Repository for Petra's work at ampli Jan-Feb 2019

collate.py 534B

123456789101112131415161718192021
  1. # Collate 12 dataframes into one (wide) combined dataframe
  2. # Made redundant by downkwh.py
  3. import pandas as p
  4. import gc
  5. from tqdm import tqdm
  6. months = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec']
  7. coldf = p.read_pickle('../data/2017-{}-5k.pkl'.format(months[0]))
  8. for i in tqdm(range(1, 12)):
  9. tdf = p.read_pickle('../data/2017-{}-5k.pkl'.format(months[i]))
  10. coldf = p.concat([coldf, tdf])
  11. del tdf
  12. gc.collect()
  13. print(coldf.info())
  14. coldf.to_pickle('../data/2017-5k-wide.pkl')