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_new.csv")
# print(data.shape)
# # # 去重并统计ID个数
# unique_ids = data.drop_duplicates(subset=["ID","communityID"])
# 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)
# import pyreadstat
# import numpy as np

# year = "2018"
# cognition, meta = pyreadstat.read_dta("/root/r_base/CHARLS/CHARLS"+year+"/Cognition.dta")
# #计算认知功能得分，分成三部分：电话问卷10分，词语回忆10分、画图1分
# cognition["dc001s1_score"] = cognition["dc001_w4"].apply(lambda x : 1 if x==1 else 0 if x==5 else np.nan)
# cognition["dc001s2_score"] = cognition["dc006_w4"].apply(lambda x : 1 if x==1 else 0 if x==5 else np.nan)
# cognition["dc001s3_score"] = cognition["dc003_w4"].apply(lambda x : 1 if x==1 else 0 if x==5 else np.nan)
# cognition["dc002_score"] = cognition["dc005_w4"].apply(lambda x : 1 if x==1 else 0 if x==5 else np.nan)
# cognition["dc003_score"] = cognition["dc002_w4"].apply(lambda x : 1 if x==1 else 0 if x==5 else np.nan)
# cognition["dc019_score"] = cognition.apply(lambda x : 0 if x["dc014_w4_1"]==97 else 1 if pd.isna(x["dc014_w4_1"]) and x["dc014_w4_1_1"]==93 else 0 if pd.isna(x["dc014_w4_1"]) and (not x["dc014_w4_1_1"]==93) else np.nan, axis=1) 
# cognition["dc020_score"] = cognition.apply(lambda x : 0 if x["dc014_w4_2"]==97 else 1 if pd.isna(x["dc014_w4_2"]) and x["dc014_w4_2_1"]==86 else 0 if pd.isna(x["dc014_w4_2"]) and (not x["dc014_w4_2_1"]==86) else np.nan, axis=1) 
# cognition["dc021_score"] = cognition.apply(lambda x : 0 if x["dc014_w4_3"]==97 else 1 if pd.isna(x["dc014_w4_3"]) and x["dc014_w4_3_1"]==79 else 0 if pd.isna(x["dc014_w4_3"]) and (not x["dc014_w4_3_1"]==79) else np.nan, axis=1)
# cognition["dc022_score"] = cognition.apply(lambda x : 0 if x["dc014_w4_4"]==97 else 1 if pd.isna(x["dc014_w4_4"]) and x["dc014_w4_4_1"]==72 else 0 if pd.isna(x["dc014_w4_4"]) and (not x["dc014_w4_4_1"]==72) else np.nan, axis=1)
# cognition["dc023_score"] = cognition.apply(lambda x : 0 if x["dc014_w4_5"]==97 else 1 if pd.isna(x["dc014_w4_5"]) and x["dc014_w4_5_1"]==65 else 0 if pd.isna(x["dc014_w4_5"]) and (not x["dc014_w4_5_1"]==65) else np.nan, axis=1)

# #词语记忆
# cognition["dc006s1_score"] = cognition.apply(lambda x : np.nan if not x["wr101_intro"] ==1 else 1 if x["dc028_w4_s1"]==1 else 0, axis=1)
# cognition["dc006s2_score"] = cognition.apply(lambda x : np.nan if not x["wr101_intro"] ==1 else 1 if x["dc028_w4_s2"]==2 else 0, axis=1)
# cognition["dc006s3_score"] = cognition.apply(lambda x : np.nan if not x["wr101_intro"] ==1 else 1 if x["dc028_w4_s3"]==3 else 0, axis=1)
# cognition["dc006s4_score"] = cognition.apply(lambda x : np.nan if not x["wr101_intro"] ==1 else 1 if x["dc028_w4_s4"]==4 else 0, axis=1) 
# cognition["dc006s5_score"] = cognition.apply(lambda x : np.nan if not x["wr101_intro"] ==1 else 1 if x["dc028_w4_s5"]==5 else 0, axis=1) 
# cognition["dc006s6_score"] = cognition.apply(lambda x : np.nan if not x["wr101_intro"] ==1 else 1 if x["dc028_w4_s6"]==6 else 0, axis=1)                                            
# cognition["dc006s7_score"] = cognition.apply(lambda x : np.nan if not x["wr101_intro"] ==1 else 1 if x["dc028_w4_s7"]==7 else 0, axis=1) 
# cognition["dc006s8_score"] = cognition.apply(lambda x : np.nan if not x["wr101_intro"] ==1 else 1 if x["dc028_w4_s8"]==8 else 0, axis=1) 
# cognition["dc006s9_score"] = cognition.apply(lambda x : np.nan if not x["wr101_intro"] ==1 else 1 if x["dc028_w4_s9"]==9 else 0, axis=1)                                            
# cognition["dc006s10_score"] = cognition.apply(lambda x : np.nan if not x["wr101_intro"] ==1 else 1 if x["dc028_w4_s10"]==10 else 0, axis=1)                                           
# # cognition["dc006s11_score"] = cognition["dc028_w4_s11"].apply(lambda x : 1 if x==11 else 0 if pd.isna(x) else 0) 
# cognition["dc027s1_score"] = cognition.apply(lambda x : np.nan if not x["wr101_intro"] ==1 else 1 if x["dc047_w4_s1"]==1 else 0, axis=1) 
# cognition["dc027s2_score"] = cognition.apply(lambda x : np.nan if not x["wr101_intro"] ==1 else 1 if x["dc047_w4_s2"]==2 else 0, axis=1) 
# cognition["dc027s3_score"] = cognition.apply(lambda x : np.nan if not x["wr101_intro"] ==1 else 1 if x["dc047_w4_s3"]==3 else 0, axis=1) 
# cognition["dc027s4_score"] = cognition.apply(lambda x : np.nan if not x["wr101_intro"] ==1 else 1 if x["dc047_w4_s4"]==4 else 0, axis=1) 
# cognition["dc027s5_score"] = cognition.apply(lambda x : np.nan if not x["wr101_intro"] ==1 else 1 if x["dc047_w4_s5"]==5 else 0, axis=1) 
# cognition["dc027s6_score"] = cognition.apply(lambda x : np.nan if not x["wr101_intro"] ==1 else 1 if x["dc047_w4_s6"]==6 else 0, axis=1)                                            
# cognition["dc027s7_score"] = cognition.apply(lambda x : np.nan if not x["wr101_intro"] ==1 else 1 if x["dc047_w4_s7"]==7 else 0, axis=1) 
# cognition["dc027s8_score"] = cognition.apply(lambda x : np.nan if not x["wr101_intro"] ==1 else 1 if x["dc047_w4_s8"]==8 else 0, axis=1) 
# cognition["dc027s9_score"] = cognition.apply(lambda x : np.nan if not x["wr101_intro"] ==1 else 1 if x["dc047_w4_s9"]==9 else 0, axis=1)                                            
# cognition["dc027s10_score"] = cognition.apply(lambda x : np.nan if not x["wr101_intro"] ==1 else 1 if x["dc047_w4_s10"]==10 else 0, axis=1)                                            
# # cognition["dc027s11_score"] = cognition["dc047_w4_s11"].apply(lambda x : 1 if x==11 else 0 if pd.isna(x) else 0)
# #画图
# cognition["draw_score"] = cognition["dc024_w4"].apply(lambda x : 1 if x==1 else 0 if x==5 else np.nan)

# cognition["Cognition_score"] = cognition["dc001s1_score"] + cognition["dc001s2_score"] + \
#     cognition["dc001s3_score"] + cognition["dc002_score"]+ cognition["dc003_score"]+ \
#     cognition["dc019_score"]+ cognition["dc020_score"] + cognition["dc021_score"]+ \
#     cognition["dc022_score"]+ cognition["dc023_score"] + cognition["dc006s1_score"] + \
#     cognition["dc006s2_score"] + cognition["dc006s3_score"] + cognition["dc006s4_score"] + \
#     cognition["dc006s5_score"] + cognition["dc006s6_score"] + cognition["dc006s7_score"] + \
#     cognition["dc006s8_score"] + cognition["dc006s9_score"] + cognition["dc006s10_score"] + \
#     cognition["dc027s1_score"]+ cognition["dc027s2_score"]+ \
#     cognition["dc027s3_score"]+ cognition["dc027s4_score"]+ cognition["dc027s5_score"]+ \
#     cognition["dc027s6_score"]+ cognition["dc027s7_score"]+ cognition["dc027s8_score"]+ \
#     cognition["dc027s9_score"]+cognition["dc027s10_score"]+\
#     cognition["draw_score"]
# cognition.to_csv("/root/r_base/CHARLS/test.csv")

# import pandas as pd
# CHARLS_data = pd.read_csv("CHARLS_data_pollutants_p_n_m_nd_h.csv")
# #合并
# merge_list = ["marital_status_m",	"Height_m",	"Weight_m",	"waist_m",	"Systolic_m",	"Diastolic_m",
#                 "Physical_activity_m",	"Smoke_m",	'Drink_m',	'Hypertension_m',	'Disabetes_or_High_Blood_Sugar_m',
#                 'Cancer_or_Malignant_Tumor_m',	'Chronic_Lung_Diseases_m',	'Heart_Problems_m',	'Emotional_Nervous_or_Psychiatric_Problems_m',
#                 'Stroke_m',	'Arthritis_or_Rheumatism_m',	'Dyslipidemia_m',	'Liver_Disease_m',	'Kidney_Diease_m',	'Stomach_or_Other_Digestive_Disease_m',
#                 'Asthma_m',	'Memory_Related_Disease_m',	'Psychiatric_score_m',	'sleep_state_m', 'Cognition_score_m']

# # 遍历 merge_list 列表
# for col_m in merge_list:
#     col = col_m.replace('_m', '')  # 去掉 '_m' 得到相应的列名
#     if col in CHARLS_data.columns and col_m in CHARLS_data.columns:
#         CHARLS_data[col] = CHARLS_data[col_m].fillna(CHARLS_data[col])

# CHARLS_data.to_csv("CHARLS_data_pollutants_p_n_m_nd_h_test.csv")


import base64

def audio_to_base64_string(file_path):
    # 打开语音文件并以二进制模式读取
    with open(file_path, "rb") as audio_file:
        audio_data = audio_file.read()
    
    # 对音频数据进行 Base64 编码
    encoded_audio = base64.b64encode(audio_data)
    
    # 将编码后的数据转换为字符串
    audio_string = encoded_audio.decode("utf-8")
    
    return audio_string

# 示例调用
file_path = "bjh_rec_0a8ed71a266044c0b72f50c1d3d6be15.wav"  # 将此处替换为你的文件路径
audio_string = audio_to_base64_string(file_path)

 # 将结果写入到文本文件中，以避免控制台显示乱码
with open("encoded_audio_string.txt", 'w') as output_file:
    output_file.write(audio_string)