{ "data_id": "1023", "name": "soybean", "exact_name": "soybean", "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). The multi-class target feature is converted to a two-class nominal target feature by re-labeling the majority class as positive ('P') and all others as negative ('N'). Originally converted by Quan Sun.", "format": "ARFF", "uploader": "Joaquin Vanschoren", "uploader_id": 2, "visibility": "public", "creator": null, "contributor": null, "date": "2014-10-04 22:45:35", "update_comment": null, "last_update": "2014-10-04 22:45:35", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/53557\/soybean.arff", "kaggle_url": null, "default_target_attribute": "binaryClass", "row_id_attribute": null, "ignore_attribute": null, "runs": 722, "suggest": { "input": [ "soybean", "Binarized version of the original data set (see version 1). The multi-class target feature is converted to a two-class nominal target feature by re-labeling the majority class as positive ('P') and all others as negative ('N'). Originally converted by Quan Sun. " ], "weight": 5 }, "qualities": { "NumberOfInstances": 683, "NumberOfFeatures": 36, "NumberOfClasses": 2, "NumberOfMissingValues": 2337, "NumberOfInstancesWithMissingValues": 121, "NumberOfNumericFeatures": 0, "NumberOfSymbolicFeatures": 36, "Quartile3MutualInformation": 0.06221584224282, "CfsSubsetEval_DecisionStumpErrRate": 0.04685212298682284, "RandomTreeDepth2ErrRate": 0.04978038067349927, "J48.00001.Kappa": 0.8600372426205263, "MeanAttributeEntropy": 0.9655890619117928, "MinorityClassSize": 92, "PercentageOfSymbolicFeatures": 100, "Quartile3SkewnessOfNumericAtts": null, "CfsSubsetEval_DecisionStumpKappa": 0.8078323104788365, "RandomTreeDepth2Kappa": 0.7844745976648788, "J48.0001.AUC": 0.9699371441398388, "MeanKurtosisOfNumericAtts": null, "NaiveBayesAUC": 0.9679798425660265, "Quartile1AttributeEntropy": 0.4629328593168401, "Quartile3StdDevOfNumericAtts": null, "CfsSubsetEval_NaiveBayesAUC": 0.9627827264248383, "RandomTreeDepth3AUC": 0.9092442615638766, "J48.0001.ErrRate": 0.03367496339677892, "MeanMeansOfNumericAtts": null, "NaiveBayesErrRate": 0.14494875549048317, "Quartile1KurtosisOfNumericAtts": null, "REPTreeDepth1AUC": 0.9247406753476054, "CfsSubsetEval_NaiveBayesErrRate": 0.04685212298682284, "RandomTreeDepth3ErrRate": 0.04978038067349927, "J48.0001.Kappa": 0.8600372426205263, "MeanMutualInformation": 0.040920676801074, "NaiveBayesKappa": 0.5497033184382096, "Quartile1MeansOfNumericAtts": null, "REPTreeDepth1ErrRate": 0.07174231332357248, "CfsSubsetEval_NaiveBayesKappa": 0.8078323104788365, "RandomTreeDepth3Kappa": 0.7844745976648788, "J48.001.AUC": 0.9699371441398388, "MeanNoiseToSignalRatio": 22.5966053691089, "NumberOfBinaryFeatures": 17, "Quartile1MutualInformation": 0.01327973389231, "REPTreeDepth1Kappa": 0.6694911069633316, "CfsSubsetEval_kNN1NAUC": 0.9627827264248383, "StdvNominalAttDistinctValues": 1.0370134162086941, "J48.001.ErrRate": 0.03367496339677892, "MeanNominalAttDistinctValues": 2.8055555555555554, "Quartile1SkewnessOfNumericAtts": null, "REPTreeDepth2AUC": 0.9247406753476054, "CfsSubsetEval_kNN1NErrRate": 0.04685212298682284, "kNN1NAUC": 0.961634664901052, "J48.001.Kappa": 0.8600372426205263, "MeanSkewnessOfNumericAtts": null, "Quartile1StdDevOfNumericAtts": null, "REPTreeDepth2ErrRate": 0.07174231332357248, "CfsSubsetEval_kNN1NKappa": 0.8078323104788365, "kNN1NErrRate": 0.02635431918008785, "MajorityClassPercentage": 86.53001464128843, "MeanStdDevOfNumericAtts": null, "Quartile2AttributeEntropy": 0.9158362664344971, "Quartile2KurtosisOfNumericAtts": null, "REPTreeDepth2Kappa": 0.6694911069633316, "ClassEntropy": 0.5701880886675914, "kNN1NKappa": 0.8869454866475394, "MajorityClassSize": 591, "MinAttributeEntropy": 0.07262476248540556, "Quartile2MeansOfNumericAtts": null, "REPTreeDepth3AUC": 0.9247406753476054, "DecisionStumpAUC": 0.7990693739424704, "MaxAttributeEntropy": 2.6849389644492594, "MinKurtosisOfNumericAtts": null, "Quartile2MutualInformation": 0.02542623807097, "REPTreeDepth3ErrRate": 0.07174231332357248, "DecisionStumpErrRate": 0.13469985358711567, "MaxKurtosisOfNumericAtts": null, "MinMeansOfNumericAtts": null, "Quartile2SkewnessOfNumericAtts": null, "REPTreeDepth3Kappa": 0.6694911069633316, "DecisionStumpKappa": 0, "MaxMeansOfNumericAtts": null, "MinMutualInformation": 0.00109099324494, "Quartile2StdDevOfNumericAtts": null, "RandomTreeDepth1AUC": 0.9092442615638766, "Dimensionality": 0.0527086383601757, "MaxMutualInformation": 0.15974909959314, "MinNominalAttDistinctValues": 2, "PercentageOfBinaryFeatures": 47.22222222222222, "Quartile3AttributeEntropy": 1.408326420019514, "RandomTreeDepth1ErrRate": 0.04978038067349927, "EquivalentNumberOfAtts": 13.933984802827755, "MaxNominalAttDistinctValues": 7, "MinSkewnessOfNumericAtts": null, "PercentageOfInstancesWithMissingValues": 17.71595900439239, "Quartile3KurtosisOfNumericAtts": null, "AutoCorrelation": 0.9941348973607038, "RandomTreeDepth1Kappa": 0.7844745976648788, "J48.00001.AUC": 0.9699371441398388, "MaxSkewnessOfNumericAtts": null, "MinStdDevOfNumericAtts": null, "PercentageOfMissingValues": 9.504636408003904, "Quartile3MeansOfNumericAtts": null, "CfsSubsetEval_DecisionStumpAUC": 0.9627827264248383, "RandomTreeDepth2AUC": 0.9092442615638766, "J48.00001.ErrRate": 0.03367496339677892, "MaxStdDevOfNumericAtts": null, "MinorityClassPercentage": 13.469985358711567, "PercentageOfNumericFeatures": 0 }, "tags": [ { "uploader": "38960", "tag": "Environmental Science" }, { "uploader": "2", "tag": "study_1" }, { "uploader": "5824", "tag": "study_144" }, { "uploader": "1", "tag": "study_41" } ], "features": [ { "name": "binaryClass", "index": "35", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "P", "N" ], [ [ "92", "0" ], [ "0", "591" ] ] ] }, { "name": "date", "index": "0", "type": "nominal", "distinct": "7", "missing": "1", "distr": [ [ "april", "may", "june", "july", "august", "september", "october" ], [ [ "5", "21" ], [ "27", "48" ], [ "28", "65" ], [ "17", "101" ], [ "8", "123" ], [ "7", "142" ], [ "0", "90" ] ] ] }, { "name": "plant-stand", "index": "1", "type": "nominal", "distinct": "2", "missing": "36", "distr": [ [ "normal", "lt-normal" ], [ [ "57", "297" ], [ "35", "258" ] ] ] }, { "name": "precip", "index": "2", "type": "nominal", "distinct": "3", "missing": "38", "distr": [ [ "lt-norm", "norm", "gt-norm" ], [ [ "0", "74" ], [ "10", "102" ], [ "82", "377" ] ] ] }, { "name": "temp", "index": "3", "type": "nominal", "distinct": "3", "missing": "30", "distr": [ [ "lt-norm", "norm", "gt-norm" ], [ [ "0", "80" ], [ "82", "292" ], [ "10", "189" ] ] ] }, { "name": "hail", "index": "4", "type": "nominal", "distinct": "2", "missing": "121", "distr": [ [ "yes", "no" ], [ [ "81", "354" ], [ "11", "116" ] ] ] }, { "name": "crop-hist", "index": "5", "type": "nominal", "distinct": "4", "missing": "16", "distr": [ [ "diff-lst-year", "same-lst-yr", "same-lst-two-yrs", "same-lst-sev-yrs" ], [ [ "2", "63" ], [ "17", "148" ], [ "37", "182" ], [ "36", "182" ] ] ] }, { "name": "area-damaged", "index": "6", "type": "nominal", "distinct": "4", "missing": "1", "distr": [ [ "scattered", "low-areas", "upper-areas", "whole-field" ], [ [ "7", "116" ], [ "17", "210" ], [ "17", "128" ], [ "51", "136" ] ] ] }, { "name": "severity", "index": "7", "type": "nominal", "distinct": "3", "missing": "121", "distr": [ [ "minor", "pot-severe", "severe" ], [ [ "11", "184" ], [ "75", "247" ], [ "6", "39" ] ] ] }, { "name": "seed-tmt", "index": "8", "type": "nominal", "distinct": "3", "missing": "121", "distr": [ [ "none", "fungicide", "other" ], [ [ "63", "242" ], [ "15", "207" ], [ "14", "21" ] ] ] }, { "name": "germination", "index": "9", "type": "nominal", "distinct": "3", "missing": "112", "distr": [ [ "90-100", "80-89", "lt-80" ], [ [ "27", "138" ], [ "33", "180" ], [ "32", "161" ] ] ] }, { "name": "plant-growth", "index": "10", "type": "nominal", "distinct": "2", "missing": "16", "distr": [ [ "norm", "abnorm" ], [ [ "83", "358" ], [ "9", "217" ] ] ] }, { "name": "leaves", "index": "11", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "norm", "abnorm" ], [ [ "0", "77" ], [ "92", "514" ] ] ] }, { "name": "leafspots-halo", "index": "12", "type": "nominal", "distinct": "3", "missing": "84", "distr": [ [ "absent", "yellow-halos", "no-yellow-halos" ], [ [ "0", "221" ], [ "0", "36" ], [ "92", "250" ] ] ] }, { "name": "leafspots-marg", "index": "13", "type": "nominal", "distinct": "3", "missing": "84", "distr": [ [ "w-s-marg", "no-w-s-marg", "dna" ], [ [ "92", "265" ], [ "0", "21" ], [ "0", "221" ] ] ] }, { "name": "leafspot-size", "index": "14", "type": "nominal", "distinct": "3", "missing": "84", "distr": [ [ "lt-1\/8", "gt-1\/8", "dna" ], [ [ "0", "51" ], [ "92", "235" ], [ "0", "221" ] ] ] }, { "name": "leaf-shread", "index": "15", "type": "nominal", "distinct": "2", "missing": "100", "distr": [ [ "absent", "present" ], [ [ "48", "439" ], [ "44", "52" ] ] ] }, { "name": "leaf-malf", "index": "16", "type": "nominal", "distinct": "2", "missing": "84", "distr": [ [ "absent", "present" ], [ [ "92", "462" ], [ "0", "45" ] ] ] }, { "name": "leaf-mild", "index": "17", "type": "nominal", "distinct": "3", "missing": "108", "distr": [ [ "absent", "upper-surf", "lower-surf" ], [ [ "92", "443" ], [ "0", "20" ], [ "0", "20" ] ] ] }, { "name": "stem", "index": "18", "type": "nominal", "distinct": "2", "missing": "16", "distr": [ [ "norm", "abnorm" ], [ [ "54", "242" ], [ "38", "333" ] ] ] }, { "name": "lodging", "index": "19", "type": "nominal", "distinct": "2", "missing": "121", "distr": [ [ "yes", "no" ], [ [ "92", "428" ], [ "0", "42" ] ] ] }, { "name": "stem-cankers", "index": "20", "type": "nominal", "distinct": "4", "missing": "38", "distr": [ [ "absent", "below-soil", "above-soil", "above-sec-nde" ], [ [ "59", "320" ], [ "0", "39" ], [ "0", "36" ], [ "33", "158" ] ] ] }, { "name": "canker-lesion", "index": "21", "type": "nominal", "distinct": "4", "missing": "38", "distr": [ [ "dna", "brown", "dk-brown-blk", "tan" ], [ [ "54", "266" ], [ "33", "50" ], [ "0", "177" ], [ "5", "60" ] ] ] }, { "name": "fruiting-bodies", "index": "22", "type": "nominal", "distinct": "2", "missing": "106", "distr": [ [ "absent", "present" ], [ [ "56", "417" ], [ "36", "68" ] ] ] }, { "name": "external-decay", "index": "23", "type": "nominal", "distinct": "3", "missing": "38", "distr": [ [ "absent", "firm-and-dry", "watery" ], [ [ "87", "410" ], [ "5", "130" ], [ "0", "13" ] ] ] }, { "name": "mycelium", "index": "24", "type": "nominal", "distinct": "2", "missing": "38", "distr": [ [ "absent", "present" ], [ [ "92", "547" ], [ "0", "6" ] ] ] }, { "name": "int-discolor", "index": "25", "type": "nominal", "distinct": "3", "missing": "38", "distr": [ [ "none", "brown", "black" ], [ [ "92", "489" ], [ "0", "44" ], [ "0", "20" ] ] ] }, { "name": "sclerotia", "index": "26", "type": "nominal", "distinct": "2", "missing": "38", "distr": [ [ "absent", "present" ], [ [ "92", "533" ], [ "0", "20" ] ] ] }, { "name": "fruit-pods", "index": "27", "type": "nominal", "distinct": "4", "missing": "84", "distr": [ [ "norm", "diseased", "few-present", "dna" ], [ [ "90", "317" ], [ "2", "128" ], [ "0", "14" ], [ "0", "48" ] ] ] }, { "name": "fruit-spots", "index": "28", "type": "nominal", "distinct": "4", "missing": "106", "distr": [ [ "absent", "colored", "brown-w\/blk-specks", "distort", "dna" ], [ [ "88", "257" ], [ "2", "73" ], [ "2", "55" ], [ "0", "0" ], [ "0", "100" ] ] ] }, { "name": "seed", "index": "29", "type": "nominal", "distinct": "2", "missing": "92", "distr": [ [ "norm", "abnorm" ], [ [ "92", "384" ], [ "0", "115" ] ] ] }, { "name": "mold-growth", "index": "30", "type": "nominal", "distinct": "2", "missing": "92", "distr": [ [ "absent", "present" ], [ [ "92", "432" ], [ "0", "67" ] ] ] }, { "name": "seed-discolor", "index": "31", "type": "nominal", "distinct": "2", "missing": "106", "distr": [ [ "absent", "present" ], [ [ "92", "421" ], [ "0", "64" ] ] ] }, { "name": "seed-size", "index": "32", "type": "nominal", "distinct": "2", "missing": "92", "distr": [ [ "norm", "lt-norm" ], [ [ "92", "440" ], [ "0", "59" ] ] ] }, { "name": "shriveling", "index": "33", "type": "nominal", "distinct": "2", "missing": "106", "distr": [ [ "absent", "present" ], [ [ "92", "447" ], [ "0", "38" ] ] ] }, { "name": "roots", "index": "34", "type": "nominal", "distinct": "3", "missing": "31", "distr": [ [ "norm", "rotted", "galls-cysts" ], [ [ "92", "459" ], [ "0", "86" ], [ "0", "15" ] ] ] } ], "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 }