
|
||||
except Exception as e:
|
||||
print_status(f"替换图片时出错: {str(e)}，但将继续处理")
|
||||
|
||||
# 如果存在注记 直接添加；如果不存在，则尝试转注记
|
||||
try:
|
||||
add_annotation(map_scale, target_map, target_layer, config_key, data_source_path)
|
||||
except Exception as e:
|
||||
print_status(f"添加注记失败: {str(e)}，但将继续处理")
|
||||
|
||||
# 标注转注记
|
||||
# try:
|
||||
# label_to_annotation(map_scale, target_map, target_layer, config_key, data_source_path)
|
||||
# except Exception as e:
|
||||
# print_status(f"标注转注记失败: {str(e)}，但将继续处理")
|
||||
|
||||
# 保存工程文件
|
||||
aprx.saveACopy(output_path)
|
||||
print_status(f"成功保存工程文件: {output_path}")
|
||||
|
||||
# 记录结果
|
||||
success_count += 1
|
||||
|
||||
arcpy.management.ClearWorkspaceCache()
|
||||
except Exception as e:
|
||||
print_status(f"处理图层 {config_key} 时出错: {str(e)}")
|
||||
continue
|
||||
|
||||
print_status(f"===== 导出处理完成 =====")
|
||||
# 结束时间
|
||||
end_time = time.time()
|
||||
elapsed_time = end_time - start_time
|
||||
print_status(f"共处理 {len(polygon_list)} 个图层，成功 {success_count} 个，耗时：{elapsed_time:.2f}秒")
|
||||
|
||||
return success_count
|
||||
|
||||
except Exception as e:
|
||||
print_status(f"导出过程中出错：{str(e)}")
|
||||
import traceback
|
||||
print_status(traceback.format_exc())
|
||||
return 0
|
||||
finally:
|
||||
# 确保释放资源
|
||||
arcpy.management.ClearWorkspaceCache()
|
||||
arcpy.env.workspace = orginal_workspace
|
||||
if 'target_layer' in locals():
|
||||
del target_layer
|
||||
if 'target_map' in locals():
|
||||
del target_map
|
||||
if 'target_layout' in locals():
|
||||
del target_layout
|
||||
if 'aprx' in locals():
|
||||
del aprx
|
||||
|
||||
def main():
|
||||
"""主函数"""
|
||||
try:
|
||||
# args1 = {
|
||||
# 'config_file': 'D:/arcpystudy/ArcGisPro/tools/ui/raster_test_config.json',
|
||||
# 'county_name': '澜沧拉祜族自治县',
|
||||
# 'polygon_list': ['AB_processed.shp'],
|
||||
# 'template_aprx_file': r'D:/工作/ArcGisPro/澜沧县模板/澜沧县模板/澜沧县模板.aprx',
|
||||
# 'output_path': 'D:/工作/三普成果编制/澜沧2/成果图',
|
||||
# 'data_source_path': 'D:/工作/三普成果编制/澜沧2/@矢量数据',
|
||||
# 'symbol_path': 'D:/工作/ArcGisPro/澜沧县模板/2.配色/华南配色',
|
||||
# 'force_regenerate': True,
|
||||
# 'pic_path': 'D:/工作/三普成果编制/澜沧2/@基础数据/面积统计表格'
|
||||
# }
|
||||
# # 将字典转为对象
|
||||
# args = argparse.Namespace(**args1)
|
||||
|
||||
|
||||
# 解析命令行参数
|
||||
args = parse_arguments()
|
||||
|
||||
# 执行导出
|
||||
with open(args.config_file,'r',encoding='utf-8') as f:
|
||||
config = json.load(f)
|
||||
|
||||
params = {
|
||||
"export_config": config["export_config"],
|
||||
"county_name": args.county_name,
|
||||
"polygon_list":args.polygon_list,
|
||||
"template_aprx_file": args.template_aprx_file,
|
||||
"output_path": args.output_path,
|
||||
"data_source_path": args.data_source_path,
|
||||
"symbol_path": args.symbol_path,
|
||||
"force_regenerate":args.force_regenerate,
|
||||
"pic_path":args.pic_path
|
||||
}
|
||||
|
||||
success_count = export_map(params)
|
||||
|
||||
# 返回结果
|
||||
if success_count > 0:
|
||||
return 0
|
||||
else:
|
||||
print_status("没有导出任何图层")
|
||||
return 1
|
||||
|
||||
except Exception as e:
|
||||
print_status(f"错误：{str(e)}")
|
||||
import traceback
|
||||
print_status(traceback.format_exc())
|
||||
return 1
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
475
tools/core/raster_to_polygon.py
Normal file
475
tools/core/raster_to_polygon.py
Normal file
@@ -0,0 +1,475 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
栅格处理模块: 提供栅格重分类、栅格转矢量和小面积图斑消除功能
|
||||
|
||||
设计用于通过 QProcess 调用，接收命令行参数，并通过标准输出返回结果和状态。
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import random
|
||||
import sys
|
||||
import time
|
||||
import traceback
|
||||
import arcpy
|
||||
import uuid
|
||||
from pathlib import Path
|
||||
from tools.core.utils.os_utils import temp_files_processor
|
||||
|
||||
try:
|
||||
from utils import common_utils
|
||||
except ImportError:
|
||||
print("错误: 未找到 utils 模块。请确保 utils.py 文件存在或已添加到 PYTHONPATH。")
|
||||
sys.exit(1)
|
||||
|
||||
def parse_arguments():
|
||||
"""解析命令行参数"""
|
||||
parser = argparse.ArgumentParser(description='处理栅格数据：重分类、转矢量、消除小图斑')
|
||||
parser.add_argument('--input_raster', required=True, help='输入栅格文件路径')
|
||||
parser.add_argument('--settings_path', required=True, help='配置文件路径')
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
if args.settings_path:
|
||||
with open(args.settings_path, 'r', encoding="utf-8") as settings_file:
|
||||
settings = json.load(settings_file)
|
||||
raster_settings = settings.get("raster_settings", {})
|
||||
|
||||
if raster_settings:
|
||||
standards_dict_path = raster_settings.get("config_file_path", "")
|
||||
|
||||
with open(standards_dict_path, 'r', encoding="utf-8") as standards_file:
|
||||
standards_dict = json.load(standards_file)
|
||||
raster_name = Path(args.input_raster).stem
|
||||
remap_table = common_utils.create_remap_table(standards_dict['export_config'][raster_name]["标准等级"])
|
||||
raster_settings["remap_table"] = remap_table
|
||||
raster_settings["input_raster"] = args.input_raster
|
||||
else:
|
||||
print("错误: 未找到有效配置文件")
|
||||
sys.exit(1)
|
||||
|
||||
return raster_settings
|
||||
|
||||
def print_status(message):
|
||||
"""
|
||||
输出状态信息到标准输出，用于 GUI 实时显示
|
||||
格式: STATUS: <message>
|
||||
"""
|
||||
print(f"STATUS:{message}")
|
||||
sys.stdout.flush() # 确保立即输出
|
||||
|
||||
def print_result(success, output_path="", error_message=""):
|
||||
"""
|
||||
输出最终结果到标准输出，用于 GUI 判断任务状态和获取结果
|
||||
格式: RESULT:True|<output_path>|
|
||||
格式: RESULT:False||<error_message>
|
||||
"""
|
||||
if success:
|
||||
print(f"RESULT:True|{output_path}|")
|
||||
else:
|
||||
# 在错误信息中替换换行符，避免干扰解析
|
||||
cleaned_error_message = error_message.replace('\n', ' ').replace('\r', '')
|
||||
print(f"RESULT:False||{cleaned_error_message}")
|
||||
sys.stdout.flush() # 确保立即输出
|
||||
|
||||
def log_arcpy_message(message):
|
||||
"""输出 ArcPy 产生的 geoprocessing 消息"""
|
||||
# 可以在这里进一步处理或过滤 ArcPy 消息
|
||||
if message.type == 'Message':
|
||||
print_status(f"ArcPy消息: {message.message}")
|
||||
elif message.type == 'Warning':
|
||||
print_status(f"ArcPy警告: {message.message}")
|
||||
elif message.type == 'Error':
|
||||
# 对于错误，也可以记录到标准错误
|
||||
print_status(f"ArcPy错误: {message.message}")
|
||||
sys.stderr.write(f"ArcPyError:{message.message}\n")
|
||||
sys.stderr.flush()
|
||||
|
||||
# --- 核心处理函数 ---
|
||||
|
||||
def reclassify_raster(input_raster, remap_table, temp_files_to_clean):
|
||||
"""
|
||||
根据重分类映射表重分类栅格数据，结果存储在内存中。
|
||||
|
||||
参数:
|
||||
input_raster (str): 输入栅格路径
|
||||
remap_table (list): 重分类映射表，格式为 [[from, to, new_value], ...]
|
||||
temp_files_to_clean (list): 用于收集临时文件路径的列表
|
||||
|
||||
返回:
|
||||
str: 内存栅格路径
|
||||
"""
|
||||
print_status(f"开始重分类栅格: {input_raster}")
|
||||
try:
|
||||
# 确保remap_table中的new_value是整数，并确保格式正确
|
||||
corrected_remap_table = []
|
||||
for item in remap_table:
|
||||
try:
|
||||
if len(item) == 3:
|
||||
from_value, to_value, new_value = item
|
||||
# 尝试转换为浮点数以处理范围值
|
||||
try:
|
||||
from_value = float(from_value)
|
||||
except (ValueError, TypeError):
|
||||
print_status(f"警告: 跳过无效的重分类项起始值: {item[0]}")
|
||||
continue
|
||||
|
||||
if isinstance(to_value, (int, float)) and to_value == float('inf'):
|
||||
to_value = 10000 # 用一个很大的数值代替
|
||||
elif isinstance(to_value, (int, float)) and to_value == float('-inf'):
|
||||
to_value = -10000 # 用一个很小的数值代替
|
||||
else:
|
||||
try:
|
||||
to_value = float(to_value)
|
||||
except (ValueError, TypeError):
|
||||
print_status(f"警告: 跳过无效的重分类项结束值: {item[1]}")
|
||||
continue
|
||||
|
||||
try:
|
||||
new_value = int(new_value)
|
||||
except (ValueError, TypeError):
|
||||
print_status(f"警告: 跳过无效的重分类项新值: {item[2]}")
|
||||
continue
|
||||
|
||||
# 验证范围的有效性
|
||||
if from_value > to_value:
|
||||
print_status(f"警告: 跳过无效范围: {from_value} > {to_value}")
|
||||
continue
|
||||
|
||||
corrected_remap_table.append([from_value, to_value, new_value])
|
||||
else:
|
||||
print_status(f"警告: 跳过无效的重分类项格式: {item}")
|
||||
except Exception as e: # 捕获更广泛的异常
|
||||
print_status(f"处理重分类项 {item} 时出错: {e}")
|
||||
|
||||
if not corrected_remap_table:
|
||||
raise ValueError("重分类映射表为空或无效，无法执行重分类。")
|
||||
|
||||
# 创建重分类对象
|
||||
remap = arcpy.sa.RemapRange(corrected_remap_table)
|
||||
|
||||
# 执行重分类到内存
|
||||
# 检查输入栅格是否存在
|
||||
if not arcpy.Exists(input_raster):
|
||||
raise FileNotFoundError(f"输入栅格不存在: {input_raster}")
|
||||
|
||||
# 设置Snap Raster和Mask环境，如果需要的话
|
||||
# arcpy.env.snapRaster = input_raster
|
||||
# arcpy.env.mask = input_raster # 如果需要按栅格范围裁剪
|
||||
|
||||
out_raster = arcpy.sa.Reclassify(input_raster, "VALUE", remap, "DATA")
|
||||
|
||||
# 保存到内存工作空间
|
||||
temp_reclass_raster_mem = f"in_memory/reclass_int_{uuid.uuid4().hex[:8]}"
|
||||
# 在返回之前保存到内存，并添加到清理列表
|
||||
out_raster.save(temp_reclass_raster_mem)
|
||||
temp_files_to_clean.append(temp_reclass_raster_mem)
|
||||
print_status(f"重分类已完成: {temp_reclass_raster_mem}")
|
||||
|
||||
return temp_reclass_raster_mem
|
||||
|
||||
except Exception as e:
|
||||
print_status(f"重分类过程出错: {str(e)}")
|
||||
# 记录ArcPy消息
|
||||
for msg in arcpy.GetMessages(2).split('\n'):
|
||||
if msg:
|
||||
print_status(f"ArcPy重分类错误详情: {msg}")
|
||||
raise # 重新抛出异常
|
||||
|
||||
def eliminate_small_polygons(input_polygon, output_polygon, min_area, area_unit, temp_files_to_clean, current_iter=1, max_iterations=8, start_area=1000):
|
||||
"""
|
||||
递归消除小于指定面积的多边形，直至没有小图斑或达到最大迭代次数。
|
||||
|
||||
参数:
|
||||
input_polygon (str): 输入多边形要素类路径
|
||||
output_polygon (str): 最终输出多边形要素类路径
|
||||
min_area (float): 最小面积阈值
|
||||
area_unit (str): 面积单位
|
||||
max_iterations (int): 最大递归次数
|
||||
current_iter (int): 当前迭代次数
|
||||
temp_files_to_clean (list): 用于收集临时文件路径的列表
|
||||
|
||||
返回:
|
||||
str: 最终输出多边形要素类路径
|
||||
"""
|
||||
# print_status(f"开始第 {current_iter} 次消除小图斑...")
|
||||
|
||||
# 检查输入多边形是否存在
|
||||
if not arcpy.Exists(input_polygon):
|
||||
raise FileNotFoundError(f"输入多边形不存在: {input_polygon}")
|
||||
|
||||
try:
|
||||
# 如果是第一次迭代，检查输出文件是否已存在，并删除
|
||||
if current_iter == 1 and arcpy.Exists(output_polygon):
|
||||
try:
|
||||
arcpy.management.Delete(output_polygon)
|
||||
print_status(f"已删除现有输出文件: {output_polygon}")
|
||||
except Exception as delete_err:
|
||||
print_status(f"警告: 无法删除现有输出文件 {output_polygon}: {str(delete_err)}")
|
||||
|
||||
#==================增加逐面积消除================
|
||||
# 计算当前迭代的面积阈值
|
||||
current_threshold = start_area * (2 ** (current_iter - 1))
|
||||
|
||||
# 如果当前阈值超过最终阈值，使用最终阈值
|
||||
if current_threshold > min_area:
|
||||
current_threshold = min_area
|
||||
#==================增加逐面积消除================
|
||||
|
||||
# 创建临时内存图层以便选择
|
||||
temp_layer = f"input_lyr_{uuid.uuid4().hex[:8]}"
|
||||
arcpy.management.MakeFeatureLayer(input_polygon, temp_layer)[0]
|
||||
# print_status(f"已创建临时图层: {temp_layer_name}")
|
||||
|
||||
|
||||
# 添加或检查面积字段
|
||||
area_field_name = "TEMP_AREA"
|
||||
fields = [f.name for f in arcpy.ListFields(temp_layer)]
|
||||
if area_field_name not in fields:
|
||||
arcpy.management.AddField(temp_layer, area_field_name, "DOUBLE")
|
||||
# print_status(f"已添加临时面积字段: {area_field_name}")
|
||||
|
||||
# 计算面积
|
||||
arcpy.management.CalculateGeometryAttributes(
|
||||
temp_layer,
|
||||
[[area_field_name, "AREA"]],
|
||||
None,
|
||||
area_unit,
|
||||
None,
|
||||
"SAME_AS_INPUT"
|
||||
)
|
||||
# print_status("面积计算完成.")
|
||||
|
||||
|
||||
# 选择小于阈值的多边形
|
||||
selection_query = f"{arcpy.AddFieldDelimiters(temp_layer, area_field_name)} < {current_threshold}"
|
||||
# print_status(f"选择查询: {selection_query}")
|
||||
arcpy.management.SelectLayerByAttribute(temp_layer, "NEW_SELECTION", selection_query)
|
||||
|
||||
# 检查选中的要素数量
|
||||
count = int(arcpy.management.GetCount(temp_layer).getOutput(0))
|
||||
# print_status(f"发现 {count} 个小于 {min_area} {area_unit} 的小图斑.")
|
||||
|
||||
# 判断是否停止迭代
|
||||
if count == 0 or current_iter >= max_iterations:
|
||||
# print_status(f"复制最终结果到: {output_polygon}")
|
||||
arcpy.management.CopyFeatures(input_polygon, output_polygon)
|
||||
|
||||
# 删除临时面积字段 (可选，如果需要保持输出干净)
|
||||
# if area_field_name in fields: # 仅在字段是我们添加的情况下删除
|
||||
# arcpy.management.DeleteField(output_polygon, area_field_name)
|
||||
|
||||
return output_polygon
|
||||
|
||||
else:
|
||||
# print_status(f"执行消除操作...")
|
||||
temp_eliminate_output = f"in_memory/temp_eliminate_{uuid.uuid4().hex[:8]}"
|
||||
temp_files_to_clean.append(temp_eliminate_output) # 添加到临时文件列表
|
||||
|
||||
# 执行消除操作
|
||||
arcpy.Eliminate_management(temp_layer, temp_eliminate_output, "LENGTH")
|
||||
|
||||
# print_status(f"执行融合操作...")
|
||||
temp_dissolve_output = f"in_memory/dissolve_polygons_{uuid.uuid4().hex[:8]}"
|
||||
temp_files_to_clean.append(temp_dissolve_output)
|
||||
|
||||
# 添加融合字段
|
||||
dissolve_fields = ["gridcode"]
|
||||
|
||||
arcpy.management.Dissolve(temp_eliminate_output, temp_dissolve_output, dissolve_fields, multi_part="SINGLE_PART")
|
||||
# print_status(f"融合结果已保存到内存: {temp_dissolve_output}")
|
||||
|
||||
|
||||
# 递归调用，使用融合后的结果作为下一次迭代的输入
|
||||
return eliminate_small_polygons(
|
||||
temp_dissolve_output, # 下一次迭代使用临时融合输出作为输入
|
||||
output_polygon,
|
||||
min_area,
|
||||
area_unit,
|
||||
temp_files_to_clean,
|
||||
current_iter + 1,
|
||||
max_iterations,
|
||||
start_area
|
||||
)
|
||||
|
||||
except Exception as e:
|
||||
print_status(f"消除小面积多边形过程出错 (迭代 {current_iter}): {str(e)}")
|
||||
# 记录ArcPy消息
|
||||
for msg in arcpy.GetMessages(2).split('\n'):
|
||||
if msg:
|
||||
print_status(f"ArcPy消除错误详情: {msg}")
|
||||
raise # 重新抛出异常
|
||||
finally:
|
||||
# 确保删除临时图层，即使出错
|
||||
if 'temp_layer' in locals() and arcpy.Exists(temp_layer):
|
||||
try:
|
||||
arcpy.management.Delete(temp_layer)
|
||||
# print_status(f"已删除临时图层: {temp_layer.name}")
|
||||
except Exception as delete_layer_err:
|
||||
print_status(f"警告: 无法删除临时图层 {temp_layer}: {str(delete_layer_err)}")
|
||||
|
||||
|
||||
# --- 主处理逻辑 ---
|
||||
|
||||
def main():
|
||||
"""主函数：解析参数，执行处理流程，输出结果和状态"""
|
||||
|
||||
|
||||
params = None
|
||||
temp_files_to_clean = []
|
||||
original_workspace = None
|
||||
|
||||
try:
|
||||
# 1. 解析参数
|
||||
params = parse_arguments()
|
||||
|
||||
input_raster = params["input_raster"]
|
||||
raster_name = Path(input_raster).stem
|
||||
input_folder = params["input_folder"]
|
||||
output_folder = params["batch_output_folder"]
|
||||
clip_features = params["clip_features"]
|
||||
clip_enabled = params["clip_enabled"]
|
||||
remap_table = params["remap_table"]
|
||||
min_area = params["min_area"]
|
||||
area_unit = params["area_unit"]
|
||||
simplify = params["simplify"]
|
||||
|
||||
# print_status(f"解析参数完成: {params}")
|
||||
|
||||
# 2. 设置工作空间和环境
|
||||
original_workspace = arcpy.env.workspace
|
||||
arcpy.env.workspace = input_folder
|
||||
arcpy.env.overwriteOutput = True
|
||||
|
||||
print_status(f"ArcPy 工作空间设置为: {arcpy.env.workspace}")
|
||||
|
||||
# 3. 校验输入/输出路径
|
||||
if not arcpy.Exists(input_raster):
|
||||
raise FileNotFoundError(f"输入栅格文件不存在: {input_raster}")
|
||||
|
||||
# 创建输出文件夹
|
||||
if not os.path.exists(output_folder):
|
||||
os.makedirs(output_folder)
|
||||
print_status(f"已创建输出文件夹: {output_folder}")
|
||||
|
||||
# 创建面积统计用文件夹
|
||||
disk_output_path = os.path.join(output_folder, "面积统计用栅格面")
|
||||
time.sleep(random.random())
|
||||
if not os.path.exists(disk_output_path):
|
||||
os.makedirs(disk_output_path)
|
||||
print_status(f"已创建面积统计文件夹: {disk_output_path}")
|
||||
|
||||
if clip_enabled and not arcpy.Exists(clip_features):
|
||||
raise FileNotFoundError(f"裁剪要素类不存在: {clip_features}")
|
||||
|
||||
# 4. 定义中间和最终输出路径
|
||||
# 根据输出文件夹类型确定文件扩展名和命名方式
|
||||
output_is_workspace = common_utils.get_data_type(output_folder) in ["Workspace", "FeatureDataset", "Geodatabase"]
|
||||
|
||||
if output_is_workspace:
|
||||
# 输出到地理数据库或要素数据集
|
||||
final_output_path = os.path.join(os.path.dirname(output_folder), f"{raster_name}_eliminate.shp")
|
||||
# final_output_path = f"{raster_name}_processed"
|
||||
|
||||
else:
|
||||
# 输出到文件夹 (例如 Shapefile)
|
||||
final_output_path = os.path.join(output_folder, f"{raster_name}_eliminate.shp")
|
||||
# final_output_path = f"{raster_name}_processed.shp"
|
||||
|
||||
|
||||
# 5. 执行重分类 (如果 remap_table 存在)
|
||||
if remap_table:
|
||||
reclassed_raster = reclassify_raster(input_raster, remap_table, temp_files_to_clean)
|
||||
arcpy.Raster(reclassed_raster).save(os.path.join(output_folder,f"{Path(input_raster).stem}分级后.tif"))
|
||||
|
||||
|
||||
# 6. 栅格转多边形
|
||||
print_status(f"开始栅格转多边形: {reclassed_raster}")
|
||||
temp_polygon_output = os.path.join("in_memory", f"raster_to_polygon_{uuid.uuid4().hex[:8]}")
|
||||
temp_files_to_clean.append(temp_polygon_output)
|
||||
|
||||
simplify_value = "SIMPLIFY" if simplify else "NO_SIMPLIFY"
|
||||
arcpy.conversion.RasterToPolygon(reclassed_raster, temp_polygon_output, simplify_value, "VALUE")
|
||||
print_status(f"栅格转多边形完成，结果在内存: {temp_polygon_output}")
|
||||
|
||||
# 将内存中的要素类保存到硬盘
|
||||
disk_output_polygon = os.path.join(disk_output_path, f"{raster_name}_reclassed_polygon.shp")
|
||||
arcpy.CopyFeatures_management(temp_polygon_output, disk_output_polygon)
|
||||
print_status(f"已将重分类转面结果保存到硬盘: {disk_output_polygon}")
|
||||
|
||||
|
||||
# 7. 裁剪 (如果 clip_features 存在)
|
||||
current_polygon_source = temp_polygon_output
|
||||
if clip_enabled:
|
||||
print_status(f"开始裁剪要素类: {current_polygon_source} using {clip_features}")
|
||||
temp_cliped_polygon_output = os.path.join("in_memory", f"cliped_{uuid.uuid4().hex[:8]}")
|
||||
temp_files_to_clean.append(temp_cliped_polygon_output)
|
||||
arcpy.analysis.Clip(current_polygon_source, clip_features, temp_cliped_polygon_output)
|
||||
current_polygon_source = temp_cliped_polygon_output
|
||||
print_status(f"裁剪完成，结果在内存: {current_polygon_source}")
|
||||
|
||||
# 多部件至单部件 (通常在裁剪后进行，确保每个要素都是独立的单部件)
|
||||
print_status(f"开始多部件至单部件转换: {current_polygon_source}")
|
||||
temp_multi_to_single_output = os.path.join("in_memory", f"single_{uuid.uuid4().hex[:8]}")
|
||||
temp_files_to_clean.append(temp_multi_to_single_output)
|
||||
arcpy.management.MultipartToSinglepart(current_polygon_source, temp_multi_to_single_output)
|
||||
current_polygon_source = temp_multi_to_single_output
|
||||
print_status(f"多部件至单部件转换完成，结果在内存: {current_polygon_source}")
|
||||
|
||||
|
||||
# 8. 消除小面积图斑
|
||||
print_status(f"开始消除小面积图斑: {current_polygon_source} (阈值: {min_area} {area_unit})")
|
||||
eliminate_small_polygons(
|
||||
current_polygon_source,
|
||||
final_output_path, # 直接传递最终输出路径
|
||||
min_area,
|
||||
area_unit,
|
||||
temp_files_to_clean # 传递临时文件列表
|
||||
)
|
||||
print_status("消除小面积图斑完成.")
|
||||
|
||||
# 9. 最终清理和输出结果
|
||||
print_status("处理流程全部完成.")
|
||||
# 清理在内存或临时位置生成的中间文件
|
||||
temp_files_processor.clean_up_temp_files(temp_files=temp_files_to_clean, workspace=original_workspace)
|
||||
|
||||
# 验证最终输出文件是否存在
|
||||
if arcpy.Exists(final_output_path):
|
||||
print_result(True, final_output_path, "")
|
||||
else:
|
||||
raise Exception(f"处理完成，但最终输出文件 {final_output_path} 不存在。")
|
||||
|
||||
|
||||
except FileNotFoundError as fnf_e:
|
||||
error_msg = f"文件不存在错误: {str(fnf_e)}"
|
||||
print_status(error_msg)
|
||||
print_result(False, "", error_msg)
|
||||
except ValueError as ve:
|
||||
error_msg = f"参数错误或数据校验失败: {str(ve)}"
|
||||
print_status(error_msg)
|
||||
print_result(False, "", error_msg)
|
||||
except arcpy.ExecuteError:
|
||||
# 捕获 ArcPy 执行错误
|
||||
error_msg = f"ArcPy 执行错误: {arcpy.GetMessages(2)}"
|
||||
print_status(error_msg)
|
||||
sys.stderr.write(f"ArcPyExecuteError:{arcpy.GetMessages(2)}\n") # 记录到标准错误
|
||||
print_result(False, "", error_msg)
|
||||
except Exception as e:
|
||||
# 捕获其他未预料的错误
|
||||
error_msg = f"发生未预料的错误: {str(e)}\n{traceback.format_exc()}"
|
||||
print_status(error_msg)
|
||||
sys.stderr.write(f"UnexpectedError:{error_msg}\n") # 记录到标准错误
|
||||
print_result(False, "", error_msg)
|
||||
|
||||
finally:
|
||||
# 确保在任何情况下都尝试清理（尽管在 except 块中也调用了）
|
||||
# 这里的调用是最后的保障，如果 except 块中的清理失败了
|
||||
print_status("脚本结束，执行最终清理...")
|
||||
temp_files_processor.clean_up_temp_files(temp_files=temp_files_to_clean, workspace=original_workspace)
|
||||
print_status("最终清理完成.")
|
||||
sys.exit(0) # 正常退出脚本
|
||||
|
||||
if __name__ == "__main__":
|
||||
print_status("脚本开始执行...")
|
||||
main()
|
||||
392
tools/core/soil_prop_stats/B1_TRZD12土壤属性分级分布.py
Normal file
392
tools/core/soil_prop_stats/B1_TRZD12土壤属性分级分布.py
Normal file
@@ -0,0 +1,392 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
import os
|
||||
import re
|
||||
import arcpy
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
from openpyxl import Workbook
|
||||
from openpyxl.styles import Font, Border, Side, Alignment
|
||||
from openpyxl.utils import get_column_letter
|
||||
|
||||
from tools.core.utils import arcgis_utils, common_utils
|
||||
from tools.core.utils.os_utils import temp_files_processor
|
||||
|
||||
|
||||
trzd5_order = ["砂质", "砂壤质", "壤质", "黏壤质", "黏质"]
|
||||
trzd12_order = ["砂土及壤质砂土", "砂质壤土", "壤土", "粉砂质壤土", "砂质黏壤土", "黏壤土", "粉砂质黏壤土", "砂质黏土", "壤质黏土", "粉砂质黏土", "黏土", "重黏土"]
|
||||
|
||||
# --- 2. 辅助函数 ---
|
||||
# 判断单元格类型
|
||||
def get_merge_type(merged_range):
|
||||
"""
|
||||
判断合并类型
|
||||
返回: 'row'（行合并）, 'column'（列合并）, 'both'（行列合并）或 None（不是合并单元格）
|
||||
"""
|
||||
if not merged_range:
|
||||
return None
|
||||
|
||||
min_row, max_row = merged_range.min_row, merged_range.max_row
|
||||
min_col, max_col = merged_range.min_col, merged_range.max_col
|
||||
|
||||
if max_row > min_row and max_col > min_col:
|
||||
return 'both' # 同时跨行和跨列
|
||||
elif max_row > min_row:
|
||||
return 'row' # 行合并（垂直合并）
|
||||
elif max_col > min_col:
|
||||
return 'column' # 列合并（水平合并）
|
||||
else:
|
||||
return None # 实际上不是合并单元格
|
||||
|
||||
# 计算属性等级
|
||||
def get_prop_level(prop_level):
|
||||
"""根据输入值判断 返回等级"""
|
||||
if pd.isna(prop_level) or str(prop_level) == "0":
|
||||
return "-"
|
||||
# 请根据您的实际分级标准调整这里的阈值
|
||||
if str(prop_level) == "8" or prop_level == '砂土及壤质砂土':
|
||||
return "砂质"
|
||||
elif str(prop_level) == "11" or prop_level == '砂质壤土':
|
||||
return "砂壤质"
|
||||
elif str(prop_level) in ["6","3"] or prop_level in ['粉砂质壤土', '壤土']:
|
||||
return "壤质"
|
||||
elif str(prop_level) in ["1","4","9"] or prop_level in ['粉砂质年壤土', '黏壤土', '砂质黏壤土']:
|
||||
return "黏壤质"
|
||||
elif str(prop_level) in ["2","5","7","10","12"] or prop_level in ['粉砂质黏土', '黏土', '壤质黏土', '砂质黏土', '重黏土']:
|
||||
return "黏质"
|
||||
else:
|
||||
return "-"
|
||||
|
||||
# 等级计算
|
||||
def process_soil_dataframe(df:pd.DataFrame, level_config, target_prop):
|
||||
"""
|
||||
处理土壤数据DataFrame，添加分级列
|
||||
"""
|
||||
result_df = df.copy()
|
||||
|
||||
if level_config and target_prop in df.columns:
|
||||
grade_standards = level_config["标准等级"]
|
||||
grade_column = "GRIDCODE"
|
||||
|
||||
# 使用向量化方法（性能更好）
|
||||
result_df[grade_column] = common_utils.vectorized_grade_assignment(
|
||||
df[target_prop].values, grade_standards
|
||||
)
|
||||
|
||||
# 统计分级结果
|
||||
result_df['YJDL'] = result_df['TDLYLX'].str[:2]
|
||||
|
||||
return result_df
|
||||
|
||||
# --- 3. 数据处理与分析 均值---
|
||||
def process_data_for_table1(gdb_path, soil_prop_feature_name, df_origin_area, target_areas_dict,xzqmc,is_by_xzq, prop_config=None):
|
||||
"""
|
||||
【最终版 v2】: 增加对制图样点数的处理，以支持加权平均计算。
|
||||
"""
|
||||
print("开始处理数据...")
|
||||
|
||||
def clean_df(df, columns):
|
||||
for col in columns:
|
||||
df[col] = df[col].astype(str).str.strip()
|
||||
df.replace(['<Null>', 'None', '', '<空>'], np.nan, inplace=True)
|
||||
df.dropna(subset=columns, inplace=True)
|
||||
return df
|
||||
|
||||
# ==a. 处理样点数据，计算“样点均值” ---
|
||||
print("--> 步骤1: 计算样点均值...")
|
||||
field_name = soil_prop_feature_name
|
||||
sample_table_path = os.path.join(gdb_path, soil_prop_feature_name)
|
||||
sample_fields = ['TDLYLX', field_name]
|
||||
df_samples = pd.DataFrame(arcpy.da.FeatureClassToNumPyArray(sample_table_path, sample_fields, skip_nulls=False))
|
||||
df_samples = clean_df(df_samples, [field_name])
|
||||
|
||||
processed_df = process_soil_dataframe(df_samples, prop_config, field_name) # 返回具有属性分级的列
|
||||
processed_df['GRIDCODE'] = processed_df['GRIDCODE'].astype('int')
|
||||
processed_df['属性分级'] = processed_df['GRIDCODE'].apply(get_prop_level)
|
||||
|
||||
# 计算全部样点均值、中位值、范围
|
||||
processed_df[field_name] = processed_df[field_name].astype('float')
|
||||
|
||||
# ===处理样点数据，计算 各分级样点数
|
||||
df_sample_means = processed_df.groupby(['属性分级','GRIDCODE']).size().reset_index(name='样点数')
|
||||
df_sample_means['样点数占比'] = df_sample_means['样点数'] / df_sample_means['样点数'].sum() * 100
|
||||
print("样点数计算完成。")
|
||||
|
||||
|
||||
# ==处理制图数据，获各等级制图面积
|
||||
# print(df_origin_area)
|
||||
df_origin_area['YJDL'] = df_origin_area['YJDL_EJDL'].str.split('_').str[0]
|
||||
df_map_data = df_origin_area.groupby(["XZQMC","YJDL", "GRIDCODE"]).agg({"temp_area": "sum"}).reset_index()
|
||||
# print(df_map_data)
|
||||
|
||||
try:
|
||||
if is_by_xzq:
|
||||
df_map_data['adjusted_area'] = df_map_data['temp_area']
|
||||
df_map_data['adjustment_factor'] = 1.0
|
||||
|
||||
# 获取所有存在的行政区和地类
|
||||
existing_districts = df_map_data['XZQMC'].unique()
|
||||
|
||||
# 检查目标字典中的行政区是否存在
|
||||
missing_districts = []
|
||||
tt = [td for td in target_areas_dict.keys()]
|
||||
for ed in existing_districts:
|
||||
if ed not in tt:
|
||||
missing_districts.append(ed)
|
||||
|
||||
# 如果有行政区不存在，返回原始数据并提示
|
||||
if missing_districts:
|
||||
print(f"警告：平差数据中不存在行政区: {missing_districts}，未进行平差")
|
||||
|
||||
# 计算每个行政区每个地类的原始总面积
|
||||
original_totals = df_map_data.groupby(['XZQMC', 'YJDL'])['temp_area'].sum()
|
||||
|
||||
# 对每个行政区的每个地类进行平差
|
||||
for xzqmc, landuse_targets in target_areas_dict.items():
|
||||
for yjdl, target_area in landuse_targets.items():
|
||||
# 检查该行政区是否有此地类数据
|
||||
if (xzqmc, yjdl) in original_totals.index and original_totals[(xzqmc, yjdl)] > 0:
|
||||
adjustment_factor = target_area / original_totals[(xzqmc, yjdl)]
|
||||
|
||||
# 应用平差系数
|
||||
mask = (df_map_data['XZQMC'] == xzqmc) & (df_map_data['YJDL'] == yjdl)
|
||||
df_map_data.loc[mask, 'temp_area'] = df_map_data.loc[mask, 'temp_area'] * adjustment_factor
|
||||
df_map_data.loc[mask, 'adjustment_factor'] = adjustment_factor
|
||||
|
||||
# print(f"{xzqmc} - 地类 {yjdl}: 平差系数 = {adjustment_factor:.6f}")
|
||||
else:
|
||||
# 用df_target_area按YJDL进行平差计算
|
||||
original_totals = df_map_data.groupby('YJDL')['temp_area'].sum().to_dict()
|
||||
# 对每个地类进行平差
|
||||
target_area_dict = target_areas_dict.get(xzqmc,"")
|
||||
# print(target_areas_dict)
|
||||
for yjdl, target_area in target_area_dict.items():
|
||||
if (yjdl in original_totals and original_totals[yjdl] > 0) or target_area > 0:
|
||||
adjustment_factor = target_area / original_totals[yjdl]
|
||||
|
||||
# 应用平差系数
|
||||
mask = df_map_data['YJDL'] == yjdl
|
||||
df_map_data.loc[mask, 'temp_area'] = df_map_data.loc[mask, 'temp_area'] * adjustment_factor
|
||||
df_map_data.loc[mask, 'adjustment_factor'] = adjustment_factor
|
||||
|
||||
# print(f"地类 {yjdl}: 平差系数 = {adjustment_factor:.6f}")
|
||||
except Exception as e:
|
||||
print(f"平差处理失败: {e}")
|
||||
|
||||
# print(df_map_data)
|
||||
df_map_data['面积_亩'] = df_map_data['temp_area']
|
||||
|
||||
df_map_data['属性分级'] = df_map_data['GRIDCODE'].apply(get_prop_level)
|
||||
df_map_areas = df_map_data.groupby(['属性分级','GRIDCODE'])['面积_亩'].sum().reset_index(name='制图面积')
|
||||
# 面积平差
|
||||
df_map_areas['制图面积_平差后'] = df_map_areas['制图面积']
|
||||
# ===计算面积占比
|
||||
df_map_areas['面积占比'] = df_map_areas['制图面积_平差后'] / df_map_areas['制图面积_平差后'].sum() * 100
|
||||
|
||||
# --- c. 合并数据 ---
|
||||
print("--> 步骤3: 合并数据...")
|
||||
df_skeleton = pd.concat([
|
||||
df_sample_means[['属性分级','GRIDCODE']],
|
||||
df_map_areas[['属性分级','GRIDCODE']]
|
||||
]).drop_duplicates().reset_index(drop=True)
|
||||
|
||||
df_final = pd.merge(df_skeleton, df_sample_means, on=['属性分级','GRIDCODE'], how='left')
|
||||
df_final = pd.merge(df_final, df_map_areas, on=['属性分级','GRIDCODE'], how='left')
|
||||
# print(df_final)
|
||||
# (可选) 按“一级地类”和“二级地类”排序
|
||||
df_final["属性分级"] = pd.Categorical(df_final['属性分级'], categories=trzd5_order, ordered=True)
|
||||
# df_final["EJDL"] = pd.Categorical(df_final['EJDL'], categories=in_ejdl_order, ordered=True)
|
||||
|
||||
df_final.sort_values(['属性分级','GRIDCODE'], inplace=True)
|
||||
|
||||
print("数据处理流程完成！")
|
||||
# print(df_final)
|
||||
return df_final
|
||||
|
||||
# --- 3. Excel 制表 总表---
|
||||
def write_to_excel_table1(df:pd.DataFrame, output_path, prop_config):
|
||||
"""
|
||||
【最终修正版】: 将处理好的数据写入格式化的 Excel 文件。
|
||||
"""
|
||||
if df.empty:
|
||||
print("警告: 没有数据可以写入 Excel，将创建一个空的报告。")
|
||||
wb = Workbook()
|
||||
ws = wb.create_sheet("Mysheet", 0)
|
||||
ws['A1'] = "没有有效的统计数据。"
|
||||
wb.save(output_path)
|
||||
return
|
||||
|
||||
print(f"开始生成 Excel 报告到 '{output_path}'...")
