refactor: 重构项目结构，将geo_tools重命名为app并更新相关引用
- 将主包名从geo_tools改为app - 更新所有模块中的引用路径 - 迁移并更新测试用例 - 添加项目规则文档 - 保持原有功能不变，仅进行结构调整
This commit is contained in:
@@ -17,8 +17,8 @@ from pathlib import Path
|
||||
import sys
|
||||
sys.path.insert(0, str(Path(__file__).parent.parent))
|
||||
|
||||
import geo_tools
|
||||
from geo_tools.utils.logger import get_logger
|
||||
import app
|
||||
from app.utils.logger import get_logger
|
||||
|
||||
logger = get_logger("example_workflow")
|
||||
|
||||
@@ -29,37 +29,37 @@ OUTPUT_DIR.mkdir(exist_ok=True)
|
||||
|
||||
def main() -> None:
|
||||
logger.info("=" * 60)
|
||||
logger.info("geo_tools 端到端工作流示例 v%s", geo_tools.__version__)
|
||||
logger.info("geo_tools 端到端工作流示例 v%s", app.__version__)
|
||||
logger.info("=" * 60)
|
||||
|
||||
# ── 1. 读取示例点数据 ──────────────────────────────────────────
|
||||
logger.info("\n[步骤 1] 读取示例点数据（GeoJSON）")
|
||||
points = geo_tools.read_vector(DATA_DIR / "sample_points.geojson")
|
||||
points = app.read_vector(DATA_DIR / "sample_points.geojson")
|
||||
logger.info(" 读取完成：%d 条要素，CRS=%s", len(points), points.crs)
|
||||
logger.info(" 字段：%s", list(points.columns))
|
||||
|
||||
# ── 2. 读取示例面数据 ──────────────────────────────────────────
|
||||
logger.info("\n[步骤 2] 读取示例区域多边形（GeoJSON）")
|
||||
regions = geo_tools.read_vector(DATA_DIR / "sample_regions.geojson")
|
||||
regions = app.read_vector(DATA_DIR / "sample_regions.geojson")
|
||||
logger.info(" 区域列表：%s", regions["name"].tolist())
|
||||
|
||||
# ── 3. 数据校验 ───────────────────────────────────────────────
|
||||
logger.info("\n[步骤 3] 几何有效性校验")
|
||||
stats = geo_tools.validate_geometry(points)
|
||||
stats = app.validate_geometry(points)
|
||||
logger.info(" 点数据校验结果：%s", stats)
|
||||
stats = geo_tools.validate_geometry(regions)
|
||||
stats = app.validate_geometry(regions)
|
||||
logger.info(" 面数据校验结果：%s", stats)
|
||||
|
||||
# ── 4. 坐标系信息 ─────────────────────────────────────────────
|
||||
logger.info("\n[步骤 4] 查询 CRS 信息")
|
||||
crs_info = geo_tools.get_crs_info("EPSG:4326")
|
||||
crs_info = app.get_crs_info("EPSG:4326")
|
||||
logger.info(" WGS84 信息：%s", crs_info)
|
||||
proj_crs = geo_tools.suggest_projected_crs(116.4, 39.9)
|
||||
proj_crs = app.suggest_projected_crs(116.4, 39.9)
|
||||
logger.info(" 北京适合的投影 CRS：%s", proj_crs)
|
||||
|
||||
# ── 5. 重投影 ─────────────────────────────────────────────────
|
||||
logger.info("\n[步骤 5] 重投影到 Web Mercator（用于可视化）")
|
||||
points_3857 = geo_tools.reproject(points, "EPSG:3857")
|
||||
points_3857 = app.reproject(points, "EPSG:3857")
|
||||
logger.info(" 重投影完成：CRS=%s", points_3857.crs)
|
||||
|
||||
# ── 6. 面积加权均值 ───────────────────────────────────────────
|
||||
@@ -68,31 +68,31 @@ def main() -> None:
|
||||
points_buffered = points.to_crs("EPSG:3857").copy()
|
||||
points_buffered["geometry"] = points_buffered.geometry.buffer(100_000) # 100km缓冲
|
||||
points_buffered = points_buffered.to_crs("EPSG:4326")
|
||||
from geo_tools.analysis.stats import area_weighted_mean
|
||||
from app.analysis.stats import area_weighted_mean
|
||||
aw_result = area_weighted_mean(points_buffered, value_col="value")
|
||||
logger.info(" 全局面积加权均值：%.4f", aw_result["area_weighted_mean"])
|
||||
|
||||
# ── 7. 按位置选择 ─────────────────────────────────────────────
|
||||
logger.info("\n[步骤 7] 按位置选择：筛选华南区域内的城市")
|
||||
hua_nan = regions[regions["name"] == "华南"]
|
||||
points_in_huanan = geo_tools.select_by_location(points, hua_nan, predicate="intersects")
|
||||
points_in_huanan = app.select_by_location(points, hua_nan, predicate="intersects")
|
||||
logger.info(" 华南区域内的城市：%s", points_in_huanan["name"].tolist())
|
||||
|
||||
# ── 8. 统计汇总 ───────────────────────────────────────────────
|
||||
logger.info("\n[步骤 8] 属性统计汇总")
|
||||
from geo_tools.analysis.stats import summarize_attributes
|
||||
from app.analysis.stats import summarize_attributes
|
||||
summary = summarize_attributes(points, columns=["value"], group_col="category")
|
||||
logger.info(" 按分类汇总：\n%s", summary.to_string(index=False))
|
||||
|
||||
# ── 9. 写出结果 ───────────────────────────────────────────────
|
||||
logger.info("\n[步骤 9] 写出处理结果")
|
||||
out_geojson = OUTPUT_DIR / "result_points_3857.geojson"
|
||||
geo_tools.write_vector(points_3857, out_geojson)
|
||||
app.write_vector(points_3857, out_geojson)
|
||||
logger.info(" GeoJSON 写出：%s", out_geojson)
|
||||
|
||||
out_gpkg = OUTPUT_DIR / "results.gpkg"
|
||||
geo_tools.write_gpkg(points, out_gpkg, layer="original_points")
|
||||
geo_tools.write_gpkg(regions, out_gpkg, layer="regions", mode="a")
|
||||
app.write_gpkg(points, out_gpkg, layer="original_points")
|
||||
app.write_gpkg(regions, out_gpkg, layer="regions", mode="a")
|
||||
logger.info(" GPKG 写出（2 图层）：%s", out_gpkg)
|
||||
|
||||
logger.info("\n" + "=" * 60)
|
||||
|
||||
188
scripts/其他工具/A耕作层厚度栅格制作_新1.py
Normal file
188
scripts/其他工具/A耕作层厚度栅格制作_新1.py
Normal file
@@ -0,0 +1,188 @@
|
||||
import os
|
||||
from pathlib import Path
|
||||
import time
|
||||
|
||||
import geopandas as gpd
|
||||
from geopandas.io import file
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
|
||||
def assign_gzchd_flexible_v2(soil_prop, point_path, polygon_path, output_path):
|
||||
print("正在读取数据...")
|
||||
points = gpd.read_file(point_path)
|
||||
polygons = gpd.read_file(polygon_path)
|
||||
|
||||
# 1. 坐标系转换
|
||||
if points.crs != polygons.crs:
|
||||
print(f"坐标系不一致，正在转换点数据...")
|
||||
points = points.to_crs(polygons.crs)
|
||||
|
||||
# 2. 预处理, 判断样点是否存在TZ字段，如果不存在，则用TDLYLX字段代替,并将其转为字符串类型,如果两个字段都不存在，则报错
|
||||
if 'TZ' not in points.columns:
|
||||
if 'TDLYLX' in points.columns:
|
||||
points['TZ'] = points['TDLYLX'].astype(str).str.strip()
|
||||
else:
|
||||
raise ValueError("点要素类中不存在TZ或TDLYLX字段，无法进行匹配！")
|
||||
else:
|
||||
points['TZ'] = points['TZ'].astype(str).str.strip()
|
||||
|
||||
polygons['TZ'] = polygons['TZ'].astype(str).str.strip()
|
||||
|
||||
# 确保 GZCHD 是数值类型，避免合并时类型冲突
|
||||
points[soil_prop] = pd.to_numeric(points[soil_prop], errors='coerce').fillna(0)
|
||||
|
||||
if soil_prop in polygons.columns:
|
||||
polygons = polygons.drop(columns=[soil_prop])
|
||||
|
||||
# 辅助函数：按指定字段分组进行最近点匹配
|
||||
def match_by_attribute(poly_gdf, pt_gdf, attr_name, suffix):
|
||||
if attr_name not in poly_gdf.columns or attr_name not in pt_gdf.columns:
|
||||
return None, []
|
||||
|
||||
poly_sub = poly_gdf[poly_gdf[attr_name].notna()].copy()
|
||||
point_sub = pt_gdf[pt_gdf[attr_name].notna()].copy()
|
||||
|
||||
if poly_sub.empty or point_sub.empty:
|
||||
return None, []
|
||||
|
||||
poly_sub[attr_name] = poly_sub[attr_name].astype(str).str.strip()
|
||||
point_sub[attr_name] = point_sub[attr_name].astype(str).str.strip()
|
||||
|
||||
common_values = set(poly_sub[attr_name].unique()) & set(point_sub[attr_name].unique())
|
||||
if not common_values:
|
||||
return None, []
|
||||
|
||||
matched_parts = []
|
||||
matched_ids = []
|
||||
for value in common_values:
|
||||
poly_part = poly_sub[poly_sub[attr_name] == value].copy()
|
||||
point_part = point_sub[point_sub[attr_name] == value][[soil_prop, 'geometry']].copy()
|
||||
if poly_part.empty or point_part.empty:
|
||||
continue
|
||||
|
||||
matched_part = gpd.sjoin_nearest(poly_part, point_part, how='left', rsuffix=suffix)
|
||||
matched_part = matched_part[~matched_part.index.duplicated(keep='first')]
|
||||
if not matched_part.empty:
|
||||
matched_parts.append(matched_part)
|
||||
matched_ids.extend(matched_part.index.tolist())
|
||||
|
||||
if matched_parts:
|
||||
return pd.concat(matched_parts), matched_ids
|
||||
return None, []
|
||||
|
||||
matched_results = []
|
||||
matched_indices = []
|
||||
|
||||
# --- 第一步：按相同 TZ 匹配 ---
|
||||
print("步骤 1: 正在匹配相同 TZ 的最近点...")
