resampling and timezone conversion using Pandas

prep_log.py

import pandas as pd


def prep_log(sec_file, min_file, src_tz='US/Pacific', dst_tz='US/Eastern', datetime_fmt='%m/%d/%y %H:%M'):
  """Preprocess a second level log file by aggregating it in a minute level and converting timezone if necessary.
  
  Args:
    sec_file: a second level CSV log file with timestamps in the first column
    min_file: a minute level CSV output log file with timestamps in the first column
    src_tz: a source timezone (default: EST)
    dst_tz: a destination timezone (default: PST)
    datetime_fmt: a datetime format (default:m/d/yy HH:MM)
    
  Return:
    save an output file as min_file
  """
  # load a second level CSV file. parse the datetime from the first column.
  df = pd.read_csv(sec_file, index_col=0, parse_dates=True)
  
  # resample the data by minutes and fill NAs with 0s.
  df_min = df.resample('Min', how='sum')
  df_min.fillna(0, inplace=True)
  
  # if necessary, convert its timezone
  if src_tz != dst_tz:
    df_min.index = df_min.index.tz_localize(src_tz).tz_convert(dst_tz)
  
  # save the minute level data as a CSV file with the datetime format given
  df_min.to_csv(min_file, date_format=datetime_fmt)