|
||||
wb = Workbook()
|
||||
ws = wb.create_sheet("Mysheet", 0)
|
||||
ws.title = "行政区酸化程度等级分布及占比"
|
||||
|
||||
# --- a. 定义样式 (不变) ---
|
||||
header_font = Font(name='宋体', size=11)
|
||||
cell_font = Font(name='宋体', size=11)
|
||||
center_align = Alignment(horizontal='center', vertical='center', wrap_text=True)
|
||||
thin_border = Border(left=Side(style='thin'), right=Side(style='thin'),
|
||||
top=Side(style='thin'), bottom=Side(style='thin'))
|
||||
|
||||
def apply_style(cell_range, font, alignment=None, border=None):
|
||||
for row in ws[cell_range]:
|
||||
for cell in row:
|
||||
cell.font = font
|
||||
if alignment: cell.alignment = alignment
|
||||
if border: cell.border = border
|
||||
|
||||
# --- b. 绘制表头 (不变) ---
|
||||
ws.merge_cells('A1:B1'); ws['A1'] = '土壤三普分类'
|
||||
ws.merge_cells('C1:D1'); ws['C1'] = '样点统计'
|
||||
ws.merge_cells('E1:F1'); ws['E1'] = '制图统计'
|
||||
|
||||
ws['A2'] = '类别'; ws['B2'] = '名称'
|
||||
ws['C2'] = '数量/个'; ws['D2'] = '占比%'
|
||||
ws['E2'] = '面积/亩'; ws['F2'] = '占比%'
|
||||
|
||||
level_dict = prop_config['标准等级']
|
||||
# 创建两个列表来分别存储上段和下段范围
|
||||
upper_ranges = {value: key for key, value in level_dict.items()}
|
||||
|
||||
# --- c. 填充数据 ---
|
||||
current_row = 3
|
||||
|
||||
df_to_write = df.copy() # 使用 .copy() 避免 SettingWithCopyWarning
|
||||
|
||||
for yl, group_yl_df in df_to_write.groupby('属性分级', sort=False, observed=False):
|
||||
|
||||
yl_start_row = current_row
|
||||
|
||||
# 1. 遍历该一级地类下的所有“二级地类”并写入数据
|
||||
for _, row_data in group_yl_df.iterrows():
|
||||
ws.cell(row=current_row, column=2).value = upper_ranges.get(str(row_data['GRIDCODE']), '-')
|
||||
|
||||
# --- 填充单元格的逻辑开始 ---
|
||||
col_start = 3 # 从第 C 列开始填充
|
||||
|
||||
# 检查是否找到了该土属的数据
|
||||
if not row_data.empty:
|
||||
|
||||
# 1. 构建要从 data_series 中查找的列名
|
||||
sample_col = f'样点数'
|
||||
sample_pct_col = f'样点数占比'
|
||||
area_col = f'制图面积_平差后'
|
||||
area_pct_col = f'面积占比'
|
||||
|
||||
# 2. 从 data_series 中安全地获取值
|
||||
sample_val = row_data.get(sample_col, 0)
|
||||
sample_pct_val = row_data.get(sample_pct_col, 0)
|
||||
area_val = row_data.get(area_col, 0)
|
||||
area_pct_val = row_data.get(area_pct_col, 0)
|
||||
|
||||
# 3. 将获取到的值填入单元格
|
||||
ws.cell(row=current_row, column=col_start).value = f"{sample_val:.0f}" if sample_val > 0 else "-"
|
||||
# 占比/%
|
||||
ws.cell(row=current_row, column=col_start + 1).value = f"{sample_pct_val:.1f}" if sample_val > 0 else "-"
|
||||
# 制图面积/亩
|
||||
ws.cell(row=current_row, column=col_start + 2).value = f"{area_val:.0f}" if area_val > 0 else "-"
|
||||
# 占比/%
|
||||
ws.cell(row=current_row, column=col_start + 3).value = f"{area_pct_val:.1f}" if area_val > 0 else "-"
|
||||
|
||||
# 移动到下一个酸化等级的起始列
|
||||
col_start += 2
|
||||
else:
|
||||
for _ in range(4):
|
||||
ws.cell(row=current_row, column=col_start).value = "-"
|
||||
col_start += 1
|
||||
|
||||
current_row += 1
|
||||
|
||||
# 合并“一级地类”单元格
|
||||
if yl_start_row <= current_row:
|
||||
ws.merge_cells(start_row=yl_start_row, start_column=1, end_row=current_row-1, end_column=1)
|
||||
ws.cell(row=yl_start_row, column=1).value = yl
|
||||
|
||||
# 2. 填充总计行
|
||||
ws.merge_cells(start_row=current_row, start_column=1, end_row=current_row, end_column=2)
|
||||
ws.cell(row=current_row, column=1).value = '全区'
|
||||
ws.cell(row=current_row, column=3).value = df['样点数'].sum()
|
||||
ws.cell(row=current_row, column=4).value = '100'
|
||||
ws.cell(row=current_row, column=5).value = f"{df['制图面积_平差后'].sum():.0f}"
|
||||
ws.cell(row=current_row, column=6).value = '100'
|
||||
|
||||
# --- d. 应用样式和调整列宽 (最终健壮版) ---
|
||||
if current_row > 1: # 确保有数据才应用样式
|
||||
apply_style(f'A1:F{current_row}', cell_font, center_align, thin_border)
|
||||
apply_style(f'A1:F2', header_font)
|
||||
|
||||
print("正在自动调整列宽...")
|
||||
|
||||
dims = {}
|
||||
for row in ws.rows:
|
||||
for cell in row:
|
||||
if cell.value:
|
||||
merged_range = next((range for range in ws.merged_cells.ranges if cell.coordinate in range), None)
|
||||
if get_merge_type(merged_range) == 'column':
|
||||
continue
|
||||
cell_len = 0.7 * len(re.findall('([\u4e00-\u9fa5])', str(cell.value))) + len(str(cell.value))
|
||||
dims[cell.column] = max(dims.get(cell.column, 0), cell_len)
|
||||
# 设置列宽
|
||||
for col, value in dims.items():
|
||||
ws.column_dimensions[get_column_letter(int(col))].width = value + 5
|
||||
|
||||
# --- e. 保存文件 ---
|
||||
wb.save(output_path)
|
||||
print("Excel 报告生成成功！")
|
||||
|
||||
|
||||
def main(gdb_path, soil_prop_name, reclassed_features_path, dltb_features, output_path, target_area_dict,xzqmc, prop_config):
|
||||
try:
|
||||
# --- 1. 用户配置 ---
|
||||
# 输出配置
|
||||
temp_files = []
|
||||
output_excel_path = os.path.join(output_path, f"{soil_prop_name}土壤分级分布.xlsx") # 生成的Excel报告文件路径
|
||||
|
||||
# 设置工作空间和变量
|
||||
arcpy.env.workspace = gdb_path
|
||||
arcpy.env.overwriteOutput = True
|
||||
|
||||
print("开始处理数据...")
|
||||
is_by_xzq = False if xzqmc not in ["北海市","来宾市","楚雄自治州"] else True
|
||||
|
||||
# out_table_mean = r"in_memory/out_table_mean"
|
||||
temp_out_feature_class = r"in_memory/temp_out_feature_class"
|
||||
temp_out_tables_area = r"in_memory/temp_out_tables_area"
|
||||
# temp_files.append(out_table_mean)
|
||||
temp_files.append(temp_out_tables_area)
|
||||
|
||||
# 求地类图斑和重分类栅格面的交集
|
||||
arcpy.analysis.Intersect(
|
||||
in_features=[dltb_features,reclassed_features_path],
|
||||
out_feature_class=temp_out_feature_class,
|
||||
join_attributes="ALL",
|
||||
output_type="INPUT"
|
||||
)
|
||||
# 行政区划和相交结果进行交集制表
|
||||
arcpy.analysis.TabulateIntersection(
|
||||
in_zone_features="行政区划", # 乡镇边界
|
||||
zone_fields="XZQMC",
|
||||
in_class_features=temp_out_feature_class,
|
||||
out_table=temp_out_tables_area,
|
||||
class_fields="gridcode;YJDL_EJDL",
|
||||
out_units="SQUARE_METERS"
|
||||
)
|
||||
clipped_table_df = arcgis_utils.read_arcgis_table(temp_out_tables_area)
|
||||
|
||||
# 生成表1 土壤属性分级分布 的统计Excel报告
|
||||
final_dataframe = process_data_for_table1(gdb_path, soil_prop_name, clipped_table_df, target_area_dict,xzqmc,is_by_xzq, prop_config)
|
||||
|
||||
write_to_excel_table1(final_dataframe, output_excel_path, prop_config)
|
||||
|
||||
# return df_with_factors
|
||||
except Exception as e:
|
||||
print(f"\n处理过程中发生严重错误: {e}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
finally:
|
||||
temp_files_processor.clean_up_temp_files(temp_files)
|
||||
import gc
|
||||
gc.collect()
|
||||
|
||||
# --- 4. 主程序入口 ---
|
||||
# if __name__ == "__main__":
|
||||
# main()
|
||||
360
tools/core/soil_prop_stats/B1_TRZD土壤属性分级分布.py
Normal file
360
tools/core/soil_prop_stats/B1_TRZD土壤属性分级分布.py
Normal file
@@ -0,0 +1,360 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
import os
|
||||
import re
|
||||
|
||||
import arcpy
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
from openpyxl import Workbook
|
||||
from openpyxl.styles import Font, Border, Side, Alignment
|
||||
from openpyxl.utils import get_column_letter
|
||||
|
||||
from tools.core.utils import arcgis_utils, common_utils
|
||||
from tools.core.utils.os_utils import temp_files_processor
|
||||
|
||||
|
||||
# --- 2. 辅助函数 ---
|
||||
# 判断单元格类型
|
||||
def get_merge_type(merged_range):
|
||||
"""
|
||||
判断合并类型
|
||||
返回: 'row'（行合并）, 'column'（列合并）, 'both'（行列合并）或 None（不是合并单元格）
|
||||
"""
|
||||
if not merged_range:
|
||||
return None
|
||||
|
||||
min_row, max_row = merged_range.min_row, merged_range.max_row
|
||||
min_col, max_col = merged_range.min_col, merged_range.max_col
|
||||
|
||||
if max_row > min_row and max_col > min_col:
|
||||
return 'both' # 同时跨行和跨列
|
||||
elif max_row > min_row:
|
||||
return 'row' # 行合并（垂直合并）
|
||||
elif max_col > min_col:
|
||||
return 'column' # 列合并（水平合并）
|
||||
else:
|
||||
return None # 实际上不是合并单元格
|
||||
|
||||
# 计算属性等级
|
||||
def get_prop_level(prop_level):
|
||||
"""根据输入值判断 返回等级"""
|
||||
if pd.isna(prop_level) or prop_level == 0:
|
||||
return "-"
|
||||
# 请根据您的实际分级标准调整这里的阈值
|
||||
if int(prop_level) == 5 or prop_level == "砂质":
|
||||
return "砂质"
|
||||
elif int(prop_level) == 4 or prop_level == "砂壤质":
|
||||
return "砂壤质"
|
||||
elif int(prop_level) == 3 or prop_level == "壤质":
|
||||
return "壤质"
|
||||
elif int(prop_level) == 1 or prop_level == "黏壤质":
|
||||
return "黏壤质"
|
||||
elif int(prop_level) == 2 or prop_level == "黏质":
|
||||
return "黏质"
|
||||
else:
|
||||
return "-"
|
||||
|
||||
# 等级计算
|
||||
def process_soil_dataframe(df:pd.DataFrame, level_config, target_prop):
|
||||
"""
|
||||
处理土壤数据DataFrame，添加分级列
|
||||
"""
|
||||
result_df = df.copy()
|
||||
|
||||
if level_config and target_prop in df.columns:
|
||||
grade_standards = level_config["标准等级"]
|
||||
grade_column = "GRIDCODE"
|
||||
|
||||
# 使用向量化方法（性能更好）
|
||||
result_df[grade_column] = common_utils.vectorized_grade_assignment(
|
||||
df[target_prop].values, grade_standards
|
||||
)
|
||||
|
||||
# 统计分级结果
|
||||
result_df['YJDL'] = result_df['TDLYLX'].str[:2]
|
||||
|
||||
return result_df
|
||||
|
||||
# --- 3. 数据处理与分析 均值---
|
||||
def process_data_for_table1(gdb_path, soil_prop_feature_name, df_origin_area, target_areas_dict,xzqmc,is_by_xzq, prop_config=None):
|
||||
"""
|
||||
【最终版 v2】: 增加对制图样点数的处理，以支持加权平均计算。
|
||||
"""
|
||||
print("开始处理数据...")
|
||||
|
||||
def clean_df(df, columns):
|
||||
for col in columns:
|
||||
df[col] = df[col].astype(str).str.strip()
|
||||
df.replace(['<Null>', 'None', '', '<空>'], np.nan, inplace=True)
|
||||
df.dropna(subset=columns, inplace=True)
|
||||
return df
|
||||
|
||||
# ==a. 处理样点数据，计算“样点均值” ---
|
||||
print("--> 步骤1: 计算样点均值...")
|
||||
field_name = soil_prop_feature_name
|
||||
sample_table_path = os.path.join(gdb_path, soil_prop_feature_name)
|
||||
sample_fields = ['TDLYLX', field_name]
|
||||
df_samples = pd.DataFrame(arcpy.da.FeatureClassToNumPyArray(sample_table_path, sample_fields, skip_nulls=False))
|
||||
df_samples = clean_df(df_samples, [field_name])
|
||||
|
||||
processed_df = df_samples.copy()
|
||||
processed_df['属性分级'] = processed_df[field_name]
|
||||
|
||||
# ===处理样点数据，计算 各分级样点数
|
||||
df_sample_means = processed_df.groupby(['属性分级']).size().reset_index(name='样点数')
|
||||
df_sample_means['样点数占比'] = df_sample_means['样点数'] / df_sample_means['样点数'].sum() * 100
|
||||
print("样点数计算完成。")
|
||||
|
||||
|
||||
# ==处理制图数据，获各等级制图面积
|
||||
# print(df_origin_area)
|
||||
df_origin_area['YJDL'] = df_origin_area['YJDL_EJDL'].str.split('_').str[0]
|
||||
df_map_data = df_origin_area.groupby(["XZQMC","YJDL", "GRIDCODE"]).agg({"temp_area": "sum"}).reset_index()
|
||||
# print(df_map_data)
|
||||
|
||||
try:
|
||||
if is_by_xzq:
|
||||
df_map_data['adjusted_area'] = df_map_data['temp_area']
|
||||
df_map_data['adjustment_factor'] = 1.0
|
||||
|
||||
# 获取所有存在的行政区和地类
|
||||
existing_districts = df_map_data['XZQMC'].unique()
|
||||
|
||||
# 检查目标字典中的行政区是否存在
|
||||
missing_districts = []
|
||||
tt = [td for td in target_areas_dict.keys()]
|
||||
for ed in existing_districts:
|
||||
if ed not in tt:
|
||||
missing_districts.append(ed)
|
||||
|
||||
# 如果有行政区不存在，返回原始数据并提示
|
||||
if missing_districts:
|
||||
print(f"警告：平差数据中不存在行政区: {missing_districts}，未进行平差")
|
||||
|
||||
# 计算每个行政区每个地类的原始总面积
|
||||
original_totals = df_map_data.groupby(['XZQMC', 'YJDL'])['temp_area'].sum()
|
||||
|
||||
# 对每个行政区的每个地类进行平差
|
||||
for xzqmc, landuse_targets in target_areas_dict.items():
|
||||
for yjdl, target_area in landuse_targets.items():
|
||||
# 检查该行政区是否有此地类数据
|
||||
if (xzqmc, yjdl) in original_totals.index and original_totals[(xzqmc, yjdl)] > 0:
|
||||
adjustment_factor = target_area / original_totals[(xzqmc, yjdl)]
|
||||
|
||||
# 应用平差系数
|
||||
mask = (df_map_data['XZQMC'] == xzqmc) & (df_map_data['YJDL'] == yjdl)
|
||||
df_map_data.loc[mask, 'temp_area'] = df_map_data.loc[mask, 'temp_area'] * adjustment_factor
|
||||
df_map_data.loc[mask, 'adjustment_factor'] = adjustment_factor
|
||||
|
||||
# print(f"{xzqmc} - 地类 {yjdl}: 平差系数 = {adjustment_factor:.6f}")
|
||||
else:
|
||||
# 用df_target_area按YJDL进行平差计算
|
||||
original_totals = df_map_data.groupby('YJDL')['temp_area'].sum().to_dict()
|
||||
# 对每个地类进行平差
|
||||
target_area_dict = target_areas_dict.get(xzqmc,"")
|
||||
# print(target_areas_dict)
|
||||
for yjdl, target_area in target_area_dict.items():
|
||||
if (yjdl in original_totals and original_totals[yjdl] > 0) or target_area > 0:
|
||||
adjustment_factor = target_area / original_totals[yjdl]
|
||||
|
||||
# 应用平差系数
|
||||
mask = df_map_data['YJDL'] == yjdl
|
||||
df_map_data.loc[mask, 'temp_area'] = df_map_data.loc[mask, 'temp_area'] * adjustment_factor
|
||||
df_map_data.loc[mask, 'adjustment_factor'] = adjustment_factor
|
||||
|
||||
# print(f"地类 {yjdl}: 平差系数 = {adjustment_factor:.6f}")
|
||||
except Exception as e:
|
||||
print(f"平差处理失败: {e}")
|
||||
|
||||
# print(df_map_data)
|
||||
df_map_data['面积_亩'] = df_map_data['temp_area']
|
||||
|
||||
df_map_data['属性分级'] = df_map_data['GRIDCODE'].apply(get_prop_level)
|
||||
df_map_areas = df_map_data.groupby(['属性分级'])['面积_亩'].sum().reset_index(name='制图面积')
|
||||
# 面积平差
|
||||
df_map_areas['制图面积_平差后'] = df_map_areas['制图面积']
|
||||
# ===计算面积占比
|
||||
df_map_areas['面积占比'] = df_map_areas['制图面积_平差后'] / df_map_areas['制图面积_平差后'].sum() * 100
|
||||
|
||||
# --- c. 合并数据 ---
|
||||
print("--> 步骤3: 合并数据...")
|
||||
df_skeleton = pd.concat([
|
||||
df_sample_means[['属性分级']],
|
||||
df_map_areas[['属性分级']]
|
||||
]).drop_duplicates().reset_index(drop=True)
|
||||
|
||||
df_final = pd.merge(df_skeleton, df_sample_means, on=['属性分级'], how='left')
|
||||
df_final = pd.merge(df_final, df_map_areas, on=['属性分级'], how='left')
|
||||
# print(df_final)
|
||||
df_final.sort_values(['属性分级'], inplace=True)
|
||||
|
||||
print("数据处理流程完成！")
|
||||
# print(df_final)
|
||||
return df_final
|
||||
|
||||
# --- 3. Excel 制表 总表---
|
||||
def write_to_excel_table1(df:pd.DataFrame, output_path, prop_config):
|
||||
"""
|
||||
【最终修正版】: 将处理好的数据写入格式化的 Excel 文件。
|
||||
"""
|
||||
if df.empty:
|
||||
print("警告: 没有数据可以写入 Excel，将创建一个空的报告。")
|
||||
wb = Workbook()
|
||||
ws = wb.create_sheet("Mysheet", 0)
|
||||
ws['A1'] = "没有有效的统计数据。"
|
||||
wb.save(output_path)
|
||||
return
|
||||
|
||||
print(f"开始生成 Excel 报告到 '{output_path}'...")
|
||||
wb = Workbook()
|
||||
ws = wb.create_sheet("Mysheet", 0)
|
||||
ws.title = "土壤质地分类分布"
|
||||
|
||||
# --- a. 定义样式 (不变) ---
|
||||
header_font = Font(name='宋体', size=11)
|
||||
cell_font = Font(name='宋体', size=11)
|
||||
center_align = Alignment(horizontal='center', vertical='center', wrap_text=True)
|
||||
thin_border = Border(left=Side(style='thin'), right=Side(style='thin'),
|
||||
top=Side(style='thin'), bottom=Side(style='thin'))
|
||||
|
||||
def apply_style(cell_range, font, alignment=None, border=None):
|
||||
for row in ws[cell_range]:
|
||||
for cell in row:
|
||||
cell.font = font
|
||||
if alignment: cell.alignment = alignment
|
||||
if border: cell.border = border
|
||||
|
||||
# --- b. 绘制表头 (不变) ---
|
||||
ws.merge_cells('A1:A2'); ws['A1'] = '土壤质地类别'
|
||||
ws.merge_cells('B1:C1'); ws['B1'] = '样点统计'
|
||||
ws.merge_cells('D1:E1'); ws['D1'] = '制图统计'
|
||||
|
||||
ws['B2'] = '数量/个'; ws['C2'] = '占比%'
|
||||
ws['D2'] = '面积/亩'; ws['E2'] = '占比%'
|
||||
|
||||
level_dict = prop_config['标准等级']
|
||||
# 创建两个列表来分别存储上段和下段范围
|
||||
upper_ranges = {value: key for key, value in level_dict.items()}
|
||||
|
||||
# --- c. 填充数据 ---
|
||||
current_row = 3
|
||||
|
||||
df_to_write = df.copy() # 使用 .copy() 避免 SettingWithCopyWarning
|
||||
|
||||
for index, row_data in df_to_write.iterrows():
|
||||
|
||||
# 检查是否找到了该土属的数据
|
||||
if not row_data.empty:
|
||||
|
||||
# 1. 构建要从 data_series 中查找的列名
|
||||
sample_col = f'样点数'
|
||||
sample_pct_col = f'样点数占比'
|
||||
area_col = f'制图面积_平差后'
|
||||
area_pct_col = f'面积占比'
|
||||
|
||||
# 2. 从 data_series 中安全地获取值
|
||||
row_name = row_data.get('属性分级', "")
|
||||
sample_val = row_data.get(sample_col, 0)
|
||||
sample_pct_val = row_data.get(sample_pct_col, 0)
|
||||
area_val = row_data.get(area_col, 0)
|
||||
area_pct_val = row_data.get(area_pct_col, 0)
|
||||
|
||||
ws.cell(row=current_row, column=1).value = f"{row_name}" if row_name else "-"
|
||||
# 3. 将获取到的值填入单元格
|
||||
ws.cell(row=current_row, column=2).value = f"{sample_val:.0f}" if sample_val > 0 else "-"
|
||||
# 占比/%
|
||||
ws.cell(row=current_row, column=3).value = f"{sample_pct_val:.1f}" if sample_val > 0 else "-"
|
||||
# 制图面积/亩
|
||||
ws.cell(row=current_row, column=4).value = f"{area_val:.0f}" if area_val > 0 else "-"
|
||||
# 占比/%
|
||||
ws.cell(row=current_row, column=5).value = f"{area_pct_val:.1f}" if area_val > 0 else "-"
|
||||
|
||||
current_row += 1
|
||||
|
||||
|
||||
# 2. 填充总计行
|
||||
ws.cell(row=current_row, column=1).value = '全区'
|
||||
ws.cell(row=current_row, column=2).value = df['样点数'].sum()
|
||||
ws.cell(row=current_row, column=3).value = '100'
|
||||
ws.cell(row=current_row, column=4).value = f"{df['制图面积_平差后'].sum():.0f}"
|
||||
ws.cell(row=current_row, column=5).value = '100'
|
||||
|
||||
# --- d. 应用样式和调整列宽 (最终健壮版) ---
|
||||
if current_row > 1: # 确保有数据才应用样式
|
||||
apply_style(f'A1:E{current_row}', cell_font, center_align, thin_border)
|
||||
apply_style(f'A1:E2', header_font)
|
||||
|
||||
print("正在自动调整列宽...")
|
||||
|
||||
dims = {}
|
||||
for row in ws.rows:
|
||||
for cell in row:
|
||||
if cell.value:
|
||||
merged_range = next((range for range in ws.merged_cells.ranges if cell.coordinate in range), None)
|
||||
if get_merge_type(merged_range) == 'column':
|
||||
continue
|
||||
cell_len = 0.7 * len(re.findall('([\u4e00-\u9fa5])', str(cell.value))) + len(str(cell.value))
|
||||
dims[cell.column] = max(dims.get(cell.column, 0), cell_len)
|
||||
# 设置列宽
|
||||
for col, value in dims.items():
|
||||
ws.column_dimensions[get_column_letter(int(col))].width = value + 5
|
||||
|
||||
# --- e. 保存文件 ---
|
||||
wb.save(output_path)
|
||||
print("Excel 报告生成成功！")
|
||||
|
||||
|
||||
def main(gdb_path, soil_prop_name, reclassed_features_path, dltb_features, output_path, target_area_dict,xzqmc, prop_config):
|
||||
try:
|
||||
# --- 1. 用户配置 ---
|
||||
# 输出配置
|
||||
temp_files = []
|
||||
output_excel_path = os.path.join(output_path, f"{soil_prop_name}土壤分级分布.xlsx") # 生成的Excel报告文件路径
|
||||
|
||||
# 设置工作空间和变量
|
||||
arcpy.env.workspace = gdb_path
|
||||
arcpy.env.overwriteOutput = True
|
||||
|
||||
print("开始处理数据...")
|
||||
is_by_xzq = False if xzqmc not in ["北海市","来宾市","楚雄自治州"] else True
|
||||
|
||||
# out_table_mean = r"in_memory/out_table_mean"
|
||||
temp_out_feature_class = r"in_memory/temp_out_feature_class"
|
||||
temp_out_tables_area = r"in_memory/temp_out_tables_area"
|
||||
# temp_files.append(out_table_mean)
|
||||
temp_files.append(temp_out_tables_area)
|
||||
|
||||
# 求地类图斑和重分类栅格面的交集
|
||||
arcpy.analysis.Intersect(
|
||||
in_features=[dltb_features,reclassed_features_path],
|
||||
out_feature_class=temp_out_feature_class,
|
||||
join_attributes="ALL",
|
||||
output_type="INPUT"
|
||||
)
|
||||
# 行政区划和相交结果进行交集制表
|
||||
arcpy.analysis.TabulateIntersection(
|
||||
in_zone_features="行政区划", # 乡镇边界
|
||||
zone_fields="XZQMC",
|
||||
in_class_features=temp_out_feature_class,
|
||||
out_table=temp_out_tables_area,
|
||||
class_fields="gridcode;YJDL_EJDL",
|
||||
out_units="SQUARE_METERS"
|
||||
)
|
||||
clipped_table_df = arcgis_utils.read_arcgis_table(temp_out_tables_area)
|
||||
|
||||
# 生成表1 土壤属性分级分布 的统计Excel报告
|
||||
final_dataframe = process_data_for_table1(gdb_path, soil_prop_name, clipped_table_df, target_area_dict,xzqmc,is_by_xzq, prop_config)
|
||||
|
||||
write_to_excel_table1(final_dataframe, output_excel_path, prop_config)
|
||||
|
||||
# return df_with_factors
|
||||
except Exception as e:
|
||||
print(f"\n处理过程中发生严重错误: {e}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
finally:
|
||||
temp_files_processor.clean_up_temp_files(temp_files)
|
||||
|
||||
# --- 4. 主程序入口 ---
|
||||
# if __name__ == "__main__":
|
||||
# main()
|
||||
513
tools/core/soil_prop_stats/B1土壤属性分级分布.py
Normal file
513
tools/core/soil_prop_stats/B1土壤属性分级分布.py
Normal file
@@ -0,0 +1,513 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
import os
|
||||
import re
|
||||
import arcpy
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
from openpyxl import Workbook
|
||||
from openpyxl.styles import Font
|
||||
|
||||
from tools.core.utils import arcgis_utils, common_utils
|
||||
from tools.core.utils.os_utils import temp_files_processor
|
||||
from tools.core.utils.excel_utils import ExcelStyleUtils
|
||||
|
||||
|
||||
# --- 2. 辅助函数 ---
|
||||
xn_region = ['天峨县', '寻甸县', '罗平县', '丘北县', '永仁县', '南华县', '双柏县', '武定县', '祥云县', '楚雄彝族自治州']
|
||||
hn_region = ['北海市', '海城区', '银海区', '铁山港区', '港南区', '容县', '平南县', '兴宁区', '武鸣区', '邕宁区', '苍梧县', '靖西市', '西畴县', '马关县', '澜沧县', '双江县', '永德县']
|
||||
# 计算属性等级
|
||||
def get_prop_level(prop_level):
|
||||
"""根据输入值判断 返回等级"""
|
||||
if pd.isna(prop_level) or prop_level == 0:
|
||||
return "-"
|
||||
# 请根据您的实际分级标准调整这里的阈值
|
||||
if int(prop_level) == 1 or int(prop_level) == 6 or prop_level == '等级一':
|
||||
return "Ⅰ级"
|
||||
elif int(prop_level) == 2 or int(prop_level) == 7 or prop_level == '等级二':
|
||||
return "Ⅱ级"
|
||||
elif int(prop_level) == 3 or int(prop_level) == 8 or prop_level == '等级三':
|
||||
return "Ⅲ级"
|
||||
elif int(prop_level) == 4 or int(prop_level) == 9 or prop_level == '等级四':
|
||||
return "Ⅳ级"
|
||||
elif int(prop_level) == 5 or int(prop_level) == 10 or prop_level == '等级五':
|
||||
return "Ⅴ级"
|
||||
else:
|
||||
return "-"
|
||||
def get_prop_level_for_pH(prop_level):
|
||||
if pd.isna(prop_level) or prop_level == 0:
|
||||
return "-"
|
||||
if int(prop_level) == 5 or prop_level == "等级五":
|
||||
return "Ⅰ级"
|
||||
elif int(prop_level) in [4, 6] or prop_level in ["等级四", "等级六"]:
|
||||
return "Ⅱ级"
|
||||
elif int(prop_level) in [3, 7] or prop_level in ["等级三", "等级七"]:
|
||||
return "Ⅲ级"
|
||||
elif int(prop_level) in [2, 8] or prop_level in ["等级二", "等级八"]:
|
||||
return "Ⅳ级"
|
||||
elif int(prop_level) in [1, 9] or prop_level in ["等级一", "等级九"]:
|
||||
return "Ⅴ级"
|
||||
else:
|
||||
return "-"
|
||||
|
||||
def get_prop_level_for_hn_TRRZ(prop_level):
|
||||
if pd.isna(prop_level) or prop_level == 0:
|
||||
return "-"
|
||||
if int(prop_level) == 3 or prop_level == "等级三":
|
||||
return "Ⅰ级"
|
||||
elif int(prop_level) == 4 or prop_level == "等级四":
|
||||
return "Ⅱ级"
|
||||
elif int(prop_level) in [2, 5] or prop_level in ["等级二", "等级五"]:
|
||||
return "Ⅲ级"
|
||||
elif int(prop_level) == 6 or prop_level == "等级六":
|
||||
return "Ⅳ级"
|
||||
elif int(prop_level) in [1, 7] or prop_level in ["等级一", "等级七"]:
|
||||
return "Ⅴ级"
|
||||
else:
|
||||
return "-"
|
||||
|
||||
def get_prop_level_for_xn_TRRZ(prop_level):
|
||||
if pd.isna(prop_level) or prop_level == 0:
|
||||
return "-"
|
||||
if int(prop_level) == 4 or prop_level == "等级四":
|
||||
return "Ⅰ级"
|
||||
elif int(prop_level) in [3,5] or prop_level in ["等级三", "等级五"]:
|
||||
return "Ⅱ级"
|
||||
elif int(prop_level) == 6 or prop_level == "等级六":
|
||||
return "Ⅲ级"
|
||||
elif int(prop_level) in [2, 7] or prop_level in ["等级二", "等级七"]:
|
||||
return "Ⅳ级"
|
||||
elif int(prop_level) in [1, 8] or prop_level in ["等级一", "等级八"]:
|
||||
return "Ⅴ级"
|
||||
else:
|
||||
return "-"
|
||||
|
||||
|
||||
# 等级计算
|
||||
def process_soil_dataframe(df:pd.DataFrame, level_config, target_prop):
|
||||
"""
|
||||
处理土壤数据DataFrame，添加分级列
|
||||
"""
|
||||
result_df = df.copy()
|
||||
|
||||
if level_config and target_prop in df.columns:
|
||||
grade_standards = level_config["标准等级"]
|
||||
grade_column = "GRIDCODE"
|
||||
|
||||
# 使用向量化方法（性能更好）
|
||||
result_df[grade_column] = common_utils.vectorized_grade_assignment(
|
||||
df[target_prop].values, grade_standards
|
||||
)
|
||||
|
||||
# 统计分级结果
|
||||
result_df['YJDL'] = result_df['TDLYLX'].str[:2]
|
||||
|
||||
return result_df
|
||||
|
||||
# --- 3. 数据处理与分析 均值---
|
||||
def process_data_for_table1(gdb_path, soil_prop_feature_name, df_origin_area, target_areas_dict,xzqmc,is_by_xzq, prop_config=None):
|
||||
"""
|
||||
【最终版 v2】: 增加对制图样点数的处理，以支持加权平均计算。
|
||||
"""
|
||||
print("开始处理数据...")
|
||||
|
||||
def clean_df(df, columns):
|
||||
for col in columns:
|
||||
df[col] = df[col].astype(str).str.strip()
|
||||
df.replace(['<Null>', 'None', '', '<空>'], np.nan, inplace=True)
|
||||
df.dropna(subset=columns, inplace=True)
|
||||
return df
|
||||
|
||||
# ==a. 处理样点数据，计算“样点均值” ---
|
||||
print("--> 步骤1: 计算样点均值...")
|
||||
field_name = soil_prop_feature_name
|
||||
sample_table_path = os.path.join(gdb_path, soil_prop_feature_name)
|
||||
sample_fields = ['TDLYLX', field_name]
|
||||
df_samples = pd.DataFrame(arcpy.da.FeatureClassToNumPyArray(sample_table_path, sample_fields, skip_nulls=False))
|
||||
df_samples = clean_df(df_samples, [field_name])
|
||||
|
||||
processed_df = process_soil_dataframe(df_samples, prop_config, field_name) # 返回具有属性分级的列
|
||||
processed_df['GRIDCODE'] = processed_df['GRIDCODE'].astype('int')
|
||||
if soil_prop_feature_name == 'PH':
|
||||
processed_df['属性分级'] = processed_df['GRIDCODE'].apply(get_prop_level_for_pH)
|
||||
elif soil_prop_feature_name == 'TRRZ' and xzqmc in hn_region:
|
||||
processed_df['属性分级'] = processed_df['GRIDCODE'].apply(get_prop_level_for_hn_TRRZ)
|
||||
elif soil_prop_feature_name == 'TRRZ' and xzqmc in xn_region:
|
||||
processed_df['属性分级'] = processed_df['GRIDCODE'].apply(get_prop_level_for_xn_TRRZ)
|
||||
else:
|
||||
processed_df['属性分级'] = processed_df['GRIDCODE'].apply(get_prop_level)
|
||||
|
||||
# 计算全部样点均值、中位值、范围
|
||||
processed_df[field_name] = processed_df[field_name].astype('float')
|
||||
stat_sample = {
|
||||
'min': processed_df[field_name].min(),
|
||||
'max': processed_df[field_name].max(),
|
||||
'mean':processed_df[field_name].mean(),
|
||||
'median': processed_df[field_name].median(),
|
||||
}
|
||||
|
||||
# ===处理样点数据，计算 各分级样点数
|
||||
df_sample_means = processed_df.groupby(['属性分级','GRIDCODE']).size().reset_index(name='样点数')
|
||||
df_sample_means['样点数占比'] = df_sample_means['样点数'] / df_sample_means['样点数'].sum() * 100
|
||||
print("样点数计算完成。")
|
||||
|
||||
|
||||
# ==处理制图数据，获各等级制图面积
|
||||
# print(df_origin_area)
|
||||
df_origin_area['YJDL'] = df_origin_area['YJDL_EJDL'].str.split('_').str[0]
|
||||
|
||||
# 定义需要过滤地类的属性列表
|
||||
filtered_props = ['ECA', 'EMG', 'ACU', 'AZN', 'AFE', 'AMN', 'AMO', 'AB', 'AS1', 'TSE']
|
||||
|
||||
# 如果当前属性在列表中，则只统计耕地和园地
|
||||
if soil_prop_feature_name in filtered_props:
|
||||
farmland_yjdl = ['耕地', '园地'] # 01: 耕地, 02: 园地
|
||||
df_origin_area = df_origin_area[df_origin_area['YJDL'].isin(farmland_yjdl)]
|
||||
print(f"过滤制图数据：仅统计耕地和园地（YJDL in {farmland_yjdl}）")
|
||||
# 如果土壤属性为GZCHD，则只需要耕地的面积统计
|
||||
if soil_prop_feature_name in ['GZCHD']:
|
||||
df_origin_area = df_origin_area[df_origin_area['YJDL'] == '耕地']
|
||||
print(f"过滤制图数据：GZCHD仅统计耕地")
|
||||
df_map_data = df_origin_area.groupby(["XZQMC","YJDL", "GRIDCODE"]).agg({"temp_area": "sum"}).reset_index()
|
||||
# print(df_map_data)
|
||||
|
||||
try:
|
||||
if is_by_xzq:
|
||||
df_map_data['adjusted_area'] = df_map_data['temp_area']
|
||||
df_map_data['adjustment_factor'] = 1.0
|
||||
|
||||
# 获取所有存在的行政区和地类
|
||||
existing_districts = df_map_data['XZQMC'].unique()
|
||||
|
||||
# 检查目标字典中的行政区是否存在
|
||||
missing_districts = []
|
||||
tt = [td for td in target_areas_dict.keys()]
|
||||
for ed in existing_districts:
|
||||
if ed not in tt:
|
||||
missing_districts.append(ed)
|
||||
|
||||
# 如果有行政区不存在，返回原始数据并提示
|
||||
if missing_districts:
|
||||
print(f"警告：平差数据中不存在行政区: {missing_districts}，未进行平差")
|
||||
|
||||
# 计算每个行政区每个地类的原始总面积
|
||||
original_totals = df_map_data.groupby(['XZQMC', 'YJDL'])['temp_area'].sum()
|
||||
|
||||
# 对每个行政区的每个地类进行平差
|
||||
for xzqmc, landuse_targets in target_areas_dict.items():
|
||||
for yjdl, target_area in landuse_targets.items():
|
||||
# 检查该行政区是否有此地类数据
|
||||
if (xzqmc, yjdl) in original_totals.index and original_totals[(xzqmc, yjdl)] > 0:
|
||||
adjustment_factor = target_area / original_totals[(xzqmc, yjdl)]
|
||||
|
||||
# 应用平差系数
|
||||
mask = (df_map_data['XZQMC'] == xzqmc) & (df_map_data['YJDL'] == yjdl)
|
||||
df_map_data.loc[mask, 'temp_area'] = df_map_data.loc[mask, 'temp_area'] * adjustment_factor
|
||||
df_map_data.loc[mask, 'adjustment_factor'] = adjustment_factor
|
||||
|
||||
# print(f"{xzqmc} - 地类 {yjdl}: 平差系数 = {adjustment_factor:.6f}")
|
||||
else:
|
||||
# 用df_target_area按YJDL进行平差计算
|
||||
original_totals = df_map_data.groupby('YJDL')['temp_area'].sum().to_dict()
|
||||
# 对每个地类进行平差
|
||||
target_area_dict = target_areas_dict.get(xzqmc,"")
|
||||
# print(target_areas_dict)
|
||||
for yjdl, target_area in target_area_dict.items():
|
||||
if (yjdl in original_totals and original_totals[yjdl] > 0) or target_area > 0:
|
||||
adjustment_factor = target_area / original_totals[yjdl]
|
||||
|
||||
# 应用平差系数
|
||||
mask = df_map_data['YJDL'] == yjdl
|
||||
df_map_data.loc[mask, 'temp_area'] = df_map_data.loc[mask, 'temp_area'] * adjustment_factor
|
||||
df_map_data.loc[mask, 'adjustment_factor'] = adjustment_factor
|
||||
|
||||
# print(f"地类 {yjdl}: 平差系数 = {adjustment_factor:.6f}")
|
||||
except Exception as e:
|
||||
print(f"平差处理失败: {e}")
|
||||
|
||||
# print(df_map_data)
|
||||
df_map_data['面积_亩'] = df_map_data['temp_area']
|
||||
|
||||
if soil_prop_feature_name == 'PH':
|
||||
df_map_data['属性分级'] = df_map_data['GRIDCODE'].apply(get_prop_level_for_pH)
|
||||
elif soil_prop_feature_name == 'TRRZ' and xzqmc in hn_region:
|
||||
df_map_data['属性分级'] = df_map_data['GRIDCODE'].apply(get_prop_level_for_hn_TRRZ)
|
||||
elif soil_prop_feature_name == 'TRRZ' and xzqmc in xn_region:
|
||||
df_map_data['属性分级'] = df_map_data['GRIDCODE'].apply(get_prop_level_for_xn_TRRZ)
|
||||
else:
|
||||
df_map_data['属性分级'] = df_map_data['GRIDCODE'].apply(get_prop_level)
|
||||
|
||||
df_map_areas = df_map_data.groupby(['属性分级','GRIDCODE'])['面积_亩'].sum().reset_index(name='制图面积')
|
||||
# 面积平差
|
||||
df_map_areas['制图面积_平差后'] = df_map_areas['制图面积']
|
||||
# ===计算面积占比
|
||||
df_map_areas['面积占比'] = df_map_areas['制图面积_平差后'] / df_map_areas['制图面积_平差后'].sum() * 100
|
||||
|
||||
# --- c. 合并数据 ---
|
||||
print("--> 步骤3: 合并数据...")
|
||||
df_skeleton = pd.concat([
|
||||
df_sample_means[['属性分级','GRIDCODE']],
|
||||
df_map_areas[['属性分级','GRIDCODE']]
|
||||
]).drop_duplicates().reset_index(drop=True)
|
||||
|
||||
df_final = pd.merge(df_skeleton, df_sample_means, on=['属性分级','GRIDCODE'], how='left')
|
||||
df_final = pd.merge(df_final, df_map_areas, on=['属性分级','GRIDCODE'], how='left')
|
||||
# print(df_final)
|
||||
df_final.sort_values(['属性分级'], inplace=True)
|
||||
|
||||
print("数据处理流程完成！")
|
||||
# print(df_final)
|
||||
return df_final, stat_sample
|
||||
|
||||
# --- 3. Excel 制表 总表---
|
||||
def write_to_excel_table1(df:pd.DataFrame, output_path, prop_config, soil_prop_tif, stat_sample):
|
||||
"""
|
||||
【最终修正版】: 将处理好的数据写入格式化的 Excel 文件。
|
||||
"""
|
||||
if df.empty:
|
||||
print("警告: 没有数据可以写入 Excel，将创建一个空的报告。")
|
||||
wb = Workbook()
|
||||
ws = wb.create_sheet("Mysheet", 0)
|
||||
ws['A1'] = "没有有效的统计数据。"
|
||||
wb.save(output_path)
|
||||
return
|
||||
|
||||
# 全区制图统计
|
||||
"""
|
||||
try:
|
||||
raster = arcpy.Raster(soil_prop_tif)
|
||||
|
||||
# 转换为numpy数组进行计算
|
||||
array = arcpy.RasterToNumPyArray(raster,nodata_to_value=9999)
|
||||
|
||||
# 过滤掉NoData值
|
||||
# 过滤NoData值和9999值
|
||||
array = array[~np.isnan(array)] # 过滤NoData
|
||||
array = array[array != 9999] # 过滤9999
|
||||
array = array.astype(np.float64)
|
||||
|
||||
stats = {
|
||||
'min': round(np.min(array),2),
|
||||
'max': round(np.max(array),2),
|
||||
'mean': round(np.mean(array),2),
|
||||
'median': round(np.median(array),2),
|
||||
'std': round(np.std(array),2)
|
||||
}
|
||||
except Exception as e:
|
||||
print(f"错误: {e}")
|
||||
"""
|
||||
# 全区样点统计
|
||||
stats = stat_sample
|
||||
|
||||
print(f"开始生成 Excel 报告到 '{output_path}'...")
