{ "data_id": "43141", "name": "ACSIncome", "exact_name": "ACSIncome", "version": 3, "version_label": "v1.0.0", "description": "The ACSIncome dataset is one of five datasets created by Ding et al. as an improved alternative to the popular UCI Adult dataset. The authors compiled data from the American Community Survey (ACS) Public Use Microdata Sample (PUMS). Data is provided for all 50 states and Puerto Rico. This upload represents the raw data from only 2018. The data contains 1,664,500 rows, 10 features, and 1 target variable. An additional column for the state code is provided for convenience. All columns are described in the original publication (https:\/\/arxiv.org\/pdf\/2108.04884.pdf) as well as in the PUMS Data Dictionary (\r\nhttps:\/\/www2.census.gov\/programs-surveys\/acs\/tech_docs\/pums\/data_dict\/PUMS_Data_Dictionary_2018.pdf). Additional detail can also be found on the author's GitHub: https:\/\/github.com\/zykls\/folktables\/", "format": "ARFF", "uploader": "Kevin Spiekermann", "uploader_id": 29520, "visibility": "public", "creator": "\"Frances Ding\",\"Moritz Hardt\",\"John Miller\",\"Ludwig Schmidt (authors are ordered alphabetically)\"", "contributor": "\"All credit goes to Frances Ding\",\"Moritz Hardt\",\"John Miller\",\"Ludwig Schmidt\"", "date": "2022-01-12 15:27:53", "update_comment": null, "last_update": "2022-01-12 15:27:53", "licence": "CC0", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/22101666\/ACSIncome_state_number.arff", "default_target_attribute": "PINCP", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "ACSIncome", "The ACSIncome dataset is one of five datasets created by Ding et al. as an improved alternative to the popular UCI Adult dataset. The authors compiled data from the American Community Survey (ACS) Public Use Microdata Sample (PUMS). Data is provided for all 50 states and Puerto Rico. This upload represents the raw data from only 2018. The data contains 1,664,500 rows, 10 features, and 1 target variable. An additional column for the state code is provided for convenience. All columns are describe " ], "weight": 5 }, "qualities": { "NumberOfInstances": 1664500, "NumberOfFeatures": 12, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 12, "NumberOfSymbolicFeatures": 0, "Dimensionality": 7.209372183838991e-6, "PercentageOfNumericFeatures": 100, "MajorityClassPercentage": null, "PercentageOfSymbolicFeatures": 0, "MajorityClassSize": null, "MinorityClassPercentage": null, "MinorityClassSize": null, "NumberOfBinaryFeatures": 0, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": -53441.07075402268, "PercentageOfMissingValues": 0 }, "tags": [ { "uploader": "38960", "tag": "Machine Learning" } ], "features": [ { "name": "PINCP", "index": "11", "type": "numeric", "distinct": "18107", "missing": "0", "target": "1", "min": "104", "max": "1423000", "mean": "56664", "stdev": "73067" }, { "name": "AGEP", "index": "0", "type": "numeric", "distinct": "80", "missing": "0", "min": "17", "max": "96", "mean": "43", "stdev": "15" }, { "name": "COW", "index": "1", "type": "numeric", "distinct": "8", "missing": "0", "min": "1", "max": "8", "mean": "2", "stdev": "2" }, { "name": "SCHL", "index": "2", "type": "numeric", "distinct": "24", "missing": "0", "min": "1", "max": "24", "mean": "19", "stdev": "3" }, { "name": "MAR", "index": "3", "type": "numeric", "distinct": "5", "missing": "0", "min": "1", "max": "5", "mean": "3", "stdev": "2" }, { "name": "OCCP", "index": "4", "type": "numeric", "distinct": "529", "missing": "0", "min": "10", "max": "9830", "mean": "4181", "stdev": "2659" }, { "name": "POBP", "index": "5", "type": "numeric", "distinct": "224", "missing": "0", "min": "1", "max": "554", "mean": "66", "stdev": "93" }, { "name": "RELP", "index": "6", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "17", "mean": "2", "stdev": "4" }, { "name": "WKHP", "index": "7", "type": "numeric", "distinct": "99", "missing": "0", "min": "1", "max": "99", "mean": "38", "stdev": "13" }, { "name": "SEX", "index": "8", "type": "numeric", "distinct": "2", "missing": "0", "min": "1", "max": "2", "mean": "1", "stdev": "0" }, { "name": "RAC1P", "index": "9", "type": "numeric", "distinct": "9", "missing": "0", "min": "1", "max": "9", "mean": "2", "stdev": "2" }, { "name": "ST", "index": "10", "type": "numeric", "distinct": "51", "missing": "0", "min": "1", "max": "72", "mean": "28", "stdev": "16" } ], "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 }