DEVELOPMENT... { "data_id": "44986", "name": "nyc_taxi_green", "exact_name": "nyc_taxi_green", "version": 2, "version_label": null, "description": "**Data Description**\n\nThe dataset includes New York City Taxi and Limousine Commission (TLC) trips of the green line in December 2016. All trips are paid with a credit card leaving some tip.\n\nThe variable 'tip_amount' was chosen as target variable.\n\n**Attribute Description**\n\n1. *VendorID* - A code indicating the LPEP provider that provided the record. 1: Creative Mobile Technologies, LLC; 2: VeriFone Inc.\n2. *store_and_fwd_flag*\n3. *RatecodeID*\n4. *PULocationID*\n5. *DOLocationID* - TLC Taxi Zone in which the taximeter was disengaged.\n6. *passenger_count* - the number of passengers in the vehicle. This is a driver-entered value\n7. *extra* - miscellaneous extras and surcharges. Currently, this only includes the $0.50 and $1 rush hour and overnight charges\n8. *mta_tax* - $0.50 MTA tax that is automatically triggered based on the metered rate in use.\n9. *tip_amount* - target feature\n10. *tolls_amount*\n11. *improvement_surcharge* - $0.30 improvement surcharge assessed on hailed trips at the flag drop\n12. *total_amount*\n13. *trip_type* - 1: Street-hail, 2: Dispatch\n14. *lpep_pickup_datetime_day*\n15. *lpep_pickup_datetime_hour*\n16. *lpep_pickup_datetime_minute*\n17. *lpep_dropoff_datetime_day*\n18. *lpep_dropoff_datetime_hour*\n19. *lpep_dropoff_datetime_minute*", "format": "arff", "uploader": "Shirley ", "uploader_id": 30127, "visibility": "public", "creator": null, "contributor": null, "date": "2022-12-22 16:17:26", "update_comment": null, "last_update": "2022-12-22 16:17:26", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111850\/file22f166d4202.arff", "default_target_attribute": "tip_amount", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "nyc_taxi_green", "The dataset includes New York City Taxi and Limousine Commission (TLC) trips of the green line in December 2016. All trips are paid with a credit card leaving some tip. The variable 'tip_amount' was chosen as target variable. 1. *VendorID* - A code indicating the LPEP provider that provided the record. 1: Creative Mobile Technologies, LLC; 2: VeriFone Inc. 2. *store_and_fwd_flag* 3. *RatecodeID* 4. *PULocationID* 5. *DOLocationID* - TLC Taxi Zone in which the taximeter was disengaged. 6. *passen " ], "weight": 5 }, "qualities": { "NumberOfInstances": 581835, "NumberOfFeatures": 19, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 10, "NumberOfSymbolicFeatures": 9, "PercentageOfSymbolicFeatures": 47.368421052631575, "AutoCorrelation": -1.1205887074318988, "PercentageOfNumericFeatures": 52.63157894736842, "PercentageOfMissingValues": 0, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfBinaryFeatures": 15.789473684210526, "NumberOfBinaryFeatures": 3, "MinorityClassSize": null, "MinorityClassPercentage": null, "MajorityClassSize": null, "MajorityClassPercentage": null, "Dimensionality": 3.265530605755927e-5 }, "tags": [], "features": [ { "name": "tip_amount", "index": "8", "type": "numeric", "distinct": "1811", "missing": "0", "target": "1", "min": "-11", "max": "251", "mean": "2", "stdev": "3" }, { "name": "tolls_amount", "index": "9", "type": "numeric", "distinct": "105", "missing": "0", "min": "0", "max": "98", "mean": "0", "stdev": "1" }, { "name": "lpep_dropoff_datetime_minute", "index": "18", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "59", "mean": "30", "stdev": "17" }, { "name": "lpep_dropoff_datetime_hour", "index": "17", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "23", "mean": "14", "stdev": "7" }, { "name": "lpep_dropoff_datetime_day", "index": "16", "type": "numeric", "distinct": "31", "missing": "0", "min": "1", "max": "31", "mean": "15", "stdev": "9" }, { "name": "lpep_pickup_datetime_minute", "index": "15", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "59", "mean": "30", "stdev": "17" }, { "name": "lpep_pickup_datetime_hour", "index": "14", "type": "numeric", "distinct": "24", "missing": "0", "min": "0", "max": "23", "mean": "14", "stdev": "7" }, { "name": "lpep_pickup_datetime_day", "index": "13", "type": "numeric", "distinct": "31", "missing": "0", "min": "1", "max": "31", "mean": "15", "stdev": "9" }, { "name": "trip_type", "index": "12", "type": "nominal", "distinct": "2", "missing": "0", "distr": [] }, { "name": "total_amount", "index": "11", "type": "numeric", "distinct": "5377", "missing": "0", "min": "-63", "max": "712", "mean": "17", "stdev": "12" }, { "name": "improvement_surcharge", "index": "10", "type": "nominal", "distinct": "3", "missing": "0", "distr": [] }, { "name": "VendorID", "index": "0", "type": "nominal", "distinct": "2", "missing": "0", "distr": [] }, { "name": "mta_tax", "index": "7", "type": "nominal", "distinct": "3", "missing": "0", "distr": [] }, { "name": "extra", "index": "6", "type": "nominal", "distinct": "5", "missing": "0", "distr": [] }, { "name": "passenger_count", "index": "5", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "DOLocationID", "index": "4", "type": "nominal", "distinct": "259", "missing": "0", "distr": [] }, { "name": "PULocationID", "index": "3", "type": "nominal", "distinct": "233", "missing": "0", "distr": [] }, { "name": "RatecodeID", "index": "2", "type": "nominal", "distinct": "5", "missing": "0", "distr": [] }, { "name": "store_and_fwd_flag", "index": "1", "type": "nominal", "distinct": "2", "missing": "0", "distr": [] } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 0, "total_downloads": 0, "reach": 0, "reuse": 0, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 0 }