{ "data_id": "45047", "name": "Airlines_DepDelay_1M", "exact_name": "Airlines_DepDelay_1M", "version": 6, "version_label": null, "description": "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 both numerical and categorical features\" benchmark. \n \n Original link: https:\/\/openml.org\/d\/42721 \n \n Original description: \n \n**Author**: Bureau of Transportation Statistics, Airline Service Quality Performance \n**Source**: [original](http:\/\/www.transtats.bts.gov\/) - 2013 \n**Please cite**: \n\nAirlines Departure Delay Prediction (Regression).\nOriginal data can be found at: http:\/\/www.transtats.bts.gov\n\nThis is a processed version of the original data, designed to predict departure delay (in seconds). \n\nA CSV of the raw data (years 1987-2013) can be be found [here](https:\/\/h2o-airlines-unpacked.s3.amazonaws.com\/allyears.1987.2013.csv). This is the first 1 million rows (and a subset of the columns) of this CSV file, in ARFF format.", "format": "arff", "uploader": "Leo Grin", "uploader_id": 26324, "visibility": "public", "creator": null, "contributor": "\"Leo Grin\"", "date": "2023-01-11 18:15:46", "update_comment": null, "last_update": "2023-01-11 18:15:46", "licence": "CC0", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22111945\/dataset", "kaggle_url": null, "default_target_attribute": "DepDelay", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "Airlines_DepDelay_1M", "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 both numerical and categorical features\" benchmark. Original link: https:\/\/openml.org\/d\/42721 Original description: Airlines Departure Delay Prediction (Regression). Original data can be found at: http:\/\/www.transtats.bts.gov This is a processed version of the original data, designed to predict departure delay (in seconds). A CSV of the " ], "weight": 5 }, "qualities": { "NumberOfInstances": 1000000, "NumberOfFeatures": 6, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 6, "NumberOfSymbolicFeatures": 0, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "AutoCorrelation": -0.9784510419232934, "PercentageOfNumericFeatures": 100, "Dimensionality": 6.0e-6, "PercentageOfSymbolicFeatures": 0, "MajorityClassPercentage": null, "MajorityClassSize": null, "MinorityClassPercentage": null, "MinorityClassSize": null, "NumberOfBinaryFeatures": 0 }, "tags": [], "features": [ { "name": "DepDelay", "index": "5", "type": "numeric", "distinct": "629", "missing": "0", "target": "1", "min": "-7", "max": "8", "mean": "0", "stdev": "2" }, { "name": "Month", "index": "0", "type": "numeric", "distinct": "12", "missing": "0", "min": "1", "max": "12", "mean": "6", "stdev": "3" }, { "name": "DayofMonth", "index": "1", "type": "numeric", "distinct": "31", "missing": "0", "min": "1", "max": "31", "mean": "16", "stdev": "9" }, { "name": "CRSDepTime", "index": "2", "type": "numeric", "distinct": "1343", "missing": "0", "min": "0", "max": "2400", "mean": "1333", "stdev": "474" }, { "name": "CRSArrTime", "index": "3", "type": "numeric", "distinct": "1429", "missing": "0", "min": "0", "max": "2400", "mean": "1492", "stdev": "491" }, { "name": "Distance", "index": "4", "type": "numeric", "distinct": "1735", "missing": "0", "min": "0", "max": "4983", "mean": "712", "stdev": "557" } ], "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 }