{ "data_id": "897", "name": "colleges_aaup", "exact_name": "colleges_aaup", "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). It converts the numeric target feature to a two-class nominal target feature by computing the mean and classifying all instances with a lower target value as positive ('P') and all others as negative ('N').", "format": "ARFF", "uploader": "Joaquin Vanschoren", "uploader_id": 2, "visibility": "public", "creator": null, "contributor": null, "date": "2014-10-04 14:36:31", "update_comment": null, "last_update": "2014-10-06 03:35:44", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/53431\/colleges_aaup.arff", "default_target_attribute": "binaryClass", "row_id_attribute": null, "ignore_attribute": "\"College_name\"", "runs": 101, "suggest": { "input": [ "colleges_aaup", "Binarized version of the original data set (see version 1). It converts the numeric target feature to a two-class nominal target feature by computing the mean and classifying all instances with a lower target value as positive ('P') and all others as negative ('N'). " ], "weight": 5 }, "qualities": { "NumberOfInstances": 1161, "NumberOfFeatures": 16, "NumberOfClasses": 2, "NumberOfMissingValues": 256, "NumberOfInstancesWithMissingValues": 87, "NumberOfNumericFeatures": 13, "NumberOfSymbolicFeatures": 3, "REPTreeDepth3Kappa": 0.8559011893870082, "DecisionStumpKappa": 0.8684712759671845, "MaxMeansOfNumericAtts": 3052.0473729543355, "MinMutualInformation": 0.0467807056168, "Quartile2SkewnessOfNumericAtts": 0.6846258112240072, "RandomTreeDepth1AUC": 0.9476714594732153, "Dimensionality": 0.013781223083548665, "MaxMutualInformation": 0.47910875218483, "MinNominalAttDistinctValues": 2, "PercentageOfBinaryFeatures": 6.25, "Quartile2StdDevOfNumericAtts": 92.28671935660121, "RandomTreeDepth1ErrRate": 0.046511627906976744, "EquivalentNumberOfAtts": 3.350418203280184, "MaxNominalAttDistinctValues": 52, "MinSkewnessOfNumericAtts": 0.34358420480988844, "PercentageOfInstancesWithMissingValues": 7.493540051679587, "Quartile3AttributeEntropy": 5.248050549098432, "RandomTreeDepth1Kappa": 0.8897470798645184, "J48.00001.AUC": 0.9649994344771033, "MaxSkewnessOfNumericAtts": 5.815258975041083, "MinStdDevOfNumericAtts": 19.514093510979706, "PercentageOfMissingValues": 1.3781223083548666, "Quartile3KurtosisOfNumericAtts": 9.790153056728322, "AutoCorrelation": 0.6474137931034483, "RandomTreeDepth2AUC": 0.9476714594732153, "J48.00001.ErrRate": 0.037037037037037035, "MaxStdDevOfNumericAtts": 2411.623526045175, "MinorityClassPercentage": 29.97416020671835, "PercentageOfNumericFeatures": 81.25, "Quartile3MeansOfNumericAtts": 525.418962026773, "CfsSubsetEval_DecisionStumpAUC": 0.9662541884039532, "RandomTreeDepth2ErrRate": 0.046511627906976744, "J48.00001.Kappa": 0.9114091172853636, "MeanAttributeEntropy": 3.341443150929032, "MinorityClassSize": 348, "PercentageOfSymbolicFeatures": 18.75, "Quartile3MutualInformation": 0.47910875218483, "CfsSubsetEval_DecisionStumpErrRate": 0.034453057708871665, "RandomTreeDepth2Kappa": 0.8897470798645184, "J48.0001.AUC": 0.9649994344771033, "MeanKurtosisOfNumericAtts": 7.297836238068724, "NaiveBayesAUC": 0.9864922956455796, "Quartile1AttributeEntropy": 1.434835752759632, "Quartile3SkewnessOfNumericAtts": 2.8091608637459133, "CfsSubsetEval_DecisionStumpKappa": 0.9176578225068619, "RandomTreeDepth3AUC": 0.9476714594732153, "J48.0001.ErrRate": 0.037037037037037035, "MeanMeansOfNumericAtts": 550.7556300141797, "NaiveBayesErrRate": 0.08096468561584841, "Quartile1KurtosisOfNumericAtts": 0.21189934058201376, "Quartile3StdDevOfNumericAtts": 131.64151497610425, "CfsSubsetEval_NaiveBayesAUC": 0.9662541884039532, "RandomTreeDepth3ErrRate": 0.046511627906976744, "J48.0001.Kappa": 0.9114091172853636, "MeanMutualInformation": 0.262944728900815, "NaiveBayesKappa": 0.8173391713028983, "Quartile1MeansOfNumericAtts": 83.74074074074076, "REPTreeDepth1AUC": 0.9609859891702364, "CfsSubsetEval_NaiveBayesErrRate": 0.034453057708871665, "RandomTreeDepth3Kappa": 0.8897470798645184, "J48.001.AUC": 0.9649994344771033, "MeanNoiseToSignalRatio": 11.707777656913796, "NumberOfBinaryFeatures": 1, "Quartile1MutualInformation": 0.0467807056168, "REPTreeDepth1ErrRate": 0.06029285099052541, "CfsSubsetEval_NaiveBayesKappa": 0.9176578225068619, "CfsSubsetEval_kNN1NAUC": 0.9662541884039532, "StdvNominalAttDistinctValues": 28.307831660749525, "J48.001.ErrRate": 0.037037037037037035, "MeanNominalAttDistinctValues": 19.333333333333336, "Quartile1SkewnessOfNumericAtts": 0.4326393685013813, "REPTreeDepth1Kappa": 0.8559011893870082, "CfsSubsetEval_kNN1NErrRate": 0.034453057708871665, "kNN1NAUC": 0.8579371138538971, "J48.001.Kappa": 0.9114091172853636, "MeanSkewnessOfNumericAtts": 1.6363623402677259, "Quartile1StdDevOfNumericAtts": 72.17282678834677, "REPTreeDepth2AUC": 0.9609859891702364, "CfsSubsetEval_kNN1NKappa": 0.9176578225068619, "kNN1NErrRate": 0.11369509043927649, "MajorityClassPercentage": 70.02583979328165, "MeanStdDevOfNumericAtts": 270.60579995448273, "Quartile2AttributeEntropy": 3.341443150929032, "REPTreeDepth2ErrRate": 0.06029285099052541, "ClassEntropy": 0.8809748061658637, "kNN1NKappa": 0.7255555078007478, "MajorityClassSize": 813, "MinAttributeEntropy": 1.434835752759632, "Quartile2KurtosisOfNumericAtts": 0.5367715420788586, "REPTreeDepth2Kappa": 0.8559011893870082, "REPTreeDepth3AUC": 0.9609859891702364, "DecisionStumpAUC": 0.938656671049469, "MaxAttributeEntropy": 5.248050549098432, "MinKurtosisOfNumericAtts": -0.029910078625991154, "Quartile2MeansOfNumericAtts": 420.3703703703703, "REPTreeDepth3ErrRate": 0.06029285099052541, "DecisionStumpErrRate": 0.05598621877691645, "MaxKurtosisOfNumericAtts": 50.90962513662791, "MinMeansOfNumericAtts": 12.735572782084397, "Quartile2MutualInformation": 0.262944728900815 }, "tags": [ { "uploader": "38960", "tag": "Chemistry" }, { "uploader": "38960", "tag": "Life Science" }, { "uploader": "1", "tag": "mythbusting_1" }, { "uploader": "2", "tag": "study_1" }, { "uploader": "5824", "tag": "study_144" }, { "uploader": "939", "tag": "study_15" }, { "uploader": "939", "tag": "study_20" } ], "features": [ { "name": "binaryClass", "index": "16", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "P", "N" ], [ [ "813", "0" ], [ "0", "348" ] ] ] }, { "name": "FICE", "index": "0", "type": "numeric", "distinct": "1160", "missing": "0", "min": "1002", "max": "29269", "mean": "3052", "stdev": "2412" }, { "name": "College_name", "index": "1", "type": "nominal", "distinct": "1140", "missing": "0", "ignore": "1", "distr": [] }, { "name": "State", "index": "2", "type": "nominal", "distinct": "52", "missing": "0", "distr": [ [ "AK", "AL", "AR", "AZ", "CA", "CO", "CT", "DC", "DE", "FL", "GA", "HI", "IA", "ID", "IL", "IN", "KS", "KY", "LA", "MA", "MD", "ME", "MI", "MN", "MO", "MS", "MT", "NC", "ND", "NE", "NH", "NJ", "NM", "NV", "NY", "OH", "OK", "OR", "PA", "RI", "SC", "SD", "TN", "TX", "UT", "VA", "VT", "WA", "WI", "WV", "WW", "WY" ], [ [ "2", "2" ], [ "14", "7" ], [ "12", "4" ], [ "1", "3" ], [ "26", "28" ], [ "9", "6" ], [ "12", "4" ], [ "2", "7" ], [ "3", "1" ], [ "10", "9" ], [ "13", "8" ], [ "2", "1" ], [ "23", "4" ], [ "3", "3" ], [ "34", "16" ], [ "34", "7" ], [ "14", "4" ], [ "15", "7" ], [ "9", "11" ], [ "31", "11" ], [ "18", "5" ], [ "12", "2" ], [ "21", "11" ], [ "18", "7" ], [ "25", "9" ], [ "9", "4" ], [ "6", "2" ], [ "30", "12" ], [ "4", "2" ], [ "13", "4" ], [ "9", "2" ], [ "14", "10" ], [ "4", "2" ], [ "0", "2" ], [ "58", "23" ], [ "40", "13" ], [ "13", "4" ], [ "15", "3" ], [ "64", "21" ], [ "5", "3" ], [ "22", "3" ], [ "7", "2" ], [ "19", "8" ], [ "35", "19" ], [ "2", "4" ], [ "29", "10" ], [ "9", "1" ], [ "11", "5" ], [ "18", "9" ], [ "13", "2" ], [ "1", "0" ], [ "0", "1" ] ] ] }, { "name": "Type", "index": "3", "type": "nominal", "distinct": "4", "missing": "0", "distr": [ [ "I", "IIA", "IIB", "VIIB" ], [ [ "6", "174" ], [ "198", "165" ], [ "608", "9" ], [ "1", "0" ] ] ] }, { "name": "Average_salary-full_professors", "index": "4", "type": "numeric", "distinct": "427", "missing": "68", "min": "270", "max": "1009", "mean": "524", "stdev": "118" }, { "name": "Average_salary-associate_professors", "index": "5", "type": "numeric", "distinct": "303", "missing": "36", "min": "234", "max": "733", "mean": "416", "stdev": "72" }, { "name": "Average_salary-assistant_professors", "index": "6", "type": "numeric", "distinct": "235", "missing": "24", "min": "199", "max": "576", "mean": "352", "stdev": "55" }, { "name": "Average_salary-all_ranks", "index": "7", "type": "numeric", "distinct": "345", "missing": "0", "min": "232", "max": "866", "mean": "420", "stdev": "92" }, { "name": "Average_compensation-full_professors", "index": "8", "type": "numeric", "distinct": "485", "missing": "68", "min": "319", "max": "1236", "mean": "653", "stdev": "152" }, { "name": "Average_compensation-associate_professors", "index": "9", "type": "numeric", "distinct": "373", "missing": "36", "min": "292", "max": "909", "mean": "524", "stdev": "97" }, { "name": "Average_compensation-assistant_professors", "index": "10", "type": "numeric", "distinct": "307", "missing": "24", "min": "246", "max": "717", "mean": "442", "stdev": "75" }, { "name": "Average_compensation-all_ranks", "index": "11", "type": "numeric", "distinct": "431", "missing": "0", "min": "265", "max": "1075", "mean": "527", "stdev": "121" }, { "name": "Number_of_full_professors", "index": "12", "type": "numeric", "distinct": "298", "missing": "0", "min": "0", "max": "997", "mean": "95", "stdev": "143" }, { "name": "Number_of_associate_professors", "index": "13", "type": "numeric", "distinct": "255", "missing": "0", "min": "0", "max": "721", "mean": "72", "stdev": "89" }, { "name": "Number_of_assistant_professors", "index": "14", "type": "numeric", "distinct": "241", "missing": "0", "min": "0", "max": "510", "mean": "69", "stdev": "73" }, { "name": "Number_of_instructors", "index": "15", "type": "numeric", "distinct": "83", "missing": "0", "min": "0", "max": "178", "mean": "13", "stdev": "20" } ], "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 }