{ "data_id": "882", "name": "pollution", "exact_name": "pollution", "version": 2, "version_label": null, "description": "**Author**: \n**Source**: Unknown - Date unknown \n**Please cite**: \n\nBinarized version of the original data set (see version 1). It converts the numeric target feature to a two-class nominal target feature by computing the mean and classifying all instances with a lower target value as positive ('P') and all others as negative ('N').", "format": "ARFF", "uploader": "Joaquin Vanschoren", "uploader_id": 2, "visibility": "public", "creator": null, "contributor": null, "date": "2014-10-04 14:36:09", "update_comment": null, "last_update": "2014-10-04 14:36:09", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/53416\/pollution.arff", "default_target_attribute": "binaryClass", "row_id_attribute": null, "ignore_attribute": null, "runs": 754, "suggest": { "input": [ "pollution", "Binarized version of the original data set (see version 1). It converts the numeric target feature to a two-class nominal target feature by computing the mean and classifying all instances with a lower target value as positive ('P') and all others as negative ('N'). " ], "weight": 5 }, "qualities": { "NumberOfInstances": 60, "NumberOfFeatures": 16, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 15, "NumberOfSymbolicFeatures": 1, "kNN1NErrRate": 0.18333333333333332, "MajorityClassPercentage": 51.66666666666667, "MeanStdDevOfNumericAtts": 114.09141591176113, "Quartile2AttributeEntropy": null, "REPTreeDepth2ErrRate": 0.4666666666666667, "CfsSubsetEval_kNN1NKappa": 0.39933259176863173, "kNN1NKappa": 0.6316964285714285, "MajorityClassSize": 31, "MinAttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 1.0878213876388565, "REPTreeDepth2Kappa": 0.05084745762711869, "ClassEntropy": 0.9991983542636398, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.7513231254866244, "Quartile2MeansOfNumericAtts": 37.36666666666667, "REPTreeDepth3AUC": 0.5122358175750834, "DecisionStumpAUC": 0.6852057842046719, "DecisionStumpErrRate": 0.35, "MaxKurtosisOfNumericAtts": 34.685215155156634, "MinMeansOfNumericAtts": 3.2631666666666668, "Quartile2MutualInformation": null, "REPTreeDepth3ErrRate": 0.4666666666666667, "DecisionStumpKappa": 0.29530201342281887, "MaxMeansOfNumericAtts": 3876.05, "MinMutualInformation": null, "Quartile2SkewnessOfNumericAtts": 0.23750820556484428, "REPTreeDepth3Kappa": 0.05084745762711869, "Dimensionality": 0.26666666666666666, "MaxMutualInformation": null, "MinNominalAttDistinctValues": 2, "PercentageOfBinaryFeatures": 6.25, "Quartile2StdDevOfNumericAtts": 5.369930929918037, "RandomTreeDepth1AUC": 0.6512791991101224, "EquivalentNumberOfAtts": null, "MaxNominalAttDistinctValues": 2, "MinSkewnessOfNumericAtts": -0.8021812079340497, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "RandomTreeDepth1ErrRate": 0.35, "RandomTreeDepth1Kappa": 0.3015521064301553, "J48.00001.AUC": 0.7152391546162402, "MaxSkewnessOfNumericAtts": 5.5934223578714, "MinStdDevOfNumericAtts": 0.1352523274860565, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 3.59099308145352, "AutoCorrelation": 0.5084745762711864, "RandomTreeDepth2AUC": 0.6512791991101224, "J48.00001.ErrRate": 0.3333333333333333, "MaxStdDevOfNumericAtts": 1454.1023607104587, "MinorityClassPercentage": 48.333333333333336, "PercentageOfNumericFeatures": 93.75, "Quartile3MeansOfNumericAtts": 57.666666666666664, "CfsSubsetEval_DecisionStumpAUC": 0.7119021134593992, "RandomTreeDepth2ErrRate": 0.35, "J48.00001.Kappa": 0.3281075027995519, "MeanAttributeEntropy": null, "MinorityClassSize": 29, "PercentageOfSymbolicFeatures": 6.25, "Quartile3MutualInformation": null, "CfsSubsetEval_DecisionStumpErrRate": 0.3, "RandomTreeDepth2Kappa": 0.3015521064301553, "J48.0001.AUC": 0.7152391546162402, "MeanKurtosisOfNumericAtts": 5.3906314688662045, "NaiveBayesAUC": 0.8398220244716351, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 1.4635241362721882, "CfsSubsetEval_DecisionStumpKappa": 0.39933259176863173, "RandomTreeDepth3AUC": 