{ "data_id": "293", "name": "covertype", "exact_name": "covertype", "version": 2, "version_label": null, "description": "**Author**: Jock A. Blackard, Dr. Denis J. Dean, Dr. Charles W. Anderson \n**Source**: [LibSVM repository](http:\/\/www.csie.ntu.edu.tw\/~cjlin\/libsvmtools\/datasets\/) - 2013-11-14 \n**Please cite**: For the binarization: R. Collobert, S. Bengio, and Y. Bengio. A parallel mixture of SVMs for very large scale problems. Neural Computation, 14(05):1105-1114, 2002.\n\nThis is the famous covertype dataset in its binary version, retrieved 2013-11-13 from the libSVM site (called covtype.binary there). Additional to the preprocessing done there (see LibSVM site for details), this dataset was created as follows:\n-load covertpype dataset, unscaled.\n-normalize each file columnwise according to the following rules:\n-If a column only contains one value (constant feature), it will set to zero and thus removed by sparsity.\n-If a column contains two values (binary feature), the value occuring more often will be set to zero, the other to one.\n-If a column contains more than two values (multinary\/real feature), the column is divided by its std deviation.\n-duplicate lines were finally removed.\n\nPreprocessing: Transform from multiclass into binary class.\n", "format": "Sparse_ARFF", "uploader": "aydin demircioglu", "uploader_id": 167, "visibility": "public", "creator": "Jock A. Blackard, Dr. Denis J. Dean, Dr. Charles W. Anderson", "contributor": null, "date": "2014-08-15 16:21:51", "update_comment": null, "last_update": "2014-08-15 16:21:51", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/49823\/covtype.arff", "default_target_attribute": "Y", "row_id_attribute": null, "ignore_attribute": null, "runs": 22, "suggest": { "input": [ "covertype", "This is the famous covertype dataset in its binary version, retrieved 2013-11-13 from the libSVM site (called covtype.binary there). Additional to the preprocessing done there (see LibSVM site for details), this dataset was created as follows: -load covertpype dataset, unscaled. -normalize each file columnwise according to the following rules: -If a column only contains one value (constant feature), it will set to zero and thus removed by sparsity. -If a column contains two values (binary featur " ], "weight": 5 }, "qualities": { "NumberOfInstances": 581012, "NumberOfFeatures": 55, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 54, "NumberOfSymbolicFeatures": 1, "Quartile2SkewnessOfNumericAtts": 6.437434921043668, "REPTreeDepth3Kappa": 0.8449003634444506, "DecisionStumpKappa": 0.3369884131972297, "MaxMeansOfNumericAtts": 11.296583346615902, "MinMutualInformation": null, "PercentageOfBinaryFeatures": 1.8181818181818181, "Quartile2StdDevOfNumericAtts": 0.1484429790403473, "RandomTreeDepth1AUC": 0.8910304634353019, "Dimensionality": 9.466241661101664e-5, "MaxMutualInformation": null, "MinNominalAttDistinctValues": 2, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "RandomTreeDepth1ErrRate": 0.10893234563141553, "EquivalentNumberOfAtts": null, "MaxNominalAttDistinctValues": 2, "MinSkewnessOfNumericAtts": -1.1811467396995312, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 315.6075154423525, "AutoCorrelation": 0.96600752825678, "RandomTreeDepth1Kappa": 0.7820142305321579, "J48.00001.AUC": 0.9516038117344053, "MaxSkewnessOfNumericAtts": 440.0780233744365, "MinStdDevOfNumericAtts": 0.002272308686918377, "PercentageOfNumericFeatures": 98.18181818181819, "Quartile3MeansOfNumericAtts": 0.12413814172467744, "CfsSubsetEval_DecisionStumpAUC": 0.776344023630082, "RandomTreeDepth2AUC": 0.8910304634353019, "J48.00001.ErrRate": 0.0601020288737582, "MaxStdDevOfNumericAtts": 1.000001102710213, "MinorityClassPercentage": 48.75992234239568, "PercentageOfSymbolicFeatures": 1.8181818181818181, "Quartile3MutualInformation": null, "CfsSubsetEval_DecisionStumpErrRate": 0.26067964172857017, "RandomTreeDepth2ErrRate": 0.10893234563141553, "J48.00001.Kappa": 0.879738312585838, "MeanAttributeEntropy": null, "MinorityClassSize": 283301, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 17.810161851584287, "CfsSubsetEval_DecisionStumpKappa": 0.4790919720166566, "RandomTreeDepth2Kappa": 0.7820142305321579, "J48.0001.AUC": 0.9516038117344053, "MeanKurtosisOfNumericAtts": 4013.3398609189735, "NaiveBayesAUC": 0.7596945559494108, "Quartile1KurtosisOfNumericAtts": 5.230444242515247, "Quartile3StdDevOfNumericAtts": 0.3240883568141914, "CfsSubsetEval_NaiveBayesAUC": 0.776344023630082, "RandomTreeDepth3AUC": 0.8910304634353019, "J48.0001.ErrRate": 0.0601020288737582, "MeanMeansOfNumericAtts": 0.8121452147721001, "NaiveBayesErrRate": 0.29909709265901563, "Quartile1MeansOfNumericAtts": 0.0031341865572500375, "REPTreeDepth1AUC": 0.9622614324527192, "CfsSubsetEval_NaiveBayesErrRate": 0.26067964172857017, "RandomTreeDepth3ErrRate": 0.10893234563141553, "J48.0001.Kappa": 0.879738312585838, "MeanMutualInformation": null, "NaiveBayesKappa": 0.40261397678439564, "Quartile1MutualInformation": null, "REPTreeDepth1ErrRate": 0.07752679806957516, "CfsSubsetEval_NaiveBayesKappa": 0.4790919720166566, "RandomTreeDepth3Kappa": 0.7820142305321579, "J48.001.AUC": 0.9516038117344053, "MeanNoiseToSignalRatio": null, "NumberOfBinaryFeatures": 1, "Quartile1SkewnessOfNumericAtts": 2.4559487337466823, "REPTreeDepth1Kappa": 0.8449003634444506, "CfsSubsetEval_kNN1NAUC": 0.776344023630082, "StdvNominalAttDistinctValues": 0, "J48.001.ErrRate": 0.0601020288737582, "MeanNominalAttDistinctValues": 2, "Quartile1StdDevOfNumericAtts": 0.05586358197098771, "REPTreeDepth2AUC": 0.9622614324527192, "CfsSubsetEval_kNN1NErrRate": 0.26067964172857017, "kNN1NAUC": 0.9449502571773352, "J48.001.Kappa": 0.879738312585838, "MeanSkewnessOfNumericAtts": 20.55133533069043, "Quartile2AttributeEntropy": null, "REPTreeDepth2ErrRate": 0.07752679806957516, "CfsSubsetEval_kNN1NKappa": 0.4790919720166566, "kNN1NErrRate": 0.05504533469188244, "MajorityClassPercentage": 51.240077657604324, "MeanStdDevOfNumericAtts": 0.3004371098679037, "Quartile2KurtosisOfNumericAtts": 39.47446864168822, "REPTreeDepth2Kappa": 0.8449003634444506, "ClassEntropy": 0.999556241348861, "kNN1NKappa": 0.8898480630921429, "MajorityClassSize": 297711, "MinAttributeEntropy": null, "Quartile2MeansOfNumericAtts": 0.022560635580707457, "REPTreeDepth3AUC": 0.9622614324527192, "DecisionStumpAUC": 0.6704579749321636, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.957727848407018, "Quartile2MutualInformation": null, "REPTreeDepth3ErrRate": 0.07752679806957516, "DecisionStumpErrRate": 0.3337900077795295, "MaxKurtosisOfNumericAtts": 193667.33331613554, "MinMeansOfNumericAtts": 5.163404542446465e-6 }, "tags": [ { "uploader": "38960", "tag": "Machine Learning" }, { "uploader": "38960", "tag": "Physical Sciences" } ], "features": [ { "name": "Y", "index": "0", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "1", "-1" ], [ [ "283301", "0" ], [ "0", "297711" ] ] ] }, { "name": "X1", "index": "1", "type": "numeric", "distinct": "1978", "missing": "0", "min": "7", "max": "14", "mean": "11", "stdev": "1" }, { "name": "X2", "index": "2", "type": "numeric", "distinct": "361", "missing": "0", "min": "0", "max": "3", "mean": "1", "stdev": "1" }, { "name": "X3", "index": "3", "type": "numeric", "distinct": "67", "missing": "0", "min": "0", "max": "9", "mean": "2", "stdev": "1" }, { "name": "X4", "index": "4", "type": "numeric", "distinct": "551", "missing": "0", "min": "0", "max": "7", "mean": "1", "stdev": "1" }, { "name": "X5", "index": "5", "type": "numeric", "distinct": "700", "missing": "0", "min": "-3", "max": "10", "mean": "1", "stdev": "1" }, { "name": "X6", "index": "6", "type": "numeric", "distinct": "5785", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "X7", "index": "7", "type": "numeric", "distinct": "207", "missing": "0", "min": "0", "max": "9", "mean": "8", "stdev": "1" }, { "name": "X8", "index": "8", "type": "numeric", "distinct": "185", "missing": "0", "min": "0", "max": "13", "mean": "11", "stdev": "1" }, { "name": "X9", "index": "9", "type": "numeric", "distinct": "255", "missing": "0", "min": "0", "max": "7", "mean": "4", "stdev": "1" }, { "name": "X10", "index": "10", "type": "numeric", "distinct": "5827", "missing": "0", "min": "0", "max": "5", "mean": "1", "stdev": "1" }, { "name": "X11", "index": "11", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X12", "index": "12", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X13", "index": "13", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X14", "index": "14", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X15", "index": "15", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X16", "index": "16", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X17", "index": "17", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X18", "index": "18", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X19", "index": "19", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X20", "index": "20", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X21", "index": "21", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X22", "index": "22", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X23", "index": "23", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X24", "index": "24", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X25", "index": "25", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X26", "index": "26", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X27", "index": "27", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X28", "index": "28", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X29", "index": "29", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X30", "index": "30", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X31", "index": "31", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X32", "index": "32", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X33", "index": "33", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X34", "index": "34", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X35", "index": "35", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X36", "index": "36", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X37", "index": "37", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X38", "index": "38", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X39", "index": "39", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X40", "index": "40", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X41", "index": "41", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X42", "index": "42", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X43", "index": "43", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X44", "index": "44", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X45", "index": "45", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X46", "index": "46", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X47", "index": "47", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X48", "index": "48", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X49", "index": "49", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X50", "index": "50", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X51", "index": "51", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X52", "index": "52", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X53", "index": "53", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "X54", "index": "54", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "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 }