nyc-taxi-green-dec-2016 (Q6036121)

String datetime information extracted to numeric columns.Trip Record Data provided by the New York City Taxi and Limousine Commission (TLC) [http://www.nyc.gov/html/tlc/html/about/trip_record_data.shtml]. The dataset includes TLC trips of the green line in December 2016. Data was downloaded on 03.11.2018. For a description of all variables in the dataset checkout the TLC homepage [http://www.nyc.gov/html/tlc/downloads/pdf/data_dictionary_trip_records_green.pdf]. The variable 'tip_amount' was chosen as target variable. The variable 'total_amount' is ignored by default, otherwise the target could be predicted deterministically. The date variables 'lpep_pickup_datetime' and 'lpep_dropoff_datetime' (ignored by default) could be used to compute additional time features. In this version, we chose only trips with 'payment_type' == 1 (credit card), as tips are not included for most other payment types. We also removed the variables 'trip_distance' and 'fare_amount' to increase the importance of the categorical features 'PULocationID' and 'DOLocationID'.