Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- import argparse
- import os
- import pandas as pd
- def parse_augments(s):
- potency = s.str.extract('([0-9\+\-]+)', expand=False)
- augment = s.replace(regex=True, to_replace='[0-9\+\-\%]', value='').str.strip()
- return augment, potency
- def parse_csv(path):
- df = pd.read_csv(path)
- augment_columns = [column for column in df.columns if 'augment' in column]
- for column in augment_columns:
- df[column], df['%s potency' % column] = parse_augments(df[column])
- return df
- if __name__ == "__main__":
- parser = argparse.ArgumentParser()
- parser.add_argument('directory', type=str, help="Directory containing augment csv files")
- args = parser.parse_args()
- df = pd.concat([parse_csv('%s\%s' % (args.directory, fn)) for fn in os.listdir(args.directory)])
- df = df.drop_duplicates()
- df.to_csv('merged.csv', index=False)
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement