Created
July 21, 2020 14:30
-
-
Save rikturr/1635e22721bcb6d1bb5805c9b0298303 to your computer and use it in GitHub Desktop.
pandas create features
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
taxi['pickup_weekday'] = taxi.tpep_pickup_datetime.dt.weekday | |
taxi['pickup_weekofyear'] = taxi.tpep_pickup_datetime.dt.weekofyear | |
taxi['pickup_hour'] = taxi.tpep_pickup_datetime.dt.hour | |
taxi['pickup_minute'] = taxi.tpep_pickup_datetime.dt.minute | |
taxi['pickup_year_seconds'] = (taxi.tpep_pickup_datetime - datetime.datetime(2019, 1, 1, 0, 0, 0)).dt.seconds | |
taxi['pickup_week_hour'] = (taxi.pickup_weekday * 24) + taxi.pickup_hour | |
taxi['passenger_count'] = taxi.passenger_count.astype(float).fillna(-1) | |
taxi = taxi.fillna(value={'VendorID': 'missing', 'RatecodeID': 'missing', 'store_and_fwd_flag': 'missing' }) | |
# keep track of column names for pipeline steps | |
numeric_feat = ['pickup_weekday', 'pickup_weekofyear', 'pickup_hour', 'pickup_minute', 'pickup_year_seconds', 'pickup_week_hour', 'passenger_count'] | |
categorical_feat = ['VendorID', 'RatecodeID', 'store_and_fwd_flag', 'PULocationID', 'DOLocationID'] | |
features = numeric_feat + categorical_feat | |
y_col = 'total_amount' |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment