{ "data_id": "452", "name": "analcatdata_broadwaymult", "exact_name": "analcatdata_broadwaymult", "version": 1, "version_label": null, "description": "**Author**: \n**Source**: Unknown - Date unknown \n**Please cite**: \n\nanalcatdata A collection of data sets used in the book \"Analyzing Categorical Data,\"\nby Jeffrey S. Simonoff, Springer-Verlag, New York, 2003. The submission\nconsists of a zip file containing two versions of each of 84 data sets,\nplus this README file. Each data set is given in comma-delimited ASCII\n(.csv) form, and Microsoft Excel (.xls) form.\n\nNOTICE: These data sets may be used freely for scientific, educational and\/or\nnoncommercial purposes, provided suitable acknowledgment is given (by citing\nthe above-named reference).\n\nFurther details concerning the book, including information on statistical software\n(including sample S-PLUS\/R and SAS code), are available at the web site\n\nhttp:\/\/www.stern.nyu.edu\/~jsimonof\/AnalCatData\n\n\nInformation about the dataset\nCLASSTYPE: nominal\nCLASSINDEX: last\n\n\nNote: Quotes, Single-Quotes and Backslashes were removed, Blanks replaced\nwith Underscores", "format": "ARFF", "uploader": "Joaquin Vanschoren", "uploader_id": 2, "visibility": "public", "creator": null, "contributor": null, "date": "2014-09-28 23:50:53", "update_comment": null, "last_update": "2014-09-28 23:50:53", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/52564\/analcatdata_broadwaymult.arff", "default_target_attribute": "Count", "row_id_attribute": null, "ignore_attribute": null, "runs": 537, "suggest": { "input": [ "analcatdata_broadwaymult", "analcatdata A collection of data sets used in the book \"Analyzing Categorical Data,\" by Jeffrey S. Simonoff, Springer-Verlag, New York, 2003. The submission consists of a zip file containing two versions of each of 84 data sets, plus this README file. Each data set is given in comma-delimited ASCII (.csv) form, and Microsoft Excel (.xls) form. NOTICE: These data sets may be used freely for scientific, educational and\/or noncommercial purposes, provided suitable acknowledgment is given (by citing " ], "weight": 5 }, "qualities": { "NumberOfInstances": 285, "NumberOfFeatures": 8, "NumberOfClasses": 7, "NumberOfMissingValues": 27, "NumberOfInstancesWithMissingValues": 18, "NumberOfNumericFeatures": 3, "NumberOfSymbolicFeatures": 5, "MajorityClassPercentage": 41.40350877192983, "MeanStdDevOfNumericAtts": 7.081738683385092, "Quartile2AttributeEntropy": 1.4242970827519021, "REPTreeDepth2ErrRate": 0.5859649122807018, "CfsSubsetEval_kNN1NKappa": 0.2820512820512821, "kNN1NErrRate": 0.7263157894736842, "kNN1NKappa": 0.03620264331574394, "MajorityClassSize": 118, "MinAttributeEntropy": 0.9864497419502245, "Quartile2KurtosisOfNumericAtts": -1.3436105548296726, "REPTreeDepth2Kappa": 0, "ClassEntropy": 2.4752634089440466, "MaxAttributeEntropy": 6.569855608330948, "MinKurtosisOfNumericAtts": -1.4802830028278906, "Quartile2MeansOfNumericAtts": 3.17029, "REPTreeDepth3AUC": 0.496260459400405, "DecisionStumpAUC": 0.6906336068579246, "MaxKurtosisOfNumericAtts": -0.5838720931912555, "MinMeansOfNumericAtts": 2.9677425806451616, "Quartile2MutualInformation": 0.31672639206438, "REPTreeDepth3ErrRate": 0.5859649122807018, "DecisionStumpErrRate": 0.49122807017543857, "MaxMeansOfNumericAtts": 75.86549450549451, "MinMutualInformation": 0.01779969570981, "Quartile2SkewnessOfNumericAtts": 0.1445599794000887, "REPTreeDepth3Kappa": 0, "DecisionStumpKappa": 