{ "data_id": "44124", "name": "kdd_ipums_la_97-small", "exact_name": "kdd_ipums_la_97-small", "version": 6, "version_label": null, "description": "Dataset used in the tabular data benchmark https:\/\/github.com\/LeoGrin\/tabular-benchmark, transformed in the same way. This dataset belongs to the \"classification on numerical features\" benchmark. Original description: \n \n**Author**: \n**Source**: Unknown - Date unknown \n**Please cite**: \n\nBinarized version of the original data set (see version 1). The multi-class target feature is converted to a two-class nominal target feature by re-labeling the majority class as positive ('P') and all others as negative ('N'). Originally converted by Quan Sun.", "format": "arff", "uploader": "Leo Grin", "uploader_id": 26324, "visibility": "public", "creator": null, "contributor": "\"Leo Grin\"", "date": "2022-07-05 20:24:41", "update_comment": null, "last_update": "2022-07-05 20:24:41", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/api.openml.org\/data\/download\/22103249\/dataset", "default_target_attribute": "binaryClass", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "kdd_ipums_la_97-small", "Dataset used in the tabular data benchmark https:\/\/github.com\/LeoGrin\/tabular-benchmark, transformed in the same way. This dataset belongs to the \"classification on numerical features\" benchmark. Original description: Binarized version of the original data set (see version 1). The multi-class target feature is converted to a two-class nominal target feature by re-labeling the majority class as positive ('P') and all others as negative ('N'). Originally converted by Quan Sun. " ], "weight": 5 }, "qualities": { "NumberOfInstances": 5188, "NumberOfFeatures": 21, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 20, "NumberOfSymbolicFeatures": 1, "PercentageOfBinaryFeatures": 4.761904761904762, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": 0.9998072103335262, "PercentageOfMissingValues": 0, "Dimensionality": 0.004047802621434078, "PercentageOfNumericFeatures": 95.23809523809523, "MajorityClassPercentage": 50, "PercentageOfSymbolicFeatures": 4.761904761904762, "MajorityClassSize": 2594, "MinorityClassPercentage": 50, "MinorityClassSize": 2594, "NumberOfBinaryFeatures": 1 }, "tags": [ { "uploader": "38960", "tag": "Computer Systems" }, { "uploader": "38960", "tag": "Machine Learning" } ], "features": [ { "name": "binaryClass", "index": "20", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "N", "P" ], [ [ "2594", "0" ], [ "0", "2594" ] ] ] }, { "name": "value", "index": "0", "type": "numeric", "distinct": "11", "missing": "0", "min": "6250", "max": "999999", "mean": "483144", "stdev": "485073" }, { "name": "rent", "index": "1", "type": "numeric", "distinct": "134", "missing": "0", "min": "0", "max": "470", "mean": "50", "stdev": "70" }, { "name": "ftotinc", "index": "2", "type": "numeric", "distinct": "395", "missing": "0", "min": "-9900", "max": "999999", "mean": "30142", "stdev": "131340" }, { "name": "momloc", "index": "3", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "12", "mean": "1", "stdev": "1" }, { "name": "famsize", "index": "4", "type": "numeric", "distinct": "15", "missing": "0", "min": "1", "max": "15", "mean": "4", "stdev": "2" }, { "name": "nchild", "index": "5", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "eldch", "index": "6", "type": "numeric", "distinct": "62", "missing": "0", "min": "0", "max": "99", "mean": "70", "stdev": "41" }, { "name": "yngch", "index": "7", "type": "numeric", "distinct": "60", "missing": "0", "min": "0", "max": "99", "mean": "68", "stdev": "43" }, { "name": "nsibs", "index": "8", "type": "numeric", "distinct": "10", "missing": "0", "min": "0", "max": "9", "mean": "1", "stdev": "1" }, { "name": "age", "index": "9", "type": "numeric", "distinct": "97", "missing": "0", "min": "0", "max": "99", "mean": "34", "stdev": "21" }, { "name": "occscore", "index": "10", "type": "numeric", "distinct": "45", "missing": "0", "min": "0", "max": "79", "mean": "17", "stdev": "15" }, { "name": "sei", "index": "11", "type": "numeric", "distinct": "80", "missing": "0", "min": "0", "max": "96", "mean": "27", "stdev": "27" }, { "name": "inctot", "index": "12", "type": "numeric", "distinct": "284", "missing": "0", "min": "-41", "max": "999999", "mean": "203219", "stdev": "396651" }, { "name": "incwage", "index": "13", "type": "numeric", "distinct": "216", "missing": "0", "min": "0", "max": "999999", "mean": "202365", "stdev": "397065" }, { "name": "incbus", "index": "14", "type": "numeric", "distinct": "105", "missing": "0", "min": "-9900", "max": "999999", "mean": "198955", "stdev": "398738" }, { "name": "incfarm", "index": "15", "type": "numeric", "distinct": "18", "missing": "0", "min": "-9900", "max": "999999", "mean": "198538", "stdev": "398934" }, { "name": "incss", "index": "16", "type": "numeric", "distinct": "38", "missing": "0", "min": "0", "max": "99999", "mean": "19947", "stdev": "39848" }, { "name": "incwelfr", "index": "17", "type": "numeric", "distinct": "37", "missing": "0", "min": "0", "max": "99999", "mean": "19894", "stdev": "39874" }, { "name": "incother", "index": "18", "type": "numeric", "distinct": "93", "missing": "0", "min": "-3", "max": "99999", "mean": "20184", "stdev": "39766" }, { "name": "poverty", "index": "19", "type": "numeric", "distinct": "479", "missing": "0", "min": "0", "max": "501", "mean": "306", "stdev": "155" } ], "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 }