DEVELOPMENT...      {
    "data_id": "42180",
    "name": "sf-police-incidents",
    "exact_name": "sf-police-incidents",
    "version": 4,
    "version_label": "4",
    "description": "Incident reports from the San Franciso Police Department between January 2003 and May 2018, provided by the City and County of San Francisco. The dataset was downloaded on 05.11.2018. from [https:\/\/data.sfgov.org\/Public-Safety\/Police-Department-Incident-Reports-Historical-2003\/tmnf-yvry]. For a description of all variables, checkout the homepage of the data provider. The original data was published under ODC Public Domain Dedication and Licence (PDDL) [https:\/\/opendatacommons.org\/licenses\/pddl\/1.0\/]. As target, the binary variable 'ViolentCrime' was created. A 'ViolentCrime' was defined as 'Category' %in% c('ASSAULT', 'ROBBERY', 'SEX OFFENSES, FORCIBLE', 'KIDNAPPING') | 'Descript' %in% c('GRAND THEFT PURSESNATCH', 'ATTEMPTED GRAND THEFT PURSESNATCH'). Additional date and time features 'Hour', 'DayOfWeek', 'Month', and 'Year' were created. The original variables 'Category', 'Descript', 'Date', 'Time', 'Resolution', 'Location', and 'PdId' were removed from the dataset. One record which contained the only missing value in the variable 'PdDistrict' was removed from the dataset. Using this dataset for machine learning was inspired by Nina Zumel's blogpost [http:\/\/www.win-vector.com\/blog\/2012\/07\/modeling-trick-impact-coding-of-categorical-variables-with-many-levels\/]. Note that incidents consist of multiple rows in the dataset when the crime belongs to more than one 'Category', which is indicated by the ID variable 'IncidntNum' (ignored by default).",
    "format": "ARFF",
    "uploader": "Heidi Smith",
    "uploader_id": 1478,
    "visibility": "public",
    "creator": null,
    "contributor": null,
    "date": "2019-10-17 11:33:56",
    "update_comment": null,
    "last_update": "2019-10-17 11:33:56",
    "licence": "CC0",
    "status": "in_preparation",
    "error_message": null,
    "url": "https:\/\/www.openml.org\/data\/download\/21756368\/police_fixed_2.arff",
    "default_target_attribute": "ViolentCrime",
    "row_id_attribute": null,
    "ignore_attribute": null,
    "runs": 0,
    "suggest": {
        "input": [
            "sf-police-incidents",
            "Incident reports from the San Franciso Police Department between January 2003 and May 2018, provided by the City and County of San Francisco. The dataset was downloaded on 05.11.2018. from [https:\/\/data.sfgov.org\/Public-Safety\/Police-Department-Incident-Reports-Historical-2003\/tmnf-yvry]. For a description of all variables, checkout the homepage of the data provider. The original data was published under ODC Public Domain Dedication and Licence (PDDL) [https:\/\/opendatacommons.org\/licenses\/pddl\/1 "
        ],
        "weight": 5
    },
    "qualities": {
        "NumberOfInstances": 2215023,
        "NumberOfFeatures": 10,
        "NumberOfClasses": 2,
        "NumberOfMissingValues": 0,
        "NumberOfInstancesWithMissingValues": 0,
        "NumberOfNumericFeatures": 4,
        "NumberOfSymbolicFeatures": 6,
        "PercentageOfSymbolicFeatures": 60,
        "AutoCorrelation": 0.7940530613239959,
        "PercentageOfNumericFeatures": 40,
        "PercentageOfMissingValues": 0,
        "PercentageOfInstancesWithMissingValues": 0,
        "PercentageOfBinaryFeatures": 10,
        "NumberOfBinaryFeatures": 1,
        "MinorityClassSize": 269319,
        "MinorityClassPercentage": 12.158745078493542,
        "MajorityClassSize": 1945704,
        "MajorityClassPercentage": 87.84125492150646,
        "Dimensionality": 4.514625807497258e-6
    },
    "tags": [],
    "features": [
        {
            "name": "ViolentCrime",
            "index": "9",
            "type": "nominal",
            "distinct": "2",
            "missing": "0",
            "target": "1",
            "distr": [
                [
                    "Yes",
                    "No"
                ],
                [
                    [
                        "269319",
                        "0"
                    ],
                    [
                        "0",
                        "1945704"
                    ]
                ]
            ]
        },
        {
            "name": "IncidntNum",
            "index": "0",
            "type": "numeric",
            "distinct": "1746913",
            "missing": "0",
            "min": "3979",
            "max": "991582377",
            "mean": "104072726",
            "stdev": "46128265"
        },
        {
            "name": "Hour",
            "index": "1",
            "type": "numeric",
            "distinct": "24",
            "missing": "0",
            "min": "0",
            "max": "23",
            "mean": "13",
            "stdev": "7"
        },
        {
            "name": "DayOfWeek",
            "index": "2",
            "type": "nominal",
            "distinct": "7",
            "missing": "0",
            "distr": [
                [
                    "1",
                    "2",
                    "3",
                    "4",
                    "5",
                    "6",
                    "7"
                ],
                [
                    [
                        "41432",
                        "253159"
                    ],
                    [
                        "37281",
                        "269306"
                    ],
                    [
                        "36622",
                        "278513"
                    ],
                    [
                        "36772",
                        "287248"
                    ],
                    [
                        "36326",
                        "279830"
                    ],
                    [
                        "39196",
                        "298745"
                    ],
                    [
                        "41690",
                        "278903"
                    ]
                ]
            ]
        },
        {
            "name": "Month",
            "index": "3",
            "type": "nominal",
            "distinct": "12",
            "missing": "0",
            "distr": [
                [
                    "1",
                    "2",
                    "3",
                    "4",
                    "5",
                    "6",
                    "7",
                    "8",
                    "9",
                    "10",
                    "11",
