{ "data_id": "40515", "name": "BNG(spambase)", "exact_name": "BNG(spambase)", "version": 2, "version_label": null, "description": "Automated file upload of BNG(spambase)", "format": "arff", "uploader": "Jan van Rijn", "uploader_id": 1, "visibility": "public", "creator": null, "contributor": null, "date": "2016-10-06 16:01:59", "update_comment": null, "last_update": "2016-10-06 16:01:59", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/4600909\/BNG(spambase).arff", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 98, "suggest": { "input": [ "BNG(spambase)", "Automated file upload of BNG(spambase) " ], "weight": 5 }, "qualities": { "NumberOfInstances": 1000000, "NumberOfFeatures": 58, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 0, "NumberOfSymbolicFeatures": 58, "ClassEntropy": 0.9673647239950673, "MeanNoiseToSignalRatio": 21.66550526806209, "Quartile2AttributeEntropy": 0.04364737232156031, "Dimensionality": 5.8e-5, "MeanNominalAttDistinctValues": 2.9827586206896552, "Quartile2KurtosisOfNumericAtts": null, "EquivalentNumberOfAtts": 351.8756388763232, "MeanSkewnessOfNumericAtts": null, "Quartile2MeansOfNumericAtts": null, "MajorityClassPercentage": 60.594800000000006, "MeanStdDevOfNumericAtts": null, "Quartile2MutualInformation": 0.00103290030496, "MajorityClassSize": 605948, "MinAttributeEntropy": 0.008134184617827288, "Quartile2SkewnessOfNumericAtts": null, "MaxAttributeEntropy": 0.22287607583565397, "MinKurtosisOfNumericAtts": null, "PercentageOfBinaryFeatures": 1.7241379310344827, "Quartile2StdDevOfNumericAtts": null, "MaxKurtosisOfNumericAtts": null, "MinMeansOfNumericAtts": null, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": 0.08843238721630471, "MaxMeansOfNumericAtts": null, "MinMutualInformation": 4.764291935e-5, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": null, "MaxMutualInformation": 0.01648641350849, "MinNominalAttDistinctValues": 2, "PercentageOfNumericFeatures": 0, "Quartile3MeansOfNumericAtts": null, "MaxNominalAttDistinctValues": 3, "MinSkewnessOfNumericAtts": null, "PercentageOfSymbolicFeatures": 100, "Quartile3MutualInformation": 0.00338655300608, "MaxSkewnessOfNumericAtts": null, "MinStdDevOfNumericAtts": null, "Quartile1AttributeEntropy": 0.02345710300627235, "Quartile3SkewnessOfNumericAtts": null, "MaxStdDevOfNumericAtts": null, "MinorityClassPercentage": 39.4052, "Quartile1KurtosisOfNumericAtts": null, "Quartile3StdDevOfNumericAtts": null, "MeanAttributeEntropy": 0.06231124813830629, "MinorityClassSize": 394052, "Quartile1MeansOfNumericAtts": null, "StdvNominalAttDistinctValues": 0.13130643285972254, "MeanKurtosisOfNumericAtts": null, "NumberOfBinaryFeatures": 1, "Quartile1MutualInformation": 0.00034701762969, "MeanMeansOfNumericAtts": null, "Quartile1SkewnessOfNumericAtts": null, "AutoCorrelation": 0.5215605215605216, "MeanMutualInformation": 0.0027491665154321054, "Quartile1StdDevOfNumericAtts": null }, "tags": [ { "uploader": "2", "tag": "artificial" }, { "uploader": "38960", "tag": "Computer Systems" }, { "uploader": "38960", "tag": "Machine Learning" }, { "uploader": "1", "tag": "study_16" } ], "features": [ { "name": "class", "index": "57", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "0", "1" ], [ [ "605948", "0" ], [ "0", "394052" ] ] ] }, { "name": "word_freq_make", "index": "0", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "600245", "391418" ], [ "4523", "2326" ], [ "1180", "308" ] ] ] }, { "name": "word_freq_address", "index": "1", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "597246", "393852" ], [ "970", "90" ], [ "7732", "110" ] ] ] }, { "name": "word_freq_all", "index": "2", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "590784", "387102" ], [ "12282", "6159" ], [ "2882", "791" ] ] ] }, { "name": "word_freq_3d", "index": "3", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "605746", "392334" ], [ "100", "544" ], [ "102", "1174" ] ] ] }, { "name": "word_freq_our", "index": "4", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "601241", "391048" ], [ "3757", "2684" ], [ "950", "320" ] ] ] }, { "name": "word_freq_over", "index": "5", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "604426", "392745" ], [ "1211", "1205" ], [ "311", "102" ] ] ] }, { "name": "word_freq_remove", "index": "6", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "605489", "390423" ], [ "343", "2905" ], [ "116", "724" ] ] ] }, { "name": "word_freq_internet", "index": "7", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "604832", "392934" ], [ "1001", "777" ], [ "115", "341" ] ] ] }, { "name": "word_freq_order", "index": "8", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "604816", "392162" ], [ "802", "1804" ], [ "330", "86" ] ] ] }, { "name": "word_freq_mail", "index": "9", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "605268", "393655" ], [ "342", "296" ], [ "338", "101" ] ] ] }, { "name": "word_freq_receive", "index": "10", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "601531", "383577" ], [ "1697", "9573" ], [ "2720", "902" ] ] ] }, { "name": "word_freq_will", "index": "11", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "586342", "392952" ], [ "18609", "992" ], [ "997", "108" ] ] ] }, { "name": "word_freq_people", "index": "12", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "603356", "392481" ], [ "2276", "1011" ], [ "316", "560" ] ] ] }, { "name": "word_freq_report", "index": "13", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "604445", "393653" ], [ "1179", "301" ], [ "324", "98" ] ] ] }, { "name": "word_freq_addresses", "index": "14", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "605108", "382166" ], [ "757", "11561" ], [ "83", "325" ] ] ] }, { "name": "word_freq_free", "index": "15", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "605086", "392506" ], [ "308", "1208" ], [ "554", "338" ] ] ] }, { "name": "word_freq_business", "index": "16", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "604273", "384098" ], [ "1193", "8352" ], [ "482", "1602" ] ] ] }, { "name": "word_freq_email", "index": "17", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "603527", "390642" ], [ "2077", "2838" ], [ "344", "572" ] ] ] }, { "name": "word_freq_you", "index": "18", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "591932", "388093" ], [ "13023", "5847" ], [ "993", "112" ] ] ] }, { "name": "word_freq_credit", "index": "19", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "605730", "393183" ], [ "97", "532" ], [ "121", "337" ] ] ] }, { "name": "word_freq_your", "index": "20", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "594738", "373370" ], [ "7458", "19795" ], [ "3752", "887" ] ] ] }, { "name": "word_freq_font", "index": "21", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "602634", "386078" ], [ "2937", "6537" ], [ "377", "1437" ] ] ] }, { "name": "word_freq_000", "index": "22", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "605307", "384814" ], [ "407", "8205" ], [ "234", "1033" ] ] ] }, { "name": "word_freq_money", "index": "23", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "604563", "391534" ], [ "496", "1648" ], [ "889", "870" ] ] ] }, { "name": "word_freq_hp", "index": "24", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "590830", "393825" ], [ "11378", "91" ], [ "3740", "136" ] ] ] }, { "name": "word_freq_hpl", "index": "25", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "600596", "393646" ], [ "4570", "199" ], [ "782", "207" ] ] ] }, { "name": "word_freq_george", "index": "26", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "579793", "393549" ], [ "21583", "250" ], [ "4572", "253" ] ] ] }, { "name": "word_freq_650", "index": "27", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "596777", "393328" ], [ "8846", "176" ], [ "325", "548" ] ] ] }, { "name": "word_freq_lab", "index": "28", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "602791", "393570" ], [ "2002", "226" ], [ "1155", "256" ] ] ] }, { "name": "word_freq_labs", "index": "29", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "591324", "393023" ], [ "9753", "741" ], [ "4871", "288" ] ] ] }, { "name": "word_freq_telnet", "index": "30", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "602570", "393443" ], [ "2819", "297" ], [ "559", "312" ] ] ] }, { "name": "word_freq_857", "index": "31", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "597084", "393206" ], [ "4613", "431" ], [ "4251", "415" ] ] ] }, { "name": "word_freq_data", "index": "32", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "604162", "393848" ], [ "1444", "111" ], [ "342", "93" ] ] ] }, { "name": "word_freq_415", "index": "33", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "597041", "393283" ], [ "4650", "393" ], [ "4257", "376" ] ] ] }, { "name": "word_freq_85", "index": "34", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "605516", "393859" ], [ "108", "107" ], [ "324", "86" ] ] ] }, { "name": "word_freq_technology", "index": "35", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "598606", "393113" ], [ "5740", "488" ], [ "1602", "451" ] ] ] }, { "name": "word_freq_1999", "index": "36", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "600851", "392728" ], [ "4792", "976" ], [ "305", "348" ] ] ] }, { "name": "word_freq_parts", "index": "37", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "604407", "393814" ], [ "779", "113" ], [ "762", "125" ] ] ] }, { "name": "word_freq_pm", "index": "38", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "602327", "393405" ], [ "2546", "314" ], [ "1075", "333" ] ] ] }, { "name": "word_freq_direct", "index": "39", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "595595", "392288" ], [ "5865", "1297" ], [ "4488", "467" ] ] ] }, { "name": "word_freq_cs", "index": "40", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "600876", "393848" ], [ "3692", "102" ], [ "1380", "102" ] ] ] }, { "name": "word_freq_meeting", "index": "41", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "598648", "393349" ], [ "5501", "362" ], [ "1799", "341" ] ] ] }, { "name": "word_freq_original", "index": "42", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "595948", "393707" ], [ "8422", "174" ], [ "1578", "171" ] ] ] }, { "name": "word_freq_project", "index": "43", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "604563", "393831" ], [ "590", "108" ], [ "795", "113" ] ] ] }, { "name": "word_freq_re", "index": "44", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "601231", "393629" ], [ "3465", "205" ], [ "1252", "218" ] ] ] }, { "name": "word_freq_edu", "index": "45", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "602341", "393852" ], [ "2855", "98" ], [ "752", "102" ] ] ] }, { "name": "word_freq_table", "index": "46", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "602850", "393842" ], [ "1897", "99" ], [ "1201", "111" ] ] ] }, { "name": "word_freq_conference", "index": "47", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "604623", "393828" ], [ "755", "105" ], [ "570", "119" ] ] ] }, { "name": "char_freq_semicolon", "index": "48", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "602148", "393408" ], [ "512", "315" ], [ "3288", "329" ] ] ] }, { "name": "char_freq_leftroundbracket", "index": "49", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "605514", "393407" ], [ "319", "326" ], [ "115", "319" ] ] ] }, { "name": "char_freq_leftbracket", "index": "50", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "604439", "393726" ], [ "616", "155" ], [ "893", "171" ] ] ] }, { "name": "char_freq_exclamation", "index": "51", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "605309", "393832" ], [ "315", "118" ], [ "324", "102" ] ] ] }, { "name": "char_freq_dolarsign", "index": "52", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "605175", "391866" ], [ "497", "1025" ], [ "276", "1161" ] ] ] }, { "name": "char_freq_doublequotes", "index": "53", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "604584", "393066" ], [ "1017", "508" ], [ "347", "478" ] ] ] }, { "name": "capital_run_length_average", "index": "54", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "605726", "392302" ], [ "106", "1191" ], [ "116", "559" ] ] ] }, { "name": "capital_run_length_longest", "index": "55", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "605530", "393459" ], [ "221", "248" ], [ "197", "345" ] ] ] }, { "name": "capital_run_length_total", "index": "56", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "B1of3", "B2of3", "B3of3" ], [ [ "604989", "392534" ], [ "710", "1053" ], [ "249", "465" ] ] ] } ], "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 }