|
||||
wb = Workbook()
|
||||
ws = wb.create_sheet("Mysheet", 0)
|
||||
ws.title = "行政区酸化程度等级分布及占比"
|
||||
|
||||
# 获取属性单位
|
||||
special_prop = ['耕作层厚度','阳离子','有机质','pH','有效磷','速效钾','交换性钙','交换性镁','有效硫','有效铁','有效锰','有效硅']
|
||||
fsn_props = ['砂粒含量','粉粒含量','黏粒含量','有效土层厚度']
|
||||
prop_name_str = prop_config.get('项目分级','')
|
||||
if prop_name_str:
|
||||
split_name = prop_name_str.split('\n')[0].strip()
|
||||
if split_name in special_prop:
|
||||
prop_name = '1f'
|
||||
elif split_name in fsn_props:
|
||||
prop_name = '0f'
|
||||
else:
|
||||
prop_name = '2f'
|
||||
else:
|
||||
prop_name = '1f'
|
||||
# print(prop_name_str, prop_name)
|
||||
|
||||
prop_unit_str = prop_config.get('分级标准', '')
|
||||
if prop_unit_str:
|
||||
prop_unit = prop_unit_str.split('\n')[1].strip()
|
||||
else:
|
||||
prop_unit = ''
|
||||
|
||||
# --- b. 绘制表头 (不变) ---
|
||||
ws.merge_cells('A1:B1'); ws['A1'] = '土壤三普分级'
|
||||
ws.merge_cells('C1:D1'); ws['C1'] = '样点统计'
|
||||
ws.merge_cells('E1:F1'); ws['E1'] = '制图统计'
|
||||
|
||||
ws['A2'] = '分级'; ws['B2'] = '值域/' + prop_unit if prop_unit else '值域'
|
||||
ws['C2'] = '数量/个'; ws['D2'] = '占比%'
|
||||
ws['E2'] = '面积/亩'; ws['F2'] = '占比%'
|
||||
|
||||
acid_levels = ['Ⅰ级','Ⅱ级', 'Ⅲ级', 'Ⅳ级', 'Ⅴ级']
|
||||
level_dict = prop_config['标准等级']
|
||||
# 创建两个列表来分别存储上段和下段范围
|
||||
upper_ranges = {}
|
||||
lower_ranges = {}
|
||||
|
||||
# 遍历排序后的等级
|
||||
for i, (level, ranges) in enumerate(sorted(level_dict.items(), key=lambda x: list(level_dict.keys()).index(x[0])), 1):
|
||||
# 分割范围字符串
|
||||
range_list = [r.strip() for r in ranges.split(',')]
|
||||
|
||||
if len(range_list) >= 1:
|
||||
upper_ranges[i] = range_list[0]
|
||||
|
||||
if len(range_list) >= 2:
|
||||
# 计算下段范围的索引（原始索引 + 等级总数）
|
||||
lower_index = i + len(level_dict)
|
||||
lower_ranges[lower_index] = range_list[1]
|
||||
|
||||
# 合并结果
|
||||
upper_ranges.update(lower_ranges)
|
||||
|
||||
# --- c. 填充数据 ---
|
||||
current_row = 3
|
||||
|
||||
df_to_write = df.copy() # 使用 .copy() 避免 SettingWithCopyWarning
|
||||
|
||||
for yl, group_yl_df in df_to_write.groupby('属性分级', sort=False, observed=False):
|
||||
|
||||
yl_start_row = current_row
|
||||
|
||||
# 1. 遍历该一级地类下的所有“二级地类”并写入数据
|
||||
for _, row_data in group_yl_df.iterrows():
|
||||
ws.cell(row=current_row, column=2).value = upper_ranges.get(row_data['GRIDCODE'], '-')
|
||||
|
||||
# --- 填充单元格的逻辑开始 ---
|
||||
col_start = 3 # 从第 C 列开始填充
|
||||
|
||||
# 检查是否找到了该土属的数据
|
||||
if not row_data.empty:
|
||||
|
||||
# 1. 构建要从 data_series 中查找的列名
|
||||
sample_col = f'样点数'
|
||||
sample_pct_col = f'样点数占比'
|
||||
area_col = f'制图面积_平差后'
|
||||
area_pct_col = f'面积占比'
|
||||
|
||||
# 2. 从 data_series 中安全地获取值
|
||||
sample_val = row_data.get(sample_col, 0)
|
||||
sample_pct_val = row_data.get(sample_pct_col, 0)
|
||||
area_val = row_data.get(area_col, 0)
|
||||
area_pct_val = row_data.get(area_pct_col, 0)
|
||||
|
||||
# 3. 将获取到的值填入单元格
|
||||
ws.cell(row=current_row, column=col_start).value = f"{sample_val:.0f}" if sample_val > 0 else "-"
|
||||
# 占比/%
|
||||
ws.cell(row=current_row, column=col_start + 1).value = f"{sample_pct_val:.1f}" if sample_val > 0 else "-"
|
||||
# 制图面积/亩
|
||||
ws.cell(row=current_row, column=col_start + 2).value = f"{area_val:.0f}" if area_val > 0 else "-"
|
||||
# 占比/%
|
||||
ws.cell(row=current_row, column=col_start + 3).value = f"{area_pct_val:.1f}" if area_val > 0 else "-"
|
||||
|
||||
# 移动到下一个酸化等级的起始列
|
||||
col_start += 2
|
||||
else:
|
||||
for _ in range(4):
|
||||
ws.cell(row=current_row, column=col_start).value = "-"
|
||||
col_start += 1
|
||||
|
||||
current_row += 1
|
||||
|
||||
# 合并“一级地类”单元格
|
||||
if yl_start_row <= current_row:
|
||||
ws.merge_cells(start_row=yl_start_row, start_column=1, end_row=current_row-1, end_column=1)
|
||||
ws.cell(row=yl_start_row, column=1).value = yl
|
||||
|
||||
# 2. 填充总计行
|
||||
ws.cell(row=current_row, column=1).value = '全区'
|
||||
ws.cell(row=current_row, column=2).value = '-'
|
||||
ws.cell(row=current_row, column=3).value = df['样点数'].sum()
|
||||
ws.cell(row=current_row, column=4).value = '100'
|
||||
ws.cell(row=current_row, column=5).value = f"{df['制图面积_平差后'].sum():.0f}"
|
||||
ws.cell(row=current_row, column=6).value = '100'
|
||||
|
||||
# 3. 合计单元格填充
|
||||
ws.merge_cells(f'B{current_row + 1}:F{current_row + 1}')
|
||||
ws.cell(row=current_row + 1, column=1).value = '全区均值'
|
||||
ws.cell(row=current_row + 1, column=2).value = f'{stats["mean"]:.{prop_name}}'
|
||||
|
||||
ws.merge_cells(f'B{current_row + 2}:F{current_row + 2}')
|
||||
ws.cell(row=current_row + 2, column=1).value = '全区中位值'
|
||||
ws.cell(row=current_row + 2, column=2).value = f'{stats["median"]:.{prop_name}}'
|
||||
|
||||
ws.merge_cells(f'B{current_row + 3}:F{current_row + 3}')
|
||||
ws.cell(row=current_row + 3, column=1).value = '全区范围'
|
||||
ws.cell(row=current_row + 3, column=2).value = f'{stats["min"]:.{prop_name}} ～ {stats["max"]:.{prop_name}}'
|
||||
|
||||
# --- a. 定义样式 ---
|
||||
header_font = Font(name='宋体', size=11, bold=True)
|
||||
|
||||
# --- d. 应用样式和调整列宽 (最终健壮版) ---
|
||||
if current_row > 1: # 确保有数据才应用样式
|
||||
ExcelStyleUtils.set_style(ws, f'A1:F{current_row+3}')
|
||||
ExcelStyleUtils.set_style(ws, f'A1:F2', header_font)
|
||||
|
||||
# 调整列宽
|
||||
ExcelStyleUtils.auto_adjust_column_width(ws)
|
||||
|
||||
# --- e. 保存文件 ---
|
||||
wb.save(output_path)
|
||||
print("Excel 报告生成成功！")
|
||||
|
||||
|
||||
def main(gdb_path, soil_prop_name, reclassed_features_path, dltb_features, soil_prop_tif, output_path, target_area_dict,xzqmc, prop_config):
|
||||
try:
|
||||
# --- 1. 用户配置 ---
|
||||
# 输出配置
|
||||
temp_files = []
|
||||
output_excel_path = os.path.join(output_path, f"{soil_prop_name}土壤分级分布.xlsx") # 生成的Excel报告文件路径
|
||||
|
||||
# 设置工作空间和变量
|
||||
arcpy.env.workspace = gdb_path
|
||||
arcpy.env.overwriteOutput = True
|
||||
|
||||
print("开始处理数据...")
|
||||
is_by_xzq = False if xzqmc not in ["北海市","来宾市","楚雄自治州"] else True
|
||||
|
||||
# out_table_mean = r"in_memory/out_table_mean"
|
||||
temp_out_feature_class = r"in_memory/temp_out_feature_class"
|
||||
temp_out_tables_area = r"in_memory/temp_out_tables_area"
|
||||
# temp_files.append(out_table_mean)
|
||||
temp_files.append(temp_out_tables_area)
|
||||
|
||||
# if not arcpy.Exists(out_table_mean):
|
||||
# # 2.用arcpy.sa.ZonalStatisticsAsTable 以表格进行分区统计
|
||||
# arcpy.sa.ZonalStatisticsAsTable(
|
||||
# dltb_features, "YJDL_EJDL", soil_prop_tif, out_table_mean, "DATA", "MEAN"
|
||||
# )
|
||||
# arcpy.management.CalculateField(out_table_mean, "YJDL", "!YJDL_EJDL!.split('_')[0]", "PYTHON3")
|
||||
# arcpy.management.CalculateField(out_table_mean, "EJDL", "!YJDL_EJDL!.split('_')[1]", "PYTHON3")
|
||||
|
||||
# 求地类图斑和重分类栅格面的交集
|
||||
arcpy.analysis.Intersect(
|
||||
in_features=[dltb_features,reclassed_features_path],
|
||||
out_feature_class=temp_out_feature_class,
|
||||
join_attributes="ALL",
|
||||
output_type="INPUT"
|
||||
)
|
||||
# 行政区划和相交结果进行交集制表
|
||||
arcpy.analysis.TabulateIntersection(
|
||||
in_zone_features="行政区划", # 乡镇边界
|
||||
zone_fields="XZQMC",
|
||||
in_class_features=temp_out_feature_class,
|
||||
out_table=temp_out_tables_area,
|
||||
class_fields="gridcode;YJDL_EJDL",
|
||||
out_units="SQUARE_METERS"
|
||||
)
|
||||
clipped_table_df = arcgis_utils.read_arcgis_table(temp_out_tables_area)
|
||||
|
||||
# 生成表1 土壤属性分级分布 的统计Excel报告
|
||||
final_dataframe,stat = process_data_for_table1(gdb_path, soil_prop_name, clipped_table_df, target_area_dict,xzqmc,is_by_xzq, prop_config)
|
||||
|
||||
write_to_excel_table1(final_dataframe, output_excel_path, prop_config, soil_prop_tif, stat)
|
||||
|
||||
# return df_with_factors
|
||||
except Exception as e:
|
||||
print(f"\n处理过程中发生严重错误: {e}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
finally:
|
||||
temp_files_processor.clean_up_temp_files(temp_files)
|
||||
import gc
|
||||
gc.collect()
|
||||
|
||||
# --- 4. 主程序入口 ---
|
||||
# if __name__ == "__main__":
|
||||
# main()
|
||||
315
tools/core/soil_prop_stats/B2_TRZD12土地利用类型土壤属性.py
Normal file
315
tools/core/soil_prop_stats/B2_TRZD12土地利用类型土壤属性.py
Normal file
@@ -0,0 +1,315 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
import os
|
||||
import re
|
||||
import arcpy
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
from openpyxl import Workbook
|
||||
from openpyxl.styles import Font, Border, Side, Alignment
|
||||
from openpyxl.utils import get_column_letter
|
||||
|
||||
from tools.config.pandas_field_cal_func import calculate_ejdl, calculate_yjdl
|
||||
from tools.core.utils.os_utils import temp_files_processor
|
||||
|
||||
|
||||
yjdl_order = ["耕地", "园地", "林地", "草地", "其他"]
|
||||
ejdl_order = ["水田", "旱地", "水浇地", "果园", "茶园", "橡胶园", "其他园地"]
|
||||
# 土壤12级地质类别
|
||||
trzd_order = ['砂土及壤质砂土', '砂质壤土','壤土','粉(砂)质壤土','砂质黏壤土','黏壤土','粉(砂)质黏壤土','砂质黏土','壤质黏土','粉(砂)质黏土','黏土','重黏土']
|
||||
|
||||
# --- 2. 辅助函数 ---
|
||||
# 判断单元格类型
|
||||
def get_merge_type(merged_range):
|
||||
"""
|
||||
判断合并类型
|
||||
返回: 'row'（行合并）, 'column'（列合并）, 'both'（行列合并）或 None（不是合并单元格）
|
||||
"""
|
||||
if not merged_range:
|
||||
return None
|
||||
|
||||
min_row, max_row = merged_range.min_row, merged_range.max_row
|
||||
min_col, max_col = merged_range.min_col, merged_range.max_col
|
||||
|
||||
if max_row > min_row and max_col > min_col:
|
||||
return 'both' # 同时跨行和跨列
|
||||
elif max_row > min_row:
|
||||
return 'row' # 行合并（垂直合并）
|
||||
elif max_col > min_col:
|
||||
return 'column' # 列合并（水平合并）
|
||||
else:
|
||||
return None # 实际上不是合并单元格
|
||||
|
||||
# --- 3. 数据处理与分析 均值---
|
||||
def process_data_for_table2(gdb_path, soil_prop_feature_name, df_dltb, target_areas_df):
|
||||
"""
|
||||
【最终版 v2】: 增加对制图样点数的处理，以支持加权平均计算。
|
||||
"""
|
||||
print("开始处理数据...")
|
||||
|
||||
def clean_df(df, columns):
|
||||
for col in columns:
|
||||
df[col] = df[col].astype(str).str.strip()
|
||||
df.replace(['<Null>', 'None', '', '<空>'], np.nan, inplace=True)
|
||||
df.dropna(subset=columns, inplace=True)
|
||||
return df
|
||||
|
||||
# ==a. 处理样点数据，计算样点数 ---
|
||||
print("--> 步骤1: 计算样点均值...")
|
||||
field_name = soil_prop_feature_name
|
||||
sample_table_path = os.path.join(gdb_path, soil_prop_feature_name)
|
||||
sample_fields = ['TDLYLX', field_name]
|
||||
df_samples = pd.DataFrame(arcpy.da.FeatureClassToNumPyArray(sample_table_path, sample_fields, skip_nulls=False))
|
||||
df_samples = clean_df(df_samples, [field_name])
|
||||
|
||||
df_samples["YJDL"] = df_samples['TDLYLX'].apply(calculate_yjdl)
|
||||
df_samples["EJDL"] = df_samples['TDLYLX'].apply(calculate_ejdl)
|
||||
df_samples["GRIDCODE"] = df_samples[field_name].astype(int)
|
||||
|
||||
# 按 YJDL, EJDL 分组，计算 属性 的均值
|
||||
df_sample_means = df_samples.groupby(['YJDL', 'EJDL', 'GRIDCODE']).size().reset_index(name="样点数")
|
||||
total_sample_count = df_sample_means['样点数'].sum()
|
||||
df_sample_means['样点数占比'] = df_sample_means['样点数'] / total_sample_count
|
||||
|
||||
# ==b. 处理制图数据，获各等级制图面积
|
||||
df_dltb["YJDL"] = df_dltb['YJDL_EJDL'].apply(lambda x: x.split('_')[0])
|
||||
df_dltb["EJDL"] = df_dltb["YJDL_EJDL"].apply(lambda x: x.split('_')[1])
|
||||
df_dltb.columns = df_dltb.columns.str.upper()
|
||||
df_dltb = clean_df(df_dltb, ['YJDL', 'EJDL'])
|
||||
|
||||
df_map_data = df_dltb.groupby(["YJDL","EJDL", "GRIDCODE"]).agg({"AREA": "sum"}).reset_index()
|
||||
df_map_data['制图面积_原始'] = df_map_data['AREA'] * 0.0015 # 单位：亩
|
||||
# df_map_data['面积占比'] = df_map_data['制图面积'] / df_map_data['制图面积'].sum()
|
||||
|
||||
# 第二步：整理目标面积表（确保字段名统一）
|
||||
target_areas_df = target_areas_df.copy()
|
||||
target_areas_df.columns = target_areas_df.columns.str.strip() # 去除字段名空格
|
||||
# 重置索引，确保EJDL是列而不是索引
|
||||
if 'EJDL' not in target_areas_df.columns:
|
||||
target_areas_df = target_areas_df.reset_index()
|
||||
target_areas_df.rename(columns={'index': 'EJDL'}, inplace=True)
|
||||
# 确保面积字段为数值型
|
||||
target_areas_df['面积'] = pd.to_numeric(target_areas_df['面积'], errors='coerce').fillna(0)
|
||||
|
||||
# 第三步：按二级地类分组计算平差系数
|
||||
# 先计算每个二级地类的原始合计面积
|
||||
ejdl_original_sum = df_map_data.groupby('EJDL')['制图面积_原始'].sum().reset_index()
|
||||
ejdl_original_sum.rename(columns={'制图面积_原始': '原始合计面积'}, inplace=True)
|
||||
# 合并目标面积
|
||||
ejdl_adj = pd.merge(ejdl_original_sum, target_areas_df, on='EJDL', how='left')
|
||||
ejdl_adj.rename(columns={'面积': '目标合计面积'}, inplace=True)
|
||||
# 填充无目标面积的二级地类（目标面积=原始面积，平差系数=1）
|
||||
ejdl_adj['目标合计面积'] = ejdl_adj['目标合计面积'].fillna(ejdl_adj['原始合计面积'])
|
||||
# 计算平差系数（目标面积 / 原始面积，避免除以0）
|
||||
ejdl_adj['平差系数'] = ejdl_adj['目标合计面积'] / ejdl_adj['原始合计面积'].replace(0, 1)
|
||||
ejdl_adj['平差系数'] = ejdl_adj['平差系数'].fillna(1) # 极端情况填充1
|
||||
|
||||
# 第四步：应用平差系数到每个质地级别的制图面积
|
||||
df_map_data = pd.merge(df_map_data, ejdl_adj[['EJDL', '平差系数']], on='EJDL', how='left')
|
||||
df_map_data['平差系数'] = df_map_data['平差系数'].fillna(1) # 未匹配到的二级地类系数=1
|
||||
# 计算平差后的制图面积
|
||||
df_map_data['制图面积'] = df_map_data['制图面积_原始'] * df_map_data['平差系数']
|
||||
# 重新计算面积占比（基于平差后的面积）
|
||||
total_adjusted_area = df_map_data['制图面积'].sum()
|
||||
df_map_data['面积占比'] = df_map_data['制图面积'] / total_adjusted_area
|
||||
df_map_data = clean_df(df_map_data, ['YJDL', 'EJDL'])
|
||||
|
||||
# --- c. 合并数据 ---
|
||||
print("--> 步骤3: 合并数据...")
|
||||
df_skeleton = pd.concat([
|
||||
df_sample_means[['YJDL', 'EJDL', 'GRIDCODE']],
|
||||
df_map_data[['YJDL', 'EJDL', 'GRIDCODE']]
|
||||
]).drop_duplicates().reset_index(drop=True)
|
||||
|
||||
df_final = pd.merge(df_skeleton, df_sample_means, on=['YJDL', 'EJDL', 'GRIDCODE'], how='left')
|
||||
df_final = pd.merge(df_final, df_map_data, on=['YJDL', 'EJDL', 'GRIDCODE'], how='left')
|
||||
|
||||
# (可选) 按“一级地类”和“二级地类”排序
|
||||
in_ejdl_order = ejdl_order + [x for x in df_final['EJDL'].unique() if x not in ejdl_order]
|
||||
df_final["YJDL"] = pd.Categorical(df_final['YJDL'], categories=yjdl_order, ordered=True)
|
||||
df_final["EJDL"] = pd.Categorical(df_final['EJDL'], categories=in_ejdl_order, ordered=True)
|
||||
df_final["GRIDCODE"] = pd.Categorical(df_final['GRIDCODE'], categories=sorted(df_final['GRIDCODE'].unique()), ordered=True)
|
||||
df_final.sort_values(['YJDL', 'EJDL', 'GRIDCODE'], inplace=True)
|
||||
|
||||
print("数据处理流程完成！")
|
||||
return df_final
|
||||
|
||||
# 写入EXCEL 表2
|
||||
def write_to_excel_table2(df, output_path, prop_config):
|
||||
"""
|
||||
将处理好的数据写入格式化的 Excel 文件。
|
||||
"""
|
||||
if df.empty:
|
||||
print("警告: 没有数据可以写入 Excel。")
|
||||
return
|
||||
|
||||
print(f"开始生成 Excel 报告到 '{output_path}'...")
|
||||
wb = Workbook()
|
||||
ws = wb.create_sheet("Mysheet", 0)
|
||||
ws.title = "不同土地利用类型属性变化统计"
|
||||
|
||||
# --- a. 定义样式 ---
|
||||
header_font = Font(name='等线', size=11, bold=True)
|
||||
cell_font = Font(name='等线', size=11)
|
||||
center_align = Alignment(horizontal='center', vertical='center', wrap_text=True)
|
||||
thin_border = Border(left=Side(style='thin'), right=Side(style='thin'),
|
||||
top=Side(style='thin'), bottom=Side(style='thin'))
|
||||
|
||||
def apply_style(cell_range, font, alignment=None, border=None):
|
||||
for row in ws[cell_range]:
|
||||
for cell in row:
|
||||
cell.font = font
|
||||
if alignment: cell.alignment = alignment
|
||||
if border: cell.border = border
|
||||
|
||||
# --- b. 绘制表头 ---
|
||||
ws.merge_cells('A1:B1'); ws['A1'] = '土地利用类型'
|
||||
ws.merge_cells('C1:E1'); ws['C1'] = '样点统计'
|
||||
ws.merge_cells('F1:G1'); ws['F1'] = '制图统计'
|
||||
|
||||
ws['A2'] = '一级'
|
||||
ws['B2'] = '二级'
|
||||
ws['C2'] = '质地类型'
|
||||
ws['D2'] = '数量/个'
|
||||
ws['E2'] = '占比%'
|
||||
ws['F2'] = '面积/亩'
|
||||
ws['G2'] = '占比%'
|
||||
|
||||
level_dict = prop_config['标准等级']
|
||||
# 创建两个列表来分别存储上段和下段范围
|
||||
upper_ranges = {value: key for key, value in level_dict.items()}
|
||||
|
||||
# --- c. 填充数据 ---
|
||||
current_row = 3
|
||||
|
||||
df_to_write = df.copy() # 使用 .copy() 避免 SettingWithCopyWarning
|
||||
|
||||
for yl, group_yl_df in df_to_write.groupby('YJDL', sort=False, observed=False):
|
||||
if group_yl_df.empty:
|
||||
continue
|
||||
|
||||
print(f"正在写入一级地类: {yl}...")
|
||||
yl_start_row = current_row
|
||||
|
||||
# 按二级地类分组
|
||||
for ej, group_ej_df in group_yl_df.groupby('EJDL', sort=False, observed=False):
|
||||
if group_ej_df.empty:
|
||||
continue
|
||||
|
||||
print(f"正在写入二级地类: {ej}...")
|
||||
ej_start_row = current_row
|
||||
|
||||
# 按“土壤质地分级”分组
|
||||
for idx, row_data in group_ej_df.iterrows():
|
||||
# 填充土壤质地分类
|
||||
ws.cell(row=current_row, column=3).value = upper_ranges.get(str(row_data['GRIDCODE']), '-')
|
||||
|
||||
# 填充样点数据
|
||||
ws.cell(row=current_row, column=4).value = row_data['样点数'] if not np.isnan(row_data['样点数']) else '-'
|
||||
ws.cell(row=current_row, column=5).value = round(row_data['样点数占比']*100, 2) if not np.isnan(row_data['样点数占比']) else '-'
|
||||
# 填充制图数据
|
||||
ws.cell(row=current_row, column=6).value = round(row_data['制图面积'], 0) if not np.isnan(row_data['制图面积']) else '-'
|
||||
ws.cell(row=current_row, column=7).value = round(row_data['面积占比']*100, 2) if not np.isnan(row_data['面积占比']) else '-'
|
||||
|
||||
current_row += 1
|
||||
|
||||
# 合并二级地类单元格
|
||||
if ej_start_row <= current_row:
|
||||
ws.merge_cells(start_row=ej_start_row, start_column=2, end_row=current_row-1, end_column=2)
|
||||
ws.cell(row=ej_start_row, column=2).value = ej
|
||||
|
||||
# 一级地类合计行
|
||||
ws.merge_cells(start_row=current_row, start_column=2, end_row=current_row, end_column=3)
|
||||
ws.cell(row=current_row, column=2).value = '合计'
|
||||
ws.cell(row=current_row, column=4).value = round(group_yl_df['样点数'].sum(), 0) if not np.isnan(group_yl_df['样点数'].sum()) else '-'
|
||||
ws.cell(row=current_row, column=5).value = round(group_yl_df['样点数占比'].sum()*100, 2) if not np.isnan(group_yl_df['样点数占比'].sum()) else '-'
|
||||
ws.cell(row=current_row, column=6).value = round(group_yl_df['制图面积'].sum(), 0) if not np.isnan(group_yl_df['制图面积'].sum()) else '-'
|
||||
ws.cell(row=current_row, column=7).value = round(group_yl_df['面积占比'].sum()*100, 2) if not np.isnan(group_yl_df['面积占比'].sum()) else '-'
|
||||
|
||||
# 合并一级地类单元格（修正合并范围）
|
||||
if yl_start_row <= current_row:
|
||||
ws.merge_cells(start_row=yl_start_row, start_column=1, end_row=current_row, end_column=1)
|
||||
ws.cell(row=yl_start_row, column=1).value = yl
|
||||
current_row += 1
|
||||
|
||||
# --- 5. 全区汇总行 ---
|
||||
ws.cell(row=current_row, column=1).value = '全区汇总'
|
||||
ws.merge_cells(start_row=current_row, start_column=1, end_row=current_row, end_column=3)
|
||||
ws.cell(row=current_row, column=4).value = round(df_to_write['样点数'].sum(), 0) if not np.isnan(df_to_write['样点数'].sum()) else '-'
|
||||
ws.cell(row=current_row, column=5).value = round(df_to_write['样点数占比'].sum()*100, 2) if not np.isnan(df_to_write['样点数占比'].sum()) else '-'
|
||||
ws.cell(row=current_row, column=6).value = round(df_to_write['制图面积'].sum(), 0) if not np.isnan(df_to_write['制图面积'].sum()) else '-'
|
||||
ws.cell(row=current_row, column=7).value = round(df_to_write['面积占比'].sum()*100, 2) if not np.isnan(df_to_write['面积占比'].sum()) else '-'
|
||||
|
||||
# --- d. 应用样式和调整列宽 ---
|
||||
max_col_letter = get_column_letter(ws.max_column)
|
||||
if current_row > 1: # 确保有数据才应用样式
|
||||
apply_style(f'A1:{max_col_letter}{current_row}', cell_font, center_align, thin_border)
|
||||
apply_style(f'A1:{max_col_letter}2', header_font)
|
||||
|
||||
print("正在自动调整列宽...")
|
||||
|
||||
dims = {}
|
||||
for row in ws.rows:
|
||||
for cell in row:
|
||||
if cell.value:
|
||||
merged_range = next((range for range in ws.merged_cells.ranges if cell.coordinate in range), None)
|
||||
if get_merge_type(merged_range) == 'column':
|
||||
continue
|
||||
cell_len = 0.7 * len(re.findall('([\u4e00-\u9fa5])', str(cell.value))) + len(str(cell.value))
|
||||
dims[cell.column] = max(dims.get(cell.column, 0), cell_len)
|
||||
# 设置列宽
|
||||
for col, value in dims.items():
|
||||
ws.column_dimensions[get_column_letter(int(col))].width = value + 5
|
||||
|
||||
# --- e. 保存文件 ---
|
||||
wb.save(output_path)
|
||||
print("Excel 报告生成成功！")
|
||||
|
||||
# def main(gdb_path, soil_prop_name, dltb_features, reclassed_feature, output_path,target_areas_df, prop_config):
|
||||
# print(target_areas_df)
|
||||
# df = pd.read_csv(r"D:\ProgramData\ArcGis_Py\测试数据.csv")
|
||||
# output_path = r"E:\@三普属性图出图\测试\AAA.xlsx"
|
||||
# write_to_excel_table2(df,output_path,prop_config)
|
||||
|
||||
|
||||
def main(gdb_path, soil_prop_name, dltb_features, reclassed_feature, output_path,target_areas_df, prop_config):
|
||||
try:
|
||||
# --- 1. 用户配置 ---
|
||||
# 输出配置
|
||||
temp_files = []
|
||||
output_excel_path = os.path.join(output_path, f"{soil_prop_name}土地利用类型土壤.xlsx") # 生成的Excel报告文件路径
|
||||
|
||||
# 设置工作空间和变量
|
||||
arcpy.env.workspace = gdb_path
|
||||
arcpy.env.overwriteOutput = True
|
||||
|
||||
print("开始处理数据...")
|
||||
|
||||
out_table_mean = r"in_memory/out_table_mean"
|
||||
temp_files.append(out_table_mean)
|
||||
if not arcpy.Exists(out_table_mean):
|
||||
# 2.使用交集制表计算每个TRZD的面积
|
||||
arcpy.analysis.TabulateIntersection(dltb_features, "YJDL_EJDL", reclassed_feature, out_table_mean, "gridcode", out_units="SQUARE_METERS")
|
||||
|
||||
dltb_df = pd.DataFrame(arcpy.da.TableToNumPyArray(out_table_mean, ["YJDL_EJDL", "gridcode", "AREA"]))
|
||||
|
||||
|
||||
# 生成表1 土壤属性分级分布 的统计Excel报告
|
||||
final_dataframe = process_data_for_table2(gdb_path, soil_prop_name, dltb_df, target_areas_df)
|
||||
|
||||
write_to_excel_table2(final_dataframe, output_excel_path, prop_config)
|
||||
|
||||
# return df_with_factors
|
||||
except Exception as e:
|
||||
print(f"\n处理过程中发生严重错误: {e}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
finally:
|
||||
temp_files_processor.clean_up_temp_files(temp_files)
|
||||
import gc
|
||||
gc.collect()
|
||||
|
||||
# --- 4. 主程序入口 ---
|
||||
# if __name__ == "__main__":
|
||||
# df = pd.read_csv(r"D:\ProgramData\ArcGis_Py\测试数据.csv")
|
||||
# output_path = r"E:\@三普属性图出图\测试\AAA.xlsx"
|
||||
# write_to_excel_table2(df,output_path)
|
||||
336
tools/core/soil_prop_stats/B2_TRZD土地利用类型土壤属性.py
Normal file
336
tools/core/soil_prop_stats/B2_TRZD土地利用类型土壤属性.py
Normal file
@@ -0,0 +1,336 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
import os
|
||||
import re
|
||||
|
||||
from matplotlib.artist import get
|
||||
import arcpy
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
from openpyxl import Workbook
|
||||
from openpyxl.styles import Font, Border, Side, Alignment
|
||||
from openpyxl.utils import get_column_letter
|
||||
|
||||
from tools.config.pandas_field_cal_func import calculate_ejdl, calculate_yjdl
|
||||
from tools.core.utils.os_utils import temp_files_processor
|
||||
|
||||
|
||||
yjdl_order = ["耕地", "园地", "林地", "草地", "其他"]
|
||||
ejdl_order = ["水田", "旱地", "水浇地", "果园", "茶园", "橡胶园", "其他园地"]
|
||||
# 土壤12级地质类别
|
||||
trzd_order = ['黏壤质','黏质','壤质','砂壤质','砂质']
|
||||
|
||||
# --- 2. 辅助函数 ---
|
||||
def get_prop_level(prop_level):
|
||||
"""根据输入值判断 返回等级"""
|
||||
if pd.isna(prop_level) or prop_level == 0:
|
||||
return "-"
|
||||
# 请根据您的实际分级标准调整这里的阈值
|
||||
if int(prop_level) == 5 or prop_level == "砂质":
|
||||
return "砂质"
|
||||
elif int(prop_level) == 4 or prop_level == "砂壤质":
|
||||
return "砂壤质"
|
||||
elif int(prop_level) == 3 or prop_level == "壤质":
|
||||
return "壤质"
|
||||
elif int(prop_level) == 1 or prop_level == "黏壤质":
|
||||
return "黏壤质"
|
||||
elif int(prop_level) == 2 or prop_level == "黏质":
|
||||
return "黏质"
|
||||
else:
|
||||
return "-"
|
||||
|
||||
# 判断单元格类型
|
||||
def get_merge_type(merged_range):
|
||||
"""
|
||||
判断合并类型
|
||||
返回: 'row'（行合并）, 'column'（列合并）, 'both'（行列合并）或 None（不是合并单元格）
|
||||
"""
|
||||
if not merged_range:
|
||||
return None
|
||||
|
||||
min_row, max_row = merged_range.min_row, merged_range.max_row
|
||||
min_col, max_col = merged_range.min_col, merged_range.max_col
|
||||
|
||||
if max_row > min_row and max_col > min_col:
|
||||
return 'both' # 同时跨行和跨列
|
||||
elif max_row > min_row:
|
||||
return 'row' # 行合并（垂直合并）
|
||||
elif max_col > min_col:
|
||||
return 'column' # 列合并（水平合并）
|
||||
else:
|
||||
return None # 实际上不是合并单元格
|
||||
|
||||
# --- 3. 数据处理与分析 均值---
|
||||
def process_data_for_table2(gdb_path, soil_prop_feature_name, df_dltb, target_areas_df):
|
||||
"""
|
||||
【最终版 v2】: 增加对制图样点数的处理，以支持加权平均计算。
|
||||
"""
|
||||
print("开始处理数据...")
|
||||
|
||||
def clean_df(df, columns):
|
||||
for col in columns:
|
||||
df[col] = df[col].astype(str).str.strip()
|
||||
df.replace(['<Null>', 'None', '', '<空>'], np.nan, inplace=True)
|
||||
df.dropna(subset=columns, inplace=True)
|
||||
return df
|
||||
|
||||
# ==a. 处理样点数据，计算样点数 ---
|
||||
print("--> 步骤1: 计算样点均值...")
|
||||
field_name = soil_prop_feature_name
|
||||
sample_table_path = os.path.join(gdb_path, soil_prop_feature_name)
|
||||
sample_fields = ['TDLYLX', field_name]
|
||||
df_samples = pd.DataFrame(arcpy.da.FeatureClassToNumPyArray(sample_table_path, sample_fields, skip_nulls=False))
|
||||
df_samples = clean_df(df_samples, [field_name])
|
||||
|
||||
df_samples["YJDL"] = df_samples['TDLYLX'].apply(calculate_yjdl)
|
||||
df_samples["EJDL"] = df_samples['TDLYLX'].apply(calculate_ejdl)
|
||||
df_samples["GRIDCODE"] = df_samples[field_name]
|
||||
|
||||
# 按 YJDL, EJDL 分组，计算 属性 的均值
|
||||
df_sample_means = df_samples.groupby(['YJDL', 'EJDL', 'GRIDCODE']).size().reset_index(name="样点数")
|
||||
total_sample_count = df_sample_means['样点数'].sum()
|
||||
df_sample_means['样点数占比'] = df_sample_means['样点数'] / total_sample_count
|
||||
|
||||
# ==b. 处理制图数据，获各等级制图面积
|
||||
df_dltb["YJDL"] = df_dltb['YJDL_EJDL'].apply(lambda x: x.split('_')[0])
|
||||
df_dltb["EJDL"] = df_dltb["YJDL_EJDL"].apply(lambda x: x.split('_')[1])
|
||||
df_dltb.columns = df_dltb.columns.str.upper()
|
||||
df_dltb = clean_df(df_dltb, ['YJDL', 'EJDL'])
|
||||
df_dltb['GRIDCODE'] = df_dltb['GRIDCODE'].apply(get_prop_level)
|
||||
|
||||
df_map_data = df_dltb.groupby(["YJDL","EJDL", "GRIDCODE"]).agg({"AREA": "sum"}).reset_index()
|
||||
df_map_data['制图面积_原始'] = df_map_data['AREA'] * 0.0015 # 单位：亩
|
||||
# df_map_data['面积占比'] = df_map_data['制图面积'] / df_map_data['制图面积'].sum()
|
||||
|
||||
# 第二步：整理目标面积表（确保字段名统一）
|
||||
target_areas_df = target_areas_df.copy()
|
||||
target_areas_df.columns = target_areas_df.columns.str.strip() # 去除字段名空格
|
||||
# 重置索引，确保EJDL是列而不是索引
|
||||
if 'EJDL' not in target_areas_df.columns:
|
||||
target_areas_df = target_areas_df.reset_index()
|
||||
target_areas_df.rename(columns={'index': 'EJDL'}, inplace=True)
|
||||
# 确保面积字段为数值型
|
||||
target_areas_df['面积'] = pd.to_numeric(target_areas_df['面积'], errors='coerce').fillna(0)
|
||||
|
||||
# 第三步：按二级地类分组计算平差系数
|
||||
# 先计算每个二级地类的原始合计面积
|
||||
ejdl_original_sum = df_map_data.groupby('EJDL')['制图面积_原始'].sum().reset_index()
|
||||
ejdl_original_sum.rename(columns={'制图面积_原始': '原始合计面积'}, inplace=True)
|
||||
# 合并目标面积
|
||||
ejdl_adj = pd.merge(ejdl_original_sum, target_areas_df, on='EJDL', how='left')
|
||||
ejdl_adj.rename(columns={'面积': '目标合计面积'}, inplace=True)
|
||||
# 填充无目标面积的二级地类（目标面积=原始面积，平差系数=1）
|
||||
ejdl_adj['目标合计面积'] = ejdl_adj['目标合计面积'].fillna(ejdl_adj['原始合计面积'])
|
||||
# 计算平差系数（目标面积 / 原始面积，避免除以0）
|
||||
ejdl_adj['平差系数'] = ejdl_adj['目标合计面积'] / ejdl_adj['原始合计面积'].replace(0, 1)
|
||||
ejdl_adj['平差系数'] = ejdl_adj['平差系数'].fillna(1) # 极端情况填充1
|
||||
|
||||
# 第四步：应用平差系数到每个质地级别的制图面积
|
||||
df_map_data = pd.merge(df_map_data, ejdl_adj[['EJDL', '平差系数']], on='EJDL', how='left')
|
||||
df_map_data['平差系数'] = df_map_data['平差系数'].fillna(1) # 未匹配到的二级地类系数=1
|
||||
# 计算平差后的制图面积
|
||||
df_map_data['制图面积'] = df_map_data['制图面积_原始'] * df_map_data['平差系数']
|
||||
# 重新计算面积占比（基于平差后的面积）
|
||||
total_adjusted_area = df_map_data['制图面积'].sum()
|
||||
df_map_data['面积占比'] = df_map_data['制图面积'] / total_adjusted_area
|
||||
df_map_data = clean_df(df_map_data, ['YJDL', 'EJDL'])
|
||||
|
||||
# --- c. 合并数据 ---
|
||||
print("--> 步骤3: 合并数据...")
|
||||
df_skeleton = pd.concat([
|
||||
df_sample_means[['YJDL', 'EJDL', 'GRIDCODE']],
|
||||
df_map_data[['YJDL', 'EJDL', 'GRIDCODE']]
|
||||
]).drop_duplicates().reset_index(drop=True)
|
||||
|
||||
df_final = pd.merge(df_skeleton, df_sample_means, on=['YJDL', 'EJDL', 'GRIDCODE'], how='left')
|
||||
df_final = pd.merge(df_final, df_map_data, on=['YJDL', 'EJDL', 'GRIDCODE'], how='left')
|
||||
|
||||
# (可选) 按“一级地类”和“二级地类”排序
|
||||
in_ejdl_order = ejdl_order + [x for x in df_final['EJDL'].unique() if x not in ejdl_order]
|
||||
df_final["YJDL"] = pd.Categorical(df_final['YJDL'], categories=yjdl_order, ordered=True)
|
||||
df_final["EJDL"] = pd.Categorical(df_final['EJDL'], categories=in_ejdl_order, ordered=True)
|
||||
df_final["GRIDCODE"] = pd.Categorical(df_final['GRIDCODE'], categories=sorted(df_final['GRIDCODE'].unique()), ordered=True)
|
||||
df_final.sort_values(['YJDL', 'EJDL', 'GRIDCODE'], inplace=True)
|
||||
|
||||
print("数据处理流程完成！")
|
||||
return df_final
|
||||
|
||||
# 写入EXCEL 表2
|
||||
def write_to_excel_table2(df, output_path, prop_config):
|
||||
"""
|
||||
将处理好的数据写入格式化的 Excel 文件。
|
||||
"""
|
||||
if df.empty:
|
||||
print("警告: 没有数据可以写入 Excel。")
|
||||
return
|
||||
|
||||
print(f"开始生成 Excel 报告到 '{output_path}'...")
|
||||
wb = Workbook()
|
||||
ws = wb.create_sheet("Mysheet", 0)
|
||||
ws.title = "不同土地利用类型属性变化统计"
|
||||
|
||||
# --- a. 定义样式 ---
|
||||
header_font = Font(name='等线', size=11, bold=True)
|
||||
cell_font = Font(name='等线', size=11)
|
||||
center_align = Alignment(horizontal='center', vertical='center', wrap_text=True)
|
||||
thin_border = Border(left=Side(style='thin'), right=Side(style='thin'),
|
||||
top=Side(style='thin'), bottom=Side(style='thin'))
|
||||
|
||||
def apply_style(cell_range, font, alignment=None, border=None):
|
||||
for row in ws[cell_range]:
|
||||
for cell in row:
|
||||
cell.font = font
|
||||
if alignment: cell.alignment = alignment
|
||||
if border: cell.border = border
|
||||
|
||||
# --- b. 绘制表头 ---
|
||||
ws.merge_cells('A1:B1'); ws['A1'] = '土地利用类型'
|
||||
ws.merge_cells('C1:E1'); ws['C1'] = '样点统计'
|
||||
ws.merge_cells('F1:G1'); ws['F1'] = '制图统计'
|
||||
|
||||
ws['A2'] = '一级'
|
||||
ws['B2'] = '二级'
|
||||
ws['C2'] = '质地类型'
|
||||
ws['D2'] = '数量/个'
|
||||
ws['E2'] = '占比%'
|
||||
ws['F2'] = '面积/亩'
|
||||
ws['G2'] = '占比%'
|
||||
|
||||
level_dict = prop_config['标准等级']
|
||||
# 创建两个列表来分别存储上段和下段范围
|
||||
upper_ranges = {value: key for key, value in level_dict.items()}
|
||||
|
||||
# --- c. 填充数据 ---
|
||||
current_row = 3
|
||||
|
||||
df_to_write = df.copy() # 使用 .copy() 避免 SettingWithCopyWarning
|
||||
|
||||
for yl, group_yl_df in df_to_write.groupby('YJDL', sort=False, observed=False):
|
||||
if group_yl_df.empty:
|
||||
continue
|
||||
|
||||
print(f"正在写入一级地类: {yl}...")
|
||||
yl_start_row = current_row
|
||||
|
||||
# 按二级地类分组
|
||||
for ej, group_ej_df in group_yl_df.groupby('EJDL', sort=False, observed=False):
|
||||
if group_ej_df.empty:
|
||||
continue
|
||||
|
||||
print(f"正在写入二级地类: {ej}...")
|
||||
ej_start_row = current_row
|
||||
|
||||
# 按“土壤质地分级”分组
|
||||
for idx, row_data in group_ej_df.iterrows():
|
||||
# 填充土壤质地分类
|
||||
ws.cell(row=current_row, column=3).value = str(row_data['GRIDCODE'])
|
||||
|
||||
# 填充样点数据
|
||||
ws.cell(row=current_row, column=4).value = row_data['样点数'] if not np.isnan(row_data['样点数']) else '-'
|
||||
ws.cell(row=current_row, column=5).value = round(row_data['样点数占比']*100, 2) if not np.isnan(row_data['样点数占比']) else '-'
|
||||
# 填充制图数据
|
||||
ws.cell(row=current_row, column=6).value = round(row_data['制图面积'], 0) if not np.isnan(row_data['制图面积']) else '-'
|
||||
ws.cell(row=current_row, column=7).value = round(row_data['面积占比']*100, 2) if not np.isnan(row_data['面积占比']) else '-'
|
||||
|
||||
current_row += 1
|
||||
|
||||
# 合并二级地类单元格
|
||||
if ej_start_row <= current_row:
|
||||
ws.merge_cells(start_row=ej_start_row, start_column=2, end_row=current_row-1, end_column=2)
|
||||
ws.cell(row=ej_start_row, column=2).value = ej
|
||||
|
||||
# 一级地类合计行
|
||||
ws.merge_cells(start_row=current_row, start_column=2, end_row=current_row, end_column=3)
|
||||
ws.cell(row=current_row, column=2).value = '合计'
|
||||
ws.cell(row=current_row, column=4).value = round(group_yl_df['样点数'].sum(), 0) if not np.isnan(group_yl_df['样点数'].sum()) else '-'
|
||||
ws.cell(row=current_row, column=5).value = round(group_yl_df['样点数占比'].sum()*100, 2) if not np.isnan(group_yl_df['样点数占比'].sum()) else '-'
|
||||
ws.cell(row=current_row, column=6).value = round(group_yl_df['制图面积'].sum(), 0) if not np.isnan(group_yl_df['制图面积'].sum()) else '-'
|
||||
ws.cell(row=current_row, column=7).value = round(group_yl_df['面积占比'].sum()*100, 2) if not np.isnan(group_yl_df['面积占比'].sum()) else '-'
|
||||
|
||||
# 合并一级地类单元格（修正合并范围）
|
||||
if yl_start_row <= current_row:
|
||||
ws.merge_cells(start_row=yl_start_row, start_column=1, end_row=current_row, end_column=1)
|
||||
ws.cell(row=yl_start_row, column=1).value = yl
|
||||
current_row += 1
|
||||
|
||||
# --- 5. 全区汇总行 ---
|
||||
ws.cell(row=current_row, column=1).value = '全区汇总'
|
||||
ws.merge_cells(start_row=current_row, start_column=1, end_row=current_row, end_column=3)
|
||||
ws.cell(row=current_row, column=4).value = round(df_to_write['样点数'].sum(), 0) if not np.isnan(df_to_write['样点数'].sum()) else '-'
|
||||
ws.cell(row=current_row, column=5).value = round(df_to_write['样点数占比'].sum()*100, 2) if not np.isnan(df_to_write['样点数占比'].sum()) else '-'
|
||||
ws.cell(row=current_row, column=6).value = round(df_to_write['制图面积'].sum(), 0) if not np.isnan(df_to_write['制图面积'].sum()) else '-'
|
||||
ws.cell(row=current_row, column=7).value = round(df_to_write['面积占比'].sum()*100, 2) if not np.isnan(df_to_write['面积占比'].sum()) else '-'
|
||||
|
||||
# --- d. 应用样式和调整列宽 ---
|
||||
max_col_letter = get_column_letter(ws.max_column)
|
||||
if current_row > 1: # 确保有数据才应用样式
|
||||
apply_style(f'A1:{max_col_letter}{current_row}', cell_font, center_align, thin_border)
|
||||
apply_style(f'A1:{max_col_letter}2', header_font)
|
||||
|
||||
print("正在自动调整列宽...")
|
||||
|
||||
dims = {}
|
||||
for row in ws.rows:
|
||||
for cell in row:
|
||||
if cell.value:
|
||||
merged_range = next((range for range in ws.merged_cells.ranges if cell.coordinate in range), None)
|
||||
if get_merge_type(merged_range) == 'column':
|
||||
continue
|
||||
cell_len = 0.7 * len(re.findall('([\u4e00-\u9fa5])', str(cell.value))) + len(str(cell.value))
|
||||
dims[cell.column] = max(dims.get(cell.column, 0), cell_len)
|
||||
# 设置列宽
|
||||
for col, value in dims.items():
|
||||
ws.column_dimensions[get_column_letter(int(col))].width = value + 5
|
||||
|
||||
# --- e. 保存文件 ---
|
||||
wb.save(output_path)
|
||||
print("Excel 报告生成成功！")
|
||||
|
||||
# def main(gdb_path, soil_prop_name, dltb_features, reclassed_feature, output_path,target_areas_df, prop_config):
|
||||
# print(target_areas_df)
|
||||
# df = pd.read_csv(r"D:\ProgramData\ArcGis_Py\测试数据.csv")
|
||||
# output_path = r"E:\@三普属性图出图\测试\AAA.xlsx"
|
||||
# write_to_excel_table2(df,output_path,prop_config)
|
||||
|
||||
|
||||
def main(gdb_path, soil_prop_name, dltb_features, reclassed_feature, output_path,target_areas_df, prop_config):
|
||||
try:
|
||||
# --- 1. 用户配置 ---
|
||||
# 输出配置
|
||||
temp_files = []
|
||||
output_excel_path = os.path.join(output_path, f"{soil_prop_name}土地利用类型土壤.xlsx") # 生成的Excel报告文件路径
|
||||
|
||||
# 设置工作空间和变量
|
||||
arcpy.env.workspace = gdb_path
|
||||
arcpy.env.overwriteOutput = True
|
||||
|
||||
print("开始处理数据...")
|
||||
|
||||
out_table_mean = r"in_memory/out_table_mean"
|
||||
temp_files.append(out_table_mean)
|
||||
if not arcpy.Exists(out_table_mean):
|
||||
# 2.使用交集制表计算每个TRZD的面积
|
||||
arcpy.analysis.TabulateIntersection(dltb_features, "YJDL_EJDL", reclassed_feature, out_table_mean, "gridcode", out_units="SQUARE_METERS")
|
||||
|
||||
dltb_df = pd.DataFrame(arcpy.da.TableToNumPyArray(out_table_mean, ["YJDL_EJDL", "gridcode", "AREA"]))
|
||||
|
||||
|
||||
# 生成表1 土壤属性分级分布 的统计Excel报告
|
||||
final_dataframe = process_data_for_table2(gdb_path, soil_prop_name, dltb_df, target_areas_df)
|
||||
|
||||
write_to_excel_table2(final_dataframe, output_excel_path, prop_config)
|
||||
|
||||
# return df_with_factors
|
||||
except Exception as e:
|
||||
print(f"\n处理过程中发生严重错误: {e}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
finally:
|
||||
temp_files_processor.clean_up_temp_files(temp_files)
|
||||
import gc
|
||||
gc.collect()
|
||||
|
||||
# --- 4. 主程序入口 ---
|
||||
# if __name__ == "__main__":
|
||||
# df = pd.read_csv(r"D:\ProgramData\ArcGis_Py\测试数据.csv")
|
||||
# output_path = r"E:\@三普属性图出图\测试\AAA.xlsx"
|
||||
# write_to_excel_table2(df,output_path)
|
||||
328
tools/core/soil_prop_stats/B2土地利用类型土壤属性.py
Normal file
328
tools/core/soil_prop_stats/B2土地利用类型土壤属性.py
Normal file
@@ -0,0 +1,328 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
import os
|
||||
import re
|
||||
import arcpy
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
from openpyxl import Workbook
|
||||
from openpyxl.styles import Font
|
||||
from openpyxl.utils import get_column_letter
|
||||
|
||||
from tools.config.pandas_field_cal_func import calculate_ejdl, calculate_yjdl
|
||||
from tools.core.utils.os_utils import temp_files_processor
|
||||
from tools.core.utils.excel_utils import ExcelStyleUtils
|
||||
|
||||
|
||||
yjdl_order = ["耕地", "园地", "林地", "草地", "其他"]
|
||||
ejdl_order = ["水田", "旱地", "水浇地", "果园", "茶园", "橡胶园", "其他园地"]
|
||||
|
||||
# --- 3. 数据处理与分析 均值---
|
||||
def process_data_for_table2(gdb_path, soil_prop_feature_name, df_dltb, target_areas_df):
|
||||
"""
|
||||
【最终版 v2】: 增加对制图样点数的处理，以支持加权平均计算。
|
||||
"""
|
||||
print("开始处理数据...")
|
||||
|
||||
def clean_df(df, columns):
|
||||
for col in columns:
|
||||
df[col] = df[col].astype(str).str.strip()
|
||||
df.replace(['<Null>', 'None', '', '<空>'], np.nan, inplace=True)
|
||||
df.dropna(subset=columns, inplace=True)
|
||||
return df
|
||||
|
||||
# ==a. 处理样点数据，计算“样点均值” ---
|
||||
print("--> 步骤1: 计算样点均值...")
|
||||
field_name = soil_prop_feature_name
|
||||
sample_table_path = os.path.join(gdb_path, soil_prop_feature_name)
|
||||
sample_fields = ['TDLYLX', field_name]
|
||||
df_samples = pd.DataFrame(arcpy.da.FeatureClassToNumPyArray(sample_table_path, sample_fields, skip_nulls=False))
|
||||
df_samples = clean_df(df_samples, [field_name])
|
||||
|
||||
df_samples["YJDL"] = df_samples['TDLYLX'].apply(calculate_yjdl)
|
||||
df_samples["EJDL"] = df_samples['TDLYLX'].apply(calculate_ejdl)
|
||||
df_samples[field_name] = df_samples[field_name].astype(float)
|
||||
|
||||
# 按 YJDL, EJDL 分组，计算 属性 的均值
|
||||
df_sample_means = df_samples.groupby(['YJDL', 'EJDL'])[field_name].agg(['count', 'max', 'min', 'mean']).reset_index()
|
||||
|
||||
# ==b. 处理制图数据，获各等级制图面积
|
||||
df_dltb["YJDL"] = df_dltb['YJDL_EJDL'].apply(lambda x: x.split('_')[0])
|
||||
df_dltb["EJDL"] = df_dltb["YJDL_EJDL"].apply(lambda x: x.split('_')[1])
|
||||
df_dltb = clean_df(df_dltb, ['YJDL', 'EJDL'])
|
||||
df_dltb.rename(columns={'MEAN': '制图均值', 'COUNT': '制图样点数'}, inplace=True)
|
||||
|
||||
# --- c. 合并数据 ---
|
||||
print("--> 步骤3: 合并数据...")
|
||||
df_skeleton = pd.concat([
|
||||
df_sample_means[['YJDL', 'EJDL']],
|
||||
df_dltb[['YJDL', 'EJDL']]
|
||||
]).drop_duplicates().reset_index(drop=True)
|
||||
|
||||
df_final = pd.merge(df_skeleton, df_sample_means, on=['YJDL', 'EJDL'], how='left')
|
||||
df_final = pd.merge(df_final, df_dltb, on=['YJDL', 'EJDL'], how='left')
|
||||
df_final = pd.merge(df_final, target_areas_df, on=['EJDL'], how='left')
|
||||
|
||||
# (可选) 按“一级地类”和“二级地类”排序
|
||||
in_ejdl_order = ejdl_order + [x for x in df_final['EJDL'].unique() if x not in ejdl_order]
|
||||
df_final["YJDL"] = pd.Categorical(df_final['YJDL'], categories=yjdl_order, ordered=True)
|
||||
df_final["EJDL"] = pd.Categorical(df_final['EJDL'], categories=in_ejdl_order, ordered=True)
|
||||
df_final.sort_values(['YJDL', 'EJDL'], inplace=True)
|
||||
|
||||
print("数据处理流程完成！")
|
||||
return df_final
|
||||
|
||||
# 写入EXCEL 表2
|
||||
def write_to_excel_table2(df, output_path, prop_config:dict, soil_prop_name: str = ''):
|
||||
"""
|
||||
将处理好的数据写入格式化的 Excel 文件。
|
||||
"""
|
||||
if df.empty:
|
||||
print("警告: 没有数据可以写入 Excel。")
|
||||
return
|
||||
|
||||
print(f"开始生成 Excel 报告到 '{output_path}'...")
|
||||
wb = Workbook()
|
||||
ws = wb.create_sheet("Mysheet", 0)
|
||||
ws.title = "不同土地利用类型属性变化统计"
|
||||
|
||||
# 获取属性单位
|
||||
special_prop = ['耕作层厚度','阳离子','有机质','pH','有效磷','速效钾','交换性钙','交换性镁','有效硫','有效铁','有效锰','有效硅','全钾']
|
||||
fsn_props = ['砂粒含量','粉粒含量','黏粒含量','有效土层厚度']
|
||||
prop_name_str = prop_config.get('项目分级','')
|
||||
if prop_name_str:
|
||||
split_name = prop_name_str.split('\n')[0].strip()
|
||||
if split_name in special_prop:
|
||||
prop_name = '1f'
|
||||
elif split_name in fsn_props:
|
||||
prop_name = '0f'
|
||||
else:
|
||||
prop_name = '2f'
|
||||
else:
|
||||
prop_name = '1f'
|
||||
|
||||
prop_unit_str = prop_config.get('分级标准', '')
|
||||
if prop_unit_str:
|
||||
prop_unit = prop_unit_str.split('\n')[1].strip()
|
||||
else:
|
||||
prop_unit = ''
|
||||
|
||||
# --- b. 绘制表头 ---
|
||||
ws.merge_cells('A1:B1'); ws['A1'] = '土地利用类型'
|
||||
ws.merge_cells('C1:E1'); ws['C1'] = '样点统计'
|
||||
ws.merge_cells('F1:G1'); ws['F1'] = '制图统计'
|
||||
|
||||
ws['A2'] = '一级'
|
||||
ws['B2'] = '二级'
|
||||
ws['C2'] = '均值/' + prop_unit
|
||||
ws['D2'] = '范围/' + prop_unit
|
||||
ws['E2'] = '数量/个'
|
||||
ws['F2'] = '均值/' + prop_unit
|
||||
ws['G2'] = '面积/亩'
|
||||
|
||||
# --- c. 填充数据 ---
|
||||
current_row = 3
|
||||
|
||||
df_to_write = df.copy() # 使用 .copy() 避免 SettingWithCopyWarning
|
||||
|
||||
filtered_props = ['ECA', 'EMG', 'ACU', 'AZN', 'AFE', 'AMN', 'AMO', 'AB', 'AS1', 'TSE']
|
||||
|
||||
for yl, group_yl_df in df_to_write.groupby('YJDL', sort=False, observed=False):
|
||||
|
||||
print(f"正在写入一级地类: {yl}...")
|
||||
yl_start_row = current_row
|
||||
|
||||
# 遍历该一级地类下的所有“二级地类”
|
||||
for _, row_data in group_yl_df.iterrows():
|
||||
ws.cell(row=current_row, column=2).value = row_data['EJDL']
|
||||
|
||||
# 填充样点数据
|
||||
sample_mean = row_data.get('mean')
|
||||
if pd.notna(sample_mean):
|
||||
ws.cell(row=current_row, column=3).value = f"{sample_mean:.{prop_name}}"
|
||||
ws.cell(row=current_row, column=4).value = f"{row_data.get('min', '-'):.{prop_name}}～{row_data.get('max', '-'):.{prop_name}}"
|
||||
ws.cell(row=current_row, column=5).value = row_data.get('count', '-')
|
||||
else:
|
||||
ws.cell(row=current_row, column=3).value = "-"
|
||||
ws.cell(row=current_row, column=4).value = "-"
|
||||
ws.cell(row=current_row, column=5).value = "-"
|
||||
|
||||
# 填充制图数据
|
||||
map_mean = row_data.get('制图均值')
|
||||
if pd.notna(map_mean):
|
||||
ws.cell(row=current_row, column=6).value = f"{map_mean:.{prop_name}}"
|
||||
ws.cell(row=current_row, column=7).value = f"{row_data.get('面积', '-'):.0f}"
|
||||
else:
|
||||
ws.cell(row=current_row, column=6).value = "-"
|
||||
ws.cell(row=current_row, column=7).value = "-"
|
||||
|
||||
current_row += 1
|
||||
|
||||
# 计算并写入“合计”行
|
||||
if ws.cell(row=current_row-1, column=2).value in ["林地", "草地", "其他"]:
|
||||
ws.merge_cells(start_row=yl_start_row, start_column=1, end_row=yl_start_row, end_column=2)
|
||||
ws.cell(row=yl_start_row, column=1).value = yl
|
||||
|
||||
if soil_prop_name in filtered_props:
|
||||
ws.cell(row=yl_start_row, column=6).value = "-"
|
||||
ws.cell(row=yl_start_row, column=7).value = "-"
|
||||
|
||||
continue
|
||||
|
||||
ws.cell(row=current_row, column=2).value = '合计'
|
||||
|
||||
# 计算合计行的均值 (均值的均值)
|
||||
total_count = group_yl_df['count'].sum()
|
||||
weighted_sum = group_yl_df['mean']*group_yl_df['count']
|
||||
if not weighted_sum.empty and total_count != 0:
|
||||
total_sample_mean = weighted_sum.sum()/group_yl_df['count'].sum()
|
||||
else:
|
||||
total_sample_mean = None
|
||||
min_min, max_max = group_yl_df['min'].min(), group_yl_df['max'].max()
|
||||
|
||||
if pd.notna(total_sample_mean):
|
||||
ws.cell(row=current_row, column=3).value = f"{total_sample_mean:.{prop_name}}"
|
||||
ws.cell(row=current_row, column=4).value = f"{min_min:.{prop_name}}～{max_max:.{prop_name}}"
|
||||
ws.cell(row=current_row, column=5).value = f"{total_count:.0f}"
|
||||
else:
|
||||
ws.cell(row=current_row, column=3).value = "-"
|
||||
ws.cell(row=current_row, column=4).value = "-"
|
||||
ws.cell(row=current_row, column=5).value = "-"
|
||||
|
||||
# b. **【核心修正】: 计算合计行的“制图均值”(加权平均)**
|
||||
# 准备加权平均的分子和分母
|
||||
weighted_sum = 0
|
||||
total_count = 0
|
||||
|
||||
# 遍历当前一级地类分组中的每一行
|
||||
for _, row in group_yl_df.iterrows():
|
||||
mean_val = row.get('制图均值')
|
||||
count_val = row.get('制图样点数')
|
||||
|
||||
# 只有当均值和样点数都存在且有效时，才参与计算
|
||||
if pd.notna(mean_val) and pd.notna(count_val) and count_val > 0:
|
||||
weighted_sum += mean_val * count_val # Σ (mean * count)
|
||||
total_count += count_val # Σ (count)
|
||||
|
||||
# 计算加权平均值
|
||||
weighted_avg = (weighted_sum / total_count) if total_count > 0 else 0
|
||||
total_area = group_yl_df['面积'].sum()
|
||||
|
||||
if weighted_avg > 0:
|
||||
ws.cell(row=current_row, column=6).value = f"{weighted_avg:.{prop_name}}"
|
||||
ws.cell(row=current_row, column=7).value = f"{total_area:.0f}"
|
||||
else:
|
||||
ws.cell(row=current_row, column=6).value = "-"
|
||||
ws.cell(row=current_row, column=7).value = "-"
|
||||
|
||||
# 合并“一级地类”单元格
|
||||
if yl_start_row <= current_row:
|
||||
ws.merge_cells(start_row=yl_start_row, start_column=1, end_row=current_row, end_column=1)
|
||||
ws.cell(row=yl_start_row, column=1).value = yl
|
||||
|
||||
current_row += 1
|
||||
|
||||
# 计算全区的均值、范围、数量
|
||||
if soil_prop_name in filtered_props:
|
||||
# 只基于耕地和园地计算全区统计
|
||||
df_for_total = df_to_write[df_to_write['YJDL'].isin(['耕地', '园地'])].copy()
|
||||
print(f"全区统计过滤：仅基于耕地和园地（YJDL in ['耕地', '园地']）")
|
||||
else:
|
||||
df_for_total = df_to_write.copy()
|
||||
|
||||
# 使用 df_for_total 进行后续计算
|
||||
total_weighted_sum = df_for_total['mean'] * df_for_total['count']
|
||||
total_counts = df_for_total['count'].sum()
|
||||
if total_counts > 0:
|
||||
total_mean = total_weighted_sum.sum() / total_counts
|
||||
else:
|
||||
total_mean = None
|
||||
|
||||
if not df_for_total.empty:
|
||||
total_range = f"{df_for_total['min'].min():.{prop_name}}～{df_for_total['max'].max():.{prop_name}}"
|
||||
total_zhitu_weighted_sum = df_for_total['制图均值']*df_for_total['面积']
|
||||
total_areas = df_for_total['面积'].sum()
|
||||
if total_areas > 0:
|
||||
total_zhitu_mean = total_zhitu_weighted_sum.sum() / total_areas
|
||||
else:
|
||||
total_zhitu_mean = None
|
||||
else:
|
||||
total_range = "-"
|
||||
total_zhitu_mean = None
|
||||
total_areas = 0
|
||||
|
||||
# 填充全区统计行
|
||||
ws.merge_cells(start_row=current_row, start_column=1, end_row=current_row, end_column=2)
|
||||
ws.cell(row=current_row, column=1).value = '全区'
|
||||
if pd.notna(total_mean):
|
||||
ws.cell(row=current_row, column=3).value = f"{total_mean:.{prop_name}}"
|
||||
else:
|
||||
ws.cell(row=current_row, column=3).value = "-"
|
||||
ws.cell(row=current_row, column=4).value = total_range
|
||||
ws.cell(row=current_row, column=5).value = f"{total_counts:.0f}" if total_counts > 0 else "-"
|
||||
if pd.notna(total_zhitu_mean):
|
||||
ws.cell(row=current_row, column=6).value = f"{total_zhitu_mean:.{prop_name}}"
|
||||
else:
|
||||
ws.cell(row=current_row, column=6).value = "-"
|
||||
ws.cell(row=current_row, column=7).value = f"{total_areas:.0f}" if total_areas > 0 else "-"
|
||||
|
||||
|
||||
# --- a. 定义样式 ---
|
||||
header_font = Font(name='等线', size=11, bold=True)
|
||||
|
||||
# --- d. 应用样式和调整列宽 ---
|
||||
max_col_letter = get_column_letter(ws.max_column)
|
||||
if current_row > 1: # 确保有数据才应用样式
|
||||
ExcelStyleUtils.set_style(ws,f'A1:{max_col_letter}{current_row}')
|
||||
ExcelStyleUtils.set_style(ws, f'A1:{max_col_letter}2', header_font)
|
||||
|
||||
print("正在自动调整列宽...")
|
||||
|
||||
# 设置列宽
|
||||
ExcelStyleUtils.auto_adjust_column_width(ws)
|
||||
|
||||
# --- e. 保存文件 ---
|
||||
wb.save(output_path)
|
||||
print("Excel 报告生成成功！")
|
||||
|
||||
|
||||
def main(gdb_path, soil_prop_name, dltb_features, soil_prop_tif, output_path,target_areas_df, prop_config):
|
||||
try:
|
||||
# --- 1. 用户配置 ---
|
||||
# 输出配置
|
||||
temp_files = []
|
||||
output_excel_path = os.path.join(output_path, f"{soil_prop_name}土地利用类型土壤.xlsx") # 生成的Excel报告文件路径
|
||||
|
||||
# 设置工作空间和变量
|
||||
arcpy.env.workspace = gdb_path
|
||||
arcpy.env.overwriteOutput = True
|
||||
|
||||
print("开始处理数据...")
|
||||
|
||||
out_table_mean = r"in_memory/out_table_mean"
|
||||
temp_files.append(out_table_mean)
|
||||
if not arcpy.Exists(out_table_mean):
|
||||
# 2.用arcpy.sa.ZonalStatisticsAsTable 以表格进行分区统计
|
||||
arcpy.sa.ZonalStatisticsAsTable(dltb_features, "YJDL_EJDL", soil_prop_tif, out_table_mean, "DATA", "MEAN")
|
||||
|
||||
dltb_df = pd.DataFrame(arcpy.da.TableToNumPyArray(out_table_mean, ["YJDL_EJDL", "MEAN", "COUNT"]))
|
||||
|
||||
|
||||
# 生成表1 土壤属性分级分布 的统计Excel报告
|
||||
final_dataframe = process_data_for_table2(gdb_path, soil_prop_name, dltb_df, target_areas_df)
|
||||
|
||||
# final_dataframe = process_data_for_table5_2(gdb_path, out_table_area, sample_table_name, df_with_factors)
|
||||
write_to_excel_table2(final_dataframe, output_excel_path, prop_config, soil_prop_name)
|
||||
|
||||
# return df_with_factors
|
||||
except Exception as e:
|
||||
print(f"\n处理过程中发生严重错误: {e}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
finally:
|
||||
temp_files_processor.clean_up_temp_files(temp_files)
|
||||
import gc
|
||||
gc.collect()
|
||||
|
||||
# --- 4. 主程序入口 ---
|
||||
# if __name__ == "__main__":
|
||||
# main()
|
||||
446
tools/core/soil_prop_stats/B3_TRZD12不同土壤类型土壤属性.py
Normal file
446
tools/core/soil_prop_stats/B3_TRZD12不同土壤类型土壤属性.py
Normal file
@@ -0,0 +1,446 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
import os
|
||||
import re
|
||||
import arcpy
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
from openpyxl import Workbook
|
||||
from openpyxl.styles import Font, Border, Side, Alignment
|
||||
from openpyxl.utils import get_column_letter
|
||||
|
||||
from tools.config.pandas_field_cal_func import calculate_muyan, calculate_muzhi
|
||||
|
||||
from tools.config.custom_sort import yl_order, ts_order
|
||||
from tools.core.utils.os_utils import temp_files_processor
|
||||
|
||||
|
||||
# --- 2. 辅助函数 ---
|
||||
# 判断单元格类型
|
||||
def get_merge_type(merged_range):
|
||||
"""
|
||||
判断合并类型
|
||||
返回: 'row'（行合并）, 'column'（列合并）, 'both'（行列合并）或 None（不是合并单元格）
|
||||
"""
|
||||
if not merged_range:
|
||||
return None
|
||||
|
||||
min_row, max_row = merged_range.min_row, merged_range.max_row
|
||||
min_col, max_col = merged_range.min_col, merged_range.max_col
|
||||
|
||||
if max_row > min_row and max_col > min_col:
|
||||
return 'both' # 同时跨行和跨列
|
||||
elif max_row > min_row:
|
||||
return 'row' # 行合并（垂直合并）
|
||||
elif max_col > min_col:
|
||||
return 'column' # 列合并（水平合并）
|
||||
else:
|
||||
return None # 实际上不是合并单元格
|
||||
|
||||
# --- 3. 数据处理与分析 均值---
|
||||
def process_data_for_table3(soil_prop_name, df_trlx_sample, df_trlx_zhitu, df_trlx, target_areas_df):
|
||||
"""
|
||||
【最终版 v2】: 增加对制图样点数的处理，以支持加权平均计算。
|
||||
"""
|
||||
print("开始处理数据...")
|
||||
|
||||
def clean_df(df, columns) -> pd.DataFrame:
|
||||
for col in columns:
|
||||
df[col] = df[col].astype(str).str.strip()
|
||||
df.replace(['<Null>', 'None', '', '<空>'], np.nan, inplace=True)
|
||||
df.dropna(subset=columns, inplace=True)
|
||||
return df
|
||||
|
||||
# ==a. 处理样点数据，计算“样点均值” ---
|
||||
print("--> 步骤1: 计算样点均值...")
|
||||
field_name = soil_prop_name
|
||||
sample_fields = ['YL', 'TS', field_name]
|
||||
df_samples = clean_df(df_trlx_sample, sample_fields)
|
||||
df_samples["GRIDCODE"] = df_samples[field_name].astype(int)
|
||||
|
||||
# 通过土属计算母岩母质
|
||||
df_samples['母岩'] = df_samples['TS'].apply(calculate_muyan)
|
||||
df_samples['母质'] = df_samples['母岩'].apply(calculate_muzhi)
|
||||
# 按 YJDL, EJDL 分组
|
||||
df_sample_means = df_samples.groupby(['YL', 'TS', 'GRIDCODE']).size().reset_index(name="样点数")
|
||||
total_sample_count = df_sample_means['样点数'].sum()
|
||||
df_sample_means['样点数占比'] = df_sample_means['样点数'] / total_sample_count
|
||||
# df_sample_mymz = df_samples.groupby(['母质', '母岩', 'TZ'])[field_name].agg(['count', 'mean', 'median']).reset_index()
|
||||
# print(df_sample_mymz)
|
||||
|
||||
# ==b. 处理制图数据，获各等级制图面积
|
||||
df_trlx_zhitu["YL"] = df_trlx_zhitu['YL_TS'].apply(lambda x: x.split('_')[0])
|
||||
df_trlx_zhitu["TS"] = df_trlx_zhitu["YL_TS"].apply(lambda x: x.split('_')[1])
|
||||
df_trlx_zhitu.columns = df_trlx_zhitu.columns.str.upper()
|
||||
df_trlx_zhitu = clean_df(df_trlx_zhitu, ['YL', 'TS'])
|
||||
|
||||
df_map_data = df_trlx_zhitu.groupby(["YL","TS", "GRIDCODE"]).agg({"AREA": "sum"}).reset_index()
|
||||
df_map_data['制图面积_原始'] = df_map_data['AREA'] * 0.0015 # 单位：亩
|
||||
|
||||
|
||||
# ==c. 处理制图数据，获各等级制图面积
|
||||
df_trlx = clean_df(df_trlx, ['YL', 'TS'])
|
||||
df_trlx["面积"] = df_trlx["Shape@Area"] * 0.0015
|
||||
|
||||
# 拿到目标df总面积，计算比例进行平差
|
||||
target_areas = target_areas_df['面积'].sum()
|
||||
original_area = df_trlx['面积'].sum()
|
||||
adjusted_area_yz = target_areas / original_area
|
||||
df_trlx["面积"] = df_trlx["面积"] * adjusted_area_yz
|
||||
df_trlx_area = df_trlx.groupby(['YL', 'TS'])['面积'].sum().reset_index()
|
||||
df_trlx_area['面积'] = pd.to_numeric(df_trlx_area['面积'], errors='coerce').fillna(0)
|
||||
# ==========================
|
||||
# 第三步：按二级地类分组计算平差系数
|
||||
# 先计算每个二级地类的原始合计面积
|
||||
ts_original_sum = df_map_data.groupby('TS')['制图面积_原始'].sum().reset_index()
|
||||
ts_original_sum.rename(columns={'制图面积_原始': '原始合计面积'}, inplace=True)
|
||||
# 合并目标面积
|
||||
ts_adj = pd.merge(ts_original_sum, df_trlx_area, on='TS', how='left')
|
||||
ts_adj.rename(columns={'面积': '目标合计面积'}, inplace=True)
|
||||
# 填充无目标面积的二级地类（目标面积=原始面积，平差系数=1）
|
||||
ts_adj['目标合计面积'] = ts_adj['目标合计面积'].fillna(ts_adj['原始合计面积'])
|
||||
# 计算平差系数（目标面积 / 原始面积，避免除以0）
|
||||
ts_adj['平差系数'] = ts_adj['目标合计面积'] / ts_adj['原始合计面积'].replace(0, 1)
|
||||
ts_adj['平差系数'] = ts_adj['平差系数'].fillna(1) # 极端情况填充1
|
||||
|
||||
# 第四步：应用平差系数到每个质地级别的制图面积
|
||||
df_map_data = pd.merge(df_map_data, ts_adj[['TS', '平差系数']], on='TS', how='left')
|
||||
df_map_data['平差系数'] = df_map_data['平差系数'].fillna(1) # 未匹配到的二级地类系数=1
|
||||
# 计算平差后的制图面积
|
||||
df_map_data['制图面积'] = df_map_data['制图面积_原始'] * df_map_data['平差系数']
|
||||
# 重新计算面积占比（基于平差后的面积）
|
||||
total_adjusted_area = df_map_data['制图面积'].sum()
|
||||
df_map_data['面积占比'] = df_map_data['制图面积'] / total_adjusted_area
|
||||
df_map_data = clean_df(df_map_data, ['YL', 'TS'])
|
||||
|
||||
# --- c. 合并数据 ---
|
||||
print("--> 步骤3: 合并数据...")
|
||||
df_skeleton = pd.concat([
|
||||
df_sample_means[['YL', 'TS', 'GRIDCODE']],
|
||||
df_map_data[['YL', 'TS', 'GRIDCODE']]
|
||||
]).drop_duplicates().reset_index(drop=True)
|
||||
|
||||
df_final = pd.merge(df_skeleton, df_sample_means, on=['YL', 'TS', 'GRIDCODE'], how='left')
|
||||
df_final = pd.merge(df_final, df_map_data, on=['YL', 'TS', 'GRIDCODE'], how='left')
|
||||
|
||||
# (可选) 按“亚类”和“土属”排序
|
||||
in_yl_order = yl_order + [x for x in df_final['YL'].unique() if x not in yl_order]
|
||||
in_ts_order = ts_order + [x for x in df_final['TS'].unique() if x not in ts_order]
|
||||
df_final["YL"] = pd.Categorical(df_final['YL'], categories=in_yl_order, ordered=True)
|
||||
df_final["TS"] = pd.Categorical(df_final['TS'], categories=in_ts_order, ordered=True)
|
||||
df_final["GRIDCODE"] = pd.Categorical(df_final['GRIDCODE'], categories=sorted(df_final['GRIDCODE'].unique()), ordered=True)
|
||||
df_final.sort_values(['YL', 'TS', 'GRIDCODE'], inplace=True)
|
||||
|
||||
print("数据处理流程完成！")
|
||||
return df_final
|
||||
# return df_final, df_sample_mymz
|
||||
|
||||
# 写入EXCEL 表2
|
||||
def write_to_excel_table3(df, output_path, prop_config:dict):
|
||||
"""
|
||||
将处理好的数据写入格式化的 Excel 文件。
|
||||
"""
|
||||
if df.empty:
|
||||
print("警告: 没有数据可以写入 Excel。")
|
||||
return
|
||||
|
||||
print(f"开始生成 Excel 报告到 '{output_path}'...")
|
||||
wb = Workbook()
|
||||
ws = wb.create_sheet("Mysheet", 0)
|
||||
ws.title = "不同土壤类型属性变化统计"
|
||||
|
||||
# --- a. 定义样式 ---
|
||||
header_font = Font(name='等线', size=11, bold=True)
|
||||
cell_font = Font(name='等线', size=11)
|
||||
center_align = Alignment(horizontal='center', vertical='center', wrap_text=True)
|
||||
thin_border = Border(left=Side(style='thin'), right=Side(style='thin'),
|
||||
top=Side(style='thin'), bottom=Side(style='thin'))
|
||||
|
||||
def apply_style(cell_range, font, alignment=None, border=None):
|
||||
for row in ws[cell_range]:
|
||||
for cell in row:
|
||||
cell.font = font
|
||||
if alignment: cell.alignment = alignment
|
||||
if border: cell.border = border
|
||||
|
||||
# --- b. 绘制表头 ---
|
||||
ws.merge_cells('A1:B1'); ws['A1'] = '土壤类型'
|
||||
ws.merge_cells('C1:E1'); ws['C1'] = '样点统计'
|
||||
ws.merge_cells('F1:G1'); ws['F1'] = '制图统计'
|
||||
|
||||
ws['A2'] = '亚类'
|
||||
ws['B2'] = '土属'
|
||||
ws['C2'] = '质地类型'
|
||||
ws['D2'] = '数量/个'
|
||||
ws['E2'] = '占比%'
|
||||
ws['F2'] = '面积/亩'
|
||||
ws['G2'] = '占比%'
|
||||
|
||||
level_dict = prop_config['标准等级']
|
||||
# 创建两个列表来分别存储上段和下段范围
|
||||
upper_ranges = {value: key for key, value in level_dict.items()}
|
||||
|
||||
# --- c. 填充数据 ---
|
||||
current_row = 3
|
||||
|
||||
df_to_write = df.copy() # 使用 .copy() 避免 SettingWithCopyWarning
|
||||
|
||||
for yl, group_yl_df in df_to_write.groupby('YL', sort=False, observed=True):
|
||||
if group_yl_df.empty:
|
||||
continue
|
||||
|
||||
print(f"正在写入亚类: {yl}...")
|
||||
yl_start_row = current_row
|
||||
|
||||
# 按二级地类分组
|
||||
for ts, group_ts_df in group_yl_df.groupby('TS', sort=False, observed=False):
|
||||
if group_ts_df.empty:
|
||||
continue
|
||||
|
||||
print(f"正在写入二级地类: {ts}...")
