{ "data_id": "43746", "name": "NYC-Uber-Pickups-with-Weather-and-Holidays", "exact_name": "NYC-Uber-Pickups-with-Weather-and-Holidays", "version": 1, "version_label": "v1.0", "description": "Context\nThis is a forked subset of the Uber Pickups in New York City, enriched with weather, borough, and holidays information.\n\nContent\nI created this dataset for a personal project of exploring and predicting pickups in the area by merging data that intuitively seem possible factors for the analysis. These are: \n\nUber Pickups in New York City, from 01\/01\/2015 to 30\/06\/2015 (uber-raw-data-janjune-15.csv). (by FiveThirtyEight via kaggle.com) \nWeather data from National Centers for Environmental Information. \nLocationID to Borough mapping. (by FiveThirtyEight) \nNYC public holidays. \n\nThe main dataset contained over 10 million observations of 4 variables which aggregated per hour and borough, and then joined with the rest of the datasets producing 29,101 observations across 13 variables. These are: \n\npickup_dt: Time period of the observations. \nborough: NYC's borough.\npickups: Number of pickups for the period.\nspd: Wind speed in miles\/hour.\nvsb: Visibility in Miles to nearest tenth.\ntemp: temperature in Fahrenheit.\ndewp: Dew point in Fahrenheit.\nslp: Sea level pressure.\npcp01: 1-hour liquid precipitation.\npcp06: 6-hour liquid precipitation.\npcp24: 24-hour liquid precipitation.\nsd: Snow depth in inches.\nhday: Being a holiday (Y) or not (N).\n\n\nAcknowledgements \/ Original datasets:\n\nUber Pickups in New York City, from 01\/01\/2015 to 30\/06\/2015 (uber-raw-data-janjune-15.csv). (by FiveThirtyEight via kaggle.com) \nWeather data from National Centers for Environmental Information. \nLocationID to Borough mapping. (by FiveThirtyEight) \n\n(Picture credits: Buck Ennis)", "format": "arff", "uploader": "Dustin Carrion", "uploader_id": 30123, "visibility": "public", "creator": null, "contributor": null, "date": "2022-03-24 07:50:50", "update_comment": null, "last_update": "2022-03-24 07:50:50", "licence": "CC0: Public Domain", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/22102571\/dataset", "default_target_attribute": null, "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "NYC-Uber-Pickups-with-Weather-and-Holidays", "Context This is a forked subset of the Uber Pickups in New York City, enriched with weather, borough, and holidays information. Content I created this dataset for a personal project of exploring and predicting pickups in the area by merging data that intuitively seem possible factors for the analysis. These are: Uber Pickups in New York City, from 01\/01\/2015 to 30\/06\/2015 (uber-raw-data-janjune-15.csv). (by FiveThirtyEight via kaggle.com) Weather data from National Centers for Environmental Info " ], "weight": 5 }, "qualities": { "NumberOfInstances": 29101, "NumberOfFeatures": 13, "NumberOfClasses": null, "NumberOfMissingValues": 3043, "NumberOfInstancesWithMissingValues": 3043, "NumberOfNumericFeatures": 10, "NumberOfSymbolicFeatures": 0, "Dimensionality": 0.0004467200439847428, "PercentageOfNumericFeatures": 76.92307692307693, "MajorityClassPercentage": null, "PercentageOfSymbolicFeatures": 0, "MajorityClassSize": null, "MinorityClassPercentage": null, "MinorityClassSize": null, "NumberOfBinaryFeatures": 0, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 10.456685337273633, "AutoCorrelation": null, "PercentageOfMissingValues": 0.8043604105595104 }, "tags": [ { "uploader": "38960", "tag": "Statistics" }, { "uploader": "38960", "tag": "Transportation" } ], "features": [ { "name": "pickup_dt", "index": "0", "type": "string", "distinct": "4343", "missing": "0" }, { "name": "borough", "index": "1", "type": "string", "distinct": "6", "missing": "3043" }, { "name": "pickups", "index": "2", "type": "numeric", "distinct": "3406", "missing": "0", "min": "0", "max": "7883", "mean": "490", "stdev": "996" }, { "name": "spd", "index": "3", "type": "numeric", "distinct": "114", "missing": "0", "min": "0", "max": "21", "mean": "6", "stdev": "4" }, { "name": "vsb", "index": "4", "type": "numeric", "distinct": "179", "missing": "0", "min": "0", "max": "10", "mean": "9", "stdev": "2" }, { "name": "temp", "index": "5", "type": "numeric", "distinct": "295", "missing": "0", "min": "2", "max": "89", "mean": "48", "stdev": "20" }, { "name": "dewp", "index": "6", "type": "numeric", "distinct": "305", "missing": "0", "min": "-16", "max": "73", "mean": "31", "stdev": "21" }, { "name": "slp", "index": "7", "type": "numeric", "distinct": "413", "missing": "0", "min": "991", "max": "1043", "mean": "1018", "stdev": "8" }, { "name": "pcp01", "index": "8", "type": "numeric", "distinct": "80", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "pcp06", "index": "9", "type": "numeric", "distinct": "318", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "pcp24", "index": "10", "type": "numeric", "distinct": "484", "missing": "0", "min": "0", "max": "2", "mean": "0", "stdev": "0" }, { "name": "sd", "index": "11", "type": "numeric", "distinct": "421", "missing": "0", "min": "0", "max": "19", "mean": "3", "stdev": "5" }, { "name": "hday", "index": "12", "type": "string", "distinct": "2", "missing": "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 }