Files
YunNanProject/Tools/T2_MaoRuXueLv.py

173 lines
7.6 KiB
Python
Raw Normal View History

2025-09-10 11:15:03 +08:00
import openpyxl # 添加缺少的导入
import json
import os
from Config.Config import EXCEL_PATH
from Util.AreaUtil import query_area_info
# 创建数据保存目录
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, 'MaoRuXueLv.json') # 修改为毛入学率的JSON路径
file_name = EXCEL_PATH
enrollment_data = []
name_conversion_errors = [] # 记录转换失败的名称
conversion_records = [] # 定义转换记录变量
try:
# 加载工作簿并选择毛入学率Sheet
workbook = openpyxl.load_workbook(file_name, read_only=True)
if '毛入学率' not in workbook.sheetnames:
print("❌ 错误:未找到'毛入学率'Sheet")
exit(1)
sheet = workbook['毛入学率']
# 定义数据列范围与英文属性映射
# 学前教育(交替列逻辑)
data_columns = {
# 学前教育 - 交替列映射2015-2024
'preschool_enrollment': {
'columns': ['D', 'F', 'H', 'J', 'L', 'N', 'P', 'R', 'T', 'V'],
'years': [2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024]
},
'preschool_enrollment_rate': {
'columns': ['E', 'G', 'I', 'K', 'M', 'O', 'Q', 'S', 'U', 'W'],
'years': [2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024]
},
# 小学教育X-AQ列交替列逻辑
'primary_enrollment': {
'columns': ['X', 'Z', 'AB', 'AD', 'AF', 'AH', 'AJ', 'AL', 'AN', 'AP'],
'years': [2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024]
},
'primary_enrollment_rate': {
'columns': ['Y', 'AA', 'AC', 'AE', 'AG', 'AI', 'AK', 'AM', 'AO', 'AQ'],
'years': [2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024]
},
# 初中教育AR-BK列交替列逻辑
'junior_high_enrollment': {
'columns': ['AR', 'AT', 'AV', 'AX', 'AZ', 'BB', 'BD', 'BF', 'BH', 'BJ'],
'years': [2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024]
},
'junior_high_enrollment_rate': {
'columns': ['AS', 'AU', 'AW', 'AY', 'BA', 'BC', 'BE', 'BG', 'BI', 'BK'],
'years': [2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024]
},
# 普通高中教育BL-CE列交替列逻辑
'senior_high_enrollment': {
'columns': ['BL', 'BN', 'BP', 'BR', 'BT', 'BV', 'BX', 'BZ', 'CB', 'CD'],
'years': [2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024]
},
'senior_high_enrollment_rate': {
'columns': ['BM', 'BO', 'BQ', 'BS', 'BU', 'BW', 'BY', 'CA', 'CC', 'CE'],
'years': [2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024]
},
# 中职教育CF-CY列交替列逻辑
'vocational_enrollment': {
'columns': ['CF', 'CH', 'CJ', 'CL', 'CN', 'CP', 'CR', 'CT', 'CV', 'CX'],
'years': [2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024]
},
'vocational_enrollment_rate': {
'columns': ['CG', 'CI', 'CK', 'CM', 'CO', 'CQ', 'CS', 'CU', 'CW', 'CY'],
'years': [2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024]
}
}
# 遍历数据行跳过前4行表头
for row_num, row in enumerate(sheet.iter_rows(min_row=5, values_only=True), start=5):
# 区域名称从B列获取索引1原代码是从A列索引0获取
raw_name = row[1] if (len(row) > 1 and row[1] is not None) else '未知地区'
if not raw_name: # 跳过空行
continue
# 区域名称转换(核心修改)
# 确保raw_name为字符串类型再调用strip()
str_raw_name = str(raw_name).strip() if raw_name is not None else '未知地区'
area_info = query_area_info(str_raw_name)
if area_info:
area_name = area_info['full_name']
area_code = area_info['area_code']
# 检查是否发生实际转换
if raw_name != area_name:
conversion_records.append({
'row': row_num,
'raw_name': raw_name,
'converted_name': area_name
})
else:
area_name = raw_name
area_code = 'unknown'
name_conversion_errors.append(f"{row_num}: '{raw_name}'")
area_data = {
'area_name': area_name,
'area_code': area_code,
'raw_name': raw_name # 保留原始名称用于调试
}
# 提取各指标年度数据
for metric, config in data_columns.items():
year_data = {}
# 仅保留显式列名映射处理逻辑(完全移除旧格式代码)
if 'columns' in config and 'years' in config:
# 遍历预设的列名和年份对应关系
for col_name, year in zip(config['columns'], config['years']):
col_idx = openpyxl.utils.column_index_from_string(col_name) - 1
if col_idx < len(row):
value = row[col_idx]
# 处理空值和非数值(增强版)
if value is None:
year_data[str(year)] = 0
else:
# 统一转换为字符串处理
str_value = str(value).strip()
if str_value == '' or str_value == '####':
year_data[str(year)] = 0
else:
try:
if '%' in str_value:
# 移除百分号并转换为小数
year_data[str(year)] = float(str_value.replace('%', ''))
else:
year_data[str(year)] = float(str_value) if '.' in str_value else int(str_value)
except (ValueError, TypeError):
year_data[str(year)] = 0
# 删除旧格式的start_col/end_col处理分支
area_data[metric] = year_data
enrollment_data.append(area_data)
workbook.close()
# 保存为JSON文件
with open(JSON_PATH, 'w', encoding='utf-8') as f:
json.dump(enrollment_data, f, ensure_ascii=False, indent=2)
# 输出转换结果统计
print(f"✅ 毛入学率数据提取完成,已保存至:{JSON_PATH}")
print(f"📊 共处理 {len(enrollment_data)} 条地区数据")
# 输出转换校验结果
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:
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)}")