{ "data_id": "42727", "name": "colleges", "exact_name": "colleges", "version": 14, "version_label": null, "description": "Modified version for the automl benchmark.\nRegroups information for about 7800 different US colleges. Including geographical information, stats about the population attending and post graduation career earnings.", "format": "arff", "uploader": "Pieter Gijsbers", "uploader_id": 869, "visibility": "public", "creator": "\"NA\"", "contributor": null, "date": "2020-11-17 21:20:06", "update_comment": null, "last_update": "2020-11-17 21:20:06", "licence": "NA", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/22044759\/dataset", "default_target_attribute": "percent_pell_grant", "row_id_attribute": "UNITID", "ignore_attribute": "\"school_name\",\"school_webpage\"", "runs": 0, "suggest": { "input": [ "colleges", "Modified version for the automl benchmark. Regroups information for about 7800 different US colleges. Including geographical information, stats about the population attending and post graduation career earnings. " ], "weight": 5 }, "qualities": { "NumberOfInstances": 7063, "NumberOfFeatures": 45, "NumberOfClasses": 0, "NumberOfMissingValues": 104249, "NumberOfInstancesWithMissingValues": 7063, "NumberOfNumericFeatures": 33, "NumberOfSymbolicFeatures": 12, "Dimensionality": 0.006371230355373071, "PercentageOfNumericFeatures": 73.33333333333333, "MajorityClassPercentage": null, "PercentageOfSymbolicFeatures": 26.666666666666668, "MajorityClassSize": null, "MinorityClassPercentage": null, "MinorityClassSize": null, "NumberOfBinaryFeatures": 0, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 100, "AutoCorrelation": 0.7872184225431891, "PercentageOfMissingValues": 32.79972312677962 }, "tags": [ { "uploader": "38960", "tag": "Astronomy" }, { "uploader": "38960", "tag": "Machine Learning" } ], "features": [ { "name": "percent_pell_grant", "index": "30", "type": "numeric", "distinct": "4502", "missing": "0", "target": "1", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "UNITID", "index": "0", "type": "numeric", "distinct": "7063", "missing": "0", "identifier": "1", "min": "100654", "max": "483212", "mean": "283687", "stdev": "132384" }, { "name": "school_name", "index": "1", "type": "string", "distinct": "6961", "missing": "0", "ignore": "1" }, { "name": "city", "index": "2", "type": "nominal", "distinct": "2460", "missing": "0", "distr": [] }, { "name": "state", "index": "3", "type": "nominal", "distinct": "59", "missing": "0", "distr": [] }, { "name": "zip", "index": "4", "type": "nominal", "distinct": "6039", "missing": "0", "distr": [] }, { "name": "school_webpage", "index": "5", "type": "string", "distinct": "5710", "missing": "56", "ignore": "1" }, { "name": "latitude", "index": "6", "type": "numeric", "distinct": "6508", "missing": "342", "min": "-14", "max": "71", "mean": "37", "stdev": "6" }, { "name": "longitude", "index": "7", "type": "numeric", "distinct": "6598", "missing": "342", "min": "-171", "max": "171", "mean": "-90", "stdev": "18" }, { "name": "admission_rate", "index": "8", "type": "numeric", "distinct": "1739", "missing": "4847", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "sat_verbal_midrange", "index": "9", "type": "numeric", "distinct": "164", "missing": "5763", "min": "290", "max": "760", "mean": "522", "stdev": "68" }, { "name": "sat_math_midrange", "index": "10", "type": "numeric", "distinct": "163", "missing": "5749", "min": "310", "max": "785", "mean": "531", "stdev": "72" }, { "name": "sat_writing_midrange", "index": "11", "type": "numeric", "distinct": "131", "missing": "6270", "min": "350", "max": "755", "mean": "521", "stdev": "78" }, { "name": "act_combined_midrange", "index": "12", "type": "numeric", "distinct": "22", "missing": "5722", "min": "2", "max": "34", "mean": "23", "stdev": "3" }, { "name": "act_english_midrange", "index": "13", "type": "numeric", "distinct": "24", "missing": "5899", "min": "2", "max": "34", "mean": "23", "stdev": "4" }, { "name": "act_math_midrange", "index": "14", "type": "numeric", "distinct": "24", "missing": "5898", "min": "2", "max": "35", "mean": "23", "stdev": "3" }, { "name": "act_writing_midrange", "index": "15", "type": "numeric", "distinct": "8", "missing": "6763", "min": "5", "max": "12", "mean": "8", "stdev": "1" }, { "name": "sat_total_average", "index": "16", "type": "numeric", "distinct": "477", "missing": "5644", "min": "666", "max": "1534", "mean": "1057", "stdev": "132" }, { "name": "undergrad_size", "index": "17", "type": "numeric", "distinct": "3020", "missing": "1", "min": "0", "max": "166816", "mean": "2341", "stdev": "5452" }, { "name": "percent_white", "index": "18", "type": "numeric", "distinct": "4453", "missing": "1", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "percent_black", "index": "19", "type": "numeric", "distinct": "3277", "missing": "1", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "percent_hispanic", "index": "20", "type": "numeric", "distinct": "2802", "missing": "1", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "percent_asian", "index": "21", "type": "numeric", "distinct": "1239", "missing": "1", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "percent_part_time", "index": "22", "type": "numeric", "distinct": "3466", "missing": "6", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "average_cost_academic_year", "index": "23", "type": "numeric", "distinct": "3802", "missing": "2928", "min": "4157", "max": "74473", "mean": "24353", "stdev": "12174" }, { "name": "average_cost_program_year", "index": "24", "type": "numeric", "distinct": "2349", "missing": "4522", "min": "3057", "max": "89422", "mean": "18495", "stdev": "6355" }, { "name": "tuition_(instate)", "index": "25", "type": "numeric", "distinct": "2981", "missing": "2926", "min": "80", "max": "64900", "mean": "13948", "stdev": "10859" }, { "name": "tuition_(out_of_state)", "index": "26", "type": "numeric", "distinct": "3039", "missing": "2926", "min": "80", "max": "64900", "mean": "16442", "stdev": "9893" }, { "name": "spend_per_student", "index": "27", "type": "numeric", "distinct": "5294", "missing": "11", "min": "0", "max": "307089", "mean": "6522", "stdev": "7825" }, { "name": "faculty_salary", "index": "28", "type": "numeric", "distinct": "3297", "missing": "2672", "min": "269", "max": "23611", "mean": "5928", "stdev": "2194" }, { "name": "percent_part_time_faculty", "index": "29", "type": "numeric", "distinct": "2332", "missing": "3161", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "completion_rate", "index": "31", "type": "numeric", "distinct": "1912", "missing": "4617", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "predominant_degree", "index": "32", "type": "nominal", "distinct": "3", "missing": "75", "distr": [] }, { "name": "highest_degree", "index": "33", "type": "nominal", "distinct": "5", "missing": "0", "distr": [] }, { "name": "ownership", "index": "34", "type": "nominal", "distinct": "3", "missing": "0", "distr": [] }, { "name": "region", "index": "35", "type": "nominal", "distinct": "10", "missing": "0", "distr": [] }, { "name": "gender", "index": "36", "type": "nominal", "distinct": "3", "missing": "0", "distr": [] }, { "name": "carnegie_basic_classification", "index": "37", "type": "nominal", "distinct": "33", "missing": "2986", "distr": [] }, { "name": "carnegie_undergraduate", "index": "38", "type": "nominal", "distinct": "13", "missing": "3506", "distr": [] }, { "name": "carnegie_size", "index": "39", "type": "nominal", "distinct": "17", "missing": "3505", "distr": [] }, { "name": "religious_affiliation", "index": "40", "type": "nominal", "distinct": "55", "missing": "6260", "distr": [] }, { "name": "percent_female", "index": "41", "type": "numeric", "distinct": "101", "missing": "1510", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "agege24", "index": "42", "type": "numeric", "distinct": "99", "missing": "1510", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "faminc", "index": "43", "type": "numeric", "distinct": "4777", "missing": "1510", "min": "640", "max": "134102", "mean": "41946", "stdev": "23651" }, { "name": "mean_earnings_6_years", "index": "44", "type": "numeric", "distinct": "494", "missing": "1451", "min": "9300", "max": "106900", "mean": "29280", "stdev": "10138" }, { "name": "median_earnings_6_years", "index": "45", "type": "numeric", "distinct": "489", "missing": "1451", "min": "7000", "max": "117400", "mean": "26519", "stdev": "9705" }, { "name": "mean_earnings_10_years", "index": "46", "type": "numeric", "distinct": "607", "missing": "1736", "min": "12300", "max": "162000", "mean": "36445", "stdev": "13426" }, { "name": "median_earnings_10_years", "index": "47", "type": "numeric", "distinct": "568", "missing": "1736", "min": "8400", "max": "121500", "mean": "32555", "stdev": "11947" } ], "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 }