|
||||
first_matched, first_ids = match_by_attribute(polygons, points, 'TZ', '_p1')
|
||||
if first_matched is not None and not first_matched.empty:
|
||||
matched_results.append(first_matched)
|
||||
matched_indices.extend(first_ids)
|
||||
|
||||
# --- 第二步：按 TS 匹配未匹配面 ---
|
||||
unmatched_mask = ~polygons.index.isin(matched_indices)
|
||||
remaining_polygons = polygons[unmatched_mask].copy()
|
||||
print(f"步骤 2: 正在为 {len(remaining_polygons)} 个要素匹配 TS 最近点...")
|
||||
|
||||
if not remaining_polygons.empty:
|
||||
ts_matched, ts_ids = match_by_attribute(remaining_polygons, points, 'TS', '_p_ts')
|
||||
if ts_matched is not None and not ts_matched.empty:
|
||||
matched_results.append(ts_matched)
|
||||
matched_indices.extend(ts_ids)
|
||||
remaining_polygons = polygons[~polygons.index.isin(matched_indices)].copy()
|
||||
print(f"已匹配 TS: {len(ts_ids)} 个要素，剩余 {len(remaining_polygons)} 个。")
|
||||
else:
|
||||
print("未匹配到 TS 类型要素，继续下一步。")
|
||||
|
||||
# --- 第三步：按 YL 匹配未匹配面 ---
|
||||
if not remaining_polygons.empty:
|
||||
print(f"步骤 3: 正在为 {len(remaining_polygons)} 个要素匹配 YL 最近点...")
|
||||
yl_matched, yl_ids = match_by_attribute(remaining_polygons, points, 'YL', '_p_yl')
|
||||
if yl_matched is not None and not yl_matched.empty:
|
||||
matched_results.append(yl_matched)
|
||||
matched_indices.extend(yl_ids)
|
||||
remaining_polygons = polygons[~polygons.index.isin(matched_indices)].copy()
|
||||
print(f"已匹配 YL: {len(yl_ids)} 个要素，剩余 {len(remaining_polygons)} 个。")
|
||||
else:
|
||||
print("未匹配到 YL 类型要素，继续下一步。")
|
||||
|
||||
# --- 第四步：按 TL 匹配未匹配面 ---
|
||||
if not remaining_polygons.empty:
|
||||
print(f"步骤 4: 正在为 {len(remaining_polygons)} 个要素匹配 TL 最近点...")
|
||||
tl_matched, tl_ids = match_by_attribute(remaining_polygons, points, 'TL', '_p_tl')
|
||||
if tl_matched is not None and not tl_matched.empty:
|
||||
matched_results.append(tl_matched)
|
||||
matched_indices.extend(tl_ids)
|
||||
remaining_polygons = polygons[~polygons.index.isin(matched_indices)].copy()
|
||||
print(f"已匹配 TL: {len(tl_ids)} 个要素，剩余 {len(remaining_polygons)} 个。")
|
||||
else:
|
||||
print("未匹配到 TL 类型要素，继续全局最近点。")
|
||||
|
||||
else:
|
||||
print("没有未匹配的面要素，跳过 TS/YL/TL 匹配。")
|
||||
|
||||
# --- 最后：全局最近点匹配剩余面 ---
|
||||
unmatched_mask = ~polygons.index.isin(matched_indices)
|
||||
remaining_polygons = polygons[unmatched_mask].copy()
|
||||
print(f"最后一步: 正在为 {len(remaining_polygons)} 个要素匹配全局最近点...")
|
||||
|
||||
if not remaining_polygons.empty:
|
||||
point_pool = points[[soil_prop, 'geometry']]
|
||||
step_final = gpd.sjoin_nearest(remaining_polygons, point_pool, how='left', rsuffix='_p2')
|
||||
step_final = step_final[~step_final.index.duplicated(keep='first')]
|
||||
matched_results.append(step_final)
|
||||
|
||||
# --- 第三步：稳健合并 ---
|
||||
print("正在合并数据...")
|
||||
# 过滤掉列表中可能的 None 或空 DataFrame，防止 FutureWarning
|
||||
to_concat = [res for res in matched_results if res is not None and not res.empty]
|
||||
|
||||
if to_concat:
|
||||
final_gdf = pd.concat(to_concat)
|
||||
else:
|
||||
# 如果没有任何匹配结果，返回带空 GZCHD 的原面要素
|
||||
final_gdf = polygons.copy()
|
||||
final_gdf[soil_prop] = 0
|
||||
|
||||
# --- 4. 清理与保存 ---
|
||||
# 删除临时列
|
||||
cols_to_drop = [
|
||||
c for c in final_gdf.columns
|
||||
if 'index_' in c
|
||||
or '_p1' in c
|
||||
or '_p2' in c
|
||||
or '_p_ts' in c
|
||||
or '_p_yl' in c
|
||||
or '_p_tl' in c
|
||||
]
|
||||
final_gdf = final_gdf.drop(columns=cols_to_drop)
|
||||
|
||||
# 强制去重复列名
|
||||
final_gdf = final_gdf.loc[:, ~final_gdf.columns.duplicated()]
|
||||
|
||||
# 填充空值并确保类型一致
|
||||
if soil_prop in final_gdf.columns:
|
||||
final_gdf[soil_prop] = final_gdf[soil_prop].fillna(0)
|
||||
else:
|
||||
final_gdf[soil_prop] = 0
|
||||
|
||||
print(f"正在保存结果至: {output_path}")
|
||||
final_gdf.to_file(output_path, encoding='utf-8')
|
||||
print("处理完成！")
|
||||
|
||||
return final_gdf
|
||||
|
||||
if __name__ == "__main__":
|
||||
# 遍历文件夹中所有样点shp文件，并进行处理
|
||||
shp_file = r"E:\@三普属性图出图\测试\YXTCHD.shp" # 样点数据文件夹
|
||||
dltb_file = r"E:\@三普属性图出图\广西天峨县\@基础数据\土壤类型图\土壤类型图.shp" # 耕地图斑
|
||||
output_folder = r"E:\@三普属性图出图\广西天峨县" # 输出文件夹
|
||||
|
||||
assign_gzchd_flexible_v2(
|
||||
soil_prop= "YXTCHD", # 耕地层厚度字段名
|
||||
point_path=shp_file, # 样点数据
|
||||
polygon_path= dltb_file,
|
||||
output_path=fr'{output_folder}\YXTCHD.shp' # 输出文件
|
||||
)
|
||||
time.sleep(2) # 防止文件读写冲突
|
||||
404
scripts/其他工具/样点剔除统计表格.py
Normal file
404
scripts/其他工具/样点剔除统计表格.py
Normal file
@@ -0,0 +1,404 @@
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
import os
|
||||
import geopandas as gpd
|
||||
from openpyxl import Workbook
|
||||
from openpyxl.styles import Alignment, Font, Border, Side
|
||||
from openpyxl.utils import get_column_letter
|
||||
|
||||
# 定义指标代码与单位的对应关系
|
||||
INDICATOR_UNITS = {
|
||||
# 基本指标
|
||||
'PH': ('pH', '-'),
|
||||
'ECA': ('交换性钙', 'cmol(½Ca²⁺)/kg'),
|
||||
'EMG': ('交换性镁', 'cmol(½Mg²⁺)/kg'),
|
||||
'TN': ('全氮', 'g/kg'),
|
||||
'TP': ('全磷', 'g/kg'),
|
||||
'TK': ('全钾', 'g/kg'),
|
||||
'AS1': ('有效硫', 'mg/kg'),
|
||||
'AB': ('有效硼', 'mg/kg'),
|
||||
'AP': ('有效磷', 'mg/kg'),
|
||||
'AFE': ('有效铁', 'mg/kg'),
|
||||
'ACU': ('有效铜', 'mg/kg'),
|
||||
'AZN': ('有效锌', 'mg/kg'),
|
||||
'AMN': ('有效锰', 'mg/kg'),
|
||||
'OM': ('有机质', 'g/kg'),
|
||||
'GZCHD': ('耕层厚度', 'cm'),
|
||||
'AK': ('速效钾', 'mg/kg'),
|
||||
'CEC': ('阳离子交换量', 'cmol/kg'),
|
||||
# 特殊指标 - 根据文件名对应字段
|
||||
'FL': ('粉粒', '%'),
|
||||
'NL': ('黏粒', '%'),
|
||||
'SL': ('砂粒', '%'),
|
||||
'TRRZPJZ': ('土壤容重', 'g/cm³'),
|
||||
'TRZD': ('土壤质地', '分类'),
|
||||
# 其他可能指标
|
||||
'AMO': ('有效钼', 'mg/kg'),
|
||||
'TSE': ('全硒', 'mg/kg'),
|
||||
'YXTCHD': ('有效土层厚度', 'cm')
|
||||
}
|
||||
|
||||
# 文件名到字段的映射
|
||||
FILENAME_TO_FIELD = {
|
||||
'粉粒': 'FL',
|
||||
'黏粒': 'NL',
|
||||
'砂粒': 'SL',
|
||||
'表层容重': 'TRRZPJZ',
|
||||
'土壤质地十二级分类': 'TRZD',
|
||||
'双江县YXTCHD': 'YXTCHD'
|
||||
}
|
||||
|
||||
# 扩展字段别名映射，支持更多pH字段名
|
||||
FIELD_ALIASES = {
|
||||
'PH': ['pH', 'PH', 'ph'], # 支持pH的各种大小写形式
|
||||
'ECA': ['交换性钙', 'ECA'],
|
||||
'EMG': ['交换性镁', 'EMG'],
|
||||
'TN': ['全氮', 'TN'],
|
||||
'TP': ['全磷', 'TP'],
|
||||
'TK': ['全钾', 'TK'],
|
||||
'AS1': ['有效硫', 'AS1'],
|
||||
'AB': ['有效硼', 'AB'],
|
||||
'AP': ['有效磷', 'AP'],
|
||||
'AFE': ['有效铁', 'AFE'],
|
||||
'ACU': ['有效铜', 'ACU'],
|
||||
'AZN': ['有效锌', 'AZN'],
|
||||
'AMN': ['有效锰', 'AMN'],
|
||||
'OM': ['有机质', 'OM'],
|
||||
'GZCHD': ['耕层厚度', 'GZCHD'],
|
||||
'AK': ['速效钾', 'AK'],
|
||||
'CEC': ['阳离子交换量', 'CEC'],
|
||||
'FL': ['粉粒', 'FL'],
|
||||
'NL': ['黏粒', 'NL'],
|
||||
'SL': ['砂粒', 'SL'],
|
||||
'TRRZPJZ': ['土壤容重', 'TRRZPJZ'],
|
||||
'TRZD': ['土壤质地', 'TRZD'],
|
||||
'AMO': ['有效钼', 'AMO'],
|
||||
'TSE': ['全硒', 'TSE'],
|
||||
'YXTCHD': ['有效土层厚度', 'YXTCHD']
|
||||
}
|
||||
|
||||
|
||||
def find_shapefiles(folder_path):
|
||||
"""在文件夹中递归查找所有的Shapefile文件"""
|
||||
shapefiles = []
|
||||
|
||||
for root, dirs, files in os.walk(folder_path):
|
||||
for file in files:
|
||||
if file.lower().endswith('.shp'):
|
||||
shapefiles.append(os.path.join(root, file))
|
||||
|
||||
