MergeData

import os import pandas as pd

# 读取社区代码表 code = pd.read_excel("社区代码.xlsx", usecols=[0, 1]) code['区划代码'] = code['区划代码'].astype("str") # 强制转化类型 code.index = code['区划代码'] # 初始化合并后数据集 merge_data = pd.DataFrame() # 通过编码获取社区名称 def get_community_name(community_code): global code print(community_code) return code.loc[community_code, :]['社区']

def get_community_code(filename): return filename[0:filename.find('_')]

def load_data(file_fullname, community_code, community_name): global merge_data df = pd.read_excel(file_fullname, skiprows=1) df['code'] = community_code df['name'] = community_name merge_data = merge_data.append(df,ignore_index=True)

def run(data_dir='data'): # 遍历当前目录子目录data下的所有xlsx文件 watch_dir = os.path.join(os.getcwd(), data_dir) for file in os.listdir(watch_dir): (filename, extension) = os.path.splitext(file) if extension.lower() in ['.xlsx']: file_fullname = os.path.join(watch_dir, file) community_code = get_community_code(filename) community_name = get_community_name(community_code) print(community_name) load_data(file_fullname, community_code, community_name) run() merge_data

print("Waiting for saving data.") merge_data.to_excel("社区合并数据.xlsx") print("Saved!")

merge_data['类型'].value_counts(sort=True)