{ "data_id": "43465", "name": "Boston-house-price-data", "exact_name": "Boston-house-price-data", "version": 1, "version_label": "v1.0", "description": "Context\nThis dataset is extracted from the The Boston Housing Dataset, and the extraction of the data is explained in Extract dataset\/dataframe from an URL\nAcknowledgements\nA Dataset derived from information collected by the U.S. Census Service concerning housing in the area of Boston Mass.\nColumn description:\nThis dataset contains information collected by the U.S Census Service concerning housing in the area of Boston Mass. It was obtained from the StatLib archive (http:\/\/lib.stat.cmu.edu\/datasets\/boston), and has been used extensively throughout the literature to benchmark algorithms. However, these comparisons were primarily done outside of Delve and are thus somewhat suspect. The dataset is small in size with only 506 cases.\nThe data was originally published by Harrison, D. and Rubinfeld, D.L. Hedonic prices and the demand for clean air', J. Environ. Economics Management, vol.5, 81-102, 1978.\nVariables in order:\n CRIM per capita crime rate by town\n ZN proportion of residential land zoned for lots over 25,000 sq.ft.\n INDUS proportion of non-retail business acres per town\n CHAS Charles River dummy variable (= 1 if tract bounds river; 0 otherwise)\n NOX nitric oxides concentration (parts per 10 million)\n RM average number of rooms per dwelling\n AGE proportion of owner-occupied units built prior to 1940\n DIS weighted distances to five Boston employment centres\n RAD index of accessibility to radial highways\n TAX full-value property-tax rate per 10,000\n PTRATIO pupil-teacher ratio by town\n B 1000(Bk - 0.63)2 where Bk is the proportion of blacks by town\n LSTAT lower status of the population\n MEDV Median value of owner-occupied homes in 1000's\n\nInspiration\nI'd like to find it as the base for data exploration in regression way", "format": "arff", "uploader": "Onur Yildirim", "uploader_id": 30126, "visibility": "public", "creator": null, "contributor": null, "date": "2022-03-23 13:23:22", "update_comment": null, "last_update": "2022-03-23 13:23:22", "licence": "CC0: Public Domain", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/22102290\/dataset", "default_target_attribute": "MEDV", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "Boston-house-price-data", "Context This dataset is extracted from the The Boston Housing Dataset, and the extraction of the data is explained in Extract dataset\/dataframe from an URL Acknowledgements A Dataset derived from information collected by the U.S. Census Service concerning housing in the area of Boston Mass. Column description: This dataset contains information collected by the U.S Census Service concerning housing in the area of Boston Mass. It was obtained from the StatLib archive (http:\/\/lib.stat.cmu.edu\/datas " ], "weight": 5 }, "qualities": { "NumberOfInstances": 506, "NumberOfFeatures": 14, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 14, "NumberOfSymbolicFeatures": 0, "MinorityClassPercentage": null, "MinorityClassSize": null, "NumberOfBinaryFeatures": 0, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": -3.3724752475247524, "PercentageOfMissingValues": 0, "Dimensionality": 0.02766798418972332, "PercentageOfNumericFeatures": 100, "MajorityClassPercentage": null, "PercentageOfSymbolicFeatures": 0, "MajorityClassSize": null }, "tags": [ { "tag": "Computer Systems", "uploader": "38960" }, { "tag": "Machine Learning", "uploader": "38960" } ], "features": [ { "name": "MEDV", "index": "13", "type": "numeric", "distinct": "229", "missing": "0", "target": "1", "min": "5", "max": "50", "mean": "23", "stdev": "9" }, { "name": "CRIM", "index": "0", "type": "numeric", "distinct": "504", "missing": "0", "min": "0", "max": "89", "mean": "4", "stdev": "9" }, { "name": "ZN", "index": "1", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "100", "mean": "11", "stdev": "23" }, { "name": "INDUS", "index": "2", "type": "numeric", "distinct": "76", "missing": "0", "min": "0", "max": "28", "mean": "11", "stdev": "7" }, { "name": "CHAS", "index": "3", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "NOX", "index": "4", "type": "numeric", "distinct": "81", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "RM", "index": "5", "type": "numeric", "distinct": "446", "missing": "0", "min": "4", "max": "9", "mean": "6", "stdev": "1" }, { "name": "AGE", "index": "6", "type": "numeric", "distinct": "356", "missing": "0", "min": "3", "max": "100", "mean": "69", "stdev": "28" }, { "name": "DIS", "index": "7", "type": "numeric", "distinct": "412", "missing": "0", "min": "1", "max": "12", "mean": "4", "stdev": "2" }, { "name": "RAD", "index": "8", "type": "numeric", "distinct": "9", "missing": "0", "min": "1", "max": "24", "mean": "10", "stdev": "9" }, { "name": "TAX", "index": "9", "type": "numeric", "distinct": "66", "missing": "0", "min": "187", "max": "711", "mean": "408", "stdev": "169" }, { "name": "PTRATIO", "index": "10", "type": "numeric", "distinct": "46", "missing": "0", "min": "13", "max": "22", "mean": "18", "stdev": "2" }, { "name": "B", "index": "11", "type": "numeric", "distinct": "357", "missing": "0", "min": "0", "max": "397", "mean": "357", "stdev": "91" }, { "name": "LSTAT", "index": "12", "type": "numeric", "distinct": "455", "missing": "0", "min": "2", "max": "38", "mean": "13", "stdev": "7" } ], "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 }