{
    "data_id": "44065",
    "name": "nyc-taxi-green-dec-2016",
    "exact_name": "nyc-taxi-green-dec-2016",
    "version": 9,
    "version_label": null,
    "description": "Dataset used in the tabular data benchmark https:\/\/github.com\/LeoGrin\/tabular-benchmark,  \n                                  transformed in the same way. This dataset belongs to the \"regression on categorical and\n                                  numerical features\" benchmark. Original description: \n \nString 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'.",
    "format": "arff",
    "uploader": "Leo Grin",
    "uploader_id": 26324,
    "visibility": "public",
    "creator": null,
    "contributor": "\"Leo Grin\"",
    "date": "2022-06-21 10:33:33",
    "update_comment": null,
    "last_update": "2022-06-21 10:33:33",
    "licence": "Public",
    "status": "active",
    "error_message": null,
    "url": "https:\/\/old.openml.org\/data\/download\/22103161\/dataset",
    "default_target_attribute": "tip_amount",
    "row_id_attribute": null,
    "ignore_attribute": null,
    "runs": 0,
    "suggest": {
        "input": [
            "nyc-taxi-green-dec-2016",
            "Dataset used in the tabular data benchmark https:\/\/github.com\/LeoGrin\/tabular-benchmark, transformed in the same way. This dataset belongs to the \"regression on categorical and numerical features\" benchmark. Original description: 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 "
        ],
        "weight": 5
    },
    "qualities": {
        "NumberOfInstances": 581835,
        "NumberOfFeatures": 17,
        "NumberOfClasses": 0,
        "NumberOfMissingValues": 0,
        "NumberOfInstancesWithMissingValues": 0,
        "NumberOfNumericFeatures": 10,
        "NumberOfSymbolicFeatures": 7,
        "PercentageOfBinaryFeatures": 17.647058823529413,
        "PercentageOfInstancesWithMissingValues": 0,
        "PercentageOfMissingValues": 0,
        "AutoCorrelation": 0.3560496958964945,
        "PercentageOfNumericFeatures": 58.82352941176471,
        "Dimensionality": 2.9217905419921456e-5,
        "PercentageOfSymbolicFeatures": 41.17647058823529,
        "MajorityClassPercentage": null,
        "MajorityClassSize": null,
        "MinorityClassPercentage": null,
        "MinorityClassSize": null,
        "NumberOfBinaryFeatures": 3
    },
    "tags": [
        {
            "uploader": "38960",
            "tag": "Computer Systems"
        },
        {
            "uploader": "38960",
            "tag": "Mathematics"
        }
    ],
    "features": [
        {
            "name": "tip_amount",
            "index": "16",
            "type": "numeric",
            "distinct": "1811",
            "missing": "0",
            "target": "1",
            "min": "-2",
            "max": "6",
            "mean": "1",
            "stdev": "1"
        },
        {
            "name": "VendorID",
            "index": "0",
            "type": "nominal",
            "distinct": "2",
            "missing": "0",
            "distr": []
        },
        {
            "name": "store_and_fwd_flag",
            "index": "1",
            "type": "nominal",
            "distinct": "2",
            "missing": "0",
            "distr": []
        },
        {
            "name": "RatecodeID",
            "index": "2",
            "type": "nominal",
            "distinct": "5",
            "missing": "0",
            "distr": []
        },
        {
            "name": "passenger_count",
            "index": "3",
            "type": "numeric",
            "distinct": "10",
            "missing": "0",
            "min": "0",
            "max": "9",
            "mean": "1",
            "stdev": "1"
        },
        {
            "name": "extra",
            "index": "4",
            "type": "nominal",
            "distinct": "5",
            "missing": "0",
            "distr": []
        },
        {
            "name": "mta_tax",
            "index": "5",
            "type": "nominal",
            "distinct": "3",
            "missing": "0",
            "distr": []
        },
        {
            "name": "tolls_amount",
            "index": "6",
            "type": "numeric",
            "distinct": "105",
            "missing": "0",
            "min": "0",
            "max": "98",
            "mean": "0",
            "stdev": "1"
        },
        {
            "name": "improvement_surcharge",
            "index": "7",
            "type": "nominal",
            "distinct": "3",
            "missing": "0",
            "distr": []
        },
        {
            "name": "total_amount",
            "index": "8",
            "type": "numeric",
            "distinct": "5377",
            "missing": "0",
            "min": "-63",
            "max": "712",
            "mean": "17",
            "stdev": "12"
        },
        {
            "name": "trip_type",
            "index": "9",
            "type": "nominal",
            "distinct": "2",
            "missing": "0",
            "distr": []
        },
        {
            "name": "lpep_pickup_datetime_day",
            "index": "10",
            "type": "numeric",
            "distinct": "31",
            "missing": "0",
            "min": "1",
            "max": "31",
            "mean": "15",
            "stdev": "9"
        },
        {
            "name": "lpep_pickup_datetime_hour",
            "index": "11",
            "type": "numeric",
            "distinct": "24",
            "missing": "0",
            "min": "0",
            "max": "23",
            "mean": "14",
            "stdev": "7"
        },
        {
            "name": "lpep_pickup_datetime_minute",
            "index": "12",
            "type": "numeric",
            "distinct": "60",
            "missing": "0",
            "min": "0",
            "max": "59",
            "mean": "30",
            "stdev": "17"
        },
        {
            "name": "lpep_dropoff_datetime_day",
            "index": "13",
            "type": "numeric",
            "distinct": "31",
            "missing": "0",
            "min": "1",
            "max": "31",
            "mean": "15",
            "stdev": "9"
        },
        {
            "name": "lpep_dropoff_datetime_hour",
            "index": "14",
            "type": "numeric",
            "distinct": "24",
            "missing": "0",
            "min": "0",
            "max": "23",
            "mean": "14",
            "stdev": "7"
        },
        {
            "name": "lpep_dropoff_datetime_minute",
            "index": "15",
            "type": "numeric",
            "distinct": "60",
            "missing": "0",
            "min": "0",
            "max": "59",
            "mean": "30",
            "stdev": "17"
        }
    ],
    "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
}