|
||||
ts_start_row = current_row
|
||||
|
||||
# 遍历该亚类下下的所有“土属”
|
||||
for _, row_data in group_ts_df.iterrows():
|
||||
ws.cell(row=current_row, column=3).value = upper_ranges.get(str(row_data['GRIDCODE']), '-')
|
||||
|
||||
# 填充样点数据
|
||||
ws.cell(row=current_row, column=4).value = row_data['样点数'] if not np.isnan(row_data['样点数']) else '-'
|
||||
ws.cell(row=current_row, column=5).value = round(row_data['样点数占比']*100, 2) if not np.isnan(row_data['样点数占比']) else '-'
|
||||
# 填充制图数据
|
||||
ws.cell(row=current_row, column=6).value = round(row_data['制图面积'], 0) if not np.isnan(row_data['制图面积']) else '-'
|
||||
ws.cell(row=current_row, column=7).value = round(row_data['面积占比']*100, 2) if not np.isnan(row_data['面积占比']) else '-'
|
||||
|
||||
current_row += 1
|
||||
|
||||
# 合并二级地类单元格
|
||||
if ts_start_row <= current_row:
|
||||
ws.merge_cells(start_row=ts_start_row, start_column=2, end_row=current_row-1, end_column=2)
|
||||
ws.cell(row=ts_start_row, column=2).value = ts
|
||||
|
||||
# 合并“一级地类”单元格
|
||||
if yl_start_row <= current_row:
|
||||
ws.merge_cells(start_row=yl_start_row, start_column=1, end_row=current_row-1, end_column=1)
|
||||
ws.cell(row=yl_start_row, column=1).value = yl
|
||||
|
||||
# 计算全区的均值、范围、数量
|
||||
total_areas = df_to_write['制图面积'].sum()
|
||||
|
||||
ws.merge_cells(start_row=current_row, start_column=1, end_row=current_row, end_column=3)
|
||||
ws.cell(row=current_row, column=1).value = '全区'
|
||||
ws.cell(row=current_row, column=4).value = df_to_write['样点数'].sum()
|
||||
ws.cell(row=current_row, column=5).value = round(df_to_write['样点数占比'].sum()*100, 2)
|
||||
ws.cell(row=current_row, column=6).value = round(total_areas, 0)
|
||||
ws.cell(row=current_row, column=7).value = round(df_to_write['面积占比'].sum()*100, 2)
|
||||
|
||||
# --- d. 应用样式和调整列宽 ---
|
||||
max_col_letter = get_column_letter(ws.max_column)
|
||||
if current_row > 1: # 确保有数据才应用样式
|
||||
apply_style(f'A1:{max_col_letter}{current_row}', cell_font, center_align, thin_border)
|
||||
apply_style(f'A1:{max_col_letter}2', header_font)
|
||||
|
||||
print("正在自动调整列宽...")
|
||||
|
||||
dims = {}
|
||||
for row in ws.rows:
|
||||
for cell in row:
|
||||
if cell.value:
|
||||
merged_range = next((range for range in ws.merged_cells.ranges if cell.coordinate in range), None)
|
||||
if get_merge_type(merged_range) == 'column':
|
||||
continue
|
||||
cell_len = 0.7 * len(re.findall('([\u4e00-\u9fa5])', str(cell.value))) + len(str(cell.value))
|
||||
dims[cell.column] = max(dims.get(cell.column, 0), cell_len)
|
||||
# 设置列宽
|
||||
for col, value in dims.items():
|
||||
ws.column_dimensions[get_column_letter(int(col))].width = value + 5
|
||||
|
||||
# --- e. 保存文件 ---
|
||||
wb.save(output_path)
|
||||
print("Excel 报告生成成功！")
|
||||
|
||||
# 母岩母质表
|
||||
def write_to_excel_table4(df:pd.DataFrame, output_path, prop_config):
|
||||
if df.empty:
|
||||
print("警告: 没有数据可以写入 Excel。")
|
||||
return
|
||||
|
||||
wb = Workbook()
|
||||
ws = wb.create_sheet("Mysheet", 0)
|
||||
ws.title = "母岩母质土壤属性统计"
|
||||
|
||||
# 获取属性单位
|
||||
special_prop = ['耕作层厚度','阳离子','有机质','pH','有效磷','速效钾','交换性钙','交换性镁','有效硫','有效铁','有效锰','有效硅','全钾','沙粒','粉粒','粘粒']
|
||||
prop_name_str = prop_config.get('项目分级','')
|
||||
if prop_name_str:
|
||||
prop_name = prop_name_str.split('\n')[0].strip() in special_prop
|
||||
else:
|
||||
prop_name = False
|
||||
|
||||
prop_unit_str = prop_config.get('分级标准', '')
|
||||
if prop_unit_str:
|
||||
prop_unit = prop_unit_str.split('\n')[1].strip()
|
||||
else:
|
||||
prop_unit = ''
|
||||
|
||||
# --- a. 定义样式 ---
|
||||
header_font = Font(name='等线', size=11, bold=True)
|
||||
cell_font = Font(name='等线', size=11)
|
||||
center_align = Alignment(horizontal='center', vertical='center', wrap_text=True)
|
||||
thin_border = Border(left=Side(style='thin'), right=Side(style='thin'),
|
||||
top=Side(style='thin'), bottom=Side(style='thin'))
|
||||
|
||||
def apply_style(cell_range, font, alignment=None, border=None):
|
||||
for row in ws[cell_range]:
|
||||
for cell in row:
|
||||
cell.font = font
|
||||
if alignment: cell.alignment = alignment
|
||||
if border: cell.border = border
|
||||
|
||||
# 写入表头
|
||||
headers = ['母岩母质','', '土种类型', '样点统计', '']
|
||||
ws.append(headers)
|
||||
ws.append(['', '', '', f'均值/{prop_unit}', '数量/个'])
|
||||
|
||||
# 合并表头单元格
|
||||
ws.merge_cells('A1:B2') # 母岩母质
|
||||
ws.merge_cells('C1:C2') # 土种类型
|
||||
ws.merge_cells('D1:E1') # 样点统计
|
||||
|
||||
current_row = 3
|
||||
|
||||
# 按母质和母岩进行分组
|
||||
grouped = df.groupby(['母质', '母岩']).agg({
|
||||
'TZ': lambda x: '，'.join(x), # 将土种名称用逗号连接
|
||||
'mean': 'mean', # 计算均值
|
||||
'count': 'sum' # 计算总数
|
||||
}).reset_index()
|
||||
|
||||
parent_materials = grouped['母质'].unique()
|
||||
|
||||
for parent_material in parent_materials:
|
||||
|
||||
parent_material_row = current_row
|
||||
|
||||
if parent_material == '未知':
|
||||
continue
|
||||
|
||||
material_group = grouped[grouped['母质'] == parent_material]
|
||||
# 写入母岩母质分组（只在第一行显示）
|
||||
first_row_in_group = True
|
||||
|
||||
for _, row_data in material_group.iterrows():
|
||||
if first_row_in_group:
|
||||
# 第一行显示母岩母质名称
|
||||
ws.cell(row=current_row, column=1, value=parent_material)
|
||||
first_row_in_group = False
|
||||
else:
|
||||
# 后续行留空
|
||||
ws.cell(row=current_row, column=1, value='')
|
||||
|
||||
# 写入母岩类型
|
||||
ws.cell(row=current_row, column=2, value=row_data['母岩'])
|
||||
|
||||
# 写入土种类型（所有土种用逗号连接）
|
||||
ws.cell(row=current_row, column=3, value=row_data['TZ'])
|
||||
|
||||
# 写入统计数据
|
||||
ws.cell(row=current_row, column=4, value=round(row_data['mean'], 1))
|
||||
ws.cell(row=current_row, column=5, value=row_data['count'])
|
||||
|
||||
current_row += 1
|
||||
|
||||
# 合并母岩母质分组
|
||||
if parent_material_row < current_row:
|
||||
ws.merge_cells(start_row=parent_material_row, start_column=1, end_row=current_row - 1, end_column=1)
|
||||
|
||||
ws.merge_cells(start_row=current_row, start_column=1, end_row=current_row, end_column=3)
|
||||
ws.cell(row=current_row, column=1, value='全区')
|
||||
|
||||
# --- d. 应用样式和调整列宽 ---
|
||||
max_col_letter = get_column_letter(ws.max_column)
|
||||
if current_row > 1: # 确保有数据才应用样式
|
||||
apply_style(f'A1:{max_col_letter}{current_row}', cell_font, center_align, thin_border)
|
||||
apply_style(f'A1:{max_col_letter}2', header_font)
|
||||
|
||||
# 设置列宽
|
||||
ws.column_dimensions["A"].width = 20
|
||||
ws.column_dimensions["B"].width = 20
|
||||
ws.column_dimensions["C"].width = 30
|
||||
ws.column_dimensions["D"].width = 20
|
||||
ws.column_dimensions["E"].width = 20
|
||||
|
||||
# 保存文件
|
||||
wb.save(output_path)
|
||||
print(f"数据已成功写入到 {output_path}")
|
||||
|
||||
|
||||
def main(gdb_path, soil_prop_name, trlx_features, reclassed_feature, output_path,target_areas_df, prop_config):
|
||||
try:
|
||||
# --- 1. 用户配置 ---
|
||||
# 输出配置
|
||||
temp_files = []
|
||||
output_excel_path = os.path.join(output_path,f"{soil_prop_name}不同土壤类型土壤.xlsx") # 生成的Excel报告文件路径
|
||||
# output_excel4_path = os.path.join(output_path,f"{soil_prop_name}不同母岩母质土壤属性.xlsx")
|
||||
soil_prop_features = os.path.join(gdb_path,soil_prop_name)
|
||||
|
||||
# 设置工作空间和变量
|
||||
arcpy.env.workspace = gdb_path
|
||||
arcpy.env.overwriteOutput = True
|
||||
|
||||
print("开始处理数据...")
|
||||
|
||||
temp_out_features = r"in_memory/temp_out_type_features"
|
||||
out_table_mean = r"in_memory/out_table_type_mean"
|
||||
temp_files.append(temp_out_features)
|
||||
temp_files.append(out_table_mean)
|
||||
|
||||
# 2. 用样点进行空间连接到土壤类型图斑
|
||||
fields_to_keep = {
|
||||
soil_prop_features: [soil_prop_name],
|
||||
trlx_features: ["YL", "TS", "TZ"],
|
||||
}
|
||||
|
||||
field_mappings = arcpy.FieldMappings()
|
||||
|
||||
for join_features in fields_to_keep.keys():
|
||||
for field_name in fields_to_keep[join_features]:
|
||||
try:
|
||||
field_map = arcpy.FieldMap()
|
||||
field_map.addInputField(join_features, field_name)
|
||||
field_map.mergeRule = "First" # 对所有连接字段使用 "First" 规则
|
||||
field_mappings.addFieldMap(field_map)
|
||||
except Exception as e:
|
||||
print(f"警告: 添加字段 '{field_name}' (来自 '{join_features}') 时出错，将跳过。错误信息: {e}")
|
||||
# 空间连接
|
||||
arcpy.analysis.SpatialJoin(soil_prop_features, trlx_features, temp_out_features, "JOIN_ONE_TO_ONE", "KEEP_ALL",field_mappings, "INTERSECT")
|
||||
|
||||
# 3. 交集制表计算每个TRZD的面积
|
||||
arcpy.analysis.TabulateIntersection(trlx_features, "YL_TS", reclassed_feature, out_table_mean, "gridcode", out_units="SQUARE_METERS")
|
||||
|
||||
trlx_zhitu_df = pd.DataFrame(arcpy.da.TableToNumPyArray(out_table_mean, ["YL_TS", "gridcode", "AREA"]))
|
||||
trlx_sample_df = pd.DataFrame(arcpy.da.FeatureClassToNumPyArray(temp_out_features, ["YL", "TS", "TZ", soil_prop_name]))
|
||||
|
||||
# 获取土壤类型图斑面积
|
||||
trlx_area_df = pd.DataFrame(arcpy.da.FeatureClassToNumPyArray(trlx_features, ["YL", "TS", "Shape@Area"]))
|
||||
|
||||
# 处理表3数据
|
||||
final_dataframe = process_data_for_table3(soil_prop_name,trlx_sample_df, trlx_zhitu_df, trlx_area_df, target_areas_df)
|
||||
# print(final_dataframe)
|
||||
|
||||
# 生成表3
|
||||
write_to_excel_table3(final_dataframe, output_excel_path, prop_config)
|
||||
# 母岩母质表
|
||||
# write_to_excel_table4(df_mymz, output_excel4_path, prop_config)
|
||||
|
||||
# return df_with_factors
|
||||
except Exception as e:
|
||||
print(f"\n处理过程中发生严重错误: {e}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
finally:
|
||||
temp_files_processor.clean_up_temp_files(temp_files)
|
||||
import gc
|
||||
gc.collect()
|
||||
|
||||
# --- 4. 主程序入口 ---
|
||||
# if __name__ == "__main__":
|
||||
# main()
|
||||
465
tools/core/soil_prop_stats/B3_TRZD不同土壤类型土壤属性.py
Normal file
465
tools/core/soil_prop_stats/B3_TRZD不同土壤类型土壤属性.py
Normal file
@@ -0,0 +1,465 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
import os
|
||||
import re
|
||||
import arcpy
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
from openpyxl import Workbook
|
||||
from openpyxl.styles import Font, Border, Side, Alignment
|
||||
from openpyxl.utils import get_column_letter
|
||||
|
||||
from tools.config.pandas_field_cal_func import calculate_muyan, calculate_muzhi
|
||||
|
||||
from tools.config.custom_sort import yl_order, ts_order
|
||||
from tools.core.utils.os_utils import temp_files_processor
|
||||
|
||||
|
||||
# --- 2. 辅助函数 ---
|
||||
def get_prop_level(prop_level):
|
||||
"""根据输入值判断 返回等级"""
|
||||
if pd.isna(prop_level) or prop_level == 0:
|
||||
return "-"
|
||||
# 请根据您的实际分级标准调整这里的阈值
|
||||
if int(prop_level) == 5 or prop_level == "砂质":
|
||||
return "砂质"
|
||||
elif int(prop_level) == 4 or prop_level == "砂壤质":
|
||||
return "砂壤质"
|
||||
elif int(prop_level) == 3 or prop_level == "壤质":
|
||||
return "壤质"
|
||||
elif int(prop_level) == 1 or prop_level == "黏壤质":
|
||||
return "黏壤质"
|
||||
elif int(prop_level) == 2 or prop_level == "黏质":
|
||||
return "黏质"
|
||||
else:
|
||||
return "-"
|
||||
|
||||
# 判断单元格类型
|
||||
def get_merge_type(merged_range):
|
||||
"""
|
||||
判断合并类型
|
||||
返回: 'row'（行合并）, 'column'（列合并）, 'both'（行列合并）或 None（不是合并单元格）
|
||||
"""
|
||||
if not merged_range:
|
||||
return None
|
||||
|
||||
min_row, max_row = merged_range.min_row, merged_range.max_row
|
||||
min_col, max_col = merged_range.min_col, merged_range.max_col
|
||||
|
||||
if max_row > min_row and max_col > min_col:
|
||||
return 'both' # 同时跨行和跨列
|
||||
elif max_row > min_row:
|
||||
return 'row' # 行合并（垂直合并）
|
||||
elif max_col > min_col:
|
||||
return 'column' # 列合并（水平合并）
|
||||
else:
|
||||
return None # 实际上不是合并单元格
|
||||
|
||||
# --- 3. 数据处理与分析 均值---
|
||||
def process_data_for_table3(soil_prop_name, df_trlx_sample, df_trlx_zhitu, df_trlx, target_areas_df):
|
||||
"""
|
||||
【最终版 v2】: 增加对制图样点数的处理，以支持加权平均计算。
|
||||
"""
|
||||
print("开始处理数据...")
|
||||
|
||||
def clean_df(df, columns) -> pd.DataFrame:
|
||||
for col in columns:
|
||||
df[col] = df[col].astype(str).str.strip()
|
||||
df.replace(['<Null>', 'None', '', '<空>'], np.nan, inplace=True)
|
||||
df.dropna(subset=columns, inplace=True)
|
||||
return df
|
||||
|
||||
# ==a. 处理样点数据，计算“样点均值” ---
|
||||
print("--> 步骤1: 计算样点均值...")
|
||||
field_name = soil_prop_name
|
||||
sample_fields = ['YL', 'TS', field_name]
|
||||
df_samples = clean_df(df_trlx_sample, sample_fields)
|
||||
df_samples["GRIDCODE"] = df_samples[field_name]
|
||||
|
||||
# 通过土属计算母岩母质
|
||||
df_samples['母岩'] = df_samples['TS'].apply(calculate_muyan)
|
||||
df_samples['母质'] = df_samples['母岩'].apply(calculate_muzhi)
|
||||
# 按 YJDL, EJDL 分组
|
||||
df_sample_means = df_samples.groupby(['YL', 'TS', 'GRIDCODE']).size().reset_index(name="样点数")
|
||||
total_sample_count = df_sample_means['样点数'].sum()
|
||||
df_sample_means['样点数占比'] = df_sample_means['样点数'] / total_sample_count
|
||||
# df_sample_mymz = df_samples.groupby(['母质', '母岩', 'TZ'])[field_name].agg(['count', 'mean', 'median']).reset_index()
|
||||
# print(df_sample_mymz)
|
||||
|
||||
# ==b. 处理制图数据，获各等级制图面积
|
||||
df_trlx_zhitu["YL"] = df_trlx_zhitu['YL_TS'].apply(lambda x: x.split('_')[0])
|
||||
df_trlx_zhitu["TS"] = df_trlx_zhitu["YL_TS"].apply(lambda x: x.split('_')[1])
|
||||
df_trlx_zhitu.columns = df_trlx_zhitu.columns.str.upper()
|
||||
df_trlx_zhitu = clean_df(df_trlx_zhitu, ['YL', 'TS'])
|
||||
df_trlx_zhitu['GRIDCODE'] = df_trlx_zhitu['GRIDCODE'].apply(get_prop_level)
|
||||
|
||||
df_map_data = df_trlx_zhitu.groupby(["YL","TS", "GRIDCODE"]).agg({"AREA": "sum"}).reset_index()
|
||||
df_map_data['制图面积_原始'] = df_map_data['AREA'] * 0.0015 # 单位：亩
|
||||
|
||||
|
||||
# ==c. 处理制图数据，获各等级制图面积
|
||||
df_trlx = clean_df(df_trlx, ['YL', 'TS'])
|
||||
df_trlx["面积"] = df_trlx["Shape@Area"] * 0.0015
|
||||
|
||||
# 拿到目标df总面积，计算比例进行平差
|
||||
target_areas = target_areas_df['面积'].sum()
|
||||
original_area = df_trlx['面积'].sum()
|
||||
adjusted_area_yz = target_areas / original_area
|
||||
df_trlx["面积"] = df_trlx["面积"] * adjusted_area_yz
|
||||
df_trlx_area = df_trlx.groupby(['YL', 'TS'])['面积'].sum().reset_index()
|
||||
df_trlx_area['面积'] = pd.to_numeric(df_trlx_area['面积'], errors='coerce').fillna(0)
|
||||
# ==========================
|
||||
# 第三步：按二级地类分组计算平差系数
|
||||
# 先计算每个二级地类的原始合计面积
|
||||
ts_original_sum = df_map_data.groupby('TS')['制图面积_原始'].sum().reset_index()
|
||||
ts_original_sum.rename(columns={'制图面积_原始': '原始合计面积'}, inplace=True)
|
||||
# 合并目标面积
|
||||
ts_adj = pd.merge(ts_original_sum, df_trlx_area, on='TS', how='left')
|
||||
ts_adj.rename(columns={'面积': '目标合计面积'}, inplace=True)
|
||||
# 填充无目标面积的二级地类（目标面积=原始面积，平差系数=1）
|
||||
ts_adj['目标合计面积'] = ts_adj['目标合计面积'].fillna(ts_adj['原始合计面积'])
|
||||
# 计算平差系数（目标面积 / 原始面积，避免除以0）
|
||||
ts_adj['平差系数'] = ts_adj['目标合计面积'] / ts_adj['原始合计面积'].replace(0, 1)
|
||||
ts_adj['平差系数'] = ts_adj['平差系数'].fillna(1) # 极端情况填充1
|
||||
|
||||
# 第四步：应用平差系数到每个质地级别的制图面积
|
||||
df_map_data = pd.merge(df_map_data, ts_adj[['TS', '平差系数']], on='TS', how='left')
|
||||
df_map_data['平差系数'] = df_map_data['平差系数'].fillna(1) # 未匹配到的二级地类系数=1
|
||||
# 计算平差后的制图面积
|
||||
df_map_data['制图面积'] = df_map_data['制图面积_原始'] * df_map_data['平差系数']
|
||||
# 重新计算面积占比（基于平差后的面积）
|
||||
total_adjusted_area = df_map_data['制图面积'].sum()
|
||||
df_map_data['面积占比'] = df_map_data['制图面积'] / total_adjusted_area
|
||||
df_map_data = clean_df(df_map_data, ['YL', 'TS'])
|
||||
|
||||
# --- c. 合并数据 ---
|
||||
print("--> 步骤3: 合并数据...")
|
||||
df_skeleton = pd.concat([
|
||||
df_sample_means[['YL', 'TS', 'GRIDCODE']],
|
||||
df_map_data[['YL', 'TS', 'GRIDCODE']]
|
||||
]).drop_duplicates().reset_index(drop=True)
|
||||
|
||||
df_final = pd.merge(df_skeleton, df_sample_means, on=['YL', 'TS', 'GRIDCODE'], how='left')
|
||||
df_final = pd.merge(df_final, df_map_data, on=['YL', 'TS', 'GRIDCODE'], how='left')
|
||||
|
||||
# (可选) 按“亚类”和“土属”排序
|
||||
in_yl_order = yl_order + [x for x in df_final['YL'].unique() if x not in yl_order]
|
||||
in_ts_order = ts_order + [x for x in df_final['TS'].unique() if x not in ts_order]
|
||||
df_final["YL"] = pd.Categorical(df_final['YL'], categories=in_yl_order, ordered=True)
|
||||
df_final["TS"] = pd.Categorical(df_final['TS'], categories=in_ts_order, ordered=True)
|
||||
df_final["GRIDCODE"] = pd.Categorical(df_final['GRIDCODE'], categories=sorted(df_final['GRIDCODE'].unique()), ordered=True)
|
||||
df_final.sort_values(['YL', 'TS', 'GRIDCODE'], inplace=True)
|
||||
|
||||
print("数据处理流程完成！")
|
||||
return df_final
|
||||
# return df_final, df_sample_mymz
|
||||
|
||||
# 写入EXCEL 表2
|
||||
def write_to_excel_table3(df, output_path, prop_config:dict):
|
||||
"""
|
||||
将处理好的数据写入格式化的 Excel 文件。
|
||||
"""
|
||||
if df.empty:
|
||||
print("警告: 没有数据可以写入 Excel。")
|
||||
return
|
||||
|
||||
print(f"开始生成 Excel 报告到 '{output_path}'...")
|
||||
wb = Workbook()
|
||||
ws = wb.create_sheet("Mysheet", 0)
|
||||
ws.title = "不同土壤类型属性变化统计"
|
||||
|
||||
# --- a. 定义样式 ---
|
||||
header_font = Font(name='等线', size=11, bold=True)
|
||||
cell_font = Font(name='等线', size=11)
|
||||
center_align = Alignment(horizontal='center', vertical='center', wrap_text=True)
|
||||
thin_border = Border(left=Side(style='thin'), right=Side(style='thin'),
|
||||
top=Side(style='thin'), bottom=Side(style='thin'))
|
||||
|
||||
def apply_style(cell_range, font, alignment=None, border=None):
|
||||
for row in ws[cell_range]:
|
||||
for cell in row:
|
||||
cell.font = font
|
||||
if alignment: cell.alignment = alignment
|
||||
if border: cell.border = border
|
||||
|
||||
# --- b. 绘制表头 ---
|
||||
ws.merge_cells('A1:B1'); ws['A1'] = '土壤类型'
|
||||
ws.merge_cells('C1:E1'); ws['C1'] = '样点统计'
|
||||
ws.merge_cells('F1:G1'); ws['F1'] = '制图统计'
|
||||
|
||||
ws['A2'] = '亚类'
|
||||
ws['B2'] = '土属'
|
||||
ws['C2'] = '质地类型'
|
||||
ws['D2'] = '数量/个'
|
||||
ws['E2'] = '占比%'
|
||||
ws['F2'] = '面积/亩'
|
||||
ws['G2'] = '占比%'
|
||||
|
||||
level_dict = prop_config['标准等级']
|
||||
# 创建两个列表来分别存储上段和下段范围
|
||||
upper_ranges = {value: key for key, value in level_dict.items()}
|
||||
|
||||
# --- c. 填充数据 ---
|
||||
current_row = 3
|
||||
|
||||
df_to_write = df.copy() # 使用 .copy() 避免 SettingWithCopyWarning
|
||||
|
||||
for yl, group_yl_df in df_to_write.groupby('YL', sort=False, observed=True):
|
||||
if group_yl_df.empty:
|
||||
continue
|
||||
|
||||
print(f"正在写入亚类: {yl}...")
|
||||
yl_start_row = current_row
|
||||
|
||||
# 按二级地类分组
|
||||
for ts, group_ts_df in group_yl_df.groupby('TS', sort=False, observed=False):
|
||||
if group_ts_df.empty:
|
||||
continue
|
||||
|
||||
print(f"正在写入二级地类: {ts}...")
|
||||
ts_start_row = current_row
|
||||
|
||||
# 遍历该亚类下下的所有“土属”
|
||||
for _, row_data in group_ts_df.iterrows():
|
||||
ws.cell(row=current_row, column=3).value = row_data['GRIDCODE']
|
||||
|
||||
# 填充样点数据
|
||||
ws.cell(row=current_row, column=4).value = row_data['样点数'] if not np.isnan(row_data['样点数']) else '-'
|
||||
ws.cell(row=current_row, column=5).value = round(row_data['样点数占比']*100, 2) if not np.isnan(row_data['样点数占比']) else '-'
|
||||
# 填充制图数据
|
||||
ws.cell(row=current_row, column=6).value = round(row_data['制图面积'], 0) if not np.isnan(row_data['制图面积']) else '-'
|
||||
ws.cell(row=current_row, column=7).value = round(row_data['面积占比']*100, 2) if not np.isnan(row_data['面积占比']) else '-'
|
||||
|
||||
current_row += 1
|
||||
|
||||
# 合并二级地类单元格
|
||||
if ts_start_row <= current_row:
|
||||
ws.merge_cells(start_row=ts_start_row, start_column=2, end_row=current_row-1, end_column=2)
|
||||
ws.cell(row=ts_start_row, column=2).value = ts
|
||||
|
||||
# 合并“一级地类”单元格
|
||||
if yl_start_row <= current_row:
|
||||
ws.merge_cells(start_row=yl_start_row, start_column=1, end_row=current_row-1, end_column=1)
|
||||
ws.cell(row=yl_start_row, column=1).value = yl
|
||||
|
||||
# 计算全区的均值、范围、数量
|
||||
total_areas = df_to_write['制图面积'].sum()
|
||||
|
||||
ws.merge_cells(start_row=current_row, start_column=1, end_row=current_row, end_column=3)
|
||||
ws.cell(row=current_row, column=1).value = '全区'
|
||||
ws.cell(row=current_row, column=4).value = df_to_write['样点数'].sum()
|
||||
ws.cell(row=current_row, column=5).value = round(df_to_write['样点数占比'].sum()*100, 2)
|
||||
ws.cell(row=current_row, column=6).value = round(total_areas, 0)
|
||||
ws.cell(row=current_row, column=7).value = round(df_to_write['面积占比'].sum()*100, 2)
|
||||
|
||||
# --- d. 应用样式和调整列宽 ---
|
||||
max_col_letter = get_column_letter(ws.max_column)
|
||||
if current_row > 1: # 确保有数据才应用样式
|
||||
apply_style(f'A1:{max_col_letter}{current_row}', cell_font, center_align, thin_border)
|
||||
apply_style(f'A1:{max_col_letter}2', header_font)
|
||||
|
||||
print("正在自动调整列宽...")
|
||||
|
||||
dims = {}
|
||||
for row in ws.rows:
|
||||
for cell in row:
|
||||
if cell.value:
|
||||
merged_range = next((range for range in ws.merged_cells.ranges if cell.coordinate in range), None)
|
||||
if get_merge_type(merged_range) == 'column':
|
||||
continue
|
||||
cell_len = 0.7 * len(re.findall('([\u4e00-\u9fa5])', str(cell.value))) + len(str(cell.value))
|
||||
dims[cell.column] = max(dims.get(cell.column, 0), cell_len)
|
||||
# 设置列宽
|
||||
for col, value in dims.items():
|
||||
ws.column_dimensions[get_column_letter(int(col))].width = value + 5
|
||||
|
||||
# --- e. 保存文件 ---
|
||||
wb.save(output_path)
|
||||
print("Excel 报告生成成功！")
|
||||
|
||||
# 母岩母质表
|
||||
def write_to_excel_table4(df:pd.DataFrame, output_path, prop_config):
|
||||
if df.empty:
|
||||
print("警告: 没有数据可以写入 Excel。")
|
||||
return
|
||||
|
||||
wb = Workbook()
|
||||
ws = wb.create_sheet("Mysheet", 0)
|
||||
ws.title = "母岩母质土壤属性统计"
|
||||
|
||||
# 获取属性单位
|
||||
special_prop = ['耕作层厚度','阳离子','有机质','pH','有效磷','速效钾','交换性钙','交换性镁','有效硫','有效铁','有效锰','有效硅','全钾','沙粒','粉粒','粘粒']
|
||||
prop_name_str = prop_config.get('项目分级','')
|
||||
if prop_name_str:
|
||||
prop_name = prop_name_str.split('\n')[0].strip() in special_prop
|
||||
else:
|
||||
prop_name = False
|
||||
|
||||
prop_unit_str = prop_config.get('分级标准', '')
|
||||
if prop_unit_str:
|
||||
prop_unit = prop_unit_str.split('\n')[1].strip()
|
||||
else:
|
||||
prop_unit = ''
|
||||
|
||||
# --- a. 定义样式 ---
|
||||
header_font = Font(name='等线', size=11, bold=True)
|
||||
cell_font = Font(name='等线', size=11)
|
||||
center_align = Alignment(horizontal='center', vertical='center', wrap_text=True)
|
||||
thin_border = Border(left=Side(style='thin'), right=Side(style='thin'),
|
||||
top=Side(style='thin'), bottom=Side(style='thin'))
|
||||
|
||||
def apply_style(cell_range, font, alignment=None, border=None):
|
||||
for row in ws[cell_range]:
|
||||
for cell in row:
|
||||
cell.font = font
|
||||
if alignment: cell.alignment = alignment
|
||||
if border: cell.border = border
|
||||
|
||||
# 写入表头
|
||||
headers = ['母岩母质','', '土种类型', '样点统计', '']
|
||||
ws.append(headers)
|
||||
ws.append(['', '', '', f'均值/{prop_unit}', '数量/个'])
|
||||
|
||||
# 合并表头单元格
|
||||
ws.merge_cells('A1:B2') # 母岩母质
|
||||
ws.merge_cells('C1:C2') # 土种类型
|
||||
ws.merge_cells('D1:E1') # 样点统计
|
||||
|
||||
current_row = 3
|
||||
|
||||
# 按母质和母岩进行分组
|
||||
grouped = df.groupby(['母质', '母岩']).agg({
|
||||
'TZ': lambda x: '，'.join(x), # 将土种名称用逗号连接
|
||||
'mean': 'mean', # 计算均值
|
||||
'count': 'sum' # 计算总数
|
||||
}).reset_index()
|
||||
|
||||
parent_materials = grouped['母质'].unique()
|
||||
|
||||
for parent_material in parent_materials:
|
||||
|
||||
parent_material_row = current_row
|
||||
|
||||
if parent_material == '未知':
|
||||
continue
|
||||
|
||||
material_group = grouped[grouped['母质'] == parent_material]
|
||||
# 写入母岩母质分组（只在第一行显示）
|
||||
first_row_in_group = True
|
||||
|
||||
for _, row_data in material_group.iterrows():
|
||||
if first_row_in_group:
|
||||
# 第一行显示母岩母质名称
|
||||
ws.cell(row=current_row, column=1, value=parent_material)
|
||||
first_row_in_group = False
|
||||
else:
|
||||
# 后续行留空
|
||||
ws.cell(row=current_row, column=1, value='')
|
||||
|
||||
# 写入母岩类型
|
||||
ws.cell(row=current_row, column=2, value=row_data['母岩'])
|
||||
|
||||
# 写入土种类型（所有土种用逗号连接）
|
||||
ws.cell(row=current_row, column=3, value=row_data['TZ'])
|
||||
|
||||
# 写入统计数据
|
||||
ws.cell(row=current_row, column=4, value=round(row_data['mean'], 1))
|
||||
ws.cell(row=current_row, column=5, value=row_data['count'])
|
||||
|
||||
current_row += 1
|
||||
|
||||
# 合并母岩母质分组
|
||||
if parent_material_row < current_row:
|
||||
ws.merge_cells(start_row=parent_material_row, start_column=1, end_row=current_row - 1, end_column=1)
|
||||
|
||||
ws.merge_cells(start_row=current_row, start_column=1, end_row=current_row, end_column=3)
|
||||
ws.cell(row=current_row, column=1, value='全区')
|
||||
|
||||
# --- d. 应用样式和调整列宽 ---
|
||||
max_col_letter = get_column_letter(ws.max_column)
|
||||
if current_row > 1: # 确保有数据才应用样式
|
||||
apply_style(f'A1:{max_col_letter}{current_row}', cell_font, center_align, thin_border)
|
||||
apply_style(f'A1:{max_col_letter}2', header_font)
|
||||
|
||||
# 设置列宽
|
||||
ws.column_dimensions["A"].width = 20
|
||||
ws.column_dimensions["B"].width = 20
|
||||
ws.column_dimensions["C"].width = 30
|
||||
ws.column_dimensions["D"].width = 20
|
||||
ws.column_dimensions["E"].width = 20
|
||||
|
||||
# 保存文件
|
||||
wb.save(output_path)
|
||||
print(f"数据已成功写入到 {output_path}")
|
||||
|
||||
|
||||
def main(gdb_path, soil_prop_name, trlx_features, reclassed_feature, output_path,target_areas_df, prop_config):
|
||||
try:
|
||||
# --- 1. 用户配置 ---
|
||||
# 输出配置
|
||||
temp_files = []
|
||||
output_excel_path = os.path.join(output_path,f"{soil_prop_name}不同土壤类型土壤.xlsx") # 生成的Excel报告文件路径
|
||||
# output_excel4_path = os.path.join(output_path,f"{soil_prop_name}不同母岩母质土壤属性.xlsx")
|
||||
soil_prop_features = os.path.join(gdb_path,soil_prop_name)
|
||||
|
||||
# 设置工作空间和变量
|
||||
arcpy.env.workspace = gdb_path
|
||||
arcpy.env.overwriteOutput = True
|
||||
|
||||
print("开始处理数据...")
|
||||
|
||||
temp_out_features = r"in_memory/temp_out_type_features"
|
||||
out_table_mean = r"in_memory/out_table_type_mean"
|
||||
temp_files.append(temp_out_features)
|
||||
temp_files.append(out_table_mean)
|
||||
|
||||
# 2. 用样点进行空间连接到土壤类型图斑
|
||||
fields_to_keep = {
|
||||
soil_prop_features: [soil_prop_name],
|
||||
trlx_features: ["YL", "TS", "TZ"],
|
||||
}
|
||||
|
||||
field_mappings = arcpy.FieldMappings()
|
||||
|
||||
for join_features in fields_to_keep.keys():
|
||||
for field_name in fields_to_keep[join_features]:
|
||||
try:
|
||||
field_map = arcpy.FieldMap()
|
||||
field_map.addInputField(join_features, field_name)
|
||||
field_map.mergeRule = "First" # 对所有连接字段使用 "First" 规则
|
||||
field_mappings.addFieldMap(field_map)
|
||||
except Exception as e:
|
||||
print(f"警告: 添加字段 '{field_name}' (来自 '{join_features}') 时出错，将跳过。错误信息: {e}")
|
||||
# 空间连接
|
||||
arcpy.analysis.SpatialJoin(soil_prop_features, trlx_features, temp_out_features, "JOIN_ONE_TO_ONE", "KEEP_ALL",field_mappings, "INTERSECT")
|
||||
|
||||
# 3. 交集制表计算每个TRZD的面积
|
||||
arcpy.analysis.TabulateIntersection(trlx_features, "YL_TS", reclassed_feature, out_table_mean, "gridcode", out_units="SQUARE_METERS")
|
||||
|
||||
trlx_zhitu_df = pd.DataFrame(arcpy.da.TableToNumPyArray(out_table_mean, ["YL_TS", "gridcode", "AREA"]))
|
||||
trlx_sample_df = pd.DataFrame(arcpy.da.FeatureClassToNumPyArray(temp_out_features, ["YL", "TS", "TZ", soil_prop_name]))
|
||||
|
||||
# 获取土壤类型图斑面积
|
||||
trlx_area_df = pd.DataFrame(arcpy.da.FeatureClassToNumPyArray(trlx_features, ["YL", "TS", "Shape@Area"]))
|
||||
|
||||
# 处理表3数据
|
||||
final_dataframe = process_data_for_table3(soil_prop_name,trlx_sample_df, trlx_zhitu_df, trlx_area_df, target_areas_df)
|
||||
# print(final_dataframe)
|
||||
|
||||
# 生成表3
|
||||
write_to_excel_table3(final_dataframe, output_excel_path, prop_config)
|
||||
# 母岩母质表
|
||||
# write_to_excel_table4(df_mymz, output_excel4_path, prop_config)
|
||||
|
||||
# return df_with_factors
|
||||
except Exception as e:
|
||||
print(f"\n处理过程中发生严重错误: {e}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
finally:
|
||||
temp_files_processor.clean_up_temp_files(temp_files)
|
||||
import gc
|
||||
gc.collect()
|
||||
|
||||
# --- 4. 主程序入口 ---
|
||||
# if __name__ == "__main__":
|
||||
# main()
|
||||
512
tools/core/soil_prop_stats/B3不同土壤类型土壤属性.py
Normal file
512
tools/core/soil_prop_stats/B3不同土壤类型土壤属性.py
Normal file
@@ -0,0 +1,512 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
import os
|
||||
import arcpy
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
from openpyxl import Workbook
|
||||
from openpyxl.styles import Font
|
||||
from openpyxl.utils import get_column_letter
|
||||
|
||||
from tools.config.pandas_field_cal_func import calculate_muyan, calculate_muzhi
|
||||
from tools.config.custom_sort import yl_order, ts_order
|
||||
from tools.core.utils.os_utils import temp_files_processor
|
||||
from tools.core.utils.excel_utils import ExcelStyleUtils
|
||||
|
||||
|
||||
# --- 3. 数据处理与分析 均值---
|
||||
def process_data_for_table3(soil_prop_name, df_trlx_sample, df_trlx_zhitu, df_trlx, target_areas_df):
|
||||
"""
|
||||
【最终版 v2】: 增加对制图样点数的处理，以支持加权平均计算。
|
||||
"""
|
||||
print("开始处理数据...")
|
||||
|
||||
def clean_df(df, columns) -> pd.DataFrame:
|
||||
for col in columns:
|
||||
df[col] = df[col].astype(str).str.strip()
|
||||
df.replace(['<Null>', 'None', '', '<空>'], np.nan, inplace=True)
|
||||
df.dropna(subset=columns, inplace=True)
|
||||
return df
|
||||
|
||||
# ==a. 处理样点数据，计算“样点均值” ---
|
||||
print("--> 步骤1: 计算样点均值...")
|
||||
field_name = soil_prop_name
|
||||
sample_fields = ['YL', 'TS', field_name]
|
||||
df_samples = clean_df(df_trlx_sample, sample_fields)
|
||||
df_samples[field_name] = df_samples[field_name].astype(float)
|
||||
|
||||
# 通过土属计算母岩母质
|
||||
df_samples['母岩'] = df_samples['TS'].apply(calculate_muyan)
|
||||
df_samples['母质'] = df_samples['母岩'].apply(calculate_muzhi)
|
||||
# 按 YJDL, EJDL 分组，计算 dPH 的均值
|
||||
df_sample_means = df_samples.groupby(['YL', 'TS'])[field_name].agg(['count', 'max', 'min', 'mean', 'median']).reset_index()
|
||||
df_sample_mymz = df_samples.groupby(['母质', '母岩', 'TZ'])[field_name].agg(['count', 'mean', 'median']).reset_index()
|
||||
# print(df_sample_mymz)
|
||||
|
||||
# ==b. 处理制图数据，获各等级制图面积
|
||||
df_trlx_zhitu["YL"] = df_trlx_zhitu['YL_TS'].apply(lambda x: x.split('_')[0])
|
||||
df_trlx_zhitu["TS"] = df_trlx_zhitu["YL_TS"].apply(lambda x: x.split('_')[1])
|
||||
df_trlx_zhitu = clean_df(df_trlx_zhitu, ['YL', 'TS'])
|
||||
df_trlx_zhitu.rename(columns={'MEAN': '制图均值', 'COUNT': '制图样点数'}, inplace=True)
|
||||
|
||||
# ==c. 处理制图数据，获各等级制图面积
|
||||
df_trlx = clean_df(df_trlx, ['YL', 'TS'])
|
||||
df_trlx["面积_亩"] = df_trlx["Shape@Area"] * 0.0015
|
||||
|
||||
filtered_props = ['ECA', 'EMG', 'ACU', 'AZN', 'AFE', 'AMN', 'AMO', 'AB', 'AS1', 'TSE']
|
||||
|
||||
# 拿到目标df总面积，计算比例进行平差
|
||||
print(target_areas_df)
|
||||
if soil_prop_name == "GZCHD":
|
||||
target_areas = target_areas_df[target_areas_df['EJDL'] == '耕地']['面积'].values[0]
|
||||
elif soil_prop_name in filtered_props:
|
||||
target_areas = target_areas_df[target_areas_df['EJDL'].isin(['耕地', '园地'])]['面积'].sum()
|
||||
else:
|
||||
target_areas = target_areas_df['面积'].sum()
|
||||
original_area = df_trlx['面积_亩'].sum()
|
||||
adjusted_area_yz = target_areas / original_area
|
||||
|
||||
df_trlx["面积_亩"] = df_trlx["面积_亩"] * adjusted_area_yz
|
||||
df_trlx_area = df_trlx.groupby(['YL', 'TS'])['面积_亩'].sum().reset_index()
|
||||
|
||||
|
||||
# --- c. 合并数据 ---
|
||||
print("--> 步骤3: 合并数据...")
