{ "data_id": "43393", "name": "USA-Housing-Listings", "exact_name": "USA-Housing-Listings", "version": 1, "version_label": "v1.0", "description": "Context\nCraigslist is the world's largest collection of privately sold housing options, yet it's very difficult to collect all of them in the same place. I built this dataset as a means in by which to perform experimental analysis on the United States states as a whole instead of isolated urban housing markets.\nContent\nThis data is scraped every few months, it contains most all relevant information that Craigslist provides on retail sales", "format": "arff", "uploader": "Onur Yildirim", "uploader_id": 30126, "visibility": "public", "creator": null, "contributor": null, "date": "2022-03-23 12:57:07", "update_comment": null, "last_update": "2022-03-23 12:57:07", "licence": "CC0: Public Domain", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/22102218\/dataset", "default_target_attribute": null, "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "USA-Housing-Listings", "Context Craigslist is the world's largest collection of privately sold housing options, yet it's very difficult to collect all of them in the same place. I built this dataset as a means in by which to perform experimental analysis on the United States states as a whole instead of isolated urban housing markets. Content This data is scraped every few months, it contains most all relevant information that Craigslist provides on retail sales " ], "weight": 5 }, "qualities": { "NumberOfInstances": 384977, "NumberOfFeatures": 22, "NumberOfClasses": null, "NumberOfMissingValues": 223551, "NumberOfInstancesWithMissingValues": 149008, "NumberOfNumericFeatures": 13, "NumberOfSymbolicFeatures": 0, "Dimensionality": 5.714627107593441e-5, "PercentageOfNumericFeatures": 59.09090909090909, "MajorityClassPercentage": null, "PercentageOfSymbolicFeatures": 0, "MajorityClassSize": null, "MinorityClassPercentage": null, "MinorityClassSize": null, "NumberOfBinaryFeatures": 0, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 38.705688911285606, "AutoCorrelation": null, "PercentageOfMissingValues": 2.6394847201025233 }, "tags": [ { "uploader": "38960", "tag": "Computer Systems" }, { "uploader": "38960", "tag": "Machine Learning" } ], "features": [ { "name": "id", "index": "0", "type": "numeric", "distinct": "384977", "missing": "0", "min": "2147483647", "max": "2147483647", "mean": "2147483647", "stdev": "8800376" }, { "name": "url", "index": "1", "type": "string", "distinct": "384977", "missing": "0" }, { "name": "region", "index": "2", "type": "string", "distinct": "404", "missing": "0" }, { "name": "region_url", "index": "3", "type": "string", "distinct": "413", "missing": "0" }, { "name": "price", "index": "4", "type": "numeric", "distinct": "3961", "missing": "0", "min": "0", "max": "2147483647", "mean": "8826", "stdev": "4462200" }, { "name": "type", "index": "5", "type": "string", "distinct": "12", "missing": "0" }, { "name": "sqfeet", "index": "6", "type": "numeric", "distinct": "3277", "missing": "0", "min": "0", "max": "8388607", "mean": "1060", "stdev": "19151" }, { "name": "beds", "index": "7", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "1100", "mean": "2", "stdev": "3" }, { "name": "baths", "index": "8", "type": "numeric", "distinct": "20", "missing": "0", "min": "0", "max": "75", "mean": "1", "stdev": "1" }, { "name": "cats_allowed", "index": "9", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "dogs_allowed", "index": "10", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "smoking_allowed", "index": "11", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "wheelchair_access", "index": "12", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "electric_vehicle_charge", "index": "13", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "comes_furnished", "index": "14", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "laundry_options", "index": "15", "type": "string", "distinct": "5", "missing": "79026" }, { "name": "parking_options", "index": "16", "type": "string", "distinct": "7", "missing": "140687" }, { "name": "image_url", "index": "17", "type": "string", "distinct": "181068", "missing": "0" }, { "name": "description", "index": "18", "type": "string", "distinct": "280644", "missing": "2" }, { "name": "lat", "index": "19", "type": "numeric", "distinct": "56772", "missing": "1918", "min": "-44", "max": "102", "mean": "37", "stdev": "6" }, { "name": "long", "index": "20", "type": "numeric", "distinct": "54035", "missing": "1918", "min": "-164", "max": "173", "mean": "-93", "stdev": "17" }, { "name": "state", "index": "21", "type": "string", "distinct": "51", "missing": "0" } ], "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 }