{ "data_id": "44013", "name": "houses", "exact_name": "houses", "version": 5, "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 \"regression on numerical features\" benchmark. Original description: \n \n**Author**: \n**Source**: Unknown - Date unknown \n**Please cite**: \n\nS&P Letters Data\nWe collected information on the variables using all the block groups in California from the 1990 Census. In this sample a block group on average includes 1425.5 individuals living in a geographically compact area. Naturally, the geographical area included varies inversely with the population density. We computed distances among the centroids of each block group as measured in latitude and longitude. We excluded all the block groups reporting zero entries for the independent and dependent variables. The final data contained 20,640 observations on 9 variables. The dependent variable is ln(median house value).\n\nBols\ttols\nINTERCEPT\t\t11.4939\t275.7518\nMEDIAN INCOME\t\t0.4790\t45.7768\nMEDIAN INCOME2\t\t-0.0166\t-9.4841\nMEDIAN INCOME3\t\t-0.0002\t-1.9157\nln(MEDIAN AGE)\t\t0.1570\t33.6123\nln(TOTAL ROOMS\/ POPULATION)\t-0.8582\t-56.1280\nln(BEDROOMS\/ POPULATION)\t0.8043\t38.0685\nln(POPULATION\/ HOUSEHOLDS)\t-0.4077\t-20.8762\nln(HOUSEHOLDS)\t\t0.0477\t13.0792\n\nThe file cadata.txt contains all th", "format": "arff", "uploader": "Leo Grin", "uploader_id": 26324, "visibility": "public", "creator": null, "contributor": "\"Leo Grin\"", "date": "2022-06-16 21:12:51", "update_comment": null, "last_update": "2022-06-16 21:12:51", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/old.openml.org\/data\/download\/22103101\/dataset", "default_target_attribute": "medianhousevalue", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "houses", "Dataset used in the tabular data benchmark https:\/\/github.com\/LeoGrin\/tabular-benchmark, transformed in the same way. This dataset belongs to the \"regression on numerical features\" benchmark. Original description: S&P Letters Data We collected information on the variables using all the block groups in California from the 1990 Census. In this sample a block group on average includes 1425.5 individuals living in a geographically compact area. Naturally, the geographical area included varies invers " ], "weight": 5 }, "qualities": { "NumberOfInstances": 20640, "NumberOfFeatures": 9, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 9, "NumberOfSymbolicFeatures": 0, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": 0.8041216659259995, "PercentageOfMissingValues": 0, "Dimensionality": 0.00043604651162790697, "PercentageOfNumericFeatures": 100, "MajorityClassPercentage": null, "PercentageOfSymbolicFeatures": 0, "MajorityClassSize": null, "MinorityClassPercentage": null, "MinorityClassSize": null, "NumberOfBinaryFeatures": 0, "PercentageOfBinaryFeatures": 0 }, "tags": [ { "uploader": "38960", "tag": "Machine Learning" }, { "uploader": "38960", "tag": "Statistics" } ], "features": [ { "name": "medianhousevalue", "index": "8", "type": "numeric", "distinct": "3842", "missing": "0", "target": "1", "min": "10", "max": "13", "mean": "12", "stdev": "1" }, { "name": "median_income", "index": "0", "type": "numeric", "distinct": "12928", "missing": "0", "min": "0", "max": "15", "mean": "4", "stdev": "2" }, { "name": "housing_median_age", "index": "1", "type": "numeric", "distinct": "52", "missing": "0", "min": "1", "max": "52", "mean": "29", "stdev": "13" }, { "name": "total_rooms", "index": "2", "type": "numeric", "distinct": "5926", "missing": "0", "min": "2", "max": "39320", "mean": "2636", "stdev": "2182" }, { "name": "total_bedrooms", "index": "3", "type": "numeric", "distinct": "1928", "missing": "0", "min": "1", "max": "6445", "mean": "538", "stdev": "421" }, { "name": "population", "index": "4", "type": "numeric", "distinct": "3888", "missing": "0", "min": "3", "max": "35682", "mean": "1425", "stdev": "1132" }, { "name": "households", "index": "5", "type": "numeric", "distinct": "1815", "missing": "0", "min": "1", "max": "6082", "mean": "500", "stdev": "382" }, { "name": "latitude", "index": "6", "type": "numeric", "distinct": "862", "missing": "0", "min": "33", "max": "42", "mean": "36", "stdev": "2" }, { "name": "longitude", "index": "7", "type": "numeric", "distinct": "844", "missing": "0", "min": "-124", "max": "0", "mean": "-120", "stdev": "2" } ], "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 }