0.2820512820512821, "MaxMutualInformation": 1.27719446087724, "MinNominalAttDistinctValues": 2, "PercentageOfBinaryFeatures": 12.5, "Quartile2StdDevOfNumericAtts": 1.3124066117749271, "RandomTreeDepth1AUC": 0.4697557841580932, "Dimensionality": 0.028070175438596492, "MaxNominalAttDistinctValues": 95, "MinSkewnessOfNumericAtts": -0.6564519517017497, "PercentageOfInstancesWithMissingValues": 6.315789473684211, "Quartile3AttributeEntropy": 5.3236323314285, "RandomTreeDepth1ErrRate": 0.7298245614035088, "EquivalentNumberOfAtts": 5.134211072512612, "MaxSkewnessOfNumericAtts": 0.2858170873557239, "MinStdDevOfNumericAtts": 1.239888951814703, "PercentageOfMissingValues": 1.1842105263157896, "Quartile3KurtosisOfNumericAtts": -0.5838720931912555, "AutoCorrelation": 0.19718309859154928, "RandomTreeDepth1Kappa": -0.036073825503355736, "J48.00001.AUC": 0.7350046072308111, "MaxStdDevOfNumericAtts": 18.692920486565647, "MinorityClassPercentage": 7.368421052631578, "PercentageOfNumericFeatures": 37.5, "Quartile3MeansOfNumericAtts": 75.86549450549451, "CfsSubsetEval_DecisionStumpAUC": 0.7538519471160182, "RandomTreeDepth2AUC": 0.4697557841580932, "J48.00001.ErrRate": 0.45964912280701753, "MeanAttributeEntropy": 2.601224878946244, "MinorityClassSize": 21, "PercentageOfSymbolicFeatures": 62.5, "Quartile3MutualInformation": 1.0956774799681825, "CfsSubsetEval_DecisionStumpErrRate": 0.49122807017543857, "RandomTreeDepth2ErrRate": 0.7298245614035088, "J48.00001.Kappa": 0.36341625603164596, "MeanKurtosisOfNumericAtts": -1.135921883616273, "NaiveBayesAUC": 0.79074931779051, "Quartile1AttributeEntropy": 1.0557452226583304, "Quartile3SkewnessOfNumericAtts": 0.2858170873557239, "CfsSubsetEval_DecisionStumpKappa": 0.2820512820512821, "RandomTreeDepth2Kappa": -0.036073825503355736, "J48.0001.AUC": 0.7350046072308111, "MeanMeansOfNumericAtts": 27.334509028713224, "NaiveBayesErrRate": 0.512280701754386, "Quartile1KurtosisOfNumericAtts": -1.4802830028278906, "Quartile3StdDevOfNumericAtts": 18.692920486565647, "CfsSubsetEval_NaiveBayesAUC": 0.7538519471160182, "RandomTreeDepth3AUC": 0.4697557841580932, "J48.0001.ErrRate": 0.45964912280701753, "MeanMutualInformation": 0.48211173517895256, "NaiveBayesKappa": 0.326044703595724, "Quartile1MeansOfNumericAtts": 2.9677425806451616, "REPTreeDepth1AUC": 0.496260459400405, "CfsSubsetEval_NaiveBayesErrRate": 0.49122807017543857, "RandomTreeDepth3ErrRate": 0.7298245614035088, "J48.0001.Kappa": 0.36341625603164596, "MeanNoiseToSignalRatio": 4.395481356579526, "NumberOfBinaryFeatures": 1, "Quartile1MutualInformation": 0.033931333504295, "REPTreeDepth1ErrRate": 0.5859649122807018, "CfsSubsetEval_NaiveBayesKappa": 0.2820512820512821, "RandomTreeDepth3Kappa": -0.036073825503355736, "J48.001.AUC": 0.7350046072308111, "J48.001.ErrRate": 0.45964912280701753, "MeanNominalAttDistinctValues": 22, "Quartile1SkewnessOfNumericAtts": -0.6564519517017497, "REPTreeDepth1Kappa": 0, "CfsSubsetEval_kNN1NAUC": 0.7538519471160182, "StdvNominalAttDistinctValues": 40.85339643163099, "J48.001.Kappa": 0.36341625603164596, "MeanSkewnessOfNumericAtts": -0.07535829498197905, "Quartile1StdDevOfNumericAtts": 1.239888951814703, "REPTreeDepth2AUC": 0.496260459400405, "CfsSubsetEval_kNN1NErrRate": 0.49122807017543857, "kNN1NAUC": 0.4987974809219122 }, "tags": [ { "tag": "study_1", "uploader": "2" }, { "tag": "study_41", "uploader": "1" }, { "tag": "study_52", "uploader": "64" } ], "features": [ { "name": "Count", "index": "7", "type": "nominal", "distinct": "7", "missing": "0", "target": "1", "distr": [ [ "0", "1", "2", "3", "4", "5", "6" ], [ [ "118", "0", "0", "0", "0", "0", "0" ], [ "0", "34", "0", "0", "0", "0", "0" ], [ "0", "0", "32", "0", "0", "0", "0" ], [ "0", "0", "0", "21", "0", "0", "0" ], [ "0", "0", "0", "0", "25", "0", "0" ], [ "0", "0", "0", "0", "0", "21", "0" ], [ "0", "0", "0", "0", "0", "0", "34" ] ] ] }, { "name": "Show", "index": "0", "type": "nominal", "distinct": "95", "missing": "0", "distr": [ [ "1776", "A_Dolls_House", "A_Thousand_Clowns", "A_View_From_the_Bridge", "Ah_Wilderness!", "Amys_View", "An_American_Daughter", "Annie", "Annie_Get_Your_Gun", "Art", "Band_in_Berlin", "Barrymore", "Cabaret", "Candide", "Chicago", "Closer", "Death_of_a_Salesman", "Dream_-_The_Johnny_Mercer_Musical", "Electra", "Eugene_Onegin", "Footloose", "Forever_Tango", "Fosse!", "Getting_and_Spending", "God_Said_Ha!", "Golden_Child", "High_Society", "Honour", "Hughie", "Into_the_Whirlwind", "It_Aint_Nothin_But_the_Blues", "Ivanov", "Jackie_-_An_American_Life", "Jekyll_and_Hyde", "Juan_Darien_-_A_Carnival_Mass", "King_David", "Little_Me", "London_Assurance", "Marlene", "More_to_Love", "Night_Must_Fall", "Not_About_Nightingales", "On_the_Town", "Once_Upon_a_Mattress", "Parade", "Peter_Pan", "Play_On!", "Present_Laughter", "Proposals", "Ragtime", "Ring_Around_the_Moon", "Rolling_on_the_T.O.B.A.", "Sex_and_Longing", "Side_Man", "Side_Show", "Skylight", "Stanley", "Steel_Pier", "Street_Corner_Symphony", "Summer_and_Smoke", "Swan_Lake", "Taking_Sides", "The_Beauty_Queen_of_Leenane", "The_Blue_Room", "The_Capeman", "The_Chairs", "The_Cherry_Orchard", "The_Civil_War:_An_American_Musical", "The_Deep_Blue_Sea", "The_Diary_of_Anne_Frank", "The_Gershwins_Fascinating_Rhythm", "The_Gin_Game", "The_Herbal_Bed", "The_Iceman_Cometh", "The_Judas_Kiss", "The_Last_Night_of_Ballyhoo", "The_Life", "The_Lion_King", "The_Lion_in_Winter", "The_Little_Foxes", "The_Lonesome_West", "The_Old_Neighborhood", "The_Rehearsal", "The_Scarlet_Pimpernel", "The_Sound_of_Music", "The_Sunshine_Boys", "The_Three_Sisters_(1)", "The_Three_Sisters_(2)", "The_Weir", "The_Young_Man_From_Atlanta", "Titanic", "Triumph_of_Love", "Twelfth_Night", "Wait_Until_Dark", "Youre_a_Good_Man_Charlie_Brown" ], [ [ "1", "0", "0", "2", "0", "0", "0" ], [ "1", "0", "1", "0", "1", "0", "0" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "0", "0", "3", "0", "0", "0", "0" ], [ "1", "0", "1", "0", "1", "0", "0" ], [ "0", "2", "0", "0", "1", "0", "0" ], [ "1", "1", "0", "0", "0", "1", "0" ], [ "1", "1", "0", "0", "0", "1", "0" ], [ "0", "1", "1", "1", "0", "0", "0" ], [ "0", "1", "1", "1", "0", "0", "0" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "1", "1", "0", "0", "0", "1", "0" ], [ "1", "0", "1", "0", "1", "0", "0" ], [ "1", "0", "0", "2", "0", "0", "0" ], [ "0", "2", "0", "0", "1", "0", "0" ], [ "1", "1", "0", "0", "0", "1", "0" ], [ "1", "0", "1", "0", "1", "0", "0" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "1", "0", "0", "2", "0", "0", "0" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "1", "1", "0", "0", "0", "1", "0" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "0", "2", "0", "0", "1", "0", "0" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "1", "0", "1", "0", "1", "0", "0" ], [ "1", "0", "1", "0", "1", "0", "0" ], [ "1", "0", "1", "0", "1", "0", "0" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "1", "0", "0", "2", "0", "0", "0" ], [ "1", "1", "0", "0", "0", "1", "0" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "1", "1", "0", "0", "0", "1", "0" ], [ "1", "0", "1", "0", "1", "0", "0" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "0", "2", "0", "0", "1", "0", "0" ], [ "1", "0", "0", "2", "0", "0", "0" ], [ "1", "1", "0", "0", "0", "1", "0" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "1", "0", "1", "0", "1", "0", "0" ], [ "1", "1", "0", "0", "0", "1", "0" ], [ "1", "1", "0", "0", "0", "1", "0" ], [ "1", "0", "1", "0", "1", "0", "0" ], [ "1", "1", "0", "0", "0", "1", "0" ], [ "1", "0", "1", "0", "1", "0", "0" ], [ "1", "1", "0", "0", "0", "1", "0" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "1", "1", "0", "0", "0", "1", "0" ], [ "1", "1", "0", "0", "0", "1", "0" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "1", "0", "1", "0", "1", "0", "0" ], [ "1", "0", "1", "0", "1", "0", "0" ], [ "1", "0", "1", "0", "1", "0", "0" ], [ "1", "0", "0", "2", "0", "0", "0" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "0", "2", "0", "0", "1", "0", "0" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "1", "0", "1", "0", "1", "0", "0" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "1", "0", "1", "0", "1", "0", "0" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "1", "1", "0", "0", "0", "1", "0" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "1", "0", "1", "0", "1", "0", "0" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "1", "0", "0", "2", "0", "0", "0" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "1", "0", "0", "2", "0", "0", "0" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "0", "1", "1", "1", "0", "0", "0" ], [ "1", "0", "1", "0", "1", "0", "0" ], [ "0", "0", "3", "0", "0", "0", "0" ], [ "1", "1", "0", "0", "0", "1", "0" ], [ "1", "1", "0", "0", "0", "1", "0" ], [ "1", "0", "1", "0", "1", "0", "0" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "1", "0", "1", "0", "1", "0", "0" ], [ "1", "1", "0", "0", "0", "1", "0" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "1", "0", "0", "2", "0", "0", "0" ], [ "1", "1", "0", "0", "0", "1", "0" ], [ "1", "1", "0", "0", "0", "1", "0" ], [ "1", "1", "0", "0", "0", "1", "0" ], [ "2", "0", "0", "0", "0", "0", "1" ], [ "0", "0", "3", "0", "0", "0", "0" ] ] ] }, { "name": "Type", "index": "1", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "Musical", "Musical_revue", "Play" ], [ [ "32", "19", "15", "5", "11", "12", "5" ], [ "11", "2", "0", "2", "1", "0", "5" ], [ "75", "13", "17", "14", "13", "9", "24" ] ] ] }, { "name": "Revival", "index": "2", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "No", "Yes" ], [ [ "71", "16", "19", "8", "16", "10", "22" ], [ "47", "18", "13", "13", "9", "11", "12" ] ] ] }, { "name": "NYT_rating", "index": "3", "type": "numeric", "distinct": "13", "missing": "6", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "DN_rating", "index": "4", "type": "numeric", "distinct": "13", "missing": "9", "min": "1", "max": "5", "mean": "3", "stdev": "1" }, { "name": "Week_1_attendance", "index": "5", "type": "numeric", "distinct": "90", "missing": "12", "min": "29", "max": "102", "mean": "76", "stdev": "19" }, { "name": "Award", "index": "6", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "Losing_nomination", "No_nomination", "Win" ], [ [ "38", "22", "16", "10", "7", "1", "1" ], [ "6", "2", "10", "11", "13", "20", "33" ], [ "74", "10", "6", "0", "5", "0", "0" ] ] ] } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 4, "total_downloads": 6, "reach": 4, "reuse": 6, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 6 }