                    "12"
                ],
                [
                    [
                        "23568",
                        "174015"
                    ],
                    [
                        "21418",
                        "157201"
                    ],
                    [
                        "23929",
                        "173651"
                    ],
                    [
                        "23159",
                        "166675"
                    ],
                    [
                        "23012",
                        "164735"
                    ],
                    [
                        "21813",
                        "152931"
                    ],
                    [
                        "21832",
                        "159990"
                    ],
                    [
                        "22607",
                        "164772"
                    ],
                    [
                        "22829",
                        "160608"
                    ],
                    [
                        "23431",
                        "167039"
                    ],
                    [
                        "21160",
                        "153872"
                    ],
                    [
                        "20561",
                        "150215"
                    ]
                ]
            ]
        },
        {
            "name": "Year",
            "index": "4",
            "type": "nominal",
            "distinct": "16",
            "missing": "0",
            "distr": [
                [
                    "2003",
                    "2004",
                    "2005",
                    "2006",
                    "2007",
                    "2008",
                    "2009",
                    "2010",
                    "2011",
                    "2012",
                    "2013",
                    "2014",
                    "2015",
                    "2016",
                    "2017",
                    "2018"
                ],
                [
                    [
                        "17858",
                        "131318"
                    ],
                    [
                        "17436",
                        "130712"
                    ],
                    [
                        "16211",
                        "125975"
                    ],
                    [
                        "17683",
                        "120170"
                    ],
                    [
                        "17671",
                        "119968"
                    ],
                    [
                        "18102",
                        "123209"
                    ],
                    [
                        "17137",
                        "122723"
                    ],
                    [
                        "16932",
                        "116591"
                    ],
                    [
                        "16889",
                        "115808"
                    ],
                    [
                        "17274",
                        "123573"
                    ],
                    [
                        "18126",
                        "134680"
                    ],
                    [
                        "17255",
                        "132873"
                    ],
                    [
                        "18209",
                        "138317"
                    ],
                    [
                        "18153",
                        "132729"
                    ],
                    [
                        "18309",
                        "136464"
                    ],
                    [
                        "6074",
                        "40594"
                    ]
                ]
            ]
        },
        {
            "name": "PdDistrict",
            "index": "5",
            "type": "nominal",
            "distinct": "10",
            "missing": "0",
            "distr": [
                [
                    "MISS",
                    "BAYVIEW",
                    "CENTRAL",
                    "INGLESIDE",
                    "MISSION",
                    "NORTHERN",
                    "PARK",
                    "RICHMOND",
                    "SOUTHERN",
                    "TARAVAL",
                    "TENDERLOIN"
                ],
                [
                    [
                        "0",
                        "0"
                    ],
                    [
                        "33208",
                        "187792"
                    ],
                    [
                        "24494",
                        "201761"
                    ],
                    [
                        "30727",
                        "163453"
                    ],
                    [
                        "40602",
                        "259474"
                    ],
                    [
                        "29517",
                        "243196"
                    ],
                    [
                        "11669",
                        "113810"
                    ],
                    [
                        "10577",
                        "106241"
                    ],
                    [
                        "44227",
                        "355558"
                    ],
                    [
                        "18686",
                        "148285"
                    ],
                    [
                        "25612",
                        "166134"
                    ]
                ]
            ]
        },
        {
            "name": "Address",
            "index": "6",
            "type": "nominal",
            "distinct": "25147",
            "missing": "0",
            "distr": []
        },
        {
            "name": "X",
            "index": "7",
            "type": "numeric",
            "distinct": "37380",
            "missing": "0",
            "min": "-123",
            "max": "0",
            "mean": "-122",
            "stdev": "0"
        },
        {
            "name": "Y",
            "index": "8",
            "type": "numeric",
            "distinct": "37402",
            "missing": "0",
            "min": "38",
            "max": "90",
            "mean": "38",
            "stdev": "0"
        }
    ],
    "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
}