{ "data_id": "43599", "name": "AirBNB-analysis-Lisbon", "exact_name": "AirBNB-analysis-Lisbon", "version": 1, "version_label": "v1.0", "description": "Dataset is from http:\/\/tomslee.net\/airbnb-data-collection-get-the-data \nroom_id: A unique number identifying an Airbnb listing. The listing has a URL on the Airbnb web site of http:\/\/airbnb.com\/rooms\/room_id\nhost_id: A unique number identifying an Airbnb host. The hosts page has a URL on the Airbnb web site of http:\/\/airbnb.com\/users\/show\/host_id\nroom_type: One of Entire home\/apt, Private room, or Shared room\nborough: A subregion of the city or search area for which the survey is carried out. The borough is taken from a shapefile of the \ncity that is obtained independently of the Airbnb web site. For some cities, there is no borough information; for others the borough may be a number. If you have better shapefiles for a city of interest, please send them to me.\nneighborhood: As with borough: a subregion of the city or search area for which the survey is carried out. For cities that have both, a neighbourhood is smaller than a borough. For some cities there is no neighbourhood information.\nreviews: The number of reviews that a listing has received. Airbnb has said that 70 of visits end up with a review, so the number of reviews can be used to estimate the number of visits. Note that such an estimate will not be reliable for an individual \nlisting (especially as reviews occasionally vanish from the site), but over a city as a whole it should be a useful metric of traffic.\noverall_satisfaction: The average rating (out of five) that the listing has received from those visitors who left a review.\naccommodates: The number of guests a listing can accommodate.\nbedrooms: The number of bedrooms a listing offers.\nprice: The price (in US) for a night stay. In early surveys, there may be some values that were recorded by month.\nminstay: The minimum stay for a visit, as posted by the host.\nlatitude and longitude: The latitude and longitude of the listing as posted on the Airbnb site: this may be off by a few hundred metres. I do not have a way to track individual listing locations with\nlast_modified: the date and time that the values were read from the Airbnb web site.\nThe first line of the CSV file holds the column headings.\nHere are the cities, the survey dates, and a link to download each zip file.\nAarhus\nSurvey dates: 2016-10-28 (2258 listings), 2016-11-26 (1900 listings), 2017-01-21 (2167 listings), 2017-02-21 (2295 listings), 2017-03-30 (2323 listings), 2017-04-18 (2398 listings), 2017-04-28 (2360 listings), 2017-05-15 (2437 listings), 2017-06-19 (2802 listings), 2017-07-28 (3142 listings)", "format": "arff", "uploader": "Dustin Carrion", "uploader_id": 30123, "visibility": "public", "creator": null, "contributor": null, "date": "2022-03-24 00:37:10", "update_comment": null, "last_update": "2022-03-24 00:37:10", "licence": "CC0: Public Domain", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/22102424\/dataset", "default_target_attribute": null, "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "AirBNB-analysis-Lisbon", "Dataset is from http:\/\/tomslee.net\/airbnb-data-collection-get-the-data room_id: A unique number identifying an Airbnb listing. The listing has a URL on the Airbnb web site of http:\/\/airbnb.com\/rooms\/room_id host_id: A unique number identifying an Airbnb host. The hosts page has a URL on the Airbnb web site of http:\/\/airbnb.com\/users\/show\/host_id room_type: One of Entire home\/apt, Private room, or Shared room borough: A subregion of the city or search area for which the survey is carried out. The " ], "weight": 5 }, "qualities": { "NumberOfInstances": 13578, "NumberOfFeatures": 20, "NumberOfClasses": null, "NumberOfMissingValues": 54347, "NumberOfInstancesWithMissingValues": 13578, "NumberOfNumericFeatures": 14, "NumberOfSymbolicFeatures": 0, "Dimensionality": 0.0014729709824716454, "PercentageOfNumericFeatures": 70, "MajorityClassPercentage": null, "PercentageOfSymbolicFeatures": 0, "MajorityClassSize": null, "MinorityClassPercentage": null, "MinorityClassSize": null, "NumberOfBinaryFeatures": 0, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 100, "AutoCorrelation": null, "PercentageOfMissingValues": 20.012888496096625 }, "tags": [ { "uploader": "38960", "tag": "Computer Systems" }, { "uploader": "38960", "tag": "Machine Learning" } ], "features": [ { "name": "room_id", "index": "0", "type": "numeric", "distinct": "13578", "missing": "0", "min": "6499", "max": "20091030", "mean": "11286531", "stdev": "6331112" }, { "name": "survey_id", "index": "1", "type": "numeric", "distinct": "1", "missing": "0", "min": "1480", "max": "1480", "mean": "1480", "stdev": "0" }, { "name": "host_id", "index": "2", "type": "numeric", "distinct": "6457", "missing": "0", "min": "14455", "max": "142658216", "mean": "40317800", "stdev": "41202576" }, { "name": "room_type", "index": "3", "type": "string", "distinct": "3", "missing": "0" }, { "name": "country", "index": "4", "type": "numeric", "distinct": "0", "missing": "13578", "min": "2147483647", "max": "0", "mean": "0", "stdev": "0" }, { "name": "city", "index": "5", "type": "string", "distinct": "1", "missing": "0" }, { "name": "borough", "index": "6", "type": "numeric", "distinct": "0", "missing": "13578", "min": "2147483647", "max": "0", "mean": "0", "stdev": "0" }, { "name": "neighborhood", "index": "7", "type": "string", "distinct": "24", "missing": "0" }, { "name": "reviews", "index": "8", "type": "numeric", "distinct": "276", "missing": "0", "min": "0", "max": "448", "mean": "30", "stdev": "44" }, { "name": "overall_satisfaction", "index": "9", "type": "numeric", "distinct": "9", "missing": "0", "min": "0", "max": "5", "mean": "3", "stdev": "2" }, { "name": "accommodates", "index": "10", "type": "numeric", "distinct": "16", "missing": "0", "min": "1", "max": "16", "mean": "4", "stdev": "2" }, { "name": "bedrooms", "index": "11", "type": "numeric", "distinct": "11", "missing": "0", "min": "0", "max": "10", "mean": "2", "stdev": "1" }, { "name": "bathrooms", "index": "12", "type": "numeric", "distinct": "0", "missing": "13578", "min": "2147483647", "max": "0", "mean": "0", "stdev": "0" }, { "name": "price", "index": "13", "type": "numeric", "distinct": "293", "missing": "0", "min": "10", "max": "4203", "mean": "88", "stdev": "123" }, { "name": "minstay", "index": "14", "type": "numeric", "distinct": "0", "missing": "13578", "min": "2147483647", "max": "0", "mean": "0", "stdev": "0" }, { "name": "name", "index": "15", "type": "string", "distinct": "13343", "missing": "35" }, { "name": "last_modified", "index": "16", "type": "string", "distinct": "13578", "missing": "0" }, { "name": "latitude", "index": "17", "type": "numeric", "distinct": "11079", "missing": "0", "min": "39", "max": "39", "