{ "data_id": "185", "name": "baseball", "exact_name": "baseball", "version": 1, "version_label": "1", "description": "**Author**: Jeffrey S. Simonoff \n**Source**: [AnalCatData](http:\/\/www.stern.nyu.edu\/~jsimonof\/AnalCatData) - 2003 \n**Please cite**: Jeffrey S. Simonoff, Analyzing Categorical Data, Springer-Verlag, New York, 2003 \n \nDatabase of baseball players and play statistics, including 'Games_played', 'At_bats', 'Runs', 'Hits', 'Doubles', 'Triples', 'Home_runs', 'RBIs', 'Walks', 'Strikeouts', 'Batting_average', 'On_base_pct', 'Slugging_pct' and 'Fielding_ave' \n\nNotes: \n* Quotes, Single-Quotes and Backslashes were removed, Blanks replaced with Underscores\n* Player is an identifier that should be ignored when modelling the data", "format": "ARFF", "uploader": "Jan van Rijn", "uploader_id": 1, "visibility": "public", "creator": null, "contributor": null, "date": "2014-04-23 13:15:17", "update_comment": "set the default target feature", "last_update": "2015-04-15 16:32:45", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3622\/dataset_189_baseball.arff", "default_target_attribute": "Hall_of_Fame", "row_id_attribute": null, "ignore_attribute": "\"Player\"", "runs": 795, "suggest": { "input": [ "baseball", "Database of baseball players and play statistics, including 'Games_played', 'At_bats', 'Runs', 'Hits', 'Doubles', 'Triples', 'Home_runs', 'RBIs', 'Walks', 'Strikeouts', 'Batting_average', 'On_base_pct', 'Slugging_pct' and 'Fielding_ave' Notes: * Quotes, Single-Quotes and Backslashes were removed, Blanks replaced with Underscores * Player is an identifier that should be ignored when modelling the data " ], "weight": 5 }, "qualities": { "NumberOfInstances": 1340, "NumberOfFeatures": 18, "NumberOfClasses": 3, "NumberOfMissingValues": 20, "NumberOfInstancesWithMissingValues": 20, "NumberOfNumericFeatures": 15, "NumberOfSymbolicFeatures": 3, "NaiveBayesKappa": 0.4238689741910336, "Quartile1MeansOfNumericAtts": 0.9663701492537313, "REPTreeDepth1AUC": 0.8524888908484827, "CfsSubsetEval_NaiveBayesErrRate": 0.08432835820895522, "RandomTreeDepth3ErrRate": 0.09477611940298507, "J48.0001.Kappa": 0.4542095109732028, "MeanMutualInformation": 0.01080667579391, "NumberOfBinaryFeatures": 0, "Quartile1MutualInformation": 0.01080667579391, "REPTreeDepth1ErrRate": 0.07611940298507462, "CfsSubsetEval_NaiveBayesKappa": 0.4418313181952225, "RandomTreeDepth3Kappa": 0.44946946169772267, "J48.001.AUC": 0.7379923166323268, "MeanNoiseToSignalRatio": 223.46022246442445, "Quartile1SkewnessOfNumericAtts": 0.4861180401193656, "REPTreeDepth1Kappa": 0.4416415770316478, "CfsSubsetEval_kNN1NAUC": 0.7322241366331184, "StdvNominalAttDistinctValues": 2.8284271247461903, "J48.001.ErrRate": 0.08208955223880597, "MeanNominalAttDistinctValues": 5, "Quartile1StdDevOfNumericAtts": 0.06056474888614795, "REPTreeDepth2AUC": 0.8524888908484827, "CfsSubsetEval_kNN1NErrRate": 0.08432835820895522, "kNN1NAUC": 0.7604723868488261, "J48.001.Kappa": 0.4542095109732028, "MeanSkewnessOfNumericAtts": 0.8335889988230164, "Quartile2AttributeEntropy": 2.425668852801949, "REPTreeDepth2ErrRate": 0.07611940298507462, "CfsSubsetEval_kNN1NKappa": 0.4418313181952225, "kNN1NErrRate": 