return shapefiles
|
||||
|
||||
|
||||
def read_shapefile_data(shapefile_path):
|
||||
"""读取Shapefile数据并返回属性表"""
|
||||
try:
|
||||
print(f" 读取Shapefile: {os.path.basename(shapefile_path)}")
|
||||
gdf = gpd.read_file(shapefile_path, encoding='utf-8')
|
||||
|
||||
print(f" 要素数量: {len(gdf)}")
|
||||
print(f" 属性字段: {list(gdf.columns)}")
|
||||
|
||||
return gdf
|
||||
except Exception as e:
|
||||
print(f" 读取Shapefile失败: {e}")
|
||||
try:
|
||||
gdf = gpd.read_file(shapefile_path, encoding='gbk')
|
||||
print(f" 使用GBK编码成功读取")
|
||||
return gdf
|
||||
except:
|
||||
return None
|
||||
|
||||
|
||||
def get_indicator_data(gdf, filename):
|
||||
"""从GeoDataFrame中获取指标数据，使用统一字段匹配逻辑"""
|
||||
indicator_data = {}
|
||||
|
||||
basename = os.path.basename(filename).replace('.shp', '')
|
||||
|
||||
# 1. 首先尝试文件名映射
|
||||
target_field = None
|
||||
if basename in FILENAME_TO_FIELD:
|
||||
target_field = FILENAME_TO_FIELD[basename]
|
||||
if target_field in gdf.columns:
|
||||
indicator_data[target_field] = gdf[target_field]
|
||||
print(f" 通过文件名映射找到字段: {target_field}")
|
||||
else:
|
||||
# 尝试通过别名查找
|
||||
for indicator_code in INDICATOR_UNITS.keys():
|
||||
if target_field == indicator_code:
|
||||
for alias in FIELD_ALIASES.get(indicator_code, []):
|
||||
if alias in gdf.columns:
|
||||
indicator_data[indicator_code] = gdf[alias]
|
||||
print(f" 通过文件名映射+别名找到字段: {alias} -> {indicator_code}")
|
||||
break
|
||||
|
||||
# 2. 如果没有通过文件名找到，尝试直接匹配所有指标和别名
|
||||
if not indicator_data:
|
||||
for indicator_code in INDICATOR_UNITS.keys():
|
||||
# 先尝试直接匹配指标代码
|
||||
if indicator_code in gdf.columns:
|
||||
indicator_data[indicator_code] = gdf[indicator_code]
|
||||
print(f" 直接匹配字段: {indicator_code}")
|
||||
continue
|
||||
|
||||
# 再尝试匹配别名
|
||||
aliases = FIELD_ALIASES.get(indicator_code, [])
|
||||
for alias in aliases:
|
||||
if alias in gdf.columns:
|
||||
indicator_data[indicator_code] = gdf[alias]
|
||||
print(f" 通过别名匹配: {alias} -> {indicator_code}")
|
||||
break
|
||||
|
||||
# 3. 额外检查：如果文件名包含特定关键词，尝试匹配
|
||||
if not indicator_data:
|
||||
filename_lower = basename.lower()
|
||||
for indicator_code, (chinese_name, unit) in INDICATOR_UNITS.items():
|
||||
if indicator_code.lower() in filename_lower or chinese_name in filename_lower:
|
||||
# 尝试匹配指标代码或中文名
|
||||
if indicator_code in gdf.columns:
|
||||
indicator_data[indicator_code] = gdf[indicator_code]
|
||||
print(f" 通过文件名关键词匹配: {indicator_code}")
|
||||
break
|
||||
elif chinese_name in gdf.columns:
|
||||
indicator_data[indicator_code] = gdf[chinese_name]
|
||||
print(f" 通过文件名关键词匹配中文名: {chinese_name} -> {indicator_code}")
|
||||
break
|
||||
|
||||
return indicator_data
|
||||
|
||||
|
||||
def get_combined_stats_from_folder(folder_path, folder_name="数据"):
|
||||
"""从文件夹中所有shapefile合并统计指定指标"""
|
||||
shapefiles = find_shapefiles(folder_path)
|
||||
|
||||
if not shapefiles:
|
||||
print(f" 未找到Shapefile文件")
|
||||
return pd.DataFrame()
|
||||
|
||||
print(f" 找到 {len(shapefiles)} 个Shapefile文件")
|
||||
|
||||
all_data = {code: [] for code in INDICATOR_UNITS.keys()}
|
||||
|
||||
for i, shp_file in enumerate(shapefiles, 1):
|
||||
print(f"\n [{i}] 处理文件: {os.path.basename(shp_file)}")
|
||||
gdf = read_shapefile_data(shp_file)
|
||||
|
||||
if gdf is not None:
|
||||
indicator_data = get_indicator_data(gdf, shp_file)
|
||||
|
||||
for indicator_code, data_series in indicator_data.items():
|
||||
if indicator_code in all_data:
|
||||
# 转换为数值类型，处理可能的非数值数据
|
||||
try:
|
||||
data_series = pd.to_numeric(data_series, errors='coerce')
|
||||
valid_data = data_series.dropna()
|
||||
if len(valid_data) > 0:
|
||||
all_data[indicator_code].extend(valid_data.tolist())
|
||||
print(f" 提取 {indicator_code}: {len(valid_data)} 个值")
|
||||
except Exception as e:
|
||||
print(f" 处理 {indicator_code} 数据时出错: {e}")
|
||||
|
||||
# 计算每个指标的合并统计
|
||||
stats_list = []
|
||||
|
||||
for indicator_code, (chinese_name, unit) in INDICATOR_UNITS.items():
|
||||
data_list = all_data.get(indicator_code, [])
|
||||
if not data_list:
|
||||
continue
|
||||
|
||||
data_series = pd.Series(data_list)
|
||||
# 过滤极端值（可选，根据实际需求调整）
|
||||
data_series = data_series[(data_series >= 0) | pd.isna(data_series)]
|
||||
|
||||
if len(data_series) == 0:
|
||||
continue
|
||||
|
||||
# 关键修复1：计算总体标准差（ddof=0），而不是默认的样本标准差（ddof=1）
|
||||
std_dev = data_series.std(ddof=0)
|
||||
mean_val = data_series.mean()
|
||||
|
||||
# 关键修复2：优化变异系数计算
|
||||
if abs(mean_val) < 1e-8: # 均值接近0时
|
||||
cv_value = 0.0
|
||||
else:
|
||||
# CV = (标准差 / 均值) * 100，保留2位小数
|
||||
cv_value = round((std_dev / mean_val) * 100, 2)
|
||||
|
||||
stats = {
|
||||
'指标代码': indicator_code,
|
||||
'指标': chinese_name,
|
||||
'单位': unit,
|
||||
'样点数': int(len(data_series)),
|
||||
'Min': round(float(data_series.min()), 2),
|
||||
'Max': round(float(data_series.max()), 2),
|
||||
'Mean': round(float(mean_val), 2),
|
||||
'Std': round(float(std_dev), 2), # 使用总体标准差
|
||||
'CV': cv_value
|
||||
}
|
||||
stats_list.append(stats)
|
||||
print(f" 统计 {chinese_name}({indicator_code}): {len(data_series)} 个样点")
|
||||
|
||||
if stats_list:
|
||||
stats_df = pd.DataFrame(stats_list)
|
||||
stats_df = stats_df.sort_values('指标')
|
||||
print(f"\n 总共统计到 {len(stats_df)} 个指标")
|
||||
return stats_df
|
||||
|
||||
print(" 未找到任何指标数据")
|
||||
return pd.DataFrame()
|
||||
|
||||
|
||||
def create_statistics_excel(before_folder, after_folder, output_path):
|
||||
"""创建融合的统计表格，在剔除后表格前加一列剔除前样点数和剔除样点数"""
|
||||
workbook = Workbook()
|
||||
|
||||
# 移除默认sheet
|
||||
if 'Sheet' in workbook.sheetnames:
|
||||
default_sheet = workbook['Sheet']
|
||||
workbook.remove(default_sheet)
|
||||
|
||||
# 定义样式
|
||||
thin_border = Border(
|
||||
left=Side(style='thin'),
|
||||
right=Side(style='thin'),
|
||||
top=Side(style='thin'),
|
||||
bottom=Side(style='thin')
|
||||
)
|
||||
|
||||
print("=" * 60)
|
||||
print("开始分析样点数据")
|
||||
print("=" * 60)
|
||||
|
||||
# 分析剔除前数据
|
||||
before_stats = None
|
||||
if os.path.exists(before_folder):
|
||||
print(f"\n[1] 分析剔除前数据:")
|
||||
print(f"文件夹路径: {before_folder}")
|
||||
before_stats = get_combined_stats_from_folder(before_folder, "剔除前")
|
||||
if not before_stats.empty:
|
||||
print(f"✓ 剔除前统计完成: {len(before_stats)} 个指标")
|
||||
else:
|
||||
print("✗ 剔除前未找到指定指标数据")
|
||||
before_stats = None
|
||||
else:
|
||||
print(f"✗ 剔除前文件夹不存在: {before_folder}")
|
||||
before_stats = None
|
||||
|
||||
# 分析剔除后数据
|
||||
if os.path.exists(after_folder):
|
||||
print(f"\n[2] 分析剔除后数据:")
|
||||
print(f"文件夹路径: {after_folder}")
|
||||
after_stats = get_combined_stats_from_folder(after_folder, "剔除后")
|
||||
|
||||
if not after_stats.empty:
|
||||
# 创建融合的统计工作表
|
||||
sheet_combined = workbook.create_sheet(title="样点统计")
|
||||
|
||||
# 新的表头：指标, 单位, 剔除前样点数, 剔除样点数, 剔除后样点数, Min, Max, Mean, Std, CV
|
||||
combined_headers = ['指标', '单位', '剔除前样点数', '剔除样点数', '剔除后样点数', 'Min', 'Max', 'Mean',
|
||||
'Std', 'CV']
|
||||
for col, header in enumerate(combined_headers, 1):
|
||||
cell = sheet_combined.cell(row=1, column=col, value=header)