|
||||
df_skeleton = pd.concat([
|
||||
df_sample_means[['YL', 'TS']],
|
||||
df_trlx_zhitu[['YL', 'TS']]
|
||||
]).drop_duplicates().reset_index(drop=True)
|
||||
|
||||
df_final = pd.merge(df_skeleton, df_sample_means, on=['YL', 'TS'], how='left')
|
||||
df_final = pd.merge(df_final, df_trlx_zhitu, on=['YL', 'TS'], how='left')
|
||||
df_final = pd.merge(df_final, df_trlx_area, on=['YL', 'TS'], how='left')
|
||||
|
||||
# (可选) 按“亚类”和“土属”排序
|
||||
in_yl_order = yl_order + [x for x in df_final['YL'].unique() if x not in yl_order]
|
||||
in_ts_order = ts_order + [x for x in df_final['TS'].unique() if x not in ts_order]
|
||||
df_final["YL"] = pd.Categorical(df_final['YL'], categories=in_yl_order, ordered=True)
|
||||
df_final["TS"] = pd.Categorical(df_final['TS'], categories=in_ts_order, ordered=True)
|
||||
df_final.sort_values(['YL', 'TS'], inplace=True)
|
||||
|
||||
print("数据处理流程完成！")
|
||||
return df_final, df_sample_mymz
|
||||
|
||||
# 写入EXCEL 表2
|
||||
def write_to_excel_table3(df, output_path, prop_config:dict, stats):
|
||||
"""
|
||||
将处理好的数据写入格式化的 Excel 文件。
|
||||
"""
|
||||
if df.empty:
|
||||
print("警告: 没有数据可以写入 Excel。")
|
||||
return
|
||||
|
||||
print(f"开始生成 Excel 报告到 '{output_path}'...")
|
||||
wb = Workbook()
|
||||
ws = wb.create_sheet("Mysheet", 0)
|
||||
ws.title = "不同土壤类型属性变化统计"
|
||||
|
||||
# 获取属性单位
|
||||
special_prop = ['耕作层厚度','阳离子','有机质','pH','有效磷','速效钾','交换性钙','交换性镁','有效硫','有效铁','有效锰','有效硅','全钾']
|
||||
fsn_props = ['砂粒含量','粉粒含量','黏粒含量']
|
||||
prop_name_str = prop_config.get('项目分级','')
|
||||
if prop_name_str:
|
||||
split_name = prop_name_str.split('\n')[0].strip()
|
||||
if split_name in special_prop:
|
||||
prop_name = '1f'
|
||||
elif split_name in fsn_props:
|
||||
prop_name = '0f'
|
||||
else:
|
||||
prop_name = '2f'
|
||||
else:
|
||||
prop_name = '1f'
|
||||
|
||||
prop_unit_str = prop_config.get('分级标准', '')
|
||||
if prop_unit_str:
|
||||
prop_unit = prop_unit_str.split('\n')[1].strip()
|
||||
else:
|
||||
prop_unit = ''
|
||||
|
||||
# --- b. 绘制表头 ---
|
||||
ws.merge_cells('A1:B1'); ws['A1'] = '土壤类型'
|
||||
ws.merge_cells('C1:F1'); ws['C1'] = '样点统计'
|
||||
ws.merge_cells('G1:H1'); ws['G1'] = '制图统计'
|
||||
|
||||
ws['A2'] = '亚类'
|
||||
ws['B2'] = '土属'
|
||||
ws['C2'] = '均值/' + prop_unit
|
||||
ws['D2'] = '中位值/' + prop_unit
|
||||
ws['E2'] = '范围/' + prop_unit
|
||||
ws['F2'] = '数量/个'
|
||||
ws['G2'] = '均值/' + prop_unit
|
||||
ws['H2'] = '面积/亩'
|
||||
|
||||
# --- c. 填充数据 ---
|
||||
current_row = 3
|
||||
|
||||
df_to_write = df.copy() # 使用 .copy() 避免 SettingWithCopyWarning
|
||||
|
||||
for yl, group_yl_df in df_to_write.groupby('YL', sort=False, observed=True):
|
||||
|
||||
print(f"正在写入亚类: {yl}...")
|
||||
yl_start_row = current_row
|
||||
|
||||
# 遍历该亚类下下的所有“土属”
|
||||
for _, row_data in group_yl_df.iterrows():
|
||||
ws.cell(row=current_row, column=2).value = row_data['TS']
|
||||
|
||||
# 填充样点数据
|
||||
sample_mean = row_data.get('mean')
|
||||
if pd.notna(sample_mean):
|
||||
ws.cell(row=current_row, column=3).value = f"{sample_mean:.{prop_name}}"
|
||||
ws.cell(row=current_row, column=4).value = f"{row_data.get('median', '-'):.{prop_name}}"
|
||||
ws.cell(row=current_row, column=5).value = f"{row_data.get('min', '-'):.{prop_name}}～{row_data.get('max', '-'):.{prop_name}}"
|
||||
ws.cell(row=current_row, column=6).value = row_data.get('count', '-')
|
||||
else:
|
||||
ws.cell(row=current_row, column=3).value = "-"
|
||||
ws.cell(row=current_row, column=4).value = "-"
|
||||
ws.cell(row=current_row, column=5).value = "-"
|
||||
ws.cell(row=current_row, column=6).value = "-"
|
||||
|
||||
# 填充制图数据
|
||||
map_mean = row_data.get('制图均值')
|
||||
if pd.notna(map_mean):
|
||||
ws.cell(row=current_row, column=7).value = f"{map_mean:.{prop_name}}"
|
||||
ws.cell(row=current_row, column=8).value = f"{row_data.get('面积_亩', '-'):.0f}"
|
||||
else:
|
||||
ws.cell(row=current_row, column=7).value = "-"
|
||||
ws.cell(row=current_row, column=8).value = "-"
|
||||
|
||||
current_row += 1
|
||||
|
||||
# 计算并写入“合计”行
|
||||
if ws.cell(row=current_row-1, column=2).value in ["林地", "草地", "其他"]:
|
||||
ws.merge_cells(start_row=yl_start_row, start_column=1, end_row=yl_start_row, end_column=2)
|
||||
ws.cell(row=yl_start_row, column=1).value = yl
|
||||
continue
|
||||
|
||||
ws.cell(row=current_row, column=2).value = '合计'
|
||||
|
||||
# 计算合计行的均值 (均值的均值)
|
||||
total_count = group_yl_df['count'].sum()
|
||||
weighted_sum = group_yl_df['mean'] * group_yl_df['count']
|
||||
if not weighted_sum.empty and total_count != 0:
|
||||
total_sample_mean = weighted_sum.sum() / total_count
|
||||
else:
|
||||
total_sample_mean = None
|
||||
total_median = group_yl_df['median'].mean()
|
||||
min_min, max_max = group_yl_df['min'].min(), group_yl_df['max'].max()
|
||||
|
||||
|
||||
if pd.notna(total_sample_mean):
|
||||
ws.cell(row=current_row, column=3).value = f"{total_sample_mean:.{prop_name}}"
|
||||
ws.cell(row=current_row, column=4).value = f"{total_median:.{prop_name}}"
|
||||
ws.cell(row=current_row, column=5).value = f"{min_min:.{prop_name}}～{max_max:.{prop_name}}"
|
||||
ws.cell(row=current_row, column=6).value = f"{total_count:.0f}"
|
||||
else:
|
||||
ws.cell(row=current_row, column=3).value = "-"
|
||||
ws.cell(row=current_row, column=4).value = "-"
|
||||
ws.cell(row=current_row, column=5).value = "-"
|
||||
ws.cell(row=current_row, column=6).value = "-"
|
||||
|
||||
# b. **【核心修正】: 计算合计行的“制图均值”(加权平均)**
|
||||
# 准备加权平均的分子和分母
|
||||
weighted_sum = 0
|
||||
total_count = 0
|
||||
|
||||
# 遍历当前一级地类分组中的每一行
|
||||
for _, row in group_yl_df.iterrows():
|
||||
mean_val = row.get('制图均值')
|
||||
count_val = row.get('制图样点数')
|
||||
|
||||
# 只有当均值和样点数都存在且有效时，才参与计算
|
||||
if pd.notna(mean_val) and pd.notna(count_val) and count_val > 0:
|
||||
weighted_sum += mean_val * count_val # Σ (mean * count)
|
||||
total_count += count_val # Σ (count)
|
||||
|
||||
# 计算加权平均值
|
||||
weighted_avg = (weighted_sum / total_count) if total_count > 0 else 0
|
||||
total_area = group_yl_df['面积_亩'].sum()
|
||||
|
||||
if weighted_avg > 0:
|
||||
ws.cell(row=current_row, column=7).value = f"{weighted_avg:.{prop_name}}"
|
||||
ws.cell(row=current_row, column=8).value = f"{total_area:.0f}"
|
||||
else:
|
||||
ws.cell(row=current_row, column=7).value = "-"
|
||||
ws.cell(row=current_row, column=8).value = "-"
|
||||
|
||||
# 合并“一级地类”单元格
|
||||
if yl_start_row <= current_row:
|
||||
ws.merge_cells(start_row=yl_start_row, start_column=1, end_row=current_row, end_column=1)
|
||||
ws.cell(row=yl_start_row, column=1).value = yl
|
||||
|
||||
current_row += 1
|
||||
|
||||
# 计算全区的均值、范围、数量
|
||||
# total_counts = df_to_write['count'].sum()
|
||||
# total_weighted_sum = df_to_write['mean'] * df_to_write['count']
|
||||
# total_mean = total_weighted_sum.sum() / total_counts
|
||||
# total_median = df_to_write['median'].mean()
|
||||
total_range = f"{df_to_write['min'].min():.{prop_name}}～{df_to_write['max'].max():.{prop_name}}"
|
||||
total_zhitu_weighted_sum = df_to_write['制图均值'] * df_to_write['面积_亩']
|
||||
total_areas = df_to_write['面积_亩'].sum()
|
||||
total_zhitu_mean = total_zhitu_weighted_sum.sum() / total_areas
|
||||
|
||||
ws.merge_cells(start_row=current_row, start_column=1, end_row=current_row, end_column=2)
|
||||
ws.cell(row=current_row, column=1).value = '全区'
|
||||
ws.cell(row=current_row, column=3).value = f"{stats['mean']:.{prop_name}}"
|
||||
ws.cell(row=current_row, column=4).value = f"{stats['median']:.{prop_name}}"
|
||||
ws.cell(row=current_row, column=5).value = total_range
|
||||
ws.cell(row=current_row, column=6).value = f"{stats['count']:.0f}"
|
||||
ws.cell(row=current_row, column=7).value = f"{total_zhitu_mean:.{prop_name}}"
|
||||
ws.cell(row=current_row, column=8).value = f"{total_areas:.0f}"
|
||||
|
||||
# --- a. 定义样式 ---
|
||||
header_font = Font(name='等线', size=11, bold=True)
|
||||
# --- d. 应用样式和调整列宽 ---
|
||||
max_col_letter = get_column_letter(ws.max_column)
|
||||
if current_row > 1: # 确保有数据才应用样式
|
||||
ExcelStyleUtils.set_style(ws, f'A1:{max_col_letter}{current_row}')
|
||||
ExcelStyleUtils.set_style(ws, f'A1:{max_col_letter}2', header_font)
|
||||
|
||||
print("正在自动调整列宽...")
|
||||
|
||||
# 设置列宽
|
||||
ExcelStyleUtils.auto_adjust_column_width(ws)
|
||||
|
||||
# --- e. 保存文件 ---
|
||||
wb.save(output_path)
|
||||
print("Excel 报告生成成功！")
|
||||
|
||||
# 母岩母质表
|
||||
def write_to_excel_table4(df:pd.DataFrame, output_path, prop_config, stats):
|
||||
if df.empty:
|
||||
print("警告: 没有数据可以写入 Excel。")
|
||||
return
|
||||
|
||||
wb = Workbook()
|
||||
ws = wb.create_sheet("Mysheet", 0)
|
||||
ws.title = "母岩母质土壤属性统计"
|
||||
|
||||
# 获取属性单位
|
||||
special_prop = ['耕作层厚度','阳离子','有机质','pH','有效磷','速效钾','交换性钙','交换性镁','有效硫','有效铁','有效锰','有效硅','全钾']
|
||||
fsn_props = ['砂粒含量','粉粒含量','黏粒含量','有效土层厚度']
|
||||
prop_name_str = prop_config.get('项目分级','')
|
||||
if prop_name_str:
|
||||
split_name = prop_name_str.split('\n')[0].strip()
|
||||
if split_name in special_prop:
|
||||
prop_name = '1f'
|
||||
elif split_name in fsn_props:
|
||||
prop_name = '0f'
|
||||
else:
|
||||
prop_name = '2f'
|
||||
else:
|
||||
prop_name = '1f'
|
||||
|
||||
prop_unit_str = prop_config.get('分级标准', '')
|
||||
if prop_unit_str:
|
||||
prop_unit = prop_unit_str.split('\n')[1].strip()
|
||||
else:
|
||||
prop_unit = ''
|
||||
|
||||
# 写入表头
|
||||
headers = ['母岩母质','', '土种类型', '样点统计', '']
|
||||
ws.append(headers)
|
||||
ws.append(['', '', '', f'均值/{prop_unit}', '数量/个'])
|
||||
|
||||
# 合并表头单元格
|
||||
ws.merge_cells('A1:B2') # 母岩母质
|
||||
ws.merge_cells('C1:C2') # 土种类型
|
||||
ws.merge_cells('D1:E1') # 样点统计
|
||||
|
||||
current_row = 3
|
||||
|
||||
# 按母质和母岩进行分组
|
||||
grouped = df.groupby(['母质', '母岩']).agg({
|
||||
'TZ': lambda x: '，'.join(x), # 将土种名称用逗号连接
|
||||
'mean': 'mean', # 计算均值
|
||||
'count': 'sum' # 计算总数
|
||||
}).reset_index()
|
||||
|
||||
parent_materials = grouped['母质'].unique()
|
||||
|
||||
for parent_material in parent_materials:
|
||||
|
||||
parent_material_row = current_row
|
||||
|
||||
if parent_material == '未知':
|
||||
continue
|
||||
|
||||
material_group = grouped[grouped['母质'] == parent_material]
|
||||
# 写入母岩母质分组（只在第一行显示）
|
||||
first_row_in_group = True
|
||||
|
||||
for _, row_data in material_group.iterrows():
|
||||
if first_row_in_group:
|
||||
# 第一行显示母岩母质名称
|
||||
ws.cell(row=current_row, column=1, value=parent_material)
|
||||
first_row_in_group = False
|
||||
else:
|
||||
# 后续行留空
|
||||
ws.cell(row=current_row, column=1, value='')
|
||||
|
||||
# 写入母岩类型
|
||||
ws.cell(row=current_row, column=2, value=row_data['母岩'])
|
||||
|
||||
# 写入土种类型（所有土种用逗号连接）
|
||||
ws.cell(row=current_row, column=3, value=row_data['TZ'])
|
||||
|
||||
# 写入统计数据
|
||||
ws.cell(row=current_row, column=4, value=round(row_data['mean'], 1))
|
||||
ws.cell(row=current_row, column=5, value=row_data['count'])
|
||||
|
||||
current_row += 1
|
||||
|
||||
# 合并母岩母质分组
|
||||
if parent_material_row < current_row:
|
||||
ws.merge_cells(start_row=parent_material_row, start_column=1, end_row=current_row - 1, end_column=1)
|
||||
|
||||
# 计算合计值并写入
|
||||
# total_mean = 0
|
||||
# total_count = df['count'].sum()
|
||||
# total_sum = df['mean'] * df['count']
|
||||
# if total_count and total_count!=0:
|
||||
# total_mean = total_sum.sum() / total_count
|
||||
|
||||
ws.merge_cells(start_row=current_row, start_column=1, end_row=current_row, end_column=3)
|
||||
ws.cell(row=current_row, column=1, value='全区')
|
||||
ws.cell(row=current_row, column=4, value=f"{stats['mean']:.{prop_name}}")
|
||||
ws.cell(row=current_row, column=5, value=f"{stats['count']:.0f}")
|
||||
|
||||
# --- a. 定义样式 ---
|
||||
header_font = Font(name='等线', size=11, bold=True)
|
||||
|
||||
# --- d. 应用样式和调整列宽 ---
|
||||
max_col_letter = get_column_letter(ws.max_column)
|
||||
if current_row > 1: # 确保有数据才应用样式
|
||||
ExcelStyleUtils.set_style(ws, f'A1:{max_col_letter}{current_row}')
|
||||
ExcelStyleUtils.set_style(ws, f'A1:{max_col_letter}2', header_font)
|
||||
|
||||
# 设置列宽
|
||||
ws.column_dimensions["A"].width = 20
|
||||
ws.column_dimensions["B"].width = 20
|
||||
ws.column_dimensions["C"].width = 30
|
||||
ws.column_dimensions["D"].width = 20
|
||||
ws.column_dimensions["E"].width = 20
|
||||
|
||||
# 保存文件
|
||||
wb.save(output_path)
|
||||
print(f"数据已成功写入到 {output_path}")
|
||||
|
||||
|
||||
def main(gdb_path, soil_prop_name, trlx_features, soil_prop_tif, output_path,target_areas_df, prop_config, dltb_features):
|
||||
try:
|
||||
# --- 1. 用户配置 ---
|
||||
# 输出配置
|
||||
temp_files = []
|
||||
output_excel_path = os.path.join(output_path,f"{soil_prop_name}不同土壤类型土壤.xlsx") # 生成的Excel报告文件路径
|
||||
output_excel4_path = os.path.join(output_path,f"{soil_prop_name}不同母岩母质土壤属性.xlsx")
|
||||
soil_prop_features = os.path.join(gdb_path,soil_prop_name)
|
||||
|
||||
# 设置工作空间和变量
|
||||
arcpy.env.workspace = gdb_path
|
||||
arcpy.env.overwriteOutput = True
|
||||
|
||||
print("开始处理数据...")
|
||||
if soil_prop_name == "GZCHD":
|
||||
temp_gdtb_trlx_out = r"in_memory/temp_gdtb_trlx_out"
|
||||
temp_gdtb_trlx = r"in_memory/temp_gdtb_trlx"
|
||||
temp_files.append(temp_gdtb_trlx)
|
||||
|
||||
temp_out_features = r"in_memory/temp_out_type_features"
|
||||
out_table_mean = r"in_memory/out_table_type_mean"
|
||||
temp_files.append(temp_out_features)
|
||||
temp_files.append(out_table_mean)
|
||||
|
||||
# 2. 用样点进行空间连接到土壤类型图斑
|
||||
fields_to_keep = {
|
||||
soil_prop_features: [soil_prop_name],
|
||||
trlx_features: ["YL", "TS", "TZ"],
|
||||
}
|
||||
|
||||
field_mappings = arcpy.FieldMappings()
|
||||
|
||||
for join_features in fields_to_keep.keys():
|
||||
for field_name in fields_to_keep[join_features]:
|
||||
try:
|
||||
field_map = arcpy.FieldMap()
|
||||
field_map.addInputField(join_features, field_name)
|
||||
field_map.mergeRule = "First" # 对所有连接字段使用 "First" 规则
|
||||
field_mappings.addFieldMap(field_map)
|
||||
except Exception as e:
|
||||
print(f"警告: 添加字段 '{field_name}' (来自 '{join_features}') 时出错，将跳过。错误信息: {e}")
|
||||
|
||||
# 定义需要过滤地类的属性列表
|
||||
filtered_props = ['ECA', 'EMG', 'ACU', 'AZN', 'AFE', 'AMN', 'AMO', 'AB', 'AS1', 'TSE']
|
||||
|
||||
# 空间连接
|
||||
arcpy.analysis.SpatialJoin(soil_prop_features, trlx_features, temp_out_features, "JOIN_ONE_TO_ONE", "KEEP_ALL",field_mappings, "INTERSECT")
|
||||
|
||||
if soil_prop_name == "GZCHD":
|
||||
arcpy.analysis.Intersect([trlx_features, dltb_features], temp_gdtb_trlx, 'NO_FID')
|
||||
arcpy.conversion.ExportFeatures(temp_gdtb_trlx,temp_gdtb_trlx_out,"DLBM LIKE '01%'")
|
||||
|
||||
# 3. 以表格显示分区统计 计算均值
|
||||
arcpy.sa.ZonalStatisticsAsTable(temp_gdtb_trlx_out, "YL_TS", soil_prop_tif, out_table_mean, "DATA", "MEAN")
|
||||
trlx_area_df = pd.DataFrame(arcpy.da.FeatureClassToNumPyArray(temp_gdtb_trlx_out, ["YL", "TS", "Shape@Area"]))
|
||||
# 如果当前属性在列表中，则只统计耕地和园地
|
||||
elif soil_prop_name in filtered_props:
|
||||
temp_gdtb_trlx_filtered = r"in_memory/temp_gdtb_trlx_filtered"
|
||||
temp_gdtb_trlx_out_filtered = r"in_memory/temp_gdtb_trlx_out_filtered"
|
||||
temp_files.append(temp_gdtb_trlx_filtered)
|
||||
temp_files.append(temp_gdtb_trlx_out_filtered)
|
||||
|
||||
# 交集土壤类型与土地利用图斑
|
||||
arcpy.analysis.Intersect([trlx_features, dltb_features], temp_gdtb_trlx_filtered, 'NO_FID')
|
||||
# 导出耕地和园地（DLBM LIKE '01%' OR DLBM LIKE '02%'）
|
||||
arcpy.conversion.ExportFeatures(temp_gdtb_trlx_filtered, temp_gdtb_trlx_out_filtered, "DLBM LIKE '01%' OR DLBM LIKE '02%'")
|
||||
|
||||
# 使用过滤后的图斑进行分区统计（制图均值）
|
||||
arcpy.sa.ZonalStatisticsAsTable(temp_gdtb_trlx_out_filtered, "YL_TS", soil_prop_tif, out_table_mean, "DATA", "MEAN")
|
||||
# 获取过滤后的面积
|
||||
trlx_area_df = pd.DataFrame(arcpy.da.FeatureClassToNumPyArray(temp_gdtb_trlx_out_filtered, ["YL", "TS", "Shape@Area"]))
|
||||
|
||||
print(f"过滤制图数据：仅统计耕地和园地（DLBM LIKE '01%' OR '02%'）")
|
||||
else:
|
||||
# 3. 以表格显示分区统计 计算均值
|
||||
arcpy.sa.ZonalStatisticsAsTable(trlx_features, "YL_TS", soil_prop_tif, out_table_mean, "DATA", "MEAN")
|
||||
# 获取土壤类型图斑面积
|
||||
trlx_area_df = pd.DataFrame(arcpy.da.FeatureClassToNumPyArray(trlx_features, ["YL", "TS", "Shape@Area"]))
|
||||
|
||||
trlx_zhitu_df = pd.DataFrame(arcpy.da.TableToNumPyArray(out_table_mean, ["YL_TS", "MEAN", "COUNT"]))
|
||||
trlx_sample_df = pd.DataFrame(arcpy.da.FeatureClassToNumPyArray(temp_out_features, ["YL", "TS", "TZ", soil_prop_name]))
|
||||
|
||||
stat_sample = {
|
||||
'min': trlx_sample_df[soil_prop_name].min(),
|
||||
'max': trlx_sample_df[soil_prop_name].max(),
|
||||
'mean':trlx_sample_df[soil_prop_name].mean(),
|
||||
'median': trlx_sample_df[soil_prop_name].median(),
|
||||
'count': trlx_sample_df[soil_prop_name].count()
|
||||
}
|
||||
|
||||
|
||||
# 处理表3数据
|
||||
final_dataframe, df_mymz = process_data_for_table3(soil_prop_name,trlx_sample_df, trlx_zhitu_df, trlx_area_df, target_areas_df)
|
||||
# print(final_dataframe)
|
||||
|
||||
# 生成表3
|
||||
write_to_excel_table3(final_dataframe, output_excel_path, prop_config, stat_sample)
|
||||
# 母岩母质表
|
||||
write_to_excel_table4(df_mymz, output_excel4_path, prop_config,stat_sample)
|
||||
|
||||
# return df_with_factors
|
||||
except Exception as e:
|
||||
print(f"\n处理过程中发生严重错误: {e}")
|
||||
import traceback
|
||||
traceback.print_exc()
|
||||
finally:
|
||||
temp_files_processor.clean_up_temp_files(temp_files)
|
||||
import gc
|
||||
gc.collect()
|
||||
|
||||
# --- 4. 主程序入口 ---
|
||||
# if __name__ == "__main__":
|
||||
# main()
|
||||
1269
tools/core/soil_prop_stats/E1土壤属性历史变化.py
Normal file
1269
tools/core/soil_prop_stats/E1土壤属性历史变化.py
Normal file
File diff suppressed because it is too large
Load Diff
0
tools/core/soil_prop_stats/__init__.py
Normal file
0
tools/core/soil_prop_stats/__init__.py
Normal file
660
tools/core/stats_area_to_excel.py
Normal file
660
tools/core/stats_area_to_excel.py
Normal file
@@ -0,0 +1,660 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
"""
|
||||
输入重分类后栅格转面要素类、乡镇边界面要素类、地类图斑要素类；
|
||||
按一级地类统计土壤属性面积 和 按乡镇统计土壤属性面积；
|
||||
将统计结果导出为Excel表格；
|
||||
将Excel表格转换为jpg图片；
|
||||
"""
|
||||
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
import sys
|
||||
import traceback
|
||||
import uuid
|
||||
import arcpy
|
||||
import argparse
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
from openpyxl.styles import Font, Alignment, Border, Side, numbers
|
||||
from openpyxl.utils import get_column_letter
|
||||
|
||||
sys.path.append(str(Path(__file__).parent))
|
||||
from tools.core.utils.os_utils import temp_files_processor
|
||||
from tools.config.common_config import guangxi_region, yunnan_region
|
||||
from utils import common_utils, 平差工具
|
||||
|
||||
def parse_arguments():
|
||||
"""解析命令行参数"""
|
||||
parser = argparse.ArgumentParser(description="将ArcGIS表格转换为Excel")
|
||||
parser.add_argument("--reclassed_polygon", required=True, help="重分类栅格的面要素")
|
||||
parser.add_argument("--settings_path", required=True, help="配置文件路径")
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
if args.settings_path:
|
||||
with open(args.settings_path, 'r', encoding="utf-8") as settings_file:
|
||||
settings = json.load(settings_file)
|
||||
area_stat_settings = settings.get("area_stat_settings", {})
|
||||
|
||||
if area_stat_settings:
|
||||
standards_dict_path = area_stat_settings.get("config_file_path", "")
|
||||
|
||||
with open(standards_dict_path, 'r', encoding="utf-8") as standards_file:
|
||||
standards_dict = json.load(standards_file)
|
||||
config_key = common_utils.get_config_key(Path(args.reclassed_polygon).stem)
|
||||
output_settings = standards_dict['export_config'][config_key]
|
||||
area_stat_settings["output_settings"] = output_settings
|
||||
area_stat_settings["reclassed_polygon"] = args.reclassed_polygon
|
||||
area_stat_settings["soil_property"] = config_key
|
||||
else:
|
||||
print_status("错误: 未找到有效配置文件")
|
||||
sys.exit(1)
|
||||
|
||||
return area_stat_settings
|
||||
|
||||
|
||||
def print_status(message):
|
||||
"""
|
||||
输出状态信息到标准输出，用于 GUI 实时显示
|
||||
格式: STATUS: <message>
|
||||
"""
|
||||
print(f"STATUS:{message}")
|
||||
sys.stdout.flush() # 确保立即输出
|
||||
|
||||
|
||||
def print_result(success, output_path="", error_message=""):
|
||||
"""
|
||||
输出最终结果到标准输出，用于 GUI 判断任务状态和获取结果
|
||||
格式: RESULT:True|<output_path>|
|
||||
格式: RESULT:False||<error_message>
|
||||
"""
|
||||
if success:
|
||||
print(f"RESULT:True|{output_path}|")
|
||||
else:
|
||||
# 在错误信息中替换换行符，避免干扰解析
|
||||
cleaned_error_message = error_message.replace('\n', ' ').replace('\r', '')
|
||||
print(f"RESULT:False||{cleaned_error_message}")
|
||||
sys.stdout.flush() # 确保立即输出
|
||||
|
||||
|
||||
def log_arcpy_message(message):
|
||||
"""输出 ArcPy 产生的 geoprocessing 消息"""
|
||||
# 可以在这里进一步处理或过滤 ArcPy 消息
|
||||
if message.type == 'Message':
|
||||
print_status(f"ArcPy消息: {message.message}")
|
||||
elif message.type == 'Warning':
|
||||
print_status(f"ArcPy警告: {message.message}")
|
||||
elif message.type == 'Error':
|
||||
# 对于错误，也可以记录到标准错误
|
||||
print_status(f"ArcPy错误: {message.message}")
|
||||
sys.stderr.write(f"ArcPyError:{message.message}\n")
|
||||
sys.stderr.flush()
|
||||
|
||||
def get_specail_map(original_dict):
|
||||
grade_map = {}
|
||||
dict_len = len(original_dict)
|
||||
order = 1
|
||||
for grade_key, range_str in original_dict.items():
|
||||
ranges = [r.strip() for r in range_str.replace('\n', ',').split(',') if r.strip()]
|
||||
s_order = 0
|
||||
for r in ranges:
|
||||
grade_map[str(order + s_order*dict_len)] = r
|
||||
s_order += 1
|
||||
order += 1
|
||||
|
||||
return grade_map
|
||||
|
||||
|
||||
class SoilQualityReporter:
|
||||
def __init__(self, output_path, grade_map: dict, landuse_map, output_settings):
|
||||
"""
|
||||
初始化土壤质量报告生成器
|
||||
|
||||
参数:
|
||||
output_path: 输出Excel文件路径
|
||||
"""
|
||||
self.output_path = output_path
|
||||
self.grade_map = grade_map
|
||||
self.landuse_map = landuse_map
|
||||
self.all_grades = [int(key) for key in self.grade_map.keys()]
|
||||
self.xiangmu_name = output_settings['项目分级'].split('\n')[0]
|
||||
self.xiangmu_jibie =self.xiangmu_name + "分级" + output_settings['分级标准'].split('\n')[1]
|
||||
|
||||
def prepare_data(self, stats):
|
||||
"""
|
||||
准备乡镇统计和地类统计两个表格
|
||||
|
||||
参数:
|
||||
stats: 包含原始统计数据的DataFrame
|
||||
需要包含列: XZQMC(乡镇名称), YJDLBM(地类编码), GRIDCODE(土壤等级), temp_area(面积)
|
||||
|
||||
返回:
|
||||
df_town: 乡镇统计表
|
||||
df_landuse: 地类统计表
|
||||
"""
|
||||
# 表格1：各乡镇耕地土壤有机质分级面积统计
|
||||
df_town = self._create_town_table(stats)
|
||||
|
||||
# 表格2：各地类土壤有机质分级面积统计
|
||||
df_landuse = self._create_landuse_table(stats)
|
||||
|
||||
return df_town, df_landuse
|
||||
|
||||
# 先创建GRIDCODE到分组的映射
|
||||
# def _map_grade(self, code):
|
||||
# code = int(code)
|
||||
# if code in (1,6):
|
||||
# return 1
|
||||
# elif code in (2, 7):
|
||||
# return 2
|
||||
# elif code in (3, 8):
|
||||
# return 3
|
||||
# elif code in (4, 9):
|
||||
# return 4
|
||||
# elif code in (5,10):
|
||||
# return 5
|
||||
|
||||
# return code
|
||||
|
||||
def _create_town_table(self, stats:pd.DataFrame):
|
||||
"""生成乡镇统计表"""
|
||||
|
||||
# 复制数据并添加分组列
|
||||
df_stats = stats.copy()
|
||||
# 如果存在YJDLBM列，确保其值为字符串
|
||||
if "YJDLBM" not in df_stats.columns:
|
||||
# 取YNDLBM列的前两位作为YJDLBM
|
||||
df_stats["YJDLBM"] = df_stats["YNDLBM"].str[:2]
|
||||
|
||||
# df_stats["GRID_GROUP"] = df_stats["GRIDCODE"].apply(self._map_grade)
|
||||
|
||||
# 使用分组列进行透视
|
||||
df = df_stats[df_stats["YJDLBM"] == "01"].pivot_table(
|
||||
index="XZQMC",
|
||||
columns="GRIDCODE",
|
||||
values="adjusted_area",
|
||||
aggfunc="sum",
|
||||
fill_value=0,
|
||||
observed=False
|
||||
)
|
||||
|
||||
# 确保所有等级列都存在
|
||||
for grade in self.all_grades:
|
||||
if grade not in df.columns:
|
||||
df[grade] = 0
|
||||
|
||||
# 按等级排序并添加总计
|
||||
df = df[self.all_grades]
|
||||
df["总计"] = df.sum(axis=1)
|
||||
df.loc["总计"] = df.sum(axis=0)
|
||||
|
||||
# 重命名列
|
||||
df.columns = [self.grade_map.get(str(col), str(col)) for col in df.columns]
|
||||
|
||||
return df
|
||||
|
||||
def _create_landuse_table(self, stats):
|
||||
"""生成地类统计表"""
|
||||
# 复制数据并添加分组列
|
||||
df_stats = stats.copy()
|
||||
# df_stats["GRID_GROUP"] = df_stats["GRIDCODE"].apply(self._map_grade)
|
||||
if "YJDLBM" not in df_stats.columns:
|
||||
df = df_stats.pivot_table(
|
||||
index="YNDLBM",
|
||||
columns="GRIDCODE",
|
||||
values="adjusted_area",
|
||||
aggfunc="sum",
|
||||
fill_value=0,
|
||||
observed=False
|
||||
)
|
||||
else:
|
||||
df = df_stats.pivot_table(
|
||||
index="YJDLBM",
|
||||
columns="GRIDCODE",
|
||||
values="adjusted_area",
|
||||
aggfunc="sum",
|
||||
fill_value=0,
|
||||
observed=False
|
||||
)
|
||||
|
||||
# 确保所有等级列都存在
|
||||
for grade in self.all_grades:
|
||||
if grade not in df.columns:
|
||||
df[grade] = 0
|
||||
|
||||
# 按等级排序并添加总计
|
||||
df = df[self.all_grades]
|
||||
df["总计"] = df.sum(axis=1)
|
||||
df.loc["总计"] = df.sum(axis=0)
|
||||
|
||||
# 重命名索引和列
|
||||
df = df.rename(index=self.landuse_map)
|
||||
df.columns = [self.grade_map.get(str(col), str(col)) for col in df.columns]
|
||||
|
||||
return df
|
||||
|
||||
def generate_report(self, stats):
|
||||
"""
|
||||
生成完整报告
|
||||
|
||||
参数:
|
||||
stats: 包含原始统计数据的DataFrame
|
||||
"""
|
||||
self.is_yunnan = True if 'YNDLBM' in stats.columns else False
|
||||
|
||||
# 准备数据
|
||||
df_town, df_landuse = self.prepare_data(stats)
|
||||
|
||||
# 导出Excel
|
||||
self._export_to_excel(df_town, df_landuse)
|
||||
|
||||
def _export_to_excel(self, df_town, df_landuse):
|
||||
"""导出数据到Excel"""
|
||||
with pd.ExcelWriter(self.output_path, engine='openpyxl') as writer:
|
||||
workbook = writer.book
|
||||
sheet = workbook.create_sheet("综合统计表")
|
||||
|
||||
# 写入乡镇统计表
|
||||
self._write_town_table(sheet, df_town)
|
||||
|
||||
# 写入地类统计表
|
||||
start_row_landuse = len(df_town) + 5
|
||||
self._write_landuse_table(sheet, df_landuse, start_row_landuse)
|
||||
|
||||
# 应用通用格式
|
||||
self._apply_common_format(sheet, start_row_landuse)
|
||||
|
||||
# 删除默认空工作表
|
||||
if 'Sheet' in workbook.sheetnames:
|
||||
workbook.remove(workbook['Sheet'])
|
||||
|
||||
def _write_town_table(self, sheet, df):
|
||||
"""写入乡镇统计表"""
|
||||
# 动态计算列数
|
||||
last_col = len(df.columns) + 2 # 最后一列的索引
|
||||
last_col_letter = get_column_letter(last_col) # 转为字母
|
||||
second_last_col_letter = get_column_letter(last_col - 1)
|
||||
|
||||
# 表头
|
||||
sheet.merge_cells(f"A1:{last_col_letter}1")
|
||||
sheet["A1"] = f"各乡镇耕地土壤{self.xiangmu_name}分级面积统计表"
|
||||
sheet["A1"].font = Font(size=18)
|
||||
sheet["A1"].alignment = Alignment(horizontal='center')
|
||||
sheet.row_dimensions[1].height = 34
|
||||
|
||||
# 单位行
|
||||
sheet[f"{last_col_letter}2"] = "单位:亩"
|
||||
sheet[f"{last_col_letter}2"].font = Font(size=14)
|
||||
sheet[f"{last_col_letter}2"].alignment = Alignment(horizontal='center')
|
||||
|
||||
# 列标题
|
||||
sheet.merge_cells("A3:B4")
|
||||
sheet["A3"] = "乡镇"
|
||||
|
||||
# 总计
|
||||
sheet.merge_cells(f"{last_col_letter}3:{last_col_letter}4")
|
||||
sheet[f"{last_col_letter}3"] = "总计"
|
||||
|
||||
sheet.merge_cells(f"C3:{second_last_col_letter}3")
|
||||
sheet["C3"] = self.xiangmu_jibie
|
||||
sheet.row_dimensions[3].height = 25
|
||||
|
||||
# 写入分级列名
|
||||
for col_num, col_name in enumerate(df.columns[:-1], start=2):
|
||||
# print(col_num, col_name)
|
||||
sheet.cell(row=4, column=col_num+1, value=col_name)
|
||||
|
||||
# 写入数据
|
||||
for r_idx, (index, row) in enumerate(df.iterrows(), start=5):
|
||||
sheet.merge_cells(f"A{r_idx}:B{r_idx}")
|
||||
sheet.cell(row=r_idx, column=1, value=index)
|
||||
for c_idx, value in enumerate(row, start=2):
|
||||
sheet.cell(row=r_idx, column=c_idx+1, value=value)
|
||||
|
||||
def _write_landuse_table(self, sheet, df, start_row):
|
||||
"""写入地类统计表"""
|
||||
# 动态计算列数
|
||||
last_col = len(df.columns) + 2 # 最后一列的索引
|
||||
last_col_letter = get_column_letter(last_col) # 转为字母
|
||||
second_last_col_letter = get_column_letter(last_col - 1)
|
||||
|
||||
# 表头
|
||||
sheet.merge_cells(f"A{start_row}:{last_col_letter}{start_row}")
|
||||
sheet[f"A{start_row}"] = f"各地类土壤{self.xiangmu_name}分级面积统计表"
|
||||
sheet.row_dimensions[start_row].height = 34
|
||||
|
||||
# 单位行
|
||||
sheet[f"{last_col_letter}{start_row+1}"] = "单位:亩"
|
||||
|
||||
# 列标题
|
||||
if self.is_yunnan:
|
||||
sheet.merge_cells(f"A{start_row+2}:B{start_row+2}")
|
||||
sheet[f"A{start_row+2}"] = "土地利用类型"
|
||||
sheet[f"A{start_row+3}"] = "一级"
|
||||
sheet[f"B{start_row+3}"] = "二级"
|
||||
else:
|
||||
sheet.merge_cells(f"A{start_row+2}:B{start_row+3}")
|
||||
sheet[f"A{start_row+2}"] = "土地利用\n类型"
|
||||
|
||||
sheet.merge_cells(f"{last_col_letter}{start_row+2}:{last_col_letter}{start_row+3}")
|
||||
sheet[f"{last_col_letter}{start_row+2}"] = "总计"
|
||||
|
||||
sheet.merge_cells(f"C{start_row+2}:{second_last_col_letter}{start_row+2}")
|
||||
sheet[f"C{start_row+2}"] = self.xiangmu_jibie
|
||||
sheet.row_dimensions[start_row+2].height = 25
|
||||
|
||||
# 写入分级列名
|
||||
for col_num, col_name in enumerate(df.columns[:-1], start=2):
|
||||
sheet.cell(row=start_row+3, column=col_num+1, value=col_name)
|
||||
|
||||
# 写入数据
|
||||
for r_idx, (index, row) in enumerate(df.iterrows(), start=start_row+4):
|
||||
sheet.merge_cells(f"A{r_idx}:B{r_idx}")
|
||||
sheet.cell(row=r_idx, column=1, value=index)
|
||||
for c_idx, value in enumerate(row, start=2):
|
||||
sheet.cell(row=r_idx, column=c_idx+1, value=value)
|
||||
|
||||
def _apply_common_format(self, sheet, landuse_start_row):
|
||||
"""应用通用格式"""
|
||||
# 设置列宽
|
||||
for col in range(1, sheet.max_column + 1):
|
||||
col_letter = chr(64 + col)
|
||||
sheet.column_dimensions[col_letter].width = 14
|
||||
|
||||
for row in range(5, sheet.max_row+1):
|
||||
if row not in [landuse_start_row,landuse_start_row+1, landuse_start_row+2,landuse_start_row+3]:
|
||||
sheet.row_dimensions[row].height = 23
|
||||
|
||||
# 定义边框样式
|
||||
thin_border = Border(
|
||||
left=Side(style='thin'),
|
||||
right=Side(style='thin'),
|
||||
top=Side(style='thin'),
|
||||
bottom=Side(style='thin')
|
||||
)
|
||||
|
||||
# 应用样式到所有单元格
|
||||
for row in sheet.iter_rows(min_row=3, max_row=sheet.max_row, min_col=1, max_col=sheet.max_column):
|
||||
for cell in row:
|
||||
cell.alignment = Alignment(horizontal='center', vertical='center', wrap_text=True)
|
||||
cell.font = Font(bold=True, size=14)
|
||||
|
||||
# 特殊格式
|
||||
if cell.column == 1 and cell.row > 3 and cell.row not in (landuse_start_row, landuse_start_row+2): # 列A
|
||||
cell.font = Font(bold=False, size=14)
|
||||
|
||||
if cell.column == sheet.max_column and cell.row == landuse_start_row+1:
|
||||
cell.font = Font(bold=False, size=14)
|
||||
|
||||
#地类统计表头
|
||||
if cell.row == landuse_start_row:
|
||||
cell.font = Font(bold=False, size=18)
|
||||
cell.alignment = Alignment(vertical='bottom', horizontal='center')
|
||||
|
||||
# 地类统计表列标题
|
||||
if (cell.row == 3 and cell.column == 2) or (cell.row == landuse_start_row+2 and cell.column == 2):
|
||||
cell.font = Font(bold=False, size=14)
|
||||
|
||||
# 数字格式
|
||||
if isinstance(cell.value, (int, float)):
|
||||
cell.number_format = numbers.FORMAT_NUMBER
|
||||
if round(cell.value,0) == 0.0:
|
||||
cell.value = "-"
|
||||
|
||||
# 边框
|
||||
if cell.row >1 and cell.row not in (landuse_start_row, landuse_start_row+1):
|
||||
cell.border = thin_border
|
||||
|
||||
|
||||
def read_arcgis_table(table_path):
|
||||
"""将ArcGIS表格转换为Pandas DataFrame"""
|
||||
array = arcpy.da.TableToNumPyArray(table_path, "*")
|
||||
|
||||
df = pd.DataFrame(array)
|
||||
# df.to_csv(r"D:\工作\三普成果编制\出图数据\广西海城区\过程数据\酸化面积统计表\temp.csv")
|
||||
|
||||
df.columns = df.columns.str.upper()
|
||||
df["temp_area"] = df["AREA"] * 0.0015
|
||||
df["temp_area"] = df["temp_area"].round(4)
|
||||
|
||||
# 删除可能存在的OID字段（如果不需要）
|
||||
if 'OID@' in df.columns:
|
||||
df = df.drop('OID@', axis=1)
|
||||
|
||||
return df
|
||||
|
||||
# 获取每个一级地类面积，主要是12类
|
||||
def get_area_by_group(dltb_class_feature, excel_target_path, xzqmc, is_by_xzq=False):
|
||||
try:
|
||||
# 读取目标面积Excel文件
|
||||
if xzqmc in yunnan_region:
|
||||
target_df = pd.read_excel(excel_target_path, sheet_name="Sheet2")
|
||||
landuse_types = {'0101':'水田', '0102':'水浇地', '0103':'旱地', '02':'园地', '03':'林地', '04':'草地', '12':'其他'}
|
||||
elif xzqmc in guangxi_region:
|
||||
target_df = pd.read_excel(excel_target_path, sheet_name="Sheet1")
|
||||
landuse_types = {'01':'耕地', '02':'园地', '03':'林地', '04':'草地', '12':'其他'}
|
||||
else:
|
||||
target_df = pd.read_excel(excel_target_path, sheet_name="Sheet1")
|
||||
landuse_types = {'01':'耕地', '02':'园地', '03':'林地', '04':'草地', '12':'其他'}
|
||||
|
||||
# 确保列名匹配
|
||||
target_df.columns = target_df.columns.str.strip()
|
||||
|
||||
if is_by_xzq:
|
||||
# 地类编码映射字典
|
||||
land_type_mapping = {
|
||||
'耕地': '01',
|
||||
'园地': '02',
|
||||
'林地': '03',
|
||||
'草地': '04',
|
||||
'其他': '12'
|
||||
}
|
||||
|
||||
# 方法1：重命名列后转换为字典
|
||||
df_encoded = target_df.rename(columns=land_type_mapping)
|
||||
result_dict = df_encoded.set_index('行政单位').to_dict('index')
|
||||
|
||||
return result_dict
|
||||
|
||||
# 检查要素类是否存在
|
||||
if not arcpy.Exists(dltb_class_feature):
|
||||
print(f"警告：输入要素类不存在: {dltb_class_feature}")
|
||||
else:
|
||||
if xzqmc in yunnan_region:
|
||||
dlbm = 'YNDLBM'
|
||||
elif xzqmc in guangxi_region:
|
||||
dlbm = 'YJDLBM'
|
||||
else:
|
||||
dlbm = 'YJDLBM'
|
||||
# 转为numpy数组供pandas统计使用
|
||||
df = pd.DataFrame(arcpy.da.TableToNumPyArray(dltb_class_feature, [dlbm, "TBDLMJ"], skip_nulls=False, null_value=np.nan))
|
||||
qtdl_df = df[df[dlbm] == '12']
|
||||
if qtdl_df['TBDLMJ'].isnull().any() or qtdl_df['TBDLMJ'].eq(0).any():
|
||||
print("警告：其他地类TBDLMJ字段 存在空值或无效的记录，将不平差其他地类")
|
||||
target_areas = {}
|
||||
else:
|
||||
area_by_group = df.groupby(dlbm)["TBDLMJ"].sum()
|
||||
|
||||
for key in area_by_group.keys():
|
||||
area_by_group[key] = area_by_group[key] * 0.0015
|
||||
|
||||
target_areas = area_by_group.to_dict()
|
||||
|
||||
# 获取目标面积
|
||||
gangnan_target = target_df[target_df['行政单位'] == xzqmc]
|
||||
|
||||
if gangnan_target.empty:
|
||||
print(f"警告：未找到{xzqmc}的目标面积数据,将使用TBDLMJ数据进行平差")
|
||||
return target_areas
|
||||
|
||||
for dlbm, dlmc in landuse_types.items():
|
||||
if dlmc in gangnan_target.columns:
|
||||
if gangnan_target[dlmc].values[0]:
|
||||
target_areas[dlbm] = gangnan_target[dlmc].values[0]
|
||||
|
||||
return target_areas
|
||||
|
||||
except Exception as e:
|
||||
print(f"计算面积时出错: {str(e)}")
|
||||
return None
|
||||
|
||||
def main():
|
||||
|
||||
params = None
|
||||
temp_files_to_clean = []
|
||||
original_workspace = None
|
||||
try:
|
||||
# 1. 解析参数
|
||||
params = parse_arguments()
|
||||
|
||||
reclassed_polygon = params["reclassed_polygon"]
|
||||
soil_property = params["soil_property"]
|
||||
xzq_polygon = params["xzq_features"]
|
||||
dltb_polygon = params["dltb_features"]
|
||||
output_path = params["batch_output_folder"]
|
||||
input_path = params["input_folder"]
|
||||
output_settings = params["output_settings"]
|
||||
xzqmc = params["xzqmc"]
|
||||
is_by_xzq = params["is_by_xzq"]
|
||||
|
||||
original_workspace = arcpy.env.workspace
|
||||
arcpy.env.workspace = input_path
|
||||
arcpy.env.overwriteOutput = True
|
||||
|
||||
if not arcpy.Exists(reclassed_polygon):
|
||||
raise FileNotFoundError(f"输入文件不存在: {reclassed_polygon}")
|
||||
if not arcpy.Exists(xzq_polygon):
|
||||
raise FileNotFoundError(f"输入文件不存在: {xzq_polygon}")
|
||||
if not arcpy.Exists(dltb_polygon):
|
||||
raise FileNotFoundError(f"输入文件不存在: {dltb_polygon}")
|
||||
|
||||
if not os.path.exists(output_path):
|
||||
os.makedirs(output_path)
|
||||
output_origin_path = os.path.join(output_path, "原始结果")
|
||||
if not os.path.exists(output_origin_path):
|
||||
os.makedirs(output_origin_path)
|
||||
|
||||
output_xlsx_path = os.path.join(output_origin_path, f"{soil_property}_原始面积统计表.xlsx")
|
||||
output_adjust_xlsx_path = os.path.join(output_path, f"{soil_property}_面积统计表.xlsx")
|
||||
output_jpg_path = os.path.join(output_path, f"{soil_property}_area_stats.jpg")
|
||||
|
||||
out_feature_class = fr"in_memory\out_feature_class_{uuid.uuid4().hex[:8]}"
|
||||
out_dbf_table = fr"in_memory\out_dbf_table_{uuid.uuid4().hex[:8]}"
|
||||
|
||||
temp_files_to_clean.append([out_feature_class, out_dbf_table])
|
||||
|
||||
# 求地类图斑和重分类栅格面的交集
|
||||
print_status(f"求地类图斑和重分类栅格面的交集...")
