Medical_code/test.py

import pandas as pd

# data = pd.read_csv("CLHLS/clhls_1998_2018_result.csv")
# print(data.shape)


# data = pd.read_csv("HRS/result_all.csv")
# print(data.shape)
# # 去重并统计ID个数
# unique_ids = data.drop_duplicates(subset=["HHID", "PN"])
# count_unique_ids = unique_ids.count()
# print(count_unique_ids)

# data = pd.read_csv("/root/r_base/UKDA-5050-stata/result_all.csv")
# print(data.shape)
# # 去重并统计ID个数
# unique_ids = data.drop_duplicates(subset=["id"])
# count_unique_ids = unique_ids.count()
# print(count_unique_ids)

# df = pd.read_stata('/root/r_base/UKDA-5050-stata/stata/stata13_se/wave_9_elsa_data_eul_v1.dta', convert_categoricals=False)
# print(df.shape)
# df = pd.read_stata('/root/r_base/UKDA-5050-stata/stata/stata13_se/wave_9_elsa_pensiongrid_eul_v2.dta', convert_categoricals=False)
# print(df.shape)
# df = pd.read_stata('/root/r_base/UKDA-5050-stata/stata/stata13_se/wave_9_financial_derived_variables.dta', convert_categoricals=False)
# print(df.shape)
# df = pd.read_stata('/root/r_base/UKDA-5050-stata/stata/stata13_se/wave_9_ifs_derived_variables.dta', convert_categoricals=False)
# print(df.shape)

# 指定文件夹路径
# import glob
# import os
# folder_path = '/root/r_base/NHANES/2017-2018'

# # 获取所有 .xpt 文件的路径
# xpt_files = glob.glob(os.path.join(folder_path, '*.XPT'))

# num = 0
# # 读取并处理每一个 .xpt 文件
# for file_path in xpt_files:
#     try:
#         # 使用 pandas 读取 .xpt 文件
#         df = pd.read_sas(file_path, format='xport')
#         # 输出数据框的前几行以进行检查
#         print(f"Data from {file_path}:")
#         print(df.shape)
#         num += df.shape[1]
#     except Exception as e:
#         print(f"Error reading {file_path}: {e}")
# print(num)

# data = pd.read_csv("/root/r_base/CHARLS/result_all.csv")
# print(data.shape)
# # 去重并统计ID个数
# unique_ids = data.drop_duplicates(subset=["householdID"])
# count_unique_ids = unique_ids.count()
# print(count_unique_ids)
# 指定文件夹路径
# import glob
# import os
# folder_path = '/root/r_base/CHARLS/CHARLS2018'

# # 获取所有 .xpt 文件的路径
# xpt_files = glob.glob(os.path.join(folder_path, '*.dta'))
# num = 0
# # 读取并处理每一个 .xpt 文件
# for file_path in xpt_files:
#     try:
#         # 使用 pandas 读取 .xpt 文件
#         df = pd.read_stata(file_path)
#         # 输出数据框的前几行以进行检查
#         print(f"Data from {file_path}:")
#         print(df.shape)
#         num += df.shape[1]
#     except Exception as e:
#         print(f"Error reading {file_path}: {e}")
# print(num)