|
||||
cell.alignment = Alignment(horizontal='center', vertical='center')
|
||||
cell.font = Font(bold=True)
|
||||
cell.border = thin_border
|
||||
|
||||
# 写入数据
|
||||
for row_idx, (index, after_row) in enumerate(after_stats.iterrows(), start=2):
|
||||
# 查找对应的剔除前数据
|
||||
before_sample_count = 0
|
||||
before_row = None
|
||||
if before_stats is not None:
|
||||
# 首先尝试通过指标代码匹配
|
||||
matching_rows = before_stats[before_stats['指标代码'] == after_row['指标代码']]
|
||||
if not matching_rows.empty:
|
||||
before_row = matching_rows.iloc[0]
|
||||
else:
|
||||
# 如果指标代码匹配失败，尝试通过指标名称匹配
|
||||
matching_rows = before_stats[before_stats['指标'] == after_row['指标']]
|
||||
if not matching_rows.empty:
|
||||
before_row = matching_rows.iloc[0]
|
||||
|
||||
if before_row is not None:
|
||||
before_sample_count = int(before_row['样点数'])
|
||||
|
||||
# 计算剔除样点数
|
||||
after_sample_count = int(after_row['样点数'])
|
||||
abnormal_count = max(0, before_sample_count - after_sample_count)
|
||||
|
||||
# 写入数据
|
||||
sheet_combined.cell(row=row_idx, column=1, value=after_row['指标']) # 指标
|
||||
sheet_combined.cell(row=row_idx, column=2, value=after_row['单位']) # 单位
|
||||
sheet_combined.cell(row=row_idx, column=3, value=before_sample_count) # 剔除前样点数
|
||||
sheet_combined.cell(row=row_idx, column=4, value=abnormal_count) # 剔除样点数
|
||||
sheet_combined.cell(row=row_idx, column=5, value=after_sample_count) # 剔除后样点数
|
||||
sheet_combined.cell(row=row_idx, column=6, value=after_row['Min']) # Min
|
||||
sheet_combined.cell(row=row_idx, column=7, value=after_row['Max']) # Max
|
||||
sheet_combined.cell(row=row_idx, column=8, value=after_row['Mean']) # Mean
|
||||
sheet_combined.cell(row=row_idx, column=9, value=after_row['Std']) # Std
|
||||
sheet_combined.cell(row=row_idx, column=10, value=after_row['CV']) # CV
|
||||
|
||||
# 设置所有单元格的样式
|
||||
for col_idx in range(1, 11):
|
||||
cell = sheet_combined.cell(row=row_idx, column=col_idx)
|
||||
cell.alignment = Alignment(horizontal='center', vertical='center')
|
||||
cell.border = thin_border
|
||||
|
||||
# 如果剔除了样点，高亮显示剔除样点数列
|
||||
if abnormal_count > 0:
|
||||
cell = sheet_combined.cell(row=row_idx, column=4) # 剔除样点数列
|
||||
cell.font = Font(bold=True, color="FF0000") # 红色加粗
|
||||
|
||||
# 调整列宽
|
||||
combined_column_widths = {
|
||||
'指标': 15,
|
||||
'单位': 12,
|
||||
'剔除前样点数': 12,
|
||||
'剔除样点数': 12,
|
||||
'剔除后样点数': 12,
|
||||
'Min': 10,
|
||||
'Max': 10,
|
||||
'Mean': 10,
|
||||
'Std': 10,
|
||||
'CV': 10
|
||||
}
|
||||
|
||||
for col_idx, col_name in enumerate(combined_headers, 1):
|
||||
column_letter = get_column_letter(col_idx)
|
||||
if col_name in combined_column_widths:
|
||||
sheet_combined.column_dimensions[column_letter].width = combined_column_widths[col_name]
|
||||
|
||||
print(f"\n✓ 融合统计完成: {len(after_stats)} 个指标")
|
||||
|
||||
# 输出匹配信息
|
||||
if before_stats is not None:
|
||||
print(f" 剔除前找到 {len(before_stats)} 个指标")
|
||||
print(f" 剔除后找到 {len(after_stats)} 个指标")
|
||||
print(
|
||||
f" 成功匹配 {len([i for i in range(2, len(after_stats) + 2) if sheet_combined.cell(row=i, column=3).value > 0])} 个指标的剔除前数据")
|
||||
else:
|
||||
print("✗ 剔除后未找到指定指标数据")
|
||||
sheet_combined = workbook.create_sheet(title="样点统计")
|
||||
sheet_combined.cell(row=1, column=1, value="未找到指定指标数据")
|
||||
else:
|
||||
print(f"✗ 剔除后文件夹不存在: {after_folder}")
|
||||
sheet_combined = workbook.create_sheet(title="样点统计")
|
||||
sheet_combined.cell(row=1, column=1, value="剔除后文件夹不存在")
|
||||
|
||||
# 保存文件
|
||||
workbook.save(output_path)
|
||||
print(f"\n" + "=" * 60)
|
||||
print(f"文件保存成功: {output_path}")
|
||||
print("=" * 60)
|
||||
|
||||
|
||||
# ================ 使用示例 ================
|
||||
if __name__ == "__main__":
|
||||
# 方式1: 处理单个样点数据对
|
||||
before_folder = r"D:\a陆平\1.5实验数据\12月新版实验室数据\云南省实验室数据成果1218\永仁县20260127"
|
||||
after_folder = r"D:\a陆平\1.5实验数据\12月新版实验室数据\云南省实验室数据成果1218\永仁县20260127剔除后"
|
||||
output_path = r"D:\a陆平\1.5实验数据\12月新版实验室数据\云南省实验室数据成果1218\永仁县样点统计结果.xlsx"
|
||||
|
||||
# 执行
|
||||
create_statistics_excel(before_folder, after_folder, output_path)
|
||||
1050
scripts/其他工具/面积加权均值_华南.py
Normal file
1050
scripts/其他工具/面积加权均值_华南.py
Normal file
File diff suppressed because it is too large
Load Diff
932
scripts/其他工具/面积加权均值_西南.py
Normal file
932
scripts/其他工具/面积加权均值_西南.py
Normal file
@@ -0,0 +1,932 @@
|
||||
# 生成完整的exactextract面积加权计算Python脚本
|
||||
# -*- coding: utf-8 -*-
|
||||
"""
|
||||
土壤属性栅格数据面积加权统计脚本
|
||||
基于exactextract库实现多属性栅格的面积加权平均值计算
|
||||
最终输出格式与土壤属性图斑数据表一致
|
||||
"""
|
||||
|
||||
import exactextract as ee
|
||||
import geopandas as gpd
|
||||
import rasterio
|
||||
import pandas as pd
|
||||
import numpy as np
|
||||
from pathlib import Path
|
||||
import warnings
|
||||
warnings.filterwarnings('ignore')
|
||||
|
||||
def init_logger():
|
||||
"""初始化日志输出，便于跟踪处理过程"""
|
||||
import logging
|
||||
logging.basicConfig(
|
||||
level=logging.INFO,
|
||||
format='%(asctime)s - %(levelname)s - %(message)s',
|
||||
datefmt='%Y-%m-%d %H:%M:%S'
|
||||
)
|
||||
return logging.getLogger(__name__)
|
||||
|
||||
def validate_data(vector_path, raster_files):
|
||||
"""
|
||||
验证输入数据的有效性
|
||||
:param vector_path: 矢量图斑文件路径
|
||||
:param raster_files: 栅格文件字典
|
||||
:return: 验证结果（布尔值）
|
||||
"""
|
||||
logger = init_logger()
|
||||
|
||||
# 验证矢量文件是否存在
|
||||
if not Path(vector_path).exists():
|
||||
logger.error(f"矢量文件不存在：{vector_path}")
|
||||
return False
|
||||
|
||||
# 验证栅格文件是否存在
|
||||
for attr_name, raster_path in raster_files.items():
|
||||
if not Path(raster_path).exists():
|
||||
logger.error(f"栅格文件不存在：{attr_name} -> {raster_path}")
|
||||
return False
|
||||
|
||||
# 验证矢量文件格式
|
||||
try:
|
||||
gdf = gpd.read_file(vector_path)
|
||||
if gdf.geometry.type.unique()[0] != 'Polygon':
|
||||
logger.error("矢量文件必须是Polygon类型（面要素）")
|
||||
return False
|
||||
except Exception as e:
|
||||
logger.error(f"矢量文件读取失败：{str(e)}")
|
||||
return False
|
||||
|
||||
# 验证栅格文件格式
|
||||
try:
|
||||
test_raster = next(iter(raster_files.values()))
|
||||
with rasterio.open(test_raster) as src:
|
||||
if src.count != 1:
|
||||
logger.error("每个栅格文件必须是单波段（每个属性单独一个栅格）")
|
||||
return False
|
||||
except Exception as e:
|
||||
logger.error(f"栅格文件读取失败：{str(e)}")
|
||||
return False
|
||||
|
||||
logger.info("所有输入数据验证通过")
|
||||
return True
|
||||
|
||||
def standardize_crs(gdf, raster_path):
|
||||
"""
|
||||
标准化矢量与栅格的坐标参考系统（CRS）
|
||||
:param gdf: 矢量GeoDataFrame
|
||||
:param raster_path: 任意一个栅格文件路径（用于获取目标CRS）
|
||||
:return: 标准化后的GeoDataFrame
|
||||
"""
|
||||
logger = init_logger()
|
||||
|
||||
# 获取栅格CRS
|
||||
with rasterio.open(raster_path) as src:
|
||||
raster_crs = src.crs
|
||||
raster_crs_str = src.crs.to_string()
|
||||
|
||||
# 获取矢量CRS
|
||||
vector_crs = gdf.crs
|
||||
vector_crs_str = gdf.crs.to_string()
|
||||
|
||||
logger.info(f"当前矢量CRS：{vector_crs_str}")
|
||||
logger.info(f"目标栅格CRS：{raster_crs_str}")
|
||||
|
||||
# 若CRS不一致，进行转换
|
||||
if vector_crs != raster_crs:
|
||||
logger.warning("矢量与栅格CRS不一致，正在进行转换...")