|
||||
in_features = [dltb_polygon, reclassed_polygon]
|
||||
arcpy.analysis.Intersect(
|
||||
in_features=in_features,
|
||||
out_feature_class=out_feature_class,
|
||||
join_attributes="ALL",
|
||||
output_type="INPUT"
|
||||
)
|
||||
|
||||
if xzqmc in yunnan_region:
|
||||
print_status(f"开始执行交集制表...")
|
||||
arcpy.analysis.TabulateIntersection(
|
||||
in_zone_features=xzq_polygon, # 乡镇边界
|
||||
zone_fields="XZQMC",
|
||||
in_class_features=out_feature_class,
|
||||
out_table=out_dbf_table,
|
||||
class_fields="gridcode;YNDLBM",
|
||||
out_units="SQUARE_METERS"
|
||||
)
|
||||
elif xzqmc in guangxi_region:
|
||||
# 交集制表
|
||||
print_status(f"开始执行交集制表...")
|
||||
arcpy.analysis.TabulateIntersection(
|
||||
in_zone_features=xzq_polygon, # 乡镇边界
|
||||
zone_fields="XZQMC",
|
||||
in_class_features=out_feature_class,
|
||||
out_table=out_dbf_table,
|
||||
class_fields="gridcode;YJDLBM",
|
||||
out_units="SQUARE_METERS"
|
||||
)
|
||||
else:
|
||||
print_status(f"未找到{xzqmc}的区域配置")
|
||||
raise ValueError(f"未找到{xzqmc}的区域配置")
|
||||
|
||||
# 读取DBF表格到Pandas DataFrame
|
||||
clipped_gdf = read_arcgis_table(out_dbf_table)
|
||||
|
||||
# 准备参数
|
||||
try:
|
||||
if xzqmc in yunnan_region:
|
||||
stats = (
|
||||
clipped_gdf.groupby(["XZQMC", "YNDLBM", "GRIDCODE"])
|
||||
.agg({"temp_area": "sum"})
|
||||
.reset_index()
|
||||
)
|
||||
elif xzqmc in guangxi_region:
|
||||
stats = (
|
||||
clipped_gdf.groupby(["XZQMC", "YJDLBM", "GRIDCODE"])
|
||||
.agg({"temp_area": "sum"})
|
||||
.reset_index()
|
||||
)
|
||||
else:
|
||||
print_status(f"未找到{xzqmc}的区域配置")
|
||||
raise ValueError(f"未找到{xzqmc}的区域配置")
|
||||
except Exception as e:
|
||||
stats = (
|
||||
clipped_gdf.groupby(["XZQMC", "YJDLBM", "GRIDCODE"])
|
||||
.agg({"temp_area": "sum"})
|
||||
.reset_index()
|
||||
)
|
||||
stats["adjusted_area"] = stats["temp_area"]
|
||||
# stats.to_csv("area_stats.csv", index=True)
|
||||
|
||||
# 重命名列（按实际土壤分级字段调整）
|
||||
if soil_property == "PH" or soil_property == "TRRZ":
|
||||
grade_map = get_specail_map(output_settings["标准等级"])
|
||||
elif "1" in output_settings["标准等级"].values(): # 土壤质地
|
||||
grade_map = {str(i+1): str(val) for i,val in enumerate(output_settings["标准等级"].keys())}
|
||||
elif "-10～-0.3" in output_settings["标准等级"].values(): # 酸化pH
|
||||
grade_map = {str(i+1): str(val) for i,val in enumerate(output_settings["标准等级"].keys())}
|
||||
elif "-10～0.1" in output_settings["标准等级"].values(): # 二普-三普变化pH
|
||||
grade_map = {str(i + 1): str(val) for i, val in enumerate(output_settings["标准等级"].keys())}
|
||||
else:
|
||||
grade_map = {str(i+1): str(val) for i,val in enumerate(output_settings["标准等级"].values())}
|
||||
|
||||
if xzqmc in guangxi_region:
|
||||
landuse_map = {"01": "耕地", "02": "园地", "03": "林地", "04": "草地", "12": "其他"}
|
||||
else:
|
||||
landuse_map = {"0101": "水田", "0102": "水浇地", "0103": "旱地", "02": "园地", "03": "林地", "04": "草地", "12": "其他"}
|
||||
|
||||
# 平差处理
|
||||
excel_target_path = Path("tools/config_json/公布的变更调查平差面积.xlsx") # 您的目标面积Excel文件路径
|
||||
each_dl_target = get_area_by_group(dltb_polygon, excel_target_path, xzqmc, is_by_xzq) # 获取每个地类目标面积
|
||||
# if soil_property == "GZCHD":
|
||||
# print(each_dl_target)
|
||||
# each_dl_target = {"01":each_dl_target["01"]}
|
||||
|
||||
if is_by_xzq:
|
||||
adjusted_stats = 平差工具.adjust_by_district_landuse(stats, each_dl_target)
|
||||
else:
|
||||
adjusted_stats = 平差工具.adjust_area_statistics(stats, each_dl_target)
|
||||
# print(adjusted_stats)
|
||||
|
||||
# 2. 生成XLSX报告
|
||||
reporter = SoilQualityReporter(output_xlsx_path, grade_map, landuse_map, output_settings)
|
||||
reporter.generate_report(stats)
|
||||
|
||||
reporter_adjust = SoilQualityReporter(output_adjust_xlsx_path, grade_map, landuse_map, output_settings)
|
||||
reporter_adjust.generate_report(adjusted_stats)
|
||||
|
||||
print_result(True, output_jpg_path, "")
|
||||
except Exception as e:
|
||||
error_msg = f"主函数错误: {str(e)}\n{traceback.format_exc()}"
|
||||
print_status(error_msg)
|
||||
print_result(False, error_message=error_msg)
|
||||
finally:
|
||||
temp_files_processor.clean_up_temp_files(temp_files_to_clean, workspace=original_workspace)
|
||||
sys.exit(0)
|
||||
|
||||
if __name__ == '__main__':
|
||||
print_status("开始执行")
|
||||
main()
|
||||
143
tools/core/stats_sh_to_excel.py
Normal file
143
tools/core/stats_sh_to_excel.py
Normal file
@@ -0,0 +1,143 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
"""
|
||||
输入重分类后栅格转面要素类、乡镇边界面要素类、地类图斑要素类；
|
||||
按一级地类统计土壤属性面积 和 按乡镇统计土壤属性面积；
|
||||
酸化情况统计表生成，第一按样点数量统计，第二按制图面积统计（分土壤类型、乡镇、土地利用类型等进行统计）
|
||||
"""
|
||||
|
||||
import json
|
||||
from pathlib import Path
|
||||
import sys
|
||||
import traceback
|
||||
import time
|
||||
import arcpy
|
||||
import argparse
|
||||
|
||||
from tools.core.utils import 平差工具
|
||||
from tools.core.utils.os_utils import temp_files_processor
|
||||
|
||||
sys.path.append(str(Path(__file__).parent))
|
||||
from acid_stats import 空间连接, 行政区划酸化统计表, 土地利用类型酸化统计表, 土壤类型图酸化统计表
|
||||
|
||||
def parse_arguments():
|
||||
"""解析命令行参数"""
|
||||
parser = argparse.ArgumentParser(description="将ArcGIS表格转换为Excel")
|
||||
parser.add_argument("--settings_path", required=True, help="配置文件路径")
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
if args.settings_path:
|
||||
with open(args.settings_path, 'r', encoding="utf-8") as settings_file:
|
||||
settings = json.load(settings_file)
|
||||
area_stat_settings = settings.get("acid_stat_settings", {})
|
||||
else:
|
||||
print_status("错误: 未找到有效配置文件")
|
||||
sys.exit(1)
|
||||
|
||||
return area_stat_settings
|
||||
|
||||
def print_status(message):
|
||||
"""
|
||||
输出状态信息到标准输出，用于 GUI 实时显示
|
||||
格式: STATUS: <message>
|
||||
"""
|
||||
print(f"STATUS:{message}")
|
||||
sys.stdout.flush() # 确保立即输出
|
||||
|
||||
def print_result(success, output_path="", error_message=""):
|
||||
"""
|
||||
输出最终结果到标准输出，用于 GUI 判断任务状态和获取结果
|
||||
格式: RESULT:True|<output_path>|
|
||||
格式: RESULT:False||<error_message>
|
||||
"""
|
||||
if success:
|
||||
print(f"RESULT:True|{output_path}|")
|
||||
else:
|
||||
# 在错误信息中替换换行符，避免干扰解析
|
||||
cleaned_error_message = error_message.replace('\n', ' ').replace('\r', '')
|
||||
print(f"RESULT:False||{cleaned_error_message}")
|
||||
sys.stdout.flush() # 确保立即输出
|
||||
|
||||
def log_arcpy_message(message):
|
||||
"""输出 ArcPy 产生的 geoprocessing 消息"""
|
||||
# 可以在这里进一步处理或过滤 ArcPy 消息
|
||||
if message.type == 'Message':
|
||||
print_status(f"ArcPy消息: {message.message}")
|
||||
elif message.type == 'Warning':
|
||||
print_status(f"ArcPy警告: {message.message}")
|
||||
elif message.type == 'Error':
|
||||
# 对于错误，也可以记录到标准错误
|
||||
print_status(f"ArcPy错误: {message.message}")
|
||||
sys.stderr.write(f"ArcPyError:{message.message}\n")
|
||||
sys.stderr.flush()
|
||||
|
||||
def main():
|
||||
|
||||
params = None
|
||||
temp_files_to_clean = []
|
||||
original_workspace = None
|
||||
try:
|
||||
# 1. 解析参数
|
||||
params = parse_arguments()
|
||||
|
||||
xzq_polygon = params["xzq_features"]
|
||||
dltb_polygon = params["dltb_features"]
|
||||
output_path = params["batch_output_folder"]
|
||||
workspace_path = params["workspace_path"]
|
||||
trlx_features = params["soil_type_features"] # 土壤类型图
|
||||
assign_raster = params["assign_raster"] # 三普或者二普栅格
|
||||
ph_sample_feature = params["ph_samples"] # PH样点
|
||||
sh_ph_tif_temp = params["acid_raster"] # 酸化PH栅格
|
||||
ph_classed_polygon = params["acid_ph_features"] # 酸化PH重分类后要素
|
||||
xzqmc = params["xzqmc"]
|
||||
ph_sample_table = "历史样点PH信息_Table"
|
||||
|
||||
|
||||
original_workspace = arcpy.env.workspace
|
||||
arcpy.env.workspace = workspace_path
|
||||
arcpy.env.overwriteOutput = True
|
||||
|
||||
# sh_ph_tif = f"in_memory/temp_ph_raster"
|
||||
# temp_files_to_clean.append(sh_ph_tif)
|
||||
|
||||
input_ph_raster = arcpy.Raster(sh_ph_tif_temp)
|
||||
filtered_raster = arcpy.sa.Con(input_ph_raster > 0.3, input_ph_raster)
|
||||
# filtered_raster.save(sh_ph_tif)
|
||||
sh_ph_tif = arcpy.Raster(filtered_raster)
|
||||
temp_files_to_clean.append(sh_ph_tif)
|
||||
|
||||
# 1. 进行空间连接及赋值PH样点
|
||||
if not arcpy.Exists(ph_sample_table):
|
||||
print_status("样点空间连接...")
|
||||
空间连接.export_to_points(ph_sample_feature, dltb_polygon, trlx_features, xzq_polygon, assign_raster, workspace_path)
|
||||
time.sleep(4)
|
||||
|
||||
excel_target_path = Path("tools/config_json/公布的变更调查平差面积.xlsx") # 您的目标面积Excel文件路径
|
||||
target_area_dict = 平差工具.get_area_by_group(dltb_polygon, excel_target_path, xzqmc) # 获取每个地类目标面积
|
||||
|
||||
# 2. 制作统计表
|
||||
print_status("生成行政区划表...")
|
||||
df_with_factor = 行政区划酸化统计表.main(workspace_path, xzq_polygon, ph_classed_polygon, dltb_polygon, sh_ph_tif, output_path, target_area_dict)
|
||||
time.sleep(4)
|
||||
|
||||
print_status("生成土地利用类型表...")
|
||||
土地利用类型酸化统计表.main(workspace_path, ph_classed_polygon,dltb_polygon, sh_ph_tif, output_path,target_area_dict)
|
||||
time.sleep(4)
|
||||
|
||||
print_status("生成土壤类型酸化表...")
|
||||
土壤类型图酸化统计表.main(workspace_path, trlx_features, ph_classed_polygon, sh_ph_tif, output_path, df_with_factor)
|
||||
time.sleep(4)
|
||||
|
||||
print_result(True, output_path, "")
|
||||
except Exception as e:
|
||||
error_msg = f"主函数错误: {str(e)}\n{traceback.format_exc()}"
|
||||
print_status(error_msg)
|
||||
print_result(False, error_message=error_msg)
|
||||
finally:
|
||||
temp_files_processor.clean_up_temp_files(temp_files_to_clean, workspace=original_workspace)
|
||||
sys.exit(0)
|
||||
|
||||
if __name__ == '__main__':
|
||||
print_status("开始执行")
|
||||
main()
|
||||
235
tools/core/stats_soil_prop_to_excel.py
Normal file
235
tools/core/stats_soil_prop_to_excel.py
Normal file
@@ -0,0 +1,235 @@
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
"""
|
||||
输入重分类后栅格转面要素类、乡镇边界面要素类、地类图斑要素类；
|
||||
按一级地类统计土壤属性面积 和 按乡镇统计土壤属性面积；
|
||||
土壤属性统计表生成，第一按样点数量统计，第二按制图面积统计（分土壤类型、乡镇、土地利用类型等进行统计）
|
||||
"""
|
||||
|
||||
import json
|
||||
import multiprocessing
|
||||
import os
|
||||
from pathlib import Path
|
||||
import sys
|
||||
import traceback
|
||||
import time
|
||||
import arcpy
|
||||
import argparse
|
||||
|
||||
from tools.core.utils import 平差工具, common_utils
|
||||
|
||||
sys.path.append(str(Path(__file__).parent))
|
||||
from soil_prop_stats import B1土壤属性分级分布, B2土地利用类型土壤属性, B3不同土壤类型土壤属性, E1土壤属性历史变化, B3_TRZD不同土壤类型土壤属性, B1_TRZD土壤属性分级分布, B2_TRZD土地利用类型土壤属性
|
||||
from soil_prop_stats import B3_TRZD12不同土壤类型土壤属性, B1_TRZD12土壤属性分级分布, B2_TRZD12土地利用类型土壤属性
|
||||
from tools.config.arcgis_field_cal_code import codeblock_dltb_yjdl, codeblock_dltb_ejdl
|
||||
from tools.core.utils.os_utils import temp_files_processor
|
||||
|
||||
def parse_arguments():
|
||||
"""解析命令行参数"""
|
||||
parser = argparse.ArgumentParser(description="将ArcGIS表格转换为Excel")
|
||||
parser.add_argument("--settings_path", required=True, help="配置文件路径")
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
if args.settings_path:
|
||||
with open(args.settings_path, 'r', encoding="utf-8") as settings_file:
|
||||
settings = json.load(settings_file)
|
||||
area_stat_settings = settings.get("soil_prop_stat_settings", {})
|
||||
else:
|
||||
print_status("错误: 未找到有效配置文件")
|
||||
sys.exit(1)
|
||||
|
||||
return area_stat_settings
|
||||
|
||||
def print_status(message):
|
||||
"""
|
||||
输出状态信息到标准输出，用于 GUI 实时显示
|
||||
格式: STATUS: <message>
|
||||
"""
|
||||
print(f"STATUS:{message}")
|
||||
sys.stdout.flush() # 确保立即输出
|
||||
|
||||
def print_result(success, output_path="", error_message=""):
|
||||
"""
|
||||
输出最终结果到标准输出，用于 GUI 判断任务状态和获取结果
|
||||
格式: RESULT:True|<output_path>|
|
||||
格式: RESULT:False||<error_message>
|
||||
"""
|
||||
if success:
|
||||
print(f"RESULT:True|{output_path}|")
|
||||
else:
|
||||
# 在错误信息中替换换行符，避免干扰解析
|
||||
cleaned_error_message = error_message.replace('\n', ' ').replace('\r', '')
|
||||
print(f"RESULT:False||{cleaned_error_message}")
|
||||
sys.stdout.flush() # 确保立即输出
|
||||
|
||||
def log_arcpy_message(message):
|
||||
"""输出 ArcPy 产生的 geoprocessing 消息"""
|
||||
# 可以在这里进一步处理或过滤 ArcPy 消息
|
||||
if message.type == 'Message':
|
||||
print_status(f"ArcPy消息: {message.message}")
|
||||
elif message.type == 'Warning':
|
||||
print_status(f"ArcPy警告: {message.message}")
|
||||
elif message.type == 'Error':
|
||||
# 对于错误，也可以记录到标准错误
|
||||
print_status(f"ArcPy错误: {message.message}")
|
||||
sys.stderr.write(f"ArcPyError:{message.message}\n")
|
||||
sys.stderr.flush()
|
||||
|
||||
def process_soil_property(args):
|
||||
"""处理单个土壤属性的函数，用于多进程"""
|
||||
soil_prop_name, config, data_source_path, history_samples_path, reclassed_features_path, history_reclassed_features_path, sanpu_prop_tif_path, history_raster_path, dltb_features, trlx_features, output_path, target_area_df1, target_area_df2, target_area_all, xzqmc = args
|
||||
|
||||
try:
|
||||
prop_config = config['export_config'][soil_prop_name]
|
||||
reclassed_features = os.path.join(reclassed_features_path, f"{soil_prop_name}_reclassed_polygon.shp")
|
||||
history_reclassed_features = os.path.join(history_reclassed_features_path, f"{soil_prop_name}_reclassed_polygon.shp")
|
||||
soil_prop_tif = os.path.join(sanpu_prop_tif_path, f"{soil_prop_name}.tif")
|
||||
history_raster = os.path.join(history_raster_path, f"{soil_prop_name}.tif")
|
||||
|
||||
if not arcpy.Exists(reclassed_features) or not arcpy.Exists(soil_prop_tif):
|
||||
print(f"缺少{soil_prop_name}的栅格或重分类要素，请检查输入文件路径是否正确！")
|
||||
return False
|
||||
|
||||
print(f"生成{soil_prop_name}的表1...")
|
||||
if soil_prop_name == "TRZD12":
|
||||
B1_TRZD12土壤属性分级分布.main(data_source_path, soil_prop_name, reclassed_features, dltb_features, output_path, target_area_all,xzqmc, prop_config)
|
||||
elif soil_prop_name == "TRZD":
|
||||
B1_TRZD土壤属性分级分布.main(data_source_path, soil_prop_name, reclassed_features, dltb_features, output_path, target_area_all,xzqmc, prop_config)
|
||||
else:
|
||||
B1土壤属性分级分布.main(data_source_path, soil_prop_name, reclassed_features, dltb_features, soil_prop_tif, output_path, target_area_all,xzqmc, prop_config)
|
||||
time.sleep(2)
|
||||
|
||||
# print(f"生成{soil_prop_name}的表2...")
|
||||
# if soil_prop_name == "TRZD12":
|
||||
# B2_TRZD12土地利用类型土壤属性.main(data_source_path, soil_prop_name, dltb_features, reclassed_features, output_path, target_area_df2, prop_config)
|
||||
# elif soil_prop_name == "TRZD":
|
||||
# B2_TRZD土地利用类型土壤属性.main(data_source_path, soil_prop_name, dltb_features, reclassed_features, output_path, target_area_df2, prop_config)
|
||||
# else:
|
||||
# B2土地利用类型土壤属性.main(data_source_path, soil_prop_name, dltb_features, soil_prop_tif, output_path, target_area_df2, prop_config)
|
||||
# time.sleep(2)
|
||||
|
||||
# print(f"生成{soil_prop_name}的表3...")
|
||||
# if soil_prop_name == "TRZD12":
|
||||
# B3_TRZD12不同土壤类型土壤属性.main(data_source_path,soil_prop_name,trlx_features,reclassed_features,output_path,target_area_df1,prop_config)
|
||||
# elif soil_prop_name == "TRZD":
|
||||
# B3_TRZD不同土壤类型土壤属性.main(data_source_path, soil_prop_name, trlx_features, reclassed_features, output_path, target_area_df1, prop_config)
|
||||
# else:
|
||||
# B3不同土壤类型土壤属性.main(data_source_path, soil_prop_name, trlx_features, soil_prop_tif, output_path, target_area_df1, prop_config, dltb_features)
|
||||
# time.sleep(2)
|
||||
|
||||
print(f"生成{soil_prop_name}的历史对比...")
|
||||
# if arcpy.Exists(history_reclassed_features) and arcpy.Exists(history_raster) and arcpy.Exists(history_samples_path):
|
||||
# E1土壤属性历史变化.main(xzqmc,data_source_path,history_samples_path,reclassed_features,history_reclassed_features, soil_prop_name, dltb_features, soil_prop_tif,history_raster, output_path, target_area_all, prop_config)
|
||||
# time.sleep(2)
|
||||
# else:
|
||||
# print_status(f"警告：缺少{soil_prop_name}的历史栅格或重分类要素，请检查输入文件路径是否正确！")
|
||||
|
||||
return True
|
||||
except Exception as e:
|
||||
print(f"处理{soil_prop_name}时出错: {str(e)}")
|
||||
return False
|
||||
|
||||
def main():
|
||||
|
||||
params = None
|
||||
temp_files_to_clean = []
|
||||
original_workspace = None
|
||||
try:
|
||||
# 1. 解析参数
|
||||
params = parse_arguments()
|
||||
|
||||
xzqmc = params["xzqmc"]
|
||||
config_file = params["config_file"]
|
||||
output_path = params["output_folder"]
|
||||
data_source_path = params["data_source_path"]
|
||||
sanpu_prop_tif_path = params["sanpu_prop_tif_folder"]
|
||||
reclassed_features_path = params["reclassed_feature_folder"]
|
||||
# history_reclassed_features_path = params["history_reclassed_feature_folder"]
|
||||
soil_prop_name_list = params["sample_list"]
|
||||
# history_samples_path = params["history_samples_folder"]
|
||||
# history_raster_path = params["history_raster_folder"]
|
||||
history_samples_path = r"E:\@三普属性图出图\广西武鸣区\@基础数据\测土配方样点数据\测土配方样点.gdb"
|
||||
history_raster_path = r"E:\@三普属性图出图\广西武鸣区\@基础数据\测土配方栅格\投影后"
|
||||
history_reclassed_features_path = r"E:\@三普属性图出图\广西武鸣区\过程数据\测土配方重分类\面积统计用栅格面"
|
||||
|
||||
|
||||
dltb_features = os.path.join(data_source_path, "地类图斑")
|
||||
trlx_features = os.path.join(data_source_path, "土壤类型图")
|
||||
|
||||
original_workspace = arcpy.env.workspace
|
||||
arcpy.env.workspace = data_source_path
|
||||
arcpy.env.overwriteOutput = True
|
||||
|
||||
excel_target = Path("tools/config_json/公布的变更调查平差面积.xlsx") # 您的目标面积Excel文件路径
|
||||
excel_target_path = str(excel_target.resolve())
|
||||
target_area_df2 = 平差工具.get_target_areas(excel_target_path,"Sheet2", xzqmc) # 获取每个二级地类目标面积
|
||||
target_area_df1 = 平差工具.get_target_areas(excel_target_path,"Sheet1", xzqmc) # 获取每个一级地类目标面积
|
||||
target_area_all = 平差工具.get_target_areas_by_group(excel_target_path)
|
||||
|
||||
# 2. 制作统计表
|
||||
# 计算土地利用类型图斑的地类
|
||||
if arcpy.Exists(dltb_features):
|
||||
try:
|
||||
check_fields = ["YJDL", "EJDL", "YJDLBM", "YJDL_EJDL"]
|
||||
if not common_utils.check_fields_exist_describe(dltb_features, check_fields):
|
||||
arcpy.management.CalculateField(dltb_features, "EJDL", "calculate_ejdl(!DLBM!,!DLMC!)", "PYTHON3", codeblock_dltb_ejdl)
|
||||
arcpy.management.CalculateField(dltb_features, "YJDL", "calculate_yjdl(!DLBM!)", "PYTHON3", codeblock_dltb_yjdl)
|
||||
arcpy.management.CalculateField(dltb_features, "YJDLBM", "!DLBM![:2]", "PYTHON3")
|
||||
arcpy.management.CalculateField(dltb_features,"YJDL_EJDL","!YJDL! + '_' + !EJDL!","PYTHON3")
|
||||
except Exception as e:
|
||||
print(f'报什么错:{e}')
|
||||
|
||||
# 计算土壤类型图斑的字段用于后续交集制表
|
||||
if arcpy.Exists(trlx_features):
|
||||
try:
|
||||
check_fields = ["YL_TS"]
|
||||
if not common_utils.check_fields_exist_describe(trlx_features, check_fields):
|
||||
# 计算YL_TS字段的值
|
||||
arcpy.management.CalculateField(trlx_features, "YL_TS", "!YL! + '_' + !TS!", "PYTHON3")
|
||||
except Exception as e:
|
||||
print(f'报什么错:{e}')
|
||||
|
||||
# 获取土壤属性配置文件
|
||||
with open(config_file, 'r', encoding='utf-8') as f:
|
||||
config = json.load(f)
|
||||
|
||||
# 准备多进程参数
|
||||
process_args = []
|
||||
for soil_prop_name in soil_prop_name_list:
|
||||
args = (soil_prop_name, config, data_source_path, history_samples_path, reclassed_features_path, history_reclassed_features_path,
|
||||
sanpu_prop_tif_path, history_raster_path, dltb_features, trlx_features, output_path,
|
||||
target_area_df1, target_area_df2, target_area_all,xzqmc)
|
||||
process_args.append(args)
|
||||
|
||||
# 使用多进程处理
|
||||
cpu_count = multiprocessing.cpu_count()
|
||||
# num_processes = min(int(cpu_count if cpu_count<2 else cpu_count/2), len(soil_prop_name_list))
|
||||
num_processes = 3
|
||||
|
||||
print(f"使用 {num_processes} 个进程并行处理 {len(soil_prop_name_list)} 个土壤属性...")
|
||||
|
||||
with multiprocessing.Pool(processes=num_processes) as pool:
|
||||
results = pool.map(process_soil_property, process_args)
|
||||
|
||||
# 检查所有任务是否成功完成
|
||||
if all(results):
|
||||
print_result(True, output_path, "")
|
||||
else:
|
||||
failed_count = results.count(False)
|
||||
error_msg = f"{failed_count} 个土壤属性处理失败"
|
||||
print_result(False, error_message=error_msg)
|
||||
|
||||
print_result(True, output_path, "")
|
||||
except Exception as e:
|
||||
error_msg = f"主函数错误: {str(e)}\n{traceback.format_exc()}"
|
||||
print_status(error_msg)
|
||||
print_result(False, error_message=error_msg)
|
||||
finally:
|
||||
temp_files_processor.clean_up_temp_files(temp_files_to_clean, workspace=original_workspace)
|
||||
sys.exit(0)
|
||||
|
||||
if __name__ == '__main__':
|
||||
print_status("开始执行")
|
||||
multiprocessing.freeze_support()
|
||||
main()
|
||||
249
tools/core/test_script.py
Normal file
249
tools/core/test_script.py
Normal file
@@ -0,0 +1,249 @@
|
||||
#!/usr/bin/env python
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
"""
|
||||
测试脚本
|
||||
用于测试ArcGIS Pro图层属性和标注功能
|
||||
"""
|
||||
|
||||
import os
|
||||
import sys
|
||||
import argparse
|
||||
import traceback
|
||||
import arcpy
|
||||
|
||||
|
||||
def log(message):
|
||||
"""日志输出函数"""
|
||||
print(message)
|
||||
|
||||
|
||||
def test_arcgis_environment():
|
||||
"""测试ArcGIS Pro环境"""
|
||||
log("=== ArcGIS Pro环境信息 ===")
|
||||
log(f"Python版本: {sys.version}")
|
||||
log(f"Python路径: {sys.executable}")
|
||||
log(f"当前工作目录: {os.getcwd()}")
|
||||
log(f"ArcPy版本: {arcpy.GetInstallInfo()['Version']}")
|
||||
log(f"ArcPy产品: {arcpy.GetInstallInfo()['ProductName']}")
|
||||
|
||||
# 当前环境设置
|
||||
log("\n=== ArcGIS环境设置 ===")
|
||||
log(f"工作空间: {arcpy.env.workspace}")
|
||||
log(f"输出坐标系统: {arcpy.env.outputCoordinateSystem}")
|
||||
log(f"覆盖输出: {arcpy.env.overwriteOutput}")
|
||||
|
||||
|
||||
def test_layer_properties(layer_path):
|
||||
"""测试图层属性"""
|
||||
log(f"\n=== 图层属性测试: {layer_path} ===")
|
||||
|
||||
if not arcpy.Exists(layer_path):
|
||||
log(f"错误: 图层不存在 - {layer_path}")
|
||||
return
|
||||
|
||||
try:
|
||||
# 创建图层对象
|
||||
log("尝试创建图层对象...")
|
||||
layer = arcpy.mp.Layer(layer_path)
|
||||
log(f"成功创建图层: {layer.name}")
|
||||
|
||||
# 图层基本属性
|
||||
log("\n图层基本属性:")
|
||||
log(f"名称: {layer.name}")
|
||||
log(f"数据源类型: {type(layer.dataSource).__name__ if hasattr(layer, 'dataSource') else 'N/A'}")
|
||||
log(f"长名称: {layer.longName if hasattr(layer, 'longName') else 'N/A'}")
|
||||
|
||||
# 图层类型
|
||||
log("\n图层类型判断:")
|
||||
log(f"是要素图层: {layer.isFeatureLayer if hasattr(layer, 'isFeatureLayer') else 'N/A'}")
|
||||
log(f"是栅格图层: {layer.isRasterLayer if hasattr(layer, 'isRasterLayer') else 'N/A'}")
|
||||
log(f"是图形图层: {layer.isGroupLayer if hasattr(layer, 'isGroupLayer') else 'N/A'}")
|
||||
|
||||
# 支持的属性
|
||||
log("\n支持的属性:")
|
||||
properties = [
|
||||
'LABELCLASSES', 'SHOWLABELS', 'NAME', 'DATASOURCE', 'DEFINITIONQUERY',
|
||||
'VISIBLE', 'TRANSPARENCY', 'BRIGHTNESS', 'CONTRAST', 'SYMBOLOGY'
|
||||
]
|
||||
|
||||
for prop in properties:
|
||||
try:
|
||||
support = hasattr(layer, prop.lower()) or (hasattr(layer, 'supports') and layer.supports(prop))
|
||||
log(f"{prop}: {'支持' if support else '不支持'}")
|
||||
except Exception as e:
|
||||
log(f"{prop}: 检查失败 - {str(e)}")
|
||||
|
||||
# 尝试获取标注类
|
||||
log("\n标注类测试:")
|
||||
try:
|
||||
if hasattr(layer, 'listLabelClasses'):
|
||||
label_classes = layer.listLabelClasses()
|
||||
log(f"找到 {len(label_classes)} 个标注类")
|
||||
|
||||
# 显示每个标注类的信息
|
||||
for i, lc in enumerate(label_classes):
|
||||
log(f"标注类 #{i+1}: {lc.name if hasattr(lc, 'name') else 'N/A'}")
|
||||
log(f" 表达式: {lc.expression if hasattr(lc, 'expression') else 'N/A'}")
|
||||
log(f" SQL查询: {lc.SQLQuery if hasattr(lc, 'SQLQuery') else 'N/A'}")
|
||||
log(f" 可见: {lc.showClassLabels if hasattr(lc, 'showClassLabels') else 'N/A'}")
|
||||
else:
|
||||
log("图层不支持listLabelClasses方法")
|
||||
|
||||
# 检查标注状态
|
||||
if hasattr(layer, 'showLabels'):
|
||||
log(f"标注显示状态: {layer.showLabels}")
|
||||
else:
|
||||
log("图层没有showLabels属性")
|
||||
except Exception as e:
|
||||
log(f"获取标注类时出错: {str(e)}")
|
||||
|
||||
# 使用arcpy.da.Describe获取详细信息
|
||||
log("\narcpy.da.Describe描述信息:")
|
||||
try:
|
||||
desc = arcpy.da.Describe(layer)
|
||||
for key in desc:
|
||||
# 跳过复杂对象
|
||||
if isinstance(desc[key], (dict, list, tuple)):
|
||||
log(f"{key}: [复杂类型]")
|
||||
else:
|
||||
log(f"{key}: {desc[key]}")
|
||||
except Exception as e:
|
||||
log(f"获取Describe信息时出错: {str(e)}")
|
||||
|
||||
except Exception as e:
|
||||
log(f"测试图层属性时出错: {str(e)}")
|
||||
log(traceback.format_exc())
|
||||
|
||||
|
||||
def test_annotation_conversion(map_path, layer_name, output_folder):
|
||||
"""测试标注转注记功能"""
|
||||
log(f"\n=== 标注转注记测试: {map_path}, 图层: {layer_name} ===")
|
||||
|
||||
if not arcpy.Exists(map_path):
|
||||
log(f"错误: 地图文档不存在 - {map_path}")
|
||||
return
|
||||
|
||||
# 确保输出文件夹存在
|
||||
if not os.path.exists(output_folder):
|
||||
os.makedirs(output_folder)
|
||||
|
||||
try:
|
||||
# 打开地图文档
|
||||
log(f"打开地图文档...")
