{ "data_id": "40869", "name": "pathogen_survey_dataset", "exact_name": "pathogen_survey_dataset", "version": 3, "version_label": "3", "description": "#study_1", "format": "ARFF", "uploader": "Patrick Schratz", "uploader_id": 3508, "visibility": "public", "creator": "\"Eugenia Iturritxa\"", "contributor": null, "date": "2017-07-06 11:43:15", "update_comment": null, "last_update": "2017-07-06 11:43:15", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/9871213\/phphmhExR", "default_target_attribute": null, "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "pathogen_survey_dataset", "#study_1 " ], "weight": 5 }, "qualities": { "NumberOfInstances": 944, "NumberOfFeatures": 17, "NumberOfClasses": null, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 10, "NumberOfSymbolicFeatures": 7, "ClassEntropy": null, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.018008474576271187, "MeanNominalAttDistinctValues": 6, "Quartile2KurtosisOfNumericAtts": -0.42006019997187827, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 0.20918639813608036, "Quartile2MeansOfNumericAtts": 135.40370653389832, "MajorityClassPercentage": null, "MeanStdDevOfNumericAtts": 4712.200112687749, "Quartile2MutualInformation": null, "MajorityClassSize": null, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 0.26032390910673764, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.2334442122121074, "PercentageOfBinaryFeatures": 23.52941176470588, "Quartile2StdDevOfNumericAtts": 44.061995996309605, "MaxKurtosisOfNumericAtts": 2.2847284819542, "MinMeansOfNumericAtts": 0.00010756038135593208, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 4779713.107359638, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 0.7169064276017333, "MaxMutualInformation": null, "MinNominalAttDistinctValues": 2, "PercentageOfNumericFeatures": 58.82352941176471, "Quartile3MeansOfNumericAtts": 133558.09453782046, "MaxNominalAttDistinctValues": 17, "MinSkewnessOfNumericAtts": -1.0453962209133247, "PercentageOfSymbolicFeatures": 41.17647058823529, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 1.2888294149132073, "MinStdDevOfNumericAtts": 0.040345432031963245, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.8110023911011726, "MaxStdDevOfNumericAtts": 32995.52947584042, "MinorityClassPercentage": null, "Quartile1KurtosisOfNumericAtts": -0.8006709384779077, "Quartile3StdDevOfNumericAtts": 3613.0953844320693, "MeanAttributeEntropy": null, "MinorityClassSize": null, "Quartile1MeansOfNumericAtts": 12.501850840572033, "StdvNominalAttDistinctValues": 6.298147875897061, "MeanKurtosisOfNumericAtts": -0.008370431248348477, "NumberOfBinaryFeatures": 4, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 531332.0222745826, "Quartile1SkewnessOfNumericAtts": -0.3891112800800378, "AutoCorrelation": null, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.6451256170036409 }, "tags": [ { "uploader": "38960", "tag": "Life Science" }, { "uploader": "38960", "tag": "Machine Learning" }, { "uploader": "2", "tag": "unspecified_target_feature" } ], "features": [ { "name": "id", "index": "0", "type": "numeric", "distinct": "944", "missing": "0", "min": "133", "max": "1174", "mean": "635", "stdev": "304" }, { "name": "x", "index": "1", "type": "numeric", "distinct": "898", "missing": "0", "min": "466043", "max": "602423", "mean": "532326", "stdev": "32996" }, { "name": "y", "index": "2", "type": "numeric", "distinct": "901", "missing": "0", "min": "4704304", "max": "4806565", "mean": "4779713", "stdev": "13540" }, { "name": "fus01", "index": "3", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "273", "269", "109", "151" ], [ "129", "0", "0", "13" ] ] ] }, { "name": "diplo01", "index": "4", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "246", "238", "79", "157" ], [ "156", "31", "30", "7" ] ] ] }, { "name": "temp", "index": "5", "type": "numeric", "distinct": "209", "missing": "0", "min": "13", "max": "17", "mean": "15", "stdev": "1" }, { "name": "p_sum", "index": "6", "type": "numeric", "distinct": "641", "missing": "0", "min": "124", "max": "497", "mean": "234", "stdev": "69" }, { "name": "r_sum", "index": "7", "type": "numeric", "distinct": "524", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "elevation", "index": "8", "type": "numeric", "distinct": "910", "missing": "0", "min": "1", "max": "886", "mean": "339", "stdev": "182" }, { "name": "slope", "index": "9", "type": "numeric", "distinct": "855", "missing": "0", "min": "0", "max": "70", "mean": "37", "stdev": "19" }, { "name": "hail", "index": "10", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "240", "231", "79", "158" ], [ "162", "38", "30", "6" ] ] ] }, { "name": "hail_new", "index": "11", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "200", "158", "32", "25" ], [ "202", "111", "77", "139" ] ] ] }, { "name": "age", "index": "12", "type": "numeric", "distinct": "38", "missing": "0", "min": "1", "max": "40", "mean": "16", "stdev": "11" }, { "name": "ph", "index": "13", "type": "numeric", "distinct": "184", "missing": "0", "min": "4", "max": "6", "mean": "5", "stdev": "0" }, { "name": "lithology", "index": "14", "type": "nominal", "distinct": "17", "missing": "0", "distr": [ [ "Depsitos superficiales", "Areniscas", "Limolitas", "Lutitas", "Detrticos alternantes", "Margas descarbonatadas", "Margas", "Calizas impuras y calcarenitas", "Calizas", "Rocas volcnicas piroclsticas", "Rocas volcnicas en coladas", "Ofitas", "Arcillas con yesos y otras sales", "Alternancia de margocalizas margas calizas y calcarenitas", "Pizarras", "Granitos de grano grueso", "Granodioritas" ], [ [ "5", "4", "3", "20" ], [ "47", "22", "2", "7" ], [ "7", "15", "2", "0" ], [ "2", "0", "0", "4" ], [ "234", "72", "53", "69" ], [ "2", "15", "0", "0" ], [ "7", "14", "0", "0" ], [ "31", "48", "17", "29" ], [ "3", "14", "3", "1" ], [ "0", "1", "0", "0" ], [ "0", "0", "0", "4" ], [ "0", "5", "0", "0" ], [ "0", "6", "0", "0" ], [ "31", "31", "13", "16" ], [ "29", "22", "16", "10" ], [ "0", "0", "0", "4" ], [ "4", "0", "0", "0" ] ] ] }, { "name": "soil", "index": "15", "type": "nominal", "distinct": "13", "missing": "0", "distr": [ [ "Cambisols", "Chernozems", "Cryosols", "Durisols", "Ferralsols", "Fluvisols", "Gleysols", "Gypsisols", "Histosols", "Kastanozems", "Leptosols", "Lixisols", "Luvisols" ], [ [ "298", "176", "78", "117" ], [ "4", "2", "3", "1" ], [ "3", "1", "0", "2" ], [ "4", "1", "0", "1" ], [ "4", "6", "4", "4" ], [ "2", "4", "1", "0" ], [ "9", "8", "2", "2" ], [ "5", "1", "0", "1" ], [ "6", "5", "1", "3" ], [ "6", "6", "2", "1" ], [ "4", "6", "2", "1" ], [ "7", "10", "1", "3" ], [ "50", "43", "15", "28" ] ] ] }, { "name": "year", "index": "16", "type": "nominal", "distinct": "4", "missing": "0", "distr": [ [ "2009", "2010", "2011", "2012" ], [ [ "402", "0", "0", "0" ], [ "0", "269", "0", "0" ], [ "0", "0", "109", "0" ], [ "0", "0", "0", "164" ] ] ] } ], "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 }