|
||||
gdf = gdf.to_crs(raster_crs)
|
||||
logger.info(f"CRS转换完成，新矢量CRS：{gdf.crs.to_string()}")
|
||||
|
||||
return gdf
|
||||
|
||||
def calculate_area_weighted_stats(vector_path, raster_files, output_path):
|
||||
"""
|
||||
核心函数：计算面积加权统计值
|
||||
:param vector_path: 矢量图斑文件路径
|
||||
:param raster_files: 栅格文件字典（键：属性名，值：栅格路径）
|
||||
:param output_path: 结果输出路径（Excel文件）
|
||||
:return: 统计结果DataFrame
|
||||
"""
|
||||
logger = init_logger()
|
||||
logger.info("开始面积加权统计计算")
|
||||
|
||||
# 1. 加载矢量数据
|
||||
logger.info(f"加载矢量数据：{vector_path}")
|
||||
gdf = gpd.read_file(vector_path)
|
||||
|
||||
# 2. 标准化CRS
|
||||
test_raster = next(iter(raster_files.values()))
|
||||
gdf = standardize_crs(gdf, test_raster)
|
||||
|
||||
# 3. 初始化结果DataFrame（保留矢量中的关键属性）
|
||||
logger.info("初始化结果数据结构")
|
||||
# 基础字段列表（与土壤属性图斑表格式对齐）
|
||||
# TODO
|
||||
base_fields = ["FID","DM","XZM","QSDWDM","QSDWMC","TL", "YL", "TS", "TZ", "DLBM", "DLMC"]
|
||||
|
||||
# 检查矢量中是否包含必要字段，若不包含则创建空字段
|
||||
result_df = pd.DataFrame()
|
||||
for field in base_fields:
|
||||
if field in gdf.columns:
|
||||
result_df[field] = gdf[field]
|
||||
else:
|
||||
result_df[field] = np.nan
|
||||
logger.warning(f"矢量中缺少'{field}'字段，将生成空值")
|
||||
|
||||
# 4. 计算图斑面积（转换为亩）
|
||||
logger.info("计算图斑面积（单位：亩）")
|
||||
# 计算平方米面积（根据CRS单位自动适应）
|
||||
gdf["area_sqm"] = gdf.geometry.area
|
||||
# 转换为亩（1亩 ≈ 666.6667平方米）
|
||||
result_df["面积亩"] = gdf["area_sqm"] * 0.0015
|
||||
# 保留6位小数，与示例数据格式一致
|
||||
result_df["面积亩"] = result_df["面积亩"].round(6)
|
||||
|
||||
# 5. 对每个土壤属性进行面积加权平均计算
|
||||
logger.info("开始处理土壤属性栅格（面积加权平均）")
|
||||
for attr_idx, (attr_name, raster_path) in enumerate(raster_files.items(), 1):
|
||||
total_attrs = len(raster_files)
|
||||
logger.info(f"处理进度：{attr_idx}/{total_attrs} - 属性：{attr_name}")
|
||||
|
||||
try:
|
||||
# 使用exactextract计算面积加权平均
|
||||
# weights="area"：按矢量与栅格的交集面积进行加权
|
||||
stats = ee.exact_extract(
|
||||
raster_path,
|
||||
gdf,
|
||||
["mean"], # 计算平均值
|
||||
output="pandas" # 输出为DataFrame格式
|
||||
)
|
||||
|
||||
# 将统计结果添加到结果DataFrame
|
||||
if stats is None:
|
||||
logger.warning(f"{attr_name}计算结果为空，可能无交集区域")
|
||||
result_df[attr_name] = np.nan
|
||||
continue
|
||||
else:
|
||||
# 确保 stats 为 pandas.DataFrame，以便使用字符串索引
|
||||
if not isinstance(stats, pd.DataFrame):
|
||||
stats = pd.DataFrame(stats)
|
||||
|
||||
# 保留4位小数，确保数据精度
|
||||
result_df[attr_name] = stats["mean"].round(4)
|
||||
|
||||
# 处理可能的空值（无交集区域）
|
||||
if result_df[attr_name].isnull().sum() > 0:
|
||||
null_count = result_df[attr_name].isnull().sum()
|
||||
logger.warning(f"{attr_name}存在{null_count}个空值（图斑与栅格无交集）")
|
||||
# 用0填充空值（可根据业务需求调整）
|
||||
result_df[attr_name] = result_df[attr_name].fillna(0)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"{attr_name}处理失败：{str(e)}")
|
||||
# 失败时填充空值，避免整个程序崩溃
|
||||
result_df[attr_name] = np.nan
|
||||
|
||||
# 6. 添加属性分级字段（根据业务规则实现）
|
||||
logger.info("添加土壤属性分级字段")
|
||||
result_df = add_attribute_classification(result_df)
|
||||
|
||||
# 7. 整理最终字段顺序（与示例表格完全对齐）
|
||||
logger.info("整理输出字段顺序")
|
||||
# TODO
|
||||
final_columns = [
|
||||
"FID","DM", "XZM", "QSDWDM", "QSDWMC",
|
||||
"TL", "YL", "TS", "TZ", "DLBM", "DLMC",
|
||||
"耕层厚度", "土壤容重", "砂粒", "粉粒", "黏粒", "酸碱度", "阳离子",
|
||||
"有机质", "全氮", "全磷", "全钾", "有效磷", "速效钾", "有效铁", "有效锰",
|
||||
"有效铜", "有效锌", "有效硼", "有效钼", "有效硫", "交换性钙", "交换性镁", "全硒",
|
||||
"有效土层厚度", "土壤质地",
|
||||
"耕层厚度分级", "土壤容重分级", "砂粒分级", "粉粒分级", "黏粒分级", "酸碱度分级", "阳离子分级",
|
||||
"有机质分级", "全氮分级", "全磷分级", "全钾分级", "有效铁分级", "速效钾分级", "有效铁分级", "有效锰分级",
|
||||
"有效铜分级", "有效锌分级", "有效硼分级", "有效钼分级", "有效硫分级", "交换性钙分级", "交换性镁分级", "全硒分级",
|
||||
"有效土层厚度分级", "土壤质地分级",
|
||||
"面积亩"
|
||||
]
|
||||
|
||||
# 补充缺失的字段（如乡代码等）
|
||||
for col in final_columns:
|
||||
if col not in result_df.columns:
|
||||
result_df[col] = np.nan
|
||||
|
||||
# 按最终顺序排列字段
|
||||
result_df = result_df[final_columns]
|
||||
|
||||
# 8. 导出结果到Excel
|
||||
logger.info(f"导出结果到：{output_path}")
|
||||
# 使用openpyxl引擎支持.xlsx格式
|
||||
result_df.to_excel(output_path, index=False, engine="openpyxl")
|
||||
logger.info(f"结果导出完成，共生成{len(result_df)}条记录")
|
||||
|
||||
return result_df
|
||||
|
||||
def add_attribute_classification(df):
|
||||
"""
|
||||
添加土壤属性分级字段（根据常见土壤分类标准实现）
|
||||
可根据实际业务需求调整分级阈值
|
||||
:param df: 包含原始属性的DataFrame
|
||||
:return: 包含分级字段的DataFrame
|
||||
"""
|
||||
# todo
|
||||
# 1. 酸碱度分级（pH值） - 按PH标准
|
||||
def classify_ph(ph):
|
||||
"""
|
||||
土壤pH值分级（第三次全国土壤普查标准）
|
||||
标准等级:
|
||||
等级一: 6.0～7.0
|
||||
等级二: 7.0～7.5, 5.5～6.0
|
||||
等级三: 7.5～8.0, 5.0～5.5
|
||||
等级四: 8.0～8.5, 4.5～5.0
|
||||
等级五: ＞8.5, ≤4.5
|
||||
"""
|
||||
if ph > 8.5 or ph <= 4.5:
|
||||
return 5 # 等级五: ＞8.5, ≤4.5
|
||||
elif (8.0 < ph <= 8.5) or (4.5 < ph <= 5.0):
|
||||
return 4 # 等级四: 8.0～8.5, 4.5～5.0
|
||||
elif (7.5 < ph <= 8.0) or (5.0 < ph <= 5.5):
|
||||
return 3 # 等级三: 7.5～8.0, 5.0～5.5
|
||||
elif (7.0 < ph <= 7.5) or (5.5 < ph <= 6.0):
|
||||
return 2 # 等级二: 7.0～7.5, 5.5～6.0
|
||||
elif 6.0 < ph <= 7.0:
|
||||
return 1 # 等级一: 6.0～7.0
|
||||
else:
|
||||
return None # 异常值
|
||||
|
||||
# 2. 有机质分级（单位：g/kg） - 按OM标准
|
||||
def classify_organic(organic):
|
||||
"""
|
||||
土壤有机质分级（第三次全国土壤普查标准）
|
||||
标准等级:
|
||||
等级一: ＞35.0
|
||||
等级二: 25.0～35.0
|
||||
等级三: 15.0～25.0
|
||||
等级四: 10.0～15.0
|
||||
等级五: ≤10.0
|
||||
"""
|
||||
if organic > 35.0:
|
||||
return 1 # 等级一: ＞35.0
|
||||
elif 25.0 < organic <= 35.0:
|
||||
return 2 # 等级二: 25.0～35.0
|
||||
elif 15.0 < organic <= 25.0:
|
||||
return 3 # 等级三: 15.0～25.0
|
||||
elif 10.0 < organic <= 15.0:
|
||||
return 4 # 等级四: 10.0～15.0
|
||||
elif organic <= 10.0:
|
||||
return 5 # 等级五: ≤10.0
|
||||
else:
|
||||
return None # 异常值
|
||||
|
||||
# 3. 阳离子交换量分级（单位：cmol/kg） - 按CEC标准
|
||||
def classify_cation(cation):
|
||||
"""
|
||||
土壤阳离子交换量分级（第三次全国土壤普查标准）
|
||||
标准等级:
|
||||
等级一: ＞30.0
|
||||
等级二: 20.0～30.0
|
||||
等级三: 15.0～20.0
|
||||
等级四: 10.0～15.0
|
||||
等级五: ≤10.0
|
||||
"""
|
||||
if cation > 30.0:
|
||||
return 1 # 等级一: ＞30.0
|
||||
elif 20.0 < cation <= 30.0:
|
||||
return 2 # 等级二: 20.0～30.0
|
||||
elif 15.0 < cation <= 20.0:
|
||||
return 3 # 等级三: 15.0～20.0
|
||||
elif 10.0 < cation <= 15.0:
|
||||
return 4 # 等级四: 10.0～15.0
|
||||
elif cation <= 10.0:
|
||||
return 5 # 等级五: ≤10.0
|
||||
else:
|
||||
return None # 异常值
|
||||
|
||||
# 4. 有效磷分级（单位：mg/kg） - 按AP标准
|
||||
def classify_available_p(p):
|
||||
"""
|
||||
土壤有效磷分级（第三次全国土壤普查标准）
|
||||
标准等级:
|
||||
等级一: ＞40.0
|
||||
等级二: 25.0～40.0
|
||||
等级三: 15.0～25.0
|
||||
等级四: 5.0～15.0
|
||||
等级五: ≤5.0
|
||||
"""
|
||||
if p > 40.0:
|
||||
return 1 # 等级一: ＞40.0
|
||||
elif 25.0 < p <= 40.0:
|
||||
return 2 # 等级二: 25.0～40.0
|
||||
elif 15.0 < p <= 25.0:
|
||||
return 3 # 等级三: 15.0～25.0
|
||||
elif 5.0 < p <= 15.0:
|
||||
return 4 # 等级四: 5.0～15.0
|
||||
elif p <= 5.0:
|
||||
return 5 # 等级五: ≤5.0
|
||||
else:
|
||||
return None # 异常值
|
||||
|
||||
# 5. 速效钾分级（单位：mg/kg） - 按AK标准
|
||||
def classify_available_k(k):
|
||||
"""
|
||||
土壤速效钾分级（第三次全国土壤普查标准）
|
||||
标准等级:
|
||||
等级一: ＞150
|
||||
等级二: 100～150
|
||||
等级三: 75～100
|
||||
等级四: 50～75
|
||||
等级五: ≤50
|
||||
"""
|
||||
if k > 150:
|
||||
return 1 # 等级一: ＞150
|
||||
elif 100 < k <= 150:
|
||||
return 2 # 等级二: 100～150
|
||||
elif 75 < k <= 100:
|
||||
return 3 # 等级三: 75～100
|
||||
elif 50 < k <= 75:
|
||||
return 4 # 等级四: 50～75
|
||||
elif k <= 50:
|
||||
return 5 # 等级五: ≤50
|
||||
else:
|
||||
return None # 异常值
|
||||
|
||||
# 6. 耕层厚度分级（单位：cm） - 按GZCHD标准
|
||||
def classify_soil_depth(depth):
|
||||
"""
|
||||
土壤耕作层厚度分级（第三次全国土壤普查标准）
|
||||
标准等级:
|
||||
等级一: ＞25.0
|
||||
等级二: 20.0～25.0
|
||||
等级三: 15.0～20.0
|
||||
等级四: 10.0～15.0
|
||||
等级五: ≤10.0
|
||||
"""
|
||||
if depth > 25.0:
|
||||
return 1 # 等级一: ＞25.0
|
||||
elif 20.0 < depth <= 25.0:
|
||||
return 2 # 等级二: 20.0～25.0
|
||||
elif 15.0 < depth <= 20.0:
|
||||
return 3 # 等级三: 15.0～20.0
|
||||
elif 10.0 < depth <= 15.0:
|
||||
return 4 # 等级四: 10.0～15.0
|
||||
elif depth <= 10.0:
|
||||
return 5 # 等级五: ≤10.0
|
||||
else:
|
||||
return None # 异常值
|
||||
|
||||
# 7. 土壤容重分级（单位：g/cm³） - 按TRRZ标准
|
||||
def classify_bulk_density(density):
|
||||
"""
|
||||
土壤容重分级（第三次全国土壤普查标准）
|
||||
标准等级:
|
||||
等级一: 1.10～1.25
|
||||
等级二: 1.25～1.35, 1.00～1.10
|
||||
等级三: 1.35～1.45
|
||||
等级四: 1.45～1.55, 0.90～1.00
|
||||
等级五: ＞1.55, ≤0.90
|
||||
"""
|
||||
if 1.10 < density <= 1.25:
|
||||
return 1 # 等级一: 1.10～1.25
|
||||
elif (1.25 < density <= 1.35) or (1.00 < density <= 1.10):
|
||||
return 2 # 等级二: 1.25～1.35, 1.00～1.10
|
||||
elif 1.35 < density <= 1.45:
|
||||
return 3 # 等级三: 1.35～1.45
|
||||
elif (1.45 < density <= 1.55) or (0.90 < density <= 1.00):
|
||||
return 4 # 等级四: 1.45～1.55, 0.90～1.00
|
||||
elif density > 1.55 or density <= 0.90:
|
||||
return 5 # 等级五: ＞1.55, ≤0.90
|
||||
else:
|
||||
return None # 异常值
|
||||
|
||||
# 8. 全氮分级（单位：g/kg） - 按TN标准
|
||||
def classify_total_n(n):
|
||||
"""
|
||||
土壤全氮分级（第三次全国土壤普查标准）
|
||||
标准等级:
|
||||
等级一: ＞2.00
|
||||
等级二: 1.50～2.00
|
||||
等级三: 1.00～1.50
|
||||
等级四: 0.50～1.00
|
||||
等级五: ≤0.50
|
||||
"""
|
||||
if n > 2.00:
|
||||
return 1 # 等级一: ＞2.00
|
||||
elif 1.50 < n <= 2.00:
|
||||
return 2 # 等级二: 1.50～2.00
|
||||
elif 1.00 < n <= 1.50:
|
||||
return 3 # 等级三: 1.00～1.50
|
||||
elif 0.50 < n <= 1.00:
|
||||
return 4 # 等级四: 0.50～1.00
|
||||
elif n <= 0.50:
|
||||
return 5 # 等级五: ≤0.50
|
||||
else:
|
||||
return None # 异常值
|
||||
|
||||
# 9. 全磷分级（单位：g/kg） - 按TP标准
|
||||
def classify_total_p(p):
|
||||
"""
|
||||
土壤全磷分级（第三次全国土壤普查标准）
|
||||
标准等级:
|
||||
等级一: ＞1.00
|
||||
等级二: 0.80～1.00
|
||||
等级三: 0.60～0.80
|
||||
等级四: 0.40～0.60
|
||||
等级五: ≤0.40
|
||||
"""
|
||||
if p > 1.00:
|
||||
return 1 # 等级一: ＞1.00
|
||||
elif 0.80 < p <= 1.00:
|
||||
return 2 # 等级二: 0.80～1.00
|
||||
elif 0.60 < p <= 0.80:
|
||||
return 3 # 等级三: 0.60～0.80
|
||||
elif 0.40 < p <= 0.60:
|
||||
return 4 # 等级四: 0.40～0.60
|
||||
elif p <= 0.40:
|
||||
return 5 # 等级五: ≤0.40
|
||||
else:
|
||||
return None # 异常值
|
||||
|
||||
# 10. 全钾分级（单位：g/kg） - 按TK标准
|
||||
def classify_total_k(k):
|
||||
"""
|
||||
土壤全钾分级（第三次全国土壤普查标准）
|
||||
标准等级:
|
||||
等级一: ＞20.0
|
||||
等级二: 15.0～20.0
|
||||
等级三: 10.0～15.0
|
||||
等级四: 5.0～10.0
|
||||
等级五: ≤5.0
|
||||
"""
|
||||
if k > 20.0:
|
||||
return 1 # 等级一: ＞20.0
|
||||
elif 15.0 < k <= 20.0:
|
||||
return 2 # 等级二: 15.0～20.0
|
||||
elif 10.0 < k <= 15.0:
|
||||
return 3 # 等级三: 10.0～15.0
|
||||
elif 5.0 < k <= 10.0:
|
||||
return 4 # 等级四: 5.0～10.0
|
||||
elif k <= 5.0:
|
||||
return 5 # 等级五: ≤5.0
|
||||
else:
|
||||
return None # 异常值
|
||||
|
||||
# 11. 有效铁分级（单位：mg/kg）
|
||||
def classify_available_fe(fe):
|
||||
"""
|
||||
土壤有效铁分级（第三次全国土壤普查标准）
|
||||
|
||||
参数:
|
||||
fe: 有效铁含量 (mg/kg)
|
||||
|
||||
返回:
|
||||
分级等级 (1-5)
|
||||
"""
|
||||
if fe <= 3.0:
|
||||
return 5 # 等级五: ≤3.0
|
||||
elif 3.0 < fe <= 5.0:
|
||||
return 4 # 等级四: 3.0～5.0
|
||||
elif 5.0 < fe <= 10.0:
|
||||
return 3 # 等级三: 5.0～10.0
|
||||
elif 10.0 < fe <= 20.0:
|
||||
return 2 # 等级二: 10.0～20.0
|
||||
else: # fe > 20.0
|
||||
return 1 # 等级一: ＞20.0
|
||||
|
||||
# 12. 有效锌分级（单位：mg/kg）
|
||||
def classify_available_zn(zn):
|
||||
"""
|
||||
土壤有效锌分级（第三次全国土壤普查标准）
|
||||
|
||||
参数:
|
||||
zn: 有效锌含量 (mg/kg)
|
||||
|
||||
返回:
|
||||
分级等级 (1-5)
|
||||
"""
|
||||
if zn <= 0.20:
|
||||
return 5 # 等级五: ≤0.20
|
||||
elif 0.20 < zn <= 0.50:
|
||||
return 4 # 等级四: 0.20～0.50
|
||||
elif 0.50 < zn <= 1.00:
|
||||
return 3 # 等级三: 0.50～1.00
|
||||
elif 1.00 < zn <= 3.00:
|
||||
return 2 # 等级二: 1.00～3.00
|
||||
else: # zn > 3.00
|
||||
return 1 # 等级一: ＞3.00
|
||||
|
||||
# 13. 有效锰分级（单位：mg/kg）
|
||||
def classify_available_mn(mn):
|
||||
"""
|
||||
土壤有效锰分级（第三次全国土壤普查标准）
|
||||
|
||||
参数:
|
||||
mn: 有效锰含量 (mg/kg)
|
||||
|
||||
返回:
|
||||
分级等级 (1-5)
|
||||
"""
|
||||
if mn <= 1.0:
|
||||
return 5 # 等级五: ≤1.0
|
||||
elif 1.0 < mn <= 5.0:
|
||||
return 4 # 等级四: 1.0～5.0
|
||||
elif 5.0 < mn <= 15.0:
|
||||
return 3 # 等级三: 5.0～15.0
|
||||
elif 15.0 < mn <= 30.0:
|
||||
return 2 # 等级二: 15.0～30.0
|
||||
else: # mn > 30.0
|
||||
return 1 # 等级一: ＞30.0
|
||||
|
||||
# 14. 有效铜分级（单位：mg/kg）
|
||||
def classify_available_cu(cu):
|
||||
"""
|
||||
土壤有效铜分级（第三次全国土壤普查标准）
|
||||
|
||||
参数:
|
||||
cu: 有效铜含量 (mg/kg)
|
||||
|
||||
返回:
|
||||
分级等级 (1-5)
|
||||
"""
|
||||
if cu <= 0.20:
|
||||
return 5 # 等级五: ≤0.20
|
||||
elif 0.20 < cu <= 0.50:
|
||||
return 4 # 等级四: 0.20～0.50
|
||||
elif 0.50 < cu <= 1.00:
|
||||
return 3 # 等级三: 0.50～1.00
|
||||
elif 1.00 < cu <= 2.00:
|
||||
return 2 # 等级二: 1.00～2.00
|
||||
else: # cu > 2.00
|
||||
return 1 # 等级一: ＞2.00
|
||||
|
||||
# 15. 有效硼分级（单位：mg/kg）
|
||||
def classify_available_b(b):
|
||||
"""
|
||||
土壤有效硼分级（第三次全国土壤普查标准）
|
||||
|
||||
参数:
|
||||
b: 有效硼含量 (mg/kg)
|
||||
|
||||
返回:
|
||||
分级等级 (1-5)
|
||||
"""
|
||||
if b <= 0.20:
|
||||
return 5 # 等级五: ≤0.20
|
||||
elif 0.20 < b <= 0.50:
|
||||
return 4 # 等级四: 0.20～0.50
|
||||
elif 0.50 < b <= 0.80:
|
||||
return 3 # 等级三: 0.50～0.80
|
||||
elif 0.80 < b <= 1.00:
|
||||
return 2 # 等级二: 0.80～1.00
|
||||
else: # b > 1.00
|
||||
return 1 # 等级一: ＞1.00
|
||||
|
||||
# 16. 有效钼分级（单位：mg/kg）
|
||||
def classify_available_mo(mo):
|
||||
"""
|
||||
土壤有效钼分级（第三次全国土壤普查标准）
|
||||
|
||||
参数:
|
||||
mo: 有效钼含量 (mg/kg)
|
||||
|
||||
返回:
|
||||
分级等级 (1-5)
|
||||
"""
|
||||
if mo <= 0.05:
|
||||
return 5 # 等级五: ≤0.05
|
||||
elif 0.05 < mo <= 0.10:
|
||||
return 4 # 等级四: 0.05～0.10
|
||||
elif 0.10 < mo <= 0.15:
|
||||
return 3 # 等级三: 0.10～0.15
|
||||
elif 0.15 < mo <= 0.20:
|
||||
return 2 # 等级二: 0.15～0.20
|
||||
else: # mo > 0.20
|
||||
return 1 # 等级一: ＞0.20
|
||||
|
||||
# 17. 有效硫分级（单位：mg/kg）
|
||||
def classify_available_s(s):
|
||||
"""
|
||||
土壤有效硫分级（第三次全国土壤普查标准）
|
||||
|
||||
参数:
|
||||
s: 有效硫含量 (mg/kg)
|
||||
|
||||
返回:
|
||||
分级等级 (1-5)
|
||||
"""
|
||||
if s <= 10.0:
|
||||
return 5 # 等级五: ≤10.0
|
||||
elif 10.0 < s <= 20.0:
|
||||
return 4 # 等级四: 10.0～20.0
|
||||
elif 20.0 < s <= 30.0:
|
||||
return 3 # 等级三: 20.0～30.0
|
||||
elif 30.0 < s <= 40.0:
|
||||
return 2 # 等级二: 30.0～40.0
|
||||
else: # s > 40.0
|
||||
return 1 # 等级一: ＞40.0
|
||||
|
||||
# 18. 交换性钙分级（单位：cmol(½Ca²⁺)/kg）
|
||||
def classify_exchangeable_ca(ca):
|
||||
"""
|
||||
土壤交换性钙分级（第三次全国土壤普查标准）
|
||||
|
||||
参数:
|
||||
ca: 交换性钙含量 (cmol(½Ca²⁺)/kg)
|
||||
|
||||
返回:
|
||||
分级等级 (1-5)
|
||||
"""
|
||||
if ca <= 1.00:
|
||||
return 5 # 等级五: ≤1.00
|
||||
elif 1.00 < ca <= 2.50:
|
||||
return 4 # 等级四: 1.00～2.50
|
||||
elif 2.50 < ca <= 4.99:
|
||||
return 3 # 等级三: 2.50～4.99
|
||||
elif 4.99 < ca <= 7.49:
|
||||
return 2 # 等级二: 4.99～7.49
|
||||
else: # ca > 7.49
|
||||
return 1 # 等级一: ＞7.49
|
||||
|
||||
# 19. 交换性镁分级（单位：cmol(½Mg²⁺)/kg）
|
||||
def classify_exchangeable_mg(mg):
|
||||
"""
|
||||
土壤交换性镁分级（第三次全国土壤普查标准）
|
||||
|
||||
参数:
|
||||
mg: 交换性镁含量 (cmol(½Mg²⁺)/kg)
|
||||
|
||||
返回:
|
||||
分级等级 (1-5)
|
||||
"""
|
||||
if mg <= 0.41:
|
||||
return 5 # 等级五: ≤0.41
|
||||
elif 0.41 < mg <= 0.82:
|
||||
return 4 # 等级四: 0.41～0.82
|
||||
elif 0.82 < mg <= 1.23:
|
||||
return 3 # 等级三: 0.82～1.23
|
||||
elif 1.23 < mg <= 1.64:
|
||||
return 2 # 等级二: 1.23～1.64
|
||||
else: # mg > 1.64
|
||||
return 1 # 等级一: ＞1.64
|
||||
|
||||
# 20. 全硒分级（单位：mg/kg）
|
||||
def classify_total_se(se):
|
||||
"""
|
||||
土壤全硒分级（第三次全国土壤普查标准）
|
||||
|
||||
参数:
|
||||
se: 全硒含量 (mg/kg)
|
||||
|
||||
返回:
|
||||
分级等级 (1-4)
|
||||
"""
|
||||
if se <= 0.17:
|
||||
return 4 # 等级四: ≤0.17
|
||||
elif 0.17 < se <= 0.40:
|
||||
return 3 # 等级三: 0.17～0.40
|
||||
elif 0.40 < se <= 3.00:
|
||||
return 2 # 等级二: 0.40～3.00
|
||||
else: # se > 3.00
|
||||
return 1 # 等级一: ＞3.00
|
||||
|
||||
# 21. 粉粒含量分级（单位：%）
|
||||
def classify_silt(silt):
|
||||
"""
|
||||
土壤粉粒含量分级（第三次全国土壤普查标准）
|
||||
|
||||
参数:
|
||||
silt: 粉粒含量 (%)
|
||||
|
||||
返回:
|
||||
分级等级 (1-5)
|
||||
"""
|
||||
if silt > 75:
|
||||
return 5 # 等级五: ＞75
|
||||
elif 45 < silt <= 75:
|
||||
return 4 # 等级四: 45～75
|
||||
elif 30 < silt <= 45:
|
||||
return 3 # 等级三: 30～45
|
||||
elif 15 < silt <= 30:
|
||||
return 2 # 等级二: 15～30
|
||||
else: # silt <= 15
|
||||
return 1 # 等级一: ≤15
|
||||
|
||||
# 22. 黏粒含量分级（单位：%）
|
||||
def classify_clay(clay):
|
||||
"""
|
||||
土壤黏粒含量分级（第三次全国土壤普查标准）
|
||||
|
||||
参数:
|
||||
clay: 黏粒含量 (%)
|
||||
|
||||
返回:
|
||||
分级等级 (1-5)
|
||||
"""
|
||||
if clay > 65:
|
||||
return 5 # 等级五: ＞65
|
||||
elif 45 < clay <= 65:
|
||||
return 4 # 等级四: 45～65
|
||||
elif 25 < clay <= 45:
|
||||
return 3 # 等级三: 25～45
|
||||
elif 15 < clay <= 25:
|
||||
return 2 # 等级二: 15～25
|
||||
else: # clay <= 15
|
||||
return 1 # 等级一: ≤15
|
||||
|
||||
# 23. 砂粒含量分级（单位：%）
|
||||
def classify_sand(sand):
|
||||
"""
|
||||
土壤砂粒含量分级（第三次全国土壤普查标准）
|
||||
|
||||
参数:
|
||||
sand: 砂粒含量 (%)
|
||||
|
||||
返回:
|
||||
分级等级 (1-5)
|
||||
"""
|
||||
if sand > 85:
|
||||
return 5 # 等级五: ＞85
|
||||
elif 55 < sand <= 85:
|
||||
return 4 # 等级四: 55～85
|
||||
elif 40 < sand <= 55:
|
||||
return 3 # 等级三: 40～55
|
||||
elif 30 < sand <= 40:
|
||||
return 2 # 等级二: 30～40
|
||||
else: # sand <= 30
|
||||
return 1 # 等级一: ≤30
|
||||
|
||||
# 24. 有效土层厚度分级（单位：cm）
|
||||
def classify_yxtchd(depth):
|
||||
"""
|
||||
土壤有效土层厚度分级（第三次全国土壤普查标准）
|
||||
|
||||
参数:
|
||||
depth: 有效土层厚度 (cm)
|
||||
|
||||
返回:
|
||||
分级等级 (1-5)
|
||||
"""
|
||||
if depth <= 40:
|
||||
return 5 # 等级五: ≤40
|
||||
elif 40 < depth <= 60:
|
||||
return 4 # 等级四: 40～60
|
||||
elif 60 < depth <= 80:
|
||||
return 3 # 等级三: 60～80
|
||||
elif 80 < depth <= 100:
|
||||
return 2 # 等级二: 80～100
|
||||
else: # depth > 100
|
||||
return 1 # 等级一: ＞100
|
||||
|
||||
# 25. 土壤质地
|
||||
def classify_trzd(trzd):
|
||||
"""
|
||||
土壤质地
|
||||
|
||||
参数:
|
||||
trzd: 土壤质地分类（1-5）
|
||||
|
||||
返回:
|
||||
分级等级 (1-5)
|
||||
"""
|
||||
trzd = round(trzd, 0)
|
||||
if trzd == 5:
|
||||
return 5 # 等级五: ≤40
|
||||
elif trzd == 4:
|
||||
return 4 # 等级四: 40～60
|
||||
elif trzd == 3:
|
||||
return 3 # 等级三: 60～80
|
||||
elif trzd == 2:
|
||||
return 2 # 等级二: 80～100
|
||||
else: # depth > 100
|
||||
return 1 # 等级一: ＞100
|
||||
|
||||
|
||||
# 应用分级函数（只处理非空值）
|
||||
if "酸碱度" in df.columns:
|
||||
df["酸碱度分级"] = df["酸碱度"].apply(lambda x: classify_ph(x) if pd.notna(x) else np.nan)
|
||||
if "有机质" in df.columns:
|
||||
df["有机质分级"] = df["有机质"].apply(lambda x: classify_organic(x) if pd.notna(x) else np.nan)
|
||||
if "阳离子" in df.columns:
|
||||
df["阳离子分级"] = df["阳离子"].apply(lambda x: classify_cation(x) if pd.notna(x) else np.nan)
|
||||
if "有效磷" in df.columns:
|
||||
df["有效磷分级"] = df["有效磷"].apply(lambda x: classify_available_p(x) if pd.notna(x) else np.nan)
|
||||
if "速效钾" in df.columns:
|
||||
df["速效钾分级"] = df["速效钾"].apply(lambda x: classify_available_k(x) if pd.notna(x) else np.nan)
|
||||
if "耕层厚度" in df.columns:
|
||||
df["耕层厚度分级"] = df["耕层厚度"].apply(lambda x: classify_soil_depth(x) if pd.notna(x) else np.nan)
|
||||
if "土壤容重" in df.columns:
|
||||
df["土壤容重分级"] = df["土壤容重"].apply(lambda x: classify_bulk_density(x) if pd.notna(x) else np.nan)
|
||||
if "全氮" in df.columns:
|
||||
df["全氮分级"] = df["全氮"].apply(lambda x: classify_total_n(x) if pd.notna(x) else np.nan)
|
||||
if "全磷" in df.columns:
|
||||
df["全磷分级"] = df["全磷"].apply(lambda x: classify_total_p(x) if pd.notna(x) else np.nan)
|
||||
if "全钾" in df.columns:
|
||||
df["全钾分级"] = df["全钾"].apply(lambda x: classify_total_k(x) if pd.notna(x) else np.nan)
|
||||
if "有效铁" in df.columns:
|
||||
df["有效铁分级"] = df["有效铁"].apply(lambda x: classify_available_fe(x) if pd.notna(x) else np.nan)
|
||||
if "有效锌" in df.columns:
|
||||
df["有效锌分级"] = df["有效锌"].apply(lambda x: classify_available_zn(x) if pd.notna(x) else np.nan)
|
||||
if "有效锰" in df.columns:
|
||||
df["有效锰分级"] = df["有效锰"].apply(lambda x: classify_available_mn(x) if pd.notna(x) else np.nan)
|
||||
if "有效铜" in df.columns:
|
||||
df["有效铜分级"] = df["有效铜"].apply(lambda x: classify_available_cu(x) if pd.notna(x) else np.nan)
|
||||
if "有效硼" in df.columns:
|
||||
df["有效硼分级"] = df["有效硼"].apply(lambda x: classify_available_b(x) if pd.notna(x) else np.nan)
|
||||
if "有效钼" in df.columns:
|
||||
df["有效钼分级"] = df["有效钼"].apply(lambda x: classify_available_mo(x) if pd.notna(x) else np.nan)
|
||||
if "有效硫" in df.columns:
|
||||
df["有效硫分级"] = df["有效硫"].apply(lambda x: classify_available_s(x) if pd.notna(x) else np.nan)
|
||||
if "交换性钙" in df.columns:
|
||||
df["交换性钙分级"] = df["交换性钙"].apply(lambda x: classify_exchangeable_ca(x) if pd.notna(x) else np.nan)
|
||||
if "交换性镁" in df.columns:
|
||||
df["交换性镁分级"] = df["交换性镁"].apply(lambda x: classify_exchangeable_mg(x) if pd.notna(x) else np.nan)
|
||||
if "全硒" in df.columns:
|
||||
df["全硒分级"] = df["全硒"].apply(lambda x: classify_total_se(x) if pd.notna(x) else np.nan)
|
||||
if "粉粒" in df.columns:
|
||||
df["粉粒分级"] = df["粉粒"].apply(lambda x: classify_silt(x) if pd.notna(x) else np.nan)
|
||||
if "黏粒" in df.columns:
|
||||
df["黏粒分级"] = df["黏粒"].apply(lambda x: classify_clay(x) if pd.notna(x) else np.nan)
|
||||
if "砂粒" in df.columns:
|
||||
df["砂粒分级"] = df["砂粒"].apply(lambda x: classify_sand(x) if pd.notna(x) else np.nan)
|
||||
if "有效土层厚度" in df.columns:
|
||||
df["有效土层厚度分级"] = df["有效土层厚度"].apply(lambda x: classify_yxtchd(x) if pd.notna(x) else np.nan)
|
||||
if "土壤质地" in df.columns:
|
||||
df["土壤质地分级"] = df["土壤质地"].apply(lambda x: classify_trzd(x) if pd.notna(x) else np.nan)
|
||||
|
||||
return df
|
||||
|
||||
def main():
|
||||
"""
|
||||
主函数：程序入口
|
||||
用户需根据实际情况修改以下参数
|
||||
"""
|
||||
logger = init_logger()
|
||||
logger.info("="*50)
|
||||
logger.info("土壤属性栅格面积加权统计程序启动")
|
||||
logger.info("="*50)
|
||||
|
||||
# --------------------------
|
||||
# 用户配置区域（必须修改！）
|
||||
# --------------------------
|
||||
# 1. 矢量图斑文件路径（支持Shapefile、GeoPackage等格式）
|
||||
# TODO
|
||||
VECTOR_PATH = r"D:\工作\三普成果编制\出图数据\北海\三普栅格\DL_ALL.shp" # 示例："D:/data/土壤图斑.shp"
|
||||
|
||||
# 2. 土壤属性栅格文件配置（键：属性名称，值：栅格文件路径）
|
||||
# 注意：属性名称必须与最终表格列名一致
|
||||
# TODO
|
||||
RASTER_FILES = {
|
||||
"耕层厚度": r"D:\工作\三普成果编制\出图数据\北海\三普栅格\GZCHD.tif", # 示例："D:/data/耕层厚度.tif"
|
||||
"土壤容重": r"D:\工作\三普成果编制\出图数据\北海\三普栅格\TRRZ.tif", # 示例："D:/data/土壤容重.tif"
|
||||
"砂粒": r"D:\工作\三普成果编制\出图数据\北海\三普栅格\SL.tif", # 示例："D:/data/砂粒含量.tif"
|
||||
"粉粒": r"D:\工作\三普成果编制\出图数据\北海\三普栅格\FL.tif", # 示例："D:/data/粉粒含量.tif"
|
||||
"黏粒": r"D:\工作\三普成果编制\出图数据\北海\三普栅格\NL.tif", # 示例："D:/data/黏粒含量.tif"
|
||||
"酸碱度": r"D:\工作\三普成果编制\出图数据\北海\三普栅格\PH.tif", # 示例："D:/data/pH值.tif"
|
||||
"阳离子": r"D:\工作\三普成果编制\出图数据\北海\三普栅格\CEC.tif", # 示例："D:/data/阳离子交换量.tif"
|
||||
"有机质": r"D:\工作\三普成果编制\出图数据\北海\三普栅格\OM.tif", # 示例："D:/data/有机质含量.tif"
|
||||
"全氮": r"D:\工作\三普成果编制\出图数据\北海\三普栅格\TN.tif", # 示例："D:/data/全氮含量.tif"
|
||||
"全磷": r"D:\工作\三普成果编制\出图数据\北海\三普栅格\TP.tif", # 示例："D:/data/全磷含量.tif"
|
||||
"全钾": r"D:\工作\三普成果编制\出图数据\北海\三普栅格\TK.tif", # 示例："D:/data/全钾含量.tif"
|
||||
"有效磷": r"D:\工作\三普成果编制\出图数据\北海\三普栅格\AP.tif", # 示例："D:/data/有效磷含量.tif"
|
||||
"速效钾": r"D:\工作\三普成果编制\出图数据\北海\三普栅格\AK.tif", # 示例："D:/data/速效钾含量.tif"
|
||||
# "有效铁": r"D:\工作\三普成果编制\出图数据\北海\三普栅格\AFE.tif", # 示例："D:/data/有效铁含量.tif"
|
||||
"有效锌": r"D:\工作\三普成果编制\出图数据\北海\三普栅格\AZN.tif", # 示例："D:/data/有效锌含量.tif"
|
||||
"有效锰": r"D:\工作\三普成果编制\出图数据\北海\三普栅格\AMN.tif", # 示例："D:/data/有效锰含量.tif"
|
||||
"有效铜": r"D:\工作\三普成果编制\出图数据\北海\三普栅格\ACU.tif", # 示例："D:/data/有效铜含量.tif"
|
||||
"有效硼": r"D:\工作\三普成果编制\出图数据\北海\三普栅格\AB.tif", # 示例："D:/data/有效硼含量.tif"
|
||||
"有效钼": r"D:\工作\三普成果编制\出图数据\北海\三普栅格\AMO.tif", # 示例："D:/data/有效钼含量.tif"
|
||||
"有效硫": r"D:\工作\三普成果编制\出图数据\北海\三普栅格\AS1.tif", # 示例："D:/data/有效硫含量.tif"
|
||||
"交换性钙": r"D:\工作\三普成果编制\出图数据\北海\三普栅格\ECA.tif", # 示例："D:/data/交换性钙含量.tif"
|
||||
"交换性镁": r"D:\工作\三普成果编制\出图数据\北海\三普栅格\EMG.tif", # 示例："D:/data/交换性镁含量.tif"
|
||||
"全硒": r"D:\工作\三普成果编制\出图数据\北海\三普栅格\TSE.tif", # 示例："D:/data/全硒含量.tif"
|
||||
"有效土层厚度": r"D:\工作\三普成果编制\出图数据\北海\三普栅格\YXTCHD.tif", # 示例："D:/data/有效土层厚度.tif"
|
||||
"土壤质地": r"D:\工作\三普成果编制\出图数据\北海\三普栅格\TRZD.tif", # 示例："D:/data/土壤质地.tif"
|
||||
}
|
||||
|
||||
# 3. 结果输出路径（Excel文件）
|
||||
OUTPUT_PATH = "土壤属性图斑数据_面积加权结果.xlsx" # 示例："D:/result/结果.xlsx"
|
||||
|
||||
# --------------------------
|
||||
# 程序执行流程（无需修改）
|
||||
# --------------------------
|
||||
try:
|
||||
# 1. 数据验证
|
||||
if not validate_data(VECTOR_PATH, RASTER_FILES):
|
||||
logger.error("数据验证失败，程序终止")
|
||||
return
|
||||
|
||||
# 2. 执行面积加权统计
|
||||
result_df = calculate_area_weighted_stats(VECTOR_PATH, RASTER_FILES, OUTPUT_PATH)
|
||||
|
||||
# 3. 显示结果预览
|
||||
logger.info("\\n结果预览（前3行）：")
|
||||
print(result_df.head(3).to_string(index=False))
|
||||
|
||||
logger.info("\\n" + "="*50)
|
||||
logger.info("程序执行完成！")
|
||||
logger.info(f"结果文件：{OUTPUT_PATH}")
|
||||
logger.info("="*50)
|
||||
|
||||
except Exception as e:
|
||||
logger.error(f"程序执行出错：{str(e)}", exc_info=True)
|
||||
logger.error("程序异常终止")
|
||||
|
||||
if __name__ == "__main__":
|
||||
# 启动主程序
|
||||
main()
|
||||
Reference in New Issue
Block a user