|
||||
aprx = arcpy.mp.ArcGISProject(map_path)
|
||||
|
||||
# 获取活动地图
|
||||
log(f"获取地图...")
|
||||
maps = aprx.listMaps()
|
||||
if not maps:
|
||||
log("错误: 地图文档中没有地图")
|
||||
return
|
||||
|
||||
target_map = maps[0] # 默认使用第一个地图
|
||||
log(f"使用地图: {target_map.name}")
|
||||
|
||||
# 查找指定图层
|
||||
log(f"查找图层: {layer_name}")
|
||||
layers = target_map.listLayers(layer_name)
|
||||
if not layers:
|
||||
log(f"错误: 找不到图层 {layer_name}")
|
||||
return
|
||||
|
||||
label_layer = layers[0]
|
||||
log(f"找到图层: {label_layer.name}")
|
||||
|
||||
# 测试图层属性
|
||||
test_layer_properties(label_layer)
|
||||
|
||||
# 尝试开启标注
|
||||
try:
|
||||
if hasattr(label_layer, 'showLabels'):
|
||||
log(f"当前标注状态: {label_layer.showLabels}")
|
||||
label_layer.showLabels = True
|
||||
log(f"已开启标注，新状态: {label_layer.showLabels}")
|
||||
except Exception as e:
|
||||
log(f"设置标注状态时出错: {str(e)}")
|
||||
|
||||
# 尝试执行标注转注记
|
||||
log("\n执行标注转注记...")
|
||||
try:
|
||||
anno_name = f"{label_layer.name}_Anno"
|
||||
output_anno = os.path.join(output_folder, anno_name)
|
||||
|
||||
# 检查是否已存在
|
||||
if arcpy.Exists(output_anno):
|
||||
log(f"注记已存在: {output_anno}，将尝试删除")
|
||||
arcpy.management.Delete(output_anno)
|
||||
|
||||
# 执行转换
|
||||
log("使用ConvertLabelsToAnnotation...")
|
||||
arcpy.cartography.ConvertLabelsToAnnotation(
|
||||
target_map,
|
||||
[label_layer],
|
||||
output_folder,
|
||||
"FEATURE_LINKED",
|
||||
"STANDARD",
|
||||
None,
|
||||
None,
|
||||
None
|
||||
)
|
||||
log("ConvertLabelsToAnnotation执行成功")
|
||||
|
||||
except Exception as e:
|
||||
log(f"执行标注转注记时出错: {str(e)}")
|
||||
log(traceback.format_exc())
|
||||
|
||||
# 尝试替代方案
|
||||
try:
|
||||
log("\n尝试使用LabelFeatures替代方案...")
|
||||
arcpy.cartography.LabelFeatures(
|
||||
in_features=label_layer,
|
||||
out_geodatabase=output_folder
|
||||
)
|
||||
log("LabelFeatures执行成功")
|
||||
except Exception as e2:
|
||||
log(f"LabelFeatures也失败: {str(e2)}")
|
||||
|
||||
except Exception as e:
|
||||
log(f"测试标注转注记时出错: {str(e)}")
|
||||
log(traceback.format_exc())
|
||||
finally:
|
||||
if 'aprx' in locals():
|
||||
del aprx
|
||||
|
||||
|
||||
def main():
|
||||
"""主函数"""
|
||||
parser = argparse.ArgumentParser(description='ArcGIS Pro图层和标注功能测试')
|
||||
parser.add_argument('--message', default='测试消息', help='测试消息')
|
||||
parser.add_argument('--count', type=int, default=1, help='重复次数')
|
||||
parser.add_argument('--map', help='地图文档路径(.aprx)')
|
||||
parser.add_argument('--layer', help='图层名称')
|
||||
parser.add_argument('--layer_path', help='图层文件路径(.lyrx)')
|
||||
parser.add_argument('--output', help='输出文件夹')
|
||||
|
||||
args = parser.parse_args()
|
||||
|
||||
# 输出系统信息
|
||||
test_arcgis_environment()
|
||||
|
||||
# 输出测试消息
|
||||
for i in range(args.count):
|
||||
log(f"\n{i+1}. {args.message}")
|
||||
|
||||
# 如果提供了图层文件路径，测试图层属性
|
||||
if args.layer_path:
|
||||
test_layer_properties(args.layer_path)
|
||||
|
||||
# 如果提供了地图文档、图层名称和输出文件夹，测试标注转注记
|
||||
if args.map and args.layer and args.output:
|
||||
test_annotation_conversion(args.map, args.layer, args.output)
|
||||
|
||||
# 退出前打印完成消息
|
||||
log("\n测试脚本执行完成")
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
0
tools/core/utils/__init__.py
Normal file
0
tools/core/utils/__init__.py
Normal file
26
tools/core/utils/arcgis_utils.py
Normal file
26
tools/core/utils/arcgis_utils.py
Normal file
@@ -0,0 +1,26 @@
|
||||
import arcpy
|
||||
import pandas as pd
|
||||
|
||||
|
||||
def read_arcgis_table(table_path):
|
||||
"""
|
||||
将ArcGIS表格转换为Pandas DataFrame
|
||||
:param table_path: ArcGIS表格路径
|
||||
:return: Pandas DataFrame
|
||||
表格字段全部转换为大写
|
||||
面积字段AREA转换为亩，保留4位小数，存储在temp_area字段中
|
||||
"""
|
||||
array = arcpy.da.TableToNumPyArray(table_path, "*")
|
||||
|
||||
df = pd.DataFrame(array)
|
||||
# df.to_csv(r"D:\工作\三普成果编制\出图数据\广西海城区\过程数据\酸化面积统计表\temp.csv")
|
||||
|
||||
df.columns = df.columns.str.upper()
|
||||
df["temp_area"] = df["AREA"] * 0.0015
|
||||
df["temp_area"] = df["temp_area"].round(4)
|
||||
|
||||
# 删除可能存在的OID字段（如果不需要）
|
||||
if 'OID@' in df.columns:
|
||||
df = df.drop('OID@', axis=1)
|
||||
|
||||
return df
|
||||
291
tools/core/utils/common_utils.py
Normal file
291
tools/core/utils/common_utils.py
Normal file
@@ -0,0 +1,291 @@
|
||||
import arcpy
|
||||
import numpy as np
|
||||
|
||||
|
||||
def get_data_type(data_path):
|
||||
"""获取数据类型
|
||||
|
||||
:param data_path: 数据路径
|
||||
:return: 数据类型
|
||||
"""
|
||||
if arcpy.Exists(data_path):
|
||||
try:
|
||||
desc = arcpy.Describe(data_path)
|
||||
return desc.dataType
|
||||
except:
|
||||
return False
|
||||
else:
|
||||
return False
|
||||
|
||||
def get_config_key(every_string: str) -> str:
|
||||
config_dict = {
|
||||
"AB": "有效硼","ACU": "有效铜","AMN": "有效锰","AMO": "有效钼","AS1": "有效硫","AZN": "有效锌","CEC": "阳离子交换量","ECA": "交换性钙",
|
||||
"EMG": "交换性镁","TSE": "全硒","TN": "全氮","TP": "全磷","TK": "全钾","AFE": "有效铁","AK": "速效钾","AP": "有效磷", "TRRZ": "土壤容重","LSFD":"砾石丰度",
|
||||
"OM": "有机质","FL": "粉粒含量","NL": "黏粒含量","SL": "砂粒含量","PH": "土壤 pH","YXTCHD": "有效土层厚度","GZCHD": "耕作层厚度","TRZD": "土壤质地","TRZD12": "土壤质地",
|
||||
"三普PH": "三普PH","二普PH": "二普PH","测土PH": "测土PH","二普-三普": "二普-三普","测土-三普": "测土-三普","二普-测土": "二普-测土"
|
||||
}
|
||||
try:
|
||||
for key in config_dict.keys():
|
||||
in_key = every_string.split("_")[0]
|
||||
if key == in_key:
|
||||
return key
|
||||
|
||||
return ""
|
||||
|
||||
except Exception as e:
|
||||
return ""
|
||||
|
||||
def parse_raster_standard(standard_str):
|
||||
"""解析重分类标准字符串，返回数值范围
|
||||
|
||||
例如：
|
||||
"＞2.00" -> (2.0, float('inf'))
|
||||
"1.00～2.00" -> (1.0, 2.0)
|
||||
"≤0.20" -> (0, 0.2)
|
||||
"""
|
||||
if "," in standard_str:
|
||||
temp = []
|
||||
parts = standard_str.split(",\n")
|
||||
for part in parts:
|
||||
temp_part = parse_raster_standard(part)
|
||||
temp.append(temp_part)
|
||||
return temp
|
||||
if "＞" in standard_str:
|
||||
value = float(standard_str.replace("＞", ""))
|
||||
return (value, float('inf'))
|
||||
elif "～" in standard_str:
|
||||
parts = standard_str.split("～")
|
||||
return (float(parts[0]), float(parts[1]))
|
||||
elif "≤" in standard_str:
|
||||
value = float(standard_str.replace("≤", ""))
|
||||
return (0, value)
|
||||
else:
|
||||
# 尝试直接解析为数值
|
||||
try:
|
||||
value = float(standard_str)
|
||||
return (value, value)
|
||||
except ValueError:
|
||||
return None
|
||||
|
||||
def create_remap_table(standards_dict):
|
||||
"""根据标准配置创建重分类映射表
|
||||
|
||||
参数:
|
||||
standards_config -- 标准配置，格式为:
|
||||
{"标准1":5-6, "标准2":7-8, ...}
|
||||
remap_values -- 重分类值数组，默认为从1开始的整数序列
|
||||
|
||||
返回:
|
||||
重分类映射表，格式为 [[old_min, old_max, new_value], ...]
|
||||
"""
|
||||
|
||||
# 确保我们有一个有效的标准列表
|
||||
if not standards_dict or not isinstance(standards_dict, dict):
|
||||
print("警告: 没有有效的标准数据")
|
||||
return []
|
||||
|
||||
# 设置重分类值
|
||||
standards_length = len(standards_dict)
|
||||
remap_values = list(range(1, 2*standards_length + 1))
|
||||
|
||||
remap_table = []
|
||||
for i, (key, value) in enumerate(standards_dict.items()):
|
||||
range_tuple = parse_raster_standard(value)
|
||||
|
||||
if range_tuple:
|
||||
if type(range_tuple) is list:
|
||||
m = 0
|
||||
for range_tuple_item in range_tuple:
|
||||
j = m * standards_length + i
|
||||
remap_table.append([range_tuple_item[0], range_tuple_item[1], remap_values[j]])
|
||||
m = m + 1
|
||||
else:
|
||||
remap_table.append([range_tuple[0], range_tuple[1], remap_values[i]])
|
||||
|
||||
return remap_table
|
||||
|
||||
|
||||
def check_fields_exist_describe(feature_class, field_names):
|
||||
"""
|
||||
使用Describe函数检查要素类中字段是否存在
|
||||
"""
|
||||
try:
|
||||
desc = arcpy.Describe(feature_class)
|
||||
existing_fields = [field.name for field in desc.fields]
|
||||
|
||||
for field_name in field_names:
|
||||
if field_name not in existing_fields:
|
||||
return False
|
||||
|
||||
return True
|
||||
|
||||
except Exception as e:
|
||||
print(f"检查字段时出错: {e}")
|
||||
return None
|
||||
|
||||
def get_grade_by_standard(value, grade_standards):
|
||||
"""
|
||||
通用的等级判断函数
|
||||
value: 数值
|
||||
grade_standards: 分级标准字典，如 {"等级一": "＞2.00", "等级二": "1.00～2.00"}
|
||||
"""
|
||||
if value is None:
|
||||
return "无数据"
|
||||
|
||||
# 按等级顺序检查（从高到低）
|
||||
sorted_grades = sorted(grade_standards.items(),
|
||||
key=lambda x: list(grade_standards.keys()).index(x[0]))
|
||||
|
||||
for grade_name, grade_standard in sorted_grades:
|
||||
if is_value_in_grade(value, grade_standard):
|
||||
return grade_name
|
||||
|
||||
return "超出范围"
|
||||
|
||||
def is_value_in_grade(value, grade_standard):
|
||||
"""
|
||||
判断数值是否在分级标准范围内
|
||||
"""
|
||||
# 处理特殊字符
|
||||
grade_standard = grade_standard.replace('＞', '>').replace('≤', '<=').replace('～', '~')
|
||||
|
||||
# 处理多范围情况（如pH值）
|
||||
if ',' in grade_standard:
|
||||
ranges = grade_standard.split(',')
|
||||
for range_str in ranges:
|
||||
if is_value_in_single_range(value, range_str.strip()):
|
||||
return True
|
||||
return False
|
||||
else:
|
||||
return is_value_in_single_range(value, grade_standard)
|
||||
|
||||
def is_value_in_single_range(value, range_str):
|
||||
"""
|
||||
判断数值是否在单个范围内
|
||||
"""
|
||||
import re
|
||||
|
||||
# 提取数值
|
||||
numbers = re.findall(r'[-+]?\d*\.\d+|\d+', range_str)
|
||||
numbers = [float(num) for num in numbers]
|
||||
|
||||
if '>' in range_str and '~' in range_str:
|
||||
# 格式：>下限~上限
|
||||
return numbers[0] < value <= numbers[1]
|
||||
elif '>' in range_str:
|
||||
# 格式：>数值
|
||||
return value > numbers[0]
|
||||
elif '<=' in range_str:
|
||||
# 格式：<=数值
|
||||
return value <= numbers[0]
|
||||
elif '~' in range_str:
|
||||
# 格式：下限~上限
|
||||
return numbers[0] < value <= numbers[1]
|
||||
else:
|
||||
# 无法解析，使用字符串匹配
|
||||
return str(value) == range_str
|
||||
|
||||
def vectorized_grade_assignment(values, grade_standards):
|
||||
"""
|
||||
向量化的等级分配（性能更好）
|
||||
"""
|
||||
# 确保输入值是数值类型，如果是字符串则转换为浮点数
|
||||
if isinstance(values, np.ndarray) and values.dtype.kind in 'OUS': # 字符串类型
|
||||
values = values.astype(float)
|
||||
elif hasattr(values, 'dtype') and values.dtype == object: # 对象类型，可能包含字符串
|
||||
values = values.astype(float)
|
||||
|
||||
conditions = []
|
||||
choices = []
|
||||
|
||||
# 按等级顺序构建条件
|
||||
# 创建两个列表来分别存储上段和下段范围
|
||||
upper_ranges = []
|
||||
lower_ranges = []
|
||||
|
||||
# 遍历排序后的等级
|
||||
for i, (level, ranges) in enumerate(sorted(grade_standards.items(), key=lambda x: list(grade_standards.keys()).index(x[0])), 1):
|
||||
# 分割范围字符串
|
||||
range_list = [r.strip() for r in ranges.split(',')]
|
||||
|
||||
if len(range_list) >= 1:
|
||||
upper_ranges.append((i, range_list[0]))
|
||||
|
||||
if len(range_list) >= 2:
|
||||
# 计算下段范围的索引（原始索引 + 等级总数）
|
||||
lower_index = i + len(grade_standards)
|
||||
lower_ranges.append((lower_index, range_list[1]))
|
||||
|
||||
# 合并结果
|
||||
sorted_grades = upper_ranges + lower_ranges
|
||||
# sorted_grades = sorted(grade_standards.items(), key=lambda x: list(grade_standards.keys()).index(x[0]))
|
||||
|
||||
for grade_name, grade_standard in sorted_grades:
|
||||
condition = create_condition(values, grade_standard)
|
||||
conditions.append(condition)
|
||||
choices.append(grade_name)
|
||||
|
||||
# 使用np.select进行向量化操作
|
||||
result = np.select(conditions, choices, default="超出范围")
|
||||
return result
|
||||
|
||||
def create_condition(values, grade_standard):
|
||||
"""
|
||||
创建numpy条件
|
||||
"""
|
||||
# 清理字符串：替换特殊字符并移除换行符和空格
|
||||
grade_standard = (grade_standard.replace('＞', '>')
|
||||
.replace('≤', '<=')
|
||||
.replace('～', '~')
|
||||
.replace('\n', '') # 移除换行符
|
||||
.replace(' ', '')) # 移除空格
|
||||
|
||||
if ',' in grade_standard:
|
||||
# 多范围处理
|
||||
ranges = grade_standard.split(',')
|
||||
condition = None
|
||||
for range_str in ranges:
|
||||
if range_str: # 确保不是空字符串
|
||||
range_condition = create_single_condition(values, range_str.strip())
|
||||
if condition is None:
|
||||
condition = range_condition
|
||||
else:
|
||||
condition = condition | range_condition
|
||||
return condition
|
||||
else:
|
||||
return create_single_condition(values, grade_standard)
|
||||
|
||||
def create_single_condition(values, range_str):
|
||||
"""
|
||||
创建单个范围的条件
|
||||
"""
|
||||
import re
|
||||
|
||||
# 调试输出，帮助排查问题
|
||||
# print(f"处理范围字符串: '{range_str}'")
|
||||
|
||||
# 提取数字
|
||||
numbers = re.findall(r'[-+]?\d*\.\d+|\d+', range_str)
|
||||
numbers = [float(num) for num in numbers]
|
||||
|
||||
if not numbers:
|
||||
raise ValueError(f"无法从字符串 '{range_str}' 中提取数字")
|
||||
|
||||
# 根据范围符号创建条件
|
||||
if '>' in range_str and '<=' in range_str:
|
||||
# 处理 >x<=y 的情况（虽然不常见）
|
||||
return (values > numbers[0]) & (values <= numbers[1])
|
||||
elif '>' in range_str and '~' in range_str:
|
||||
return (values > numbers[0]) & (values <= numbers[1])
|
||||
elif '>' in range_str:
|
||||
return values > numbers[0]
|
||||
elif '<=' in range_str:
|
||||
return values <= numbers[0]
|
||||
elif '~' in range_str:
|
||||
return (values > numbers[0]) & (values <= numbers[1])
|
||||
else:
|
||||
# 如果是单个数字
|
||||
try:
|
||||
return values == float(range_str)
|
||||
except ValueError:
|
||||
raise ValueError(f"无法解析的范围字符串: '{range_str}'")
|
||||
59
tools/core/utils/excel_utils.py
Normal file
59
tools/core/utils/excel_utils.py
Normal file
@@ -0,0 +1,59 @@
|
||||
# utils/excel_utils.py
|
||||
import re
|
||||
from openpyxl.styles import Font, Alignment, Border, Side
|
||||
from openpyxl.utils import get_column_letter
|
||||
from openpyxl.worksheet.worksheet import Worksheet
|
||||
|
||||
class ExcelStyleUtils:
|
||||
"""Excel样式工具类"""
|
||||
@staticmethod
|
||||
def set_style(
|
||||
ws: Worksheet,
|
||||
cell_range: str,
|
||||
font: Font=Font(name='宋体', size=11),
|
||||
align: Alignment=Alignment(horizontal='center', vertical='center', wrap_text=True),
|
||||
border: Border=Border(left=Side(style='thin'), right=Side(style='thin'),top=Side(style='thin'), bottom=Side(style='thin'))):
|
||||
"""设置单元格样式"""
|
||||
if cell_range:
|
||||
for row in ws[cell_range]:
|
||||
for cell in row:
|
||||
cell.font = font
|
||||
cell.alignment = align
|
||||
cell.border = border
|
||||
|
||||
@staticmethod
|
||||
def auto_adjust_column_width(ws: Worksheet):
|
||||
"""自动调整列宽"""
|
||||
dims = {}
|
||||
for row in ws.rows:
|
||||
for cell in row:
|
||||
if cell.value:
|
||||
merged_range = next((range for range in ws.merged_cells.ranges if cell.coordinate in range), None)
|
||||
if get_merge_type(merged_range) == 'column':
|
||||
continue
|
||||
cell_len = 0.7 * len(re.findall('([\u4e00-\u9fa5])', str(cell.value))) + len(str(cell.value))
|
||||
dims[cell.column] = max(dims.get(cell.column, 0), cell_len)
|
||||
# 设置列宽
|
||||
for col, value in dims.items():
|
||||
ws.column_dimensions[get_column_letter(int(col))].width = value + 5
|
||||
|
||||
# 判断单元格类型
|
||||
def get_merge_type(merged_range):
|
||||
"""
|
||||
判断合并类型
|
||||
返回: 'row'（行合并）, 'column'（列合并）, 'both'（行列合并）或 None（不是合并单元格）
|
||||
"""
|
||||
if not merged_range:
|
||||
return None
|
||||
|
||||
min_row, max_row = merged_range.min_row, merged_range.max_row
|
||||
min_col, max_col = merged_range.min_col, merged_range.max_col
|
||||
|
||||
if max_row > min_row and max_col > min_col:
|
||||
return 'both' # 同时跨行和跨列
|
||||
elif max_row > min_row:
|
||||
return 'row' # 行合并（垂直合并）
|
||||
elif max_col > min_col:
|
||||
return 'column' # 列合并（水平合并）
|
||||
else:
|
||||
return None # 实际上不是合并单元格
|
||||
147
tools/core/utils/math_utils.py
Normal file
147
tools/core/utils/math_utils.py
Normal file
@@ -0,0 +1,147 @@
|
||||
from typing import List, Union
|
||||
|
||||
import numpy as np
|
||||
|
||||
|
||||
# 解决百分比相加不为100%
|
||||
def fix_percentages(values: List[float], total: float) -> List[float]:
|
||||
"""
|
||||
修正百分比相加不为100%的问题。
|
||||
|
||||
Args:
|
||||
values (list[float]): 百分比列表，元素个数与总和相同
|
||||
total (float): 总和
|
||||
|
||||
Returns:
|
||||
list[float]: 修正后的百分比列表
|
||||
|
||||
Examples:
|
||||
>>> values = [0.2, 0.3, 0.5]
|
||||
>>> total = 1
|
||||
>>> fix_percentages(values, total)
|
||||
[20.0, 30.0, 50.0]
|
||||
|
||||
>>> values = [0.2, 0.3, 0.5]
|
||||
>>> total = 0.8
|
||||
>>> fix_percentages(values, total)
|
||||
[25.0, 37.5, 62.5]
|
||||
"""
|
||||
exact = [v / total * 100 for v in values]
|
||||
floor = [np.floor(p * 100) / 100 for p in exact] # 向下取整到2位小数
|
||||
remainders = [exact[i] - floor[i] for i in range(len(exact))]
|
||||
|
||||
# 需要分配的百分点数（以0.01%为单位）
|
||||
to_distribute = int(round(10000 - sum(floor) * 100))
|
||||
|
||||
# 按余数大小分配
|
||||
indices = sorted(range(len(remainders)), key=lambda i: remainders[i], reverse=True)
|
||||
|
||||
fixed = floor.copy()
|
||||
for i in range(to_distribute):
|
||||
fixed[indices[i]] += 0.01
|
||||
|
||||
return [round(p, 2) for p in fixed]
|
||||
|
||||
|
||||
# === 误差矫正 ===
|
||||
def correct_rounding_error(target_total:Union[int,float], adjusted_areas:List[float], original_areas:List[float]) -> List[int]:
|
||||
"""
|
||||
健壮的数值舍入误差矫正函数：将浮点型面积值四舍五入后，调整至目标总和。
|
||||
核心逻辑：基于原始数值的小数部分优先级，逐次增减1来抵消舍入误差，确保最终总和匹配目标值，
|
||||
同时避免调整后数值出现负数，防止无限循环。
|
||||
|
||||
Args:
|
||||
target_total (int/float): 目标总和（最终舍入后数值的合计值），函数内部会转为整型
|
||||
adjusted_areas (list[float]): 经过比例调整后的浮点型面积列表（待舍入的原始数据）
|
||||
original_areas (list[float]): 调整前的原始浮点型面积列表（用于计算小数部分优先级）
|
||||
|
||||
Returns:
|
||||
list[int]: 矫正后的整型面积列表，总和尽可能接近/等于target_total；
|
||||
若无法完全矫正，返回尽可能接近的结果并打印警告
|
||||
|
||||
Raises:
|
||||
无显式抛出异常，所有异常会被捕获并打印错误信息，返回保底的四舍五入结果
|
||||
|
||||
Notes:
|
||||
1. 误差矫正规则：
|
||||
- 误差>0（当前总和 < 目标总和）：优先给小数部分大的数值+1
|
||||
- 误差<0（当前总和 > 目标总和）：优先给小数部分小的数值-1
|
||||
2. 边界限制：调整时确保数值≥0（避免出现负数面积）
|
||||
3. 防无限循环：最大迭代次数为 len(adjusted_areas) * 10，超出则终止并提示剩余误差
|
||||
|
||||
Examples:
|
||||
>>> target = 10
|
||||
>>> adjusted = [3.2, 2.8, 4.1] # 四舍五入后总和=3+3+4=10，无误差
|
||||
>>> original = [3.2, 2.8, 4.1]
|
||||
>>> correct_rounding_error(target, adjusted, original)
|
||||
[3, 3, 4]
|
||||
|
||||
>>> target = 10
|
||||
>>> adjusted = [3.1, 2.1, 4.1] # 四舍五入后总和=3+2+4=9，误差+1
|
||||
>>> original = [3.1, 2.1, 4.1]
|
||||
>>> correct_rounding_error(target, adjusted, original)
|
||||
[3, 2, 5] # 优先给小数部分最大的4.1+1
|
||||
|
||||
>>> target = 8
|
||||
>>> adjusted = [3.9, 2.9, 1.9] # 四舍五入后总和=4+3+2=9，误差-1
|
||||
>>> original = [3.9, 2.9, 1.9]
|
||||
>>> correct_rounding_error(target, adjusted, original)
|
||||
[3, 3, 2] # 优先给小数部分最小的1.9-1（实际小数1.9>2.9>3.9，故调整3.9）
|
||||
"""
|
||||
try:
|
||||
target_total = int(target_total)
|
||||
rounded_areas = [int(round(area)) for area in adjusted_areas]
|
||||
current_total = sum(rounded_areas)
|
||||
error = target_total - current_total
|
||||
|
||||
if error == 0 or len(adjusted_areas) == 0:
|
||||
return rounded_areas
|
||||
|
||||
# 使用循环分配直到误差为0或无法再分配
|
||||
remaining_error = error
|
||||
max_iterations = len(adjusted_areas) * 10 # 防止无限循环
|
||||
|
||||
for _ in range(max_iterations):
|
||||
if remaining_error == 0:
|
||||
break
|
||||
|
||||
# 每次迭代重新计算小数部分和排序
|
||||
decimal_parts = [float(area - int(area)) for area in original_areas]
|
||||
indices = list(range(len(adjusted_areas)))
|
||||
|
||||
if remaining_error > 0:
|
||||
indices.sort(key=lambda i: decimal_parts[i], reverse=True)
|
||||
adjustment = 1
|
||||
else:
|
||||
indices.sort(key=lambda i: decimal_parts[i])
|
||||
adjustment = -1
|
||||
|
||||
# 尝试分配一次调整
|
||||
adjusted = False
|
||||
for idx in indices:
|
||||
if (adjustment == 1 and rounded_areas[idx] >= 0) or (adjustment == -1 and rounded_areas[idx] > 0):
|
||||
rounded_areas[idx] += adjustment
|
||||
remaining_error -= adjustment
|
||||
adjusted = True
|
||||
break
|
||||
|
||||
if not adjusted: # 无法再调整
|
||||
break
|
||||
|
||||
if remaining_error != 0:
|
||||
print(f"警告：无法完全矫正误差，剩余: {remaining_error}")
|
||||
|
||||
return rounded_areas
|
||||
|
||||
except Exception as e:
|
||||
print(f"误差矫正出错: {e}")
|
||||
# 返回原始四舍五入结果作为保底
|
||||
return [int(round(area)) for area in adjusted_areas]
|
||||
|
||||
if __name__ == '__main__':
|
||||
target = 10
|
||||
adjusted = [3.3, 3.9, 4.2] # 四舍五入后总和=3+3+4=10，无误差
|
||||
original = [3.25, 2.85, 4.15]
|
||||
print(correct_rounding_error(target, adjusted, original))
|
||||
|
||||
|
||||
47
tools/core/utils/os_utils/temp_files_processor.py
Normal file
47
tools/core/utils/os_utils/temp_files_processor.py
Normal file
@@ -0,0 +1,47 @@
|
||||
import gc
|
||||
import sys
|
||||
import arcpy
|
||||
|
||||
# 临时文件清理
|
||||
def clean_up_temp_files(temp_files, workspace=None):
|
||||
"""安全清理临时文件和内存工作空间"""
|
||||
try:
|
||||
if temp_files:
|
||||
for temp_file in temp_files:
|
||||
if arcpy.Exists(temp_file):
|
||||
try:
|
||||
arcpy.management.Delete(temp_file)
|
||||
# print_status(f"已删除临时文件: {temp_file}")
|
||||
except Exception as delete_err:
|
||||
sys.stderr.write(f"CleanupError:无法删除临时文件 {temp_file}: {str(delete_err)}\n")
|
||||
|
||||
# 清理内存工作空间 (确保在 in_memory 工作空间中操作，而不是删除其他地方的同名项)
|
||||
try:
|
||||
# 切换到内存工作空间进行清理
|
||||
if arcpy.Exists("in_memory"):
|
||||
arcpy.env.workspace = "in_memory"
|
||||
# 删除内存工作空间中的所有内容
|
||||
for item in arcpy.ListDatasets() + arcpy.ListFeatureClasses() + arcpy.ListRasters():
|
||||
try:
|
||||
arcpy.management.Delete(item)
|
||||
# print_status(f"已清理内存项: in_memory/{item}")
|
||||
except Exception as delete_mem_item_err:
|
||||
sys.stderr.write(f"CleanupError:无法清理内存项 in_memory/{item}: {str(delete_mem_item_err)}\n")
|
||||
|
||||
except Exception as delete_in_memory_err:
|
||||
sys.stderr.write(f"CleanupError:清理 in_memory 工作空间时发生错误: {str(delete_in_memory_err)}\n")
|
||||
|
||||
# 恢复原始工作空间
|
||||
if workspace and arcpy.Exists(workspace):
|
||||
try:
|
||||
arcpy.env.workspace = workspace
|
||||
arcpy.management.ClearWorkspaceCache()
|
||||
except Exception as restore_ws_err:
|
||||
sys.stderr.write(f"CleanupError:无法恢复原始工作空间 {workspace}: {str(restore_ws_err)}\n")
|
||||
|
||||
except Exception as cleanup_err:
|
||||
# 外层异常捕获
|
||||
sys.stderr.write(f"CleanupError:清理临时文件过程中发生未预料的错误: {str(cleanup_err)}\n")
|
||||
|
||||
# 强制垃圾回收
|
||||
gc.collect()
|
||||
201
tools/core/utils/平差工具.py
Normal file
201
tools/core/utils/平差工具.py
Normal file
@@ -0,0 +1,201 @@
|
||||
# 获取每个一级地类面积，主要是12类
|
||||
import arcpy
|
||||
import numpy as np
|
||||
import pandas as pd
|
||||
from .math_utils import correct_rounding_error
|
||||
|
||||
|
||||
# 获取目标面积
|
||||
def get_area_by_group(dltb_class_feature, excel_target_path, xzqmc, is_by_xzq=False):
|
||||
try:
|
||||
# 读取目标面积Excel文件
|
||||
target_df = pd.read_excel(excel_target_path)
|
||||
|
||||
# 确保列名匹配
|
||||
target_df.columns = target_df.columns.str.strip()
|
||||
|
||||
if is_by_xzq:
|
||||
# 地类编码映射字典
|
||||
land_type_mapping = {
|
||||
'耕地': '01',
|
||||
'园地': '02',
|
||||
'林地': '03',
|
||||
'草地': '04',
|
||||
'其他地类': '12'
|
||||
}
|
||||
|
||||
# 方法1：重命名列后转换为字典
|
||||
df_encoded = target_df.rename(columns=land_type_mapping)
|
||||
result_dict = df_encoded.set_index('行政单位').to_dict('index')
|
||||
|
||||
return result_dict
|
||||
|
||||
# 检查要素类是否存在
|
||||
if not arcpy.Exists(dltb_class_feature):
|
||||
print(f"警告：输入要素类不存在: {dltb_class_feature}")
|
||||
else:
|
||||
# 转为numpy数组供pandas统计使用
|
||||
df = pd.DataFrame(arcpy.da.TableToNumPyArray(dltb_class_feature, ["YJDLBM", "TBDLMJ"], skip_nulls=False, null_value=np.nan))
|
||||
qtdl_df = df[df['YJDLBM'] == '12']
|
||||
if qtdl_df['TBDLMJ'].isnull().any() or qtdl_df['TBDLMJ'].eq(0).any():
|
||||
print("警告：其他地类TBDLMJ字段 存在空值或无效的记录，将不平差其他地类")
|
||||
target_areas = {}
|
||||
else:
|
||||
area_by_group = df.groupby("YJDLBM")["TBDLMJ"].sum()
|
||||
|
||||
for key in area_by_group.keys():
|
||||
area_by_group[key] = area_by_group[key] * 0.0015
|
||||
|
||||
target_areas = area_by_group.to_dict()
|
||||
|
||||
# 获取铁山港区的目标面积
|
||||
gangnan_target = target_df[target_df['行政单位'] == xzqmc]
|
||||
|
||||
if gangnan_target.empty:
|
||||
print(f"警告：未找到{xzqmc}的目标面积数据,将使用TBDLMJ数据进行平差")
|
||||
return target_areas
|
||||
|
||||
# 提取各土地利用类型的目标面积
|
||||
landuse_types = {'01':'耕地', '02':'园地', '03':'林地', '04':'草地', '12':'其他地类'}
|
||||
|
||||
for dlbm, dlmc in landuse_types.items():
|
||||
if dlmc in gangnan_target.columns:
|
||||
if gangnan_target[dlmc].values[0] and not np.isnan(gangnan_target[dlmc].values[0]):
|
||||
target_areas[dlbm] = gangnan_target[dlmc].values[0]
|
||||
|
||||
return target_areas
|
||||
|
||||
except Exception as e:
|
||||
print(f"计算面积时出错: {str(e)}")
|
||||
return {}
|
||||
|
||||
# 按地类平差（全区统一平差）
|
||||
def adjust_area_statistics(stats_df, target_areas):
|
||||
"""
|
||||
根据Excel中的目标面积对统计数据进行平差处理
|
||||
|
||||
Parameters:
|
||||
stats_df: 原始统计数据DataFrame
|
||||
excel_target_path: 包含目标面积的Excel文件路径
|
||||
|
||||
Returns:
|
||||
adjusted_df: 平差后的DataFrame
|
||||
"""
|
||||
try:
|
||||
if target_areas is None:
|
||||
print("警告：目标面积数据为空，不进行平差")
|
||||
return stats_df
|
||||
|
||||
# 准备平差数据
|
||||
adjusted_df = stats_df.copy()
|
||||
if "YJDLBM" not in adjusted_df.columns:
|
||||
dlbm = "YNDLBM"
|
||||
else:
|
||||
dlbm = "YJDLBM"
|
||||
|
||||
adjusted_df['adjusted_area'] = adjusted_df['temp_area']
|
||||
adjusted_df['adjustment_factor'] = 1.0
|
||||
|
||||
# 计算每个地类的原始总面积
|
||||
original_totals = stats_df.groupby(dlbm)['temp_area'].sum().to_dict()
|
||||
|
||||
# 对每个地类进行平差
|
||||
for yjdl, target_area in target_areas.items():
|
||||
if (yjdl in original_totals and original_totals[yjdl] > 0) or target_area > 0:
|
||||
adjustment_factor = target_area / original_totals[yjdl]
|
||||
|
||||
# 应用平差系数
|
||||
mask = adjusted_df[dlbm] == yjdl
|
||||
adjusted_df.loc[mask, 'adjusted_area'] = adjusted_df.loc[mask, 'temp_area'] * adjustment_factor
|
||||
adjusted_df.loc[mask, 'adjustment_factor'] = adjustment_factor
|
||||
|
||||
# 应用误差矫正，确保总和等于目标值
|
||||
adjusted_areas = adjusted_df.loc[mask, 'adjusted_area'].tolist()
|
||||
original_areas = stats_df.loc[mask, 'temp_area'].tolist()
|
||||
corrected_areas = correct_rounding_error(target_area, adjusted_areas, original_areas)
|
||||
adjusted_df.loc[mask, 'adjusted_area'] = corrected_areas
|
||||
|
||||
print(f"地类 {yjdl}: 平差系数 = {adjustment_factor:.6f}, 目标面积 = {target_area}, 矫正后总面积 = {sum(corrected_areas)}")
|
||||
|
||||
return adjusted_df
|
||||
|
||||
except Exception as e:
|
||||
print(f"平差处理失败: {e}")
|
||||
return stats_df
|
||||
|
||||
# 按行政区+地类进行平差
|
||||
def adjust_by_district_landuse(stats_df:pd.DataFrame, target_areas_dict:dict):
|
||||
"""
|
||||
按行政区+地类进行平差
|
||||
|
||||
Parameters:
|
||||
stats_df: 原始统计数据DataFrame
|
||||
target_areas_dict: 目标面积字典，格式：{'行政区': {'地类': 目标面积}}
|
||||
|
||||
Returns:
|
||||
adjusted_df: 平差后的DataFrame
|
||||
"""
|
||||
# 复制原始数据
|
||||
adjusted_df = stats_df.copy()
|
||||
adjusted_df['adjusted_area'] = adjusted_df['temp_area']
|
||||
adjusted_df['adjustment_factor'] = 1.0
|
||||
|
||||
# 获取所有存在的行政区和地类
|
||||
existing_districts = adjusted_df['XZQMC'].unique()
|
||||
|
||||
# 检查目标字典中的行政区是否存在
|
||||
missing_districts = []
|
||||
tt = [td for td in target_areas_dict.keys()]
|
||||
for ed in existing_districts:
|
||||
if ed not in tt:
|
||||
missing_districts.append(ed)
|
||||
|
||||
# 如果有行政区不存在，返回原始数据并提示
|
||||
if missing_districts:
|
||||
print(f"警告：平差数据中不存在行政区: {missing_districts}，未进行平差")
|
||||
return stats_df
|
||||
|
||||
# 计算每个行政区每个地类的原始总面积
|
||||
original_totals = stats_df.groupby(['XZQMC', 'YJDLBM'])['temp_area'].sum()
|
||||
|
||||
# 对每个行政区的每个地类进行平差
|
||||
for xzqmc, landuse_targets in target_areas_dict.items():
|
||||
for yjdl, target_area in landuse_targets.items():
|
||||
# 检查该行政区是否有此地类数据
|
||||
if (xzqmc, yjdl) in original_totals.index and original_totals.at[(xzqmc, yjdl)] > 0:
|
||||
adjustment_factor = target_area / original_totals[(xzqmc, yjdl)]
|
||||
|
||||
# 应用平差系数
|
||||
mask = (adjusted_df['XZQMC'] == xzqmc) & (adjusted_df['YJDLBM'] == yjdl)
|
||||
adjusted_df.loc[mask, 'adjusted_area'] = adjusted_df.loc[mask, 'temp_area'] * adjustment_factor
|
||||
adjusted_df.loc[mask, 'adjustment_factor'] = adjustment_factor
|
||||
|
||||
# 应用误差矫正，确保总和等于目标值
|
||||
adjusted_areas = adjusted_df.loc[mask, 'adjusted_area'].tolist()
|
||||
original_areas = stats_df.loc[mask, 'temp_area'].tolist()
|
||||
corrected_areas = correct_rounding_error(target_area, adjusted_areas, original_areas)
|
||||
adjusted_df.loc[mask, 'adjusted_area'] = corrected_areas
|
||||
|
||||
print(f"{xzqmc} - 地类 {yjdl}: 平差系数 = {adjustment_factor:.6f}, 目标面积 = {target_area}, 矫正后总面积 = {sum(corrected_areas)}")
|
||||
|
||||
return adjusted_df
|
||||
|
||||
|
||||
def get_target_areas(excel_path:str, sheet_name:str, xzqmc:str) -> pd.DataFrame:
|
||||
df_excel = pd.read_excel(excel_path, sheet_name)
|
||||
target_df = df_excel[df_excel['行政单位'] == xzqmc]
|
||||
|
||||
df_area_for_merge = target_df.set_index('行政单位').iloc[0].reset_index(name='面积').rename(columns={'index': 'EJDL'})
|
||||
|
||||
return df_area_for_merge
|
||||
|
||||
def get_target_areas_by_group(excel_target_path):
|
||||
# 读取目标面积Excel文件
|
||||
target_df = pd.read_excel(excel_target_path,"Sheet1")
|
||||
|
||||
# 确保列名匹配
|
||||
target_df.columns = target_df.columns.str.strip()
|
||||
|
||||
result_dict = target_df.set_index('行政单位').to_dict('index')
|
||||
|
||||
return result_dict
|
||||
Reference in New Issue
Block a user