0.08507462686567165, "MajorityClassPercentage": 90.67164179104478, "MeanStdDevOfNumericAtts": 324.92966790949765, "Quartile2KurtosisOfNumericAtts": 1.0929791300745273, "REPTreeDepth2Kappa": 0.4416415770316478, "ClassEntropy": 0.5400978590902226, "kNN1NKappa": 0.47854938693028193, "MajorityClassSize": 1215, "MinAttributeEntropy": 2.425668852801949, "Quartile2MeansOfNumericAtts": 203.22537313432835, "REPTreeDepth3AUC": 0.8524888908484827, "DecisionStumpAUC": 0.8463216676547555, "MaxAttributeEntropy": 2.425668852801949, "MinKurtosisOfNumericAtts": 0.2523895391254345, "Quartile2MutualInformation": 0.01080667579391, "REPTreeDepth3ErrRate": 0.07611940298507462, "DecisionStumpErrRate": 0.09328358208955224, "MaxKurtosisOfNumericAtts": 8.03249062149215, "MinMeansOfNumericAtts": 0.2687738805970149, "Quartile2SkewnessOfNumericAtts": 0.9564090413257389, "REPTreeDepth3Kappa": 0.4416415770316478, "DecisionStumpKappa": 0, "MaxMeansOfNumericAtts": 4534.612686567164, "MinMutualInformation": 0.01080667579391, "PercentageOfBinaryFeatures": 0, "Quartile2StdDevOfNumericAtts": 116.57605266414018, "RandomTreeDepth1AUC": 0.7624240000950409, "Dimensionality": 0.013432835820895522, "MaxMutualInformation": 0.01080667579391, "MinNominalAttDistinctValues": 3, "PercentageOfInstancesWithMissingValues": 1.4925373134328357, "Quartile3AttributeEntropy": 2.425668852801949, "RandomTreeDepth1ErrRate": 0.09477611940298507, "EquivalentNumberOfAtts": 49.97816806853682, "MaxNominalAttDistinctValues": 7, "MinSkewnessOfNumericAtts": -1.8663891071518195, "PercentageOfMissingValues": 0.08291873963515754, "Quartile3KurtosisOfNumericAtts": 3.550029422261427, "AutoCorrelation": 0.830470500373413, "RandomTreeDepth1Kappa": 0.44946946169772267, "J48.00001.AUC": 0.7379923166323268, "MaxSkewnessOfNumericAtts": 2.4656389038958446, "MinStdDevOfNumericAtts": 0.025192884084429993, "MinorityClassPercentage": 4.253731343283582, "PercentageOfNumericFeatures": 83.33333333333334, "Quartile3MeansOfNumericAtts": 635.3134328358208, "CfsSubsetEval_DecisionStumpAUC": 0.7322241366331184, "RandomTreeDepth2AUC": 0.7624240000950409, "J48.00001.ErrRate": 0.08208955223880597, "MaxStdDevOfNumericAtts": 2094.191123804227, "MinorityClassSize": 57, "PercentageOfSymbolicFeatures": 16.666666666666664, "Quartile3MutualInformation": 0.01080667579391, "CfsSubsetEval_DecisionStumpErrRate": 0.08432835820895522, "RandomTreeDepth2ErrRate": 0.09477611940298507, "J48.00001.Kappa": 0.4542095109732028, "MeanAttributeEntropy": 2.425668852801949, "NaiveBayesAUC": 0.9505150531149896, "Quartile1AttributeEntropy": 2.425668852801949, "Quartile3SkewnessOfNumericAtts": 1.517274889777313, "CfsSubsetEval_DecisionStumpKappa": 0.4418313181952225, "RandomTreeDepth2Kappa": 0.44946946169772267, "J48.0001.AUC": 0.7379923166323268, "MeanKurtosisOfNumericAtts": 2.1412222749209304, "NaiveBayesErrRate": 0.15970149253731344, "Quartile1KurtosisOfNumericAtts": 0.6304206769153993, "Quartile3StdDevOfNumericAtts": 376.400804482129, "CfsSubsetEval_NaiveBayesAUC": 0.7322241366331184, "RandomTreeDepth3AUC": 0.7624240000950409, "J48.0001.ErrRate": 0.08208955223880597, "MeanMeansOfNumericAtts": 637.4240550806572 }, "tags": [ { "tag": "study_1", "uploader": "2" }, { "tag": "study_144", "uploader": "5824" }, { "tag": "study_37", "uploader": "1" }, { "tag": "study_52", "uploader": "64" }, { "tag": "study_70", "uploader": "1856" } ], "features": [ { "name": "Hall_of_Fame", "index": "17", "type": "nominal", "distinct": "3", "missing": "0", "target": "1", "distr": [ [ "0", "1", "2" ], [ [ "1215", "0", "0" ], [ "0", "57", "0" ], [ "0", "0", "68" ] ] ] }, { "name": "Player", "index": "0", "type": "nominal", "distinct": "1339", "missing": "0", "ignore": "1", "distr": [] }, { "name": "Number_seasons", "index": "1", "type": "numeric", "distinct": "17", "missing": "0", "min": "10", "max": "26", "mean": "13", "stdev": "3" }, { "name": "Games_played", "index": "2", "type": "numeric", "distinct": "981", "missing": "0", "min": "140", "max": "3562", "mean": "1331", "stdev": "519" }, { "name": "At_bats", "index": "3", "type": "numeric", "distinct": "1239", "missing": "0", "min": "252", "max": "14053", "mean": "4535", "stdev": "2094" }, { "name": "Runs", "index": "4", "type": "numeric", "distinct": "812", "missing": "0", "min": "20", "max": "2246", "mean": "635", "stdev": "376" }, { "name": "Hits", "index": "5", "type": "numeric", "distinct": "999", "missing": "0", "min": "48", "max": "4256", "mean": "1249", "stdev": "648" }, { "name": "Doubles", "index": "6", "type": "numeric", "distinct": "418", "missing": "0", "min": "6", "max": "792", "mean": "203", "stdev": "117" }, { "name": "Triples", "index": "7", "type": "numeric", "distinct": "180", "missing": "0", "min": "0", "max": "309", "mean": "51", "stdev": "41" }, { "name": "Home_runs", "index": "8", "type": "numeric", "distinct": "291", "missing": "0", "min": "0", "max": "755", "mean": "85", "stdev": "98" }, { "name": "RBIs", "index": "9", "type": "numeric", "distinct": "795", "missing": "0", "min": "21", "max": "2297", "mean": "566", "stdev": "357" }, { "name": "Walks", "index": "10", "type": "numeric", "distinct": "712", "missing": "0", "min": "17", "max": "2056", "mean": "446", "stdev": "295" }, { "name": "Strikeouts", "index": "11", "type": "numeric", "distinct": "722", "missing": "20", "min": "0", "max": "2597", "mean": "446", "stdev": "325" }, { "name": "Batting_average", "index": "12", "type": "numeric", "distinct": "143", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "On_base_pct", "index": "13", "type": "numeric", "distinct": "176", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "Slugging_pct", "index": "14", "type": "numeric", "distinct": "274", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "Fielding_ave", "index": "15", "type": "numeric", "distinct": "125", "missing": "0", "min": "1", "max": "1", "mean": "1", "stdev": "0" }, { "name": "Position", "index": "16", "type": "nominal", "distinct": "7", "missing": "0", "distr": [ [ "Catcher", "Designated_hitter", "First_base", "Outfield", "Second_base", "Shortstop", "Third_base" ], [ [ "243", "5", "6" ], [ "8", "0", "0" ], [ "120", "10", "9" ], [ "437", "25", "30" ], [ "133", "7", "8" ], [ "137", "6", "11" ], [ "137", "4", "4" ] ] ] } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 10, "total_downloads": 15, "reach": 10, "reuse": 2, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 2 }