import pandas as pd
from pathlib import Path
from concurrent.futures import ProcessPoolExecutor

parse_path = '/data1/v-gazh/CRSP/dsf_full_fields/parse'
source_path = '/data1/v-gazh/CRSP/dsf_full_fields/2th_split' # 目錄中有3.3W個csv文件，串行的話，效率大打折扣


def parseData():
  source_path_list = list(Path(source_path).glob('*.csv'))
  multi_process = ProcessPoolExecutor(max_workers=20)
  multi_results = multi_process.map(func, source_path_list)


def func(p):
  source_p = str(p)
  parse_p = str(p).replace('2th_split', 'parse')
  df = pd.read_csv(source_p)
  df['date'] = pd.to_datetime(df['date'].astype(str)).dt.date
  df.sort_values(['date'], inplace=True)
  # 處理close為負(fù)的值(abs)，添加status標(biāo)識
  df['is_close'] = df['PRC'].map(lambda x: 0 if x < 0 or pd.isna(x) else 1)
  df['PRC'] = df['PRC'].abs()
  df.rename(columns={'CFACPR': 'factor'}, inplace=True)
  df['adj_low'] = df['BIDLO'] * df['factor']
  df['adj_high'] = df['ASKHI'] * df['factor']
  df['adj_close'] = df['PRC'] * df['factor']
  df['adj_open'] = df['OPENPRC'] * df['factor']
  df['adj_volume'] = df['VOL'] / df['factor']
  # calc change
  df['change'] = df['adj_close'].diff(1) / df['adj_close'].shift(1)　　 df.drop_duplicates(inplace=True)
  df.to_csv(parse_p, index=False)
parseData()