{ "data_id": "42721", "name": "Airlines_DepDelay_1M", "exact_name": "Airlines_DepDelay_1M", "version": 1, "version_label": null, "description": "**Author**: Bureau of Transportation Statistics, Airline Service Quality Performance \r\n**Source**: [original](http:\/\/www.transtats.bts.gov\/) - 2013 \r\n**Please cite**: \r\n\r\nAirlines Departure Delay Prediction (Regression).\r\nOriginal data can be found at: http:\/\/www.transtats.bts.gov\r\n\r\nThis is a processed version of the original data, designed to predict departure delay (in seconds). \r\n\r\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": "Erin LeDell", "uploader_id": 475, "visibility": "public", "creator": null, "contributor": null, "date": "2020-11-14 02:59:33", "update_comment": null, "last_update": "2020-11-14 02:59:33", "licence": "CC0", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/22044748\/airlines_train_regression_1000000.arff", "default_target_attribute": "DepDelay", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "Airlines_DepDelay_1M", "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 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. " ], "weight": 5 }, "qualities": { "NumberOfInstances": 1000000, "NumberOfFeatures": 10, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 7, "NumberOfSymbolicFeatures": 3, "Dimensionality": 1.0e-5, "PercentageOfNumericFeatures": 70, "MajorityClassPercentage": null, "PercentageOfSymbolicFeatures": 30, "MajorityClassSize": null, "MinorityClassPercentage": null, "MinorityClassSize": null, "NumberOfBinaryFeatures": 0, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": -16.955274955274955, "PercentageOfMissingValues": 0 }, "tags": [ { "uploader": "38960", "tag": "Machine Learning" } ], "features": [ { "name": "DepDelay", "index": "0", "type": "numeric", "distinct": "629", "missing": "0", "target": "1", "min": "-1197", "max": "2119", "mean": "8", "stdev": "29" }, { "name": "Month", "index": "1", "type": "numeric", "distinct": "12", "missing": "0", "min": "1", "max": "12", "mean": "6", "stdev": "3" }, { "name": "DayofMonth", "index": "2", "type": "numeric", "distinct": "31", "missing": "0", "min": "1", "max": "31", "mean": "16", "stdev": "9" }, { "name": "DayOfWeek", "index": "3", "type": "numeric", "distinct": "7", "missing": "0", "min": "1", "max": "7", "mean": "4", "stdev": "2" }, { "name": "CRSDepTime", "index": "4", "type": "numeric", "distinct": "1343", "missing": "0", "min": "0", "max": "2400", "mean": "1333", "stdev": "474" }, { "name": "CRSArrTime", "index": "5", "type": "numeric", "distinct": "1429", "missing": "0", "min": "0", "max": "2400", "mean": "1492", "stdev": "491" }, { "name": "UniqueCarrier", "index": "6", "type": "nominal", "distinct": "30", "missing": "0", "distr": [] }, { "name": "Origin", "index": "7", "type": "nominal", "distinct": "362", "missing": "0", "distr": [] }, { "name": "Dest", "index": "8", "type": "nominal", "distinct": "360", "missing": "0", "distr": [] }, { "name": "Distance", "index": "9", "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 }