{ "data_id": "930", "name": "colleges_usnews", "exact_name": "colleges_usnews", "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 14:37:26", "update_comment": null, "last_update": "2014-10-06 03:36:58", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/53464\/colleges_usnews.arff", "default_target_attribute": "binaryClass", "row_id_attribute": null, "ignore_attribute": "\"College_name\"", "runs": 104, "suggest": { "input": [ "colleges_usnews", "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": 1302, "NumberOfFeatures": 34, "NumberOfClasses": 2, "NumberOfMissingValues": 7830, "NumberOfInstancesWithMissingValues": 1144, "NumberOfNumericFeatures": 32, "NumberOfSymbolicFeatures": 2, "RandomTreeDepth1AUC": 0.702400686694475, "Dimensionality": 0.026113671274961597, "MaxMutualInformation": 0.10942146400494, "MinNominalAttDistinctValues": 2, "PercentageOfBinaryFeatures": 2.941176470588235, "Quartile2StdDevOfNumericAtts": 99.95006637027188, "RandomTreeDepth1ErrRate": 0.3279569892473118, "EquivalentNumberOfAtts": 9.117668014005309, "MaxNominalAttDistinctValues": 51, "MinSkewnessOfNumericAtts": -0.6230301616625689, "PercentageOfInstancesWithMissingValues": 87.86482334869432, "Quartile3AttributeEntropy": 5.250159212499937, "RandomTreeDepth1Kappa": 0.34351287458877594, "J48.00001.AUC": 0.6986673432987144, "MaxSkewnessOfNumericAtts": 6.1364697337087515, "MinStdDevOfNumericAtts": 0.4804701944013999, "PercentageOfMissingValues": 17.68772024939008, "Quartile3KurtosisOfNumericAtts": 16.6010075312928, "AutoCorrelation": 0.5941583397386626, "RandomTreeDepth2AUC": 0.702400686694475, "J48.00001.ErrRate": 0.29877112135176653, "MaxStdDevOfNumericAtts": 5348.162626265424, "MinorityClassPercentage": 47.15821812596006, "PercentageOfNumericFeatures": 94.11764705882352, "Quartile3MeansOfNumericAtts": 2401.257425601352, "CfsSubsetEval_DecisionStumpAUC": 0.729145756003333, "RandomTreeDepth2ErrRate": 0.3279569892473118, "J48.00001.Kappa": 0.4014125622546158, "MeanAttributeEntropy": 5.250159212499937, "MinorityClassSize": 614, "PercentageOfSymbolicFeatures": 5.88235294117647, "Quartile3MutualInformation": 0.10942146400494, "CfsSubsetEval_DecisionStumpErrRate": 0.2887864823348694, "CfsSubsetEval_DecisionStumpKappa": 0.4239859935803909, "RandomTreeDepth2Kappa": 0.34351287458877594, "J48.0001.AUC": 0.6986673432987144, "MeanKurtosisOfNumericAtts": 8.589933861939347, "NaiveBayesAUC": 0.8023312976918031, "Quartile1AttributeEntropy": 5.250159212499937, "Quartile3SkewnessOfNumericAtts": 2.810618423165535, "CfsSubsetEval_NaiveBayesAUC": 0.729145756003333, "RandomTreeDepth3AUC": 0.702400686694475, "J48.0001.ErrRate": 0.29877112135176653, "MeanMeansOfNumericAtts": 1716.3688539909351, "NaiveBayesErrRate": 0.27572964669738864, "Quartile1KurtosisOfNumericAtts": 0.16536863272151126, "Quartile3StdDevOfNumericAtts": 1548.9729655108426, "CfsSubsetEval_NaiveBayesErrRate": 0.2887864823348694, "RandomTreeDepth3ErrRate": 0.3279569892473118, "J48.0001.Kappa": 0.4014125622546158, "MeanMutualInformation": 0.10942146400494, "NaiveBayesKappa": 0.4564186415408553, "Quartile1MeansOfNumericAtts": 70.29203498737186, "REPTreeDepth1AUC": 0.672063841416962, "CfsSubsetEval_NaiveBayesKappa": 0.4239859935803909, "RandomTreeDepth3Kappa": 0.34351287458877594, "J48.001.AUC": 0.6986673432987144, "MeanNoiseToSignalRatio": 46.98107263729272, "NumberOfBinaryFeatures": 1, "Quartile1MutualInformation": 0.10942146400494, "REPTreeDepth1ErrRate": 0.3563748079877112, "REPTreeDepth1Kappa": 0.28481525151648596, "CfsSubsetEval_kNN1NAUC": 0.729145756003333, "StdvNominalAttDistinctValues": 34.64823227814083, "J48.001.ErrRate": 0.29877112135176653, "MeanNominalAttDistinctValues": 26.5, "Quartile1SkewnessOfNumericAtts": 0.3885434178202273, "REPTreeDepth2AUC": 0.672063841416962, "CfsSubsetEval_kNN1NErrRate": 0.2887864823348694, "kNN1NAUC": 0.6104911559730324, "J48.001.Kappa": 0.4014125622546158, "MeanSkewnessOfNumericAtts": 1.4966319491800042, "Quartile1StdDevOfNumericAtts": 18.954792106261337, "REPTreeDepth2ErrRate": 0.3563748079877112, "CfsSubsetEval_kNN1NKappa": 0.4239859935803909, "kNN1NErrRate": 0.3824884792626728, "MajorityClassPercentage": 52.84178187403994, "MeanStdDevOfNumericAtts": 1117.107958645161, "Quartile2AttributeEntropy": 5.250159212499937, "REPTreeDepth2Kappa": 0.28481525151648596, "ClassEntropy": 0.9976685824034748, "kNN1NKappa": 0.2235671108471361, "MajorityClassSize": 688, "MinAttributeEntropy": 5.250159212499937, "Quartile2KurtosisOfNumericAtts": 0.7367557965357074, "REPTreeDepth3AUC": 0.672063841416962, "DecisionStumpAUC": 0.7039061908188774, "MaxAttributeEntropy": 5.250159212499937, "MinKurtosisOfNumericAtts": -1.666672182032963, "Quartile2MeansOfNumericAtts": 540.2124796506102, "REPTreeDepth3ErrRate": 0.3563748079877112, "DecisionStumpErrRate": 0.33563748079877115, "MaxKurtosisOfNumericAtts": 50.07915787245156, "MinMeansOfNumericAtts": 1.6390168970814132, "Quartile2MutualInformation": 0.10942146400494, "REPTreeDepth3Kappa": 0.28481525151648596, "DecisionStumpKappa": 0.32884222943084646, "MaxMeansOfNumericAtts": 9276.905616224645, "MinMutualInformation": 0.10942146400494, "Quartile2SkewnessOfNumericAtts": 0.6316364403193302 }, "tags": [ { "uploader": "2", "tag": "binarized_regression_problem" }, { "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": "34", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "P", "N" ], [ [ "614", "0" ], [ "0", "688" ] ] ] }, { "name": "FICE", "index": "0", "type": "numeric", "distinct": "1302", "missing": "0", "min": "1002", "max": "30431", "mean": "3126", "stdev": "2970" }, { "name": "College_name", "index": "1", "type": "nominal", "distinct": "1274", "missing": "0", "ignore": "1", "distr": [] }, { "name": "State", "index": "2", "type": "nominal", "distinct": "51", "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", "WY" ], [ [ "2", "2" ], [ "18", "7" ], [ "7", "10" ], [ "3", "2" ], [ "34", "36" ], [ "10", "6" ], [ "4", "15" ], [ "1", "8" ], [ "3", "2" ], [ "16", "14" ], [ "25", "11" ], [ "2", "3" ], [ "8", "21" ], [ "6", "0" ], [ "22", "27" ], [ "15", "27" ], [ "18", "2" ], [ "13", "11" ], [ "16", "4" ], [ "15", "41" ], [ "9", "14" ], [ "5", "9" ], [ "21", "15" ], [ "10", "15" ], [ "21", "14" ], [ "11", "4" ], [ "5", "4" ], [ "26", "20" ], [ "7", "1" ], [ "11", "5" ], [ "4", "9" ], [ "15", "12" ], [ "7", "2" ], [ "3", "0" ], [ "32", "69" ], [ "15", "37" ], [ "16", "4" ], [ "9", "9" ], [ "15", "68" ], [ "1", "7" ], [ "13", "13" ], [ "6", "5" ], [ "21", "13" ], [ "39", "21" ], [ "5", "1" ], [ "15", "25" ], [ "4", "10" ], [ "4", "12" ], [ "14", "15" ], [ "11", "6" ], [ "1", "0" ] ] ] }, { "name": "Public\/private_indicator", "index": "3", "type": "numeric", "distinct": "2", "missing": "0", "min": "1", "max": "2", "mean": "2", "stdev": "0" }, { "name": "Average_Math_SAT_score", "index": "4", "type": "numeric", "distinct": "248", "missing": "525", "min": "320", "max": "750", "mean": "507", "stdev": "68" }, { "name": "Average_Verbal_SAT_score", "index": "5", "type": "numeric", "distinct": "222", "missing": "525", "min": "280", "max": "665", "mean": "461", "stdev": "58" }, { "name": "Average_Combined_SAT_score", "index": "6", "type": "numeric", "distinct": "339", "missing": "523", "min": "600", "max": "1410", "mean": "968", "stdev": "124" }, { "name": "Average_ACT_score", "index": "7", "type": "numeric", "distinct": "17", "missing": "588", "min": "11", "max": "31", "mean": "22", "stdev": "3" }, { "name": "First_quartile-Math_SAT", "index": "8", "type": "numeric", "distinct": "85", "missing": "530", "min": "220", "max": "740", "mean": "462", "stdev": "76" }, { "name": "Third_quartile-Math_SAT", "index": "9", "type": "numeric", "distinct": "85", "missing": "530", "min": "330", "max": "785", "mean": "583", "stdev": "71" }, { "name": "First_quartile-Verbal_SAT", "index": "10", "type": "numeric", "distinct": "66", "missing": "530", "min": "200", "max": "630", "mean": "418", "stdev": "64" }, { "name": "Third_quartile-Verbal_SAT", "index": "11", "type": "numeric", "distinct": "85", "missing": "530", "min": "330", "max": "720", "mean": "530", "stdev": "65" }, { "name": "First_quartile-ACT", "index": "12", "type": "numeric", "distinct": "20", "missing": "639", "min": "10", "max": "29", "mean": "20", "stdev": "3" }, { "name": "Third_quartile-ACT", "index": "13", "type": "numeric", "distinct": "19", "missing": "639", "min": "15", "max": "35", "mean": "25", "stdev": "3" }, { "name": "Number_of_applications_received", "index": "14", "type": "numeric", "distinct": "1127", "missing": "10", "min": "35", "max": "48094", "mean": "2752", "stdev": "3542" }, { "name": "Number_of_applicants_accepted", "index": "15", "type": "numeric", "distinct": "1065", "missing": "11", "min": "35", "max": "26330", "mean": "1871", "stdev": "2251" }, { "name": "Number_of_new_students_enrolled", "index": "16", "type": "numeric", "distinct": "870", "missing": "5", "min": "18", "max": "7425", "mean": "779", "stdev": "885" }, { "name": "Pct._new_students_from_top_10Perc_of_H.S._class", "index": "17", "type": "numeric", "distinct": "90", "missing": "235", "min": "1", "max": "98", "mean": "26", "stdev": "18" }, { "name": "Pct._new_students_from_top_25Perc_of_H.S._class", "index": "18", "type": "numeric", "distinct": "93", "missing": "202", "min": "6", "max": "100", "mean": "52", "stdev": "21" }, { "name": "Number_of_fulltime_undergraduates", "index": "19", "type": "numeric", "distinct": "1151", "missing": "3", "min": "59", "max": "31643", "mean": "3693", "stdev": "4545" }, { "name": "Number_of_parttime_undergraduates", "index": "20", "type": "numeric", "distinct": "883", "missing": "32", "min": "1", "max": "21836", "mean": "1082", "stdev": "1672" }, { "name": "In-state_tuition", "index": "21", "type": "numeric", "distinct": "948", "missing": "30", "min": "480", "max": "25750", "mean": "7897", "stdev": "5348" }, { "name": "Out-of-state_tuition", "index": "22", "type": "numeric", "distinct": "963", "missing": "20", "min": "1044", "max": "25750", "mean": "9277", "stdev": "4171" }, { "name": "Room_and_board_costs", "index": "23", "type": "numeric", "distinct": "798", "missing": "76", "min": "1260", "max": "8700", "mean": "4162", "stdev": "1179" }, { "name": "Room_costs", "index": "24", "type": "numeric", "distinct": "598", "missing": "321", "min": "500", "max": "7400", "mean": "2515", "stdev": "1151" }, { "name": "Board_costs", "index": "25", "type": "numeric", "distinct": "465", "missing": "498", "min": "531", "max": "6250", "mean": "2061", "stdev": "662" }, { "name": "Additional_fees", "index": "26", "type": "numeric", "distinct": "433", "missing": "274", "min": "9", "max": "4374", "mean": "392", "stdev": "469" }, { "name": "Estimated_book_costs", "index": "27", "type": "numeric", "distinct": "164", "missing": "48", "min": "90", "max": "2340", "mean": "550", "stdev": "167" }, { "name": "Estimated_personal_spending", "index": "28", "type": "numeric", "distinct": "406", "missing": "181", "min": "75", "max": "6900", "mean": "1389", "stdev": "714" }, { "name": "Pct._of_faculty_with_Ph.D.s", "index": "29", "type": "numeric", "distinct": "90", "missing": "32", "min": "8", "max": "105", "mean": "69", "stdev": "18" }, { "name": "Pct._of_faculty_with_terminal_degree", "index": "30", "type": "numeric", "distinct": "77", "missing": "30", "min": "20", "max": "100", "mean": "75", "stdev": "17" }, { "name": "Student\/faculty_ratio", "index": "31", "type": "numeric", "distinct": "208", "missing": "2", "min": "23", "max": "918", "mean": "149", "stdev": "52" }, { "name": "Pct.alumni_who_donate", "index": "32", "type": "numeric", "distinct": "62", "missing": "222", "min": "0", "max": "81", "mean": "21", "stdev": "13" }, { "name": "Instructional_expenditure_per_student", "index": "33", "type": "numeric", "distinct": "1181", "missing": "39", "min": "1834", "max": "62469", "mean": "8988", "stdev": "5347" } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 7, "total_downloads": 7, "reach": 7, "reuse": 15, "impact_of_reuse": 0, "reach_of_reuse": 1, "impact": 15 }