story_bike_share_clean_2.py

# Identify the date structure used by each of the files as a dict:
#      * Key: data file name
#      * Value: [datetime format, hour difference bewteen timezone used and Eastern timezone]
date_formats = {
    'Bikeshare Ridership (2017 Q1).csv': ['%d/%m/%Y %H:%M', -4],
    'Bikeshare Ridership (2017 Q2).csv': ['%d/%m/%Y %H:%M', -4],
    'Bikeshare Ridership (2017 Q3).csv': ['%m/%d/%Y %H:%M', 0],
    'Bikeshare Ridership (2017 Q4).csv': ['%m/%d/%y %H:%M:%S', 0],
}
df = pd.DataFrame() # Initiate an empty DataFrame
for fn, fmt in date_formats.items():
    tmp = pd.read_csv(os.path.join('./data', fn))
    
    # Read the datetime in the specified format
    tmp['trip_start_time'] = pd.to_datetime(tmp['trip_start_time'], format=fmt[0], errors='coerce')
    # Convert the input time to the Easter timezone
    tmp['trip_start_time'] = tmp['trip_start_time'] + timedelta(hours=fmt[1])

df = pd.concat([df, tmp], sort=False).reset_index(drop=True)