'commit'

2025-09-10 13:50:18 +08:00
parent a19db36b7d
commit 3009beeb3d
6 changed files with 355 additions and 211 deletions
--- a/Tools/T1_RenKou.py
+++ b/Tools/T1_RenKou.py
@@ -1,49 +1,63 @@
-import openpyxl  # 添加缺少的导入
+import openpyxl
 import json
 import os
-
+from typing import List, Dict, Any
 from Config.Config import EXCEL_PATH
 from Util.AreaUtil import query_area_info

-# 创建数据保存目录
+# ======================= 配置常量 =======================
 DATA_DIR = os.path.join(os.path.dirname(os.path.dirname(__file__)), 'Data')
-os.makedirs(DATA_DIR, exist_ok=True)
 JSON_PATH = os.path.join(DATA_DIR, 'RenKou.json')
+SHEET_NAME = '人口'                  # 工作表名称
+REGION_NAME_COLUMN = 'A'            # 区域名称所在列
+START_ROW = 3                       # 数据起始行
+YEAR_RANGE = range(2015, 2025)      # 年份范围

-file_name = EXCEL_PATH
-population_data = []
-name_conversion_errors = []  # 记录转换失败的名称
-conversion_records = []  # 新增：定义转换记录变量
+# 数据列配置 (指标: (起始列, 结束列))
+DATA_COLUMNS = {
+    'total_population': ('B', 'K'),      # 年末总人口
+    'urban_population': ('L', 'U'),      # 城镇人口
+    'rural_population': ('V', 'AE'),     # 乡村人口
+    'urbanization_rate': ('AF', 'AO'),   # 城镇化率
+    'birth_population': ('AP', 'AY')     # 出生人口
+}

-try:
-    # 加载工作簿并选择人口Sheet
-    workbook = openpyxl.load_workbook(file_name, read_only=True)
-    if '人口' not in workbook.sheetnames:
-        print("❌ 错误：未找到'人口'Sheet")
-        exit(1)
-    sheet = workbook['人口']
+# ======================= 工具函数 =======================
+def init_directories() -> None:
+    """初始化数据目录"""
+    os.makedirs(DATA_DIR, exist_ok=True)

-    # 定义数据列范围与英文属性映射
-    data_columns = {
-        'total_population': {'start_col': 'B', 'end_col': 'K', 'year_start': 2015},  # 年末总人口
-        'urban_population': {'start_col': 'L', 'end_col': 'U', 'year_start': 2015},   # 城镇人口
-        'rural_population': {'start_col': 'V', 'end_col': 'AE', 'year_start': 2015},  # 乡村人口
-        'urbanization_rate': {'start_col': 'AF', 'end_col': 'AO', 'year_start': 2015}, # 城镇化率
-        'birth_population': {'start_col': 'AP', 'end_col': 'AY', 'year_start': 2015}   # 出生人口
-    }

-    # 遍历数据行（跳过前2行表头）
-    for row_num, row in enumerate(sheet.iter_rows(min_row=3, values_only=True), start=3):
-        raw_name = row[0] if row[0] else '未知地区'
-        if not raw_name:  # 跳过空行
+def process_value(value: Any) -> int | float | int:
+    """处理单元格值，转换为合适的数值类型"""
+    if value is None or str(value).strip() == '':
+        return 0
+    try:
+        if isinstance(value, str):
+            value = value.replace(',', '').strip()
+        return float(value) if '.' in str(value) else int(value)
+    except (ValueError, TypeError):
+        return 0
+
+# ======================= 核心逻辑 =======================
+def extract_area_data(sheet: openpyxl.worksheet.worksheet.Worksheet) -> List[Dict[str, Any]]:
+    """从工作表提取区域数据"""
+    population_data: List[Dict[str, Any]] = []
+    conversion_records: List[Dict[str, str]] = []
+    name_conversion_errors: List[str] = []
+
+    # 遍历数据行
+    for row_num in range(START_ROW, sheet.max_row + 1):
+        row = sheet[row_num]
+        raw_name = str(row[openpyxl.utils.column_index_from_string(REGION_NAME_COLUMN)-1].value or '未知地区').strip()
+        if not raw_name:
            continue

-        # 区域名称转换（核心修改）
-        area_info = query_area_info(raw_name.strip())
+        # 区域名称转换
+        area_info = query_area_info(raw_name)
        if area_info:
            area_name = area_info['full_name']
            area_code = area_info['area_code']
-            # 新增：检查是否发生实际转换
            if raw_name != area_name:
                conversion_records.append({
                    'row': row_num,
@@ -55,58 +69,77 @@ try:
            area_code = 'unknown'
            name_conversion_errors.append(f"行 {row_num}: '{raw_name}'")

+        # 构建区域数据
        area_data = {
            'area_name': area_name,
            'area_code': area_code,
-            'raw_name': raw_name  # 保留原始名称用于调试
+            'raw_name': raw_name
        }

        # 提取各指标年度数据
-        for metric, config in data_columns.items():
-            start_col = openpyxl.utils.column_index_from_string(config['start_col']) - 1
-            end_col = openpyxl.utils.column_index_from_string(config['end_col']) - 1
+        for metric, (start_col, end_col) in DATA_COLUMNS.items():
+            start_idx = openpyxl.utils.column_index_from_string(start_col) - 1
+            end_idx = openpyxl.utils.column_index_from_string(end_col) - 1
            year_data = {}

-            for col_idx, year in zip(range(start_col, end_col + 1), range(config['year_start'], 2025)):
-                value = row[col_idx]
-                # 处理空值和非数值
-                if value is None or str(value).strip() == '':
-                    year_data[str(year)] = 0
-                else:
-                    try:
-                        year_data[str(year)] = float(value) if '.' in str(value) else int(value)
-                    except (ValueError, TypeError):
-                        year_data[str(year)] = 0
+            for col_idx, year in zip(range(start_idx, end_idx + 1), YEAR_RANGE):
+                cell_value = row[col_idx].value
+                year_data[str(year)] = process_value(cell_value)

            area_data[metric] = year_data

        population_data.append(area_data)

-    workbook.close()
+    # 输出转换统计
+    print_conversion_stats(conversion_records, name_conversion_errors)
+    return population_data

-    # 保存为JSON文件
-    with open(JSON_PATH, 'w', encoding='utf-8') as f:
-        json.dump(population_data, f, ensure_ascii=False, indent=2)

-    # 输出转换结果统计
-    print(f"✅ 人口数据提取完成，已保存至：{JSON_PATH}")
-    print(f"📊 共处理 {len(population_data)} 条地区数据")
-    # 输出转换校验结果
+def print_conversion_stats(conversion_records: List[Dict[str, str]], errors: List[str]) -> None:
+    """打印名称转换统计信息"""
    print("\n=== 名称转换记录 ===")
-    if conversion_records:
-        for record in conversion_records:
-            print(f"🔄 行 {record['row']}: {record['raw_name']} → {record['converted_name']}")
-        print(f"📊 共检测到 {len(conversion_records)} 项名称转换")
-    else:
-        print("📝 不存在名称转换的情况")
-    if name_conversion_errors:
-        print(f"⚠️ 发现 {len(name_conversion_errors)} 个区域名称转换失败：")
-        for error in name_conversion_errors:
+    for record in conversion_records:
+        print(f"🔄 行 {record['row']}: {record['raw_name']} → {record['converted_name']}")
+    print(f"📊 共检测到 {len(conversion_records)} 项名称转换")
+
+    if errors:
+        print(f"⚠️ 发现 {len(errors)} 个区域名称转换失败：")
+        for error in errors:
            print(f"  - {error}")
    else:
        print("✅ 所有区域名称均成功转换为全称")

-except FileNotFoundError:
-    print(f"🔴 错误：Excel文件 '{file_name}' 不存在")
-except Exception as e:
-    print(f"🔴 处理数据时发生错误：{str(e)}")
+# ======================= 主函数 =======================
+def main() -> None:
+    """人口数据提取主函数"""
+    init_directories()
+    try:
+        # 加载工作簿
+        workbook = openpyxl.load_workbook(EXCEL_PATH, read_only=True, data_only=True)
+        if SHEET_NAME not in workbook.sheetnames:
+            print(f"❌ 错误：未找到'{SHEET_NAME}'工作表")
+            return
+
+        # 提取并处理数据
+        sheet = workbook[SHEET_NAME]
+        population_data = extract_area_data(sheet)
+
+        # 保存结果
+        with open(JSON_PATH, 'w', encoding='utf-8') as f:
+            json.dump(population_data, f, ensure_ascii=False, indent=2)
+
+        print(f"✅ 人口数据提取完成，已保存至：{JSON_PATH}")
+        print(f"📊 共处理 {len(population_data)} 条地区数据")
+
+    except FileNotFoundError:
+        print(f"🔴 错误：Excel文件 '{EXCEL_PATH}' 不存在")
+    except Exception as e:
+        print(f"🔴 处理数据时发生错误：{str(e)}")
+    finally:
+        try:
+            workbook.close()
+        except:
+            pass
+
+if __name__ == '__main__':
+    main()