0.6512791991101224, "J48.0001.ErrRate": 0.3333333333333333, "MeanMeansOfNumericAtts": 291.34598888888894, "NaiveBayesErrRate": 0.25, "Quartile1KurtosisOfNumericAtts": 0.04384505760874635, "Quartile3StdDevOfNumericAtts": 46.33328963945426, "CfsSubsetEval_NaiveBayesAUC": 0.7119021134593992, "RandomTreeDepth3ErrRate": 0.35, "J48.0001.Kappa": 0.3281075027995519, "MeanMutualInformation": null, "NaiveBayesKappa": 0.49438202247191015, "Quartile1MeansOfNumericAtts": 11.87, "REPTreeDepth1AUC": 0.5122358175750834, "CfsSubsetEval_NaiveBayesErrRate": 0.3, "RandomTreeDepth3Kappa": 0.3015521064301553, "J48.001.AUC": 0.7152391546162402, "MeanNoiseToSignalRatio": null, "NumberOfBinaryFeatures": 1, "Quartile1MutualInformation": null, "REPTreeDepth1ErrRate": 0.4666666666666667, "CfsSubsetEval_NaiveBayesKappa": 0.39933259176863173, "StdvNominalAttDistinctValues": 0, "J48.001.ErrRate": 0.3333333333333333, "MeanNominalAttDistinctValues": 2, "Quartile1SkewnessOfNumericAtts": -0.22492857009747344, "REPTreeDepth1Kappa": 0.05084745762711869, "CfsSubsetEval_kNN1NAUC": 0.7119021134593992, "kNN1NAUC": 0.8147942157953281, "J48.001.Kappa": 0.3281075027995519, "MeanSkewnessOfNumericAtts": 1.0740504823789847, "Quartile1StdDevOfNumericAtts": 4.160095609505386, "REPTreeDepth2AUC": 0.5122358175750834, "CfsSubsetEval_kNN1NErrRate": 0.3 }, "tags": [ { "tag": "binarized", "uploader": "1" }, { "tag": "mythbusting_1", "uploader": "1" }, { "tag": "study_1", "uploader": "2" }, { "tag": "study_123", "uploader": "3886" }, { "tag": "study_15", "uploader": "939" }, { "tag": "study_20", "uploader": "939" }, { "tag": "study_41", "uploader": "1" } ], "features": [ { "name": "binaryClass", "index": "15", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "P", "N" ], [ [ "29", "0" ], [ "0", "31" ] ] ] }, { "name": "PREC", "index": "0", "type": "numeric", "distinct": "30", "missing": "0", "min": "10", "max": "60", "mean": "37", "stdev": "10" }, { "name": "JANT", "index": "1", "type": "numeric", "distinct": "28", "missing": "0", "min": "12", "max": "67", "mean": "34", "stdev": "10" }, { "name": "JULT", "index": "2", "type": "numeric", "distinct": "20", "missing": "0", "min": "63", "max": "85", "mean": "75", "stdev": "5" }, { "name": "OVR65", "index": "3", "type": "numeric", "distinct": "39", "missing": "0", "min": "6", "max": "12", "mean": "9", "stdev": "1" }, { "name": "POPN", "index": "4", "type": "numeric", "distinct": "35", "missing": "0", "min": "3", "max": "4", "mean": "3", "stdev": "0" }, { "name": "EDUC", "index": "5", "type": "numeric", "distinct": "26", "missing": "0", "min": "9", "max": "12", "mean": "11", "stdev": "1" }, { "name": "HOUS", "index": "6", "type": "numeric", "distinct": "53", "missing": "0", "min": "67", "max": "91", "mean": "81", "stdev": "5" }, { "name": "DENS", "index": "7", "type": "numeric", "distinct": "60", "missing": "0", "min": "1441", "max": "9699", "mean": "3876", "stdev": "1454" }, { "name": "NONW", "index": "8", "type": "numeric", "distinct": "54", "missing": "0", "min": "1", "max": "39", "mean": "12", "stdev": "9" }, { "name": "WWDRK", "index": "9", "type": "numeric", "distinct": "51", "missing": "0", "min": "34", "max": "60", "mean": "46", "stdev": "5" }, { "name": "POOR", "index": "10", "type": "numeric", "distinct": "46", "missing": "0", "min": "9", "max": "26", "mean": "14", "stdev": "4" }, { "name": "HC", "index": "11", "type": "numeric", "distinct": "34", "missing": "0", "min": "1", "max": "648", "mean": "38", "stdev": "92" }, { "name": "NOX", "index": "12", "type": "numeric", "distinct": "30", "missing": "0", "min": "1", "max": "319", "mean": "23", "stdev": "46" }, { "name": "SO@", "index": "13", "type": "numeric", "distinct": "44", "missing": "0", "min": "1", "max": "278", "mean": "54", "stdev": "63" }, { "name": "HUMID", "index": "14", "type": "numeric", "distinct": "17", "missing": "0", "min": "38", "max": "73", "mean": "58", "stdev": "5" } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 10, "total_downloads": 11, "reach": 10, "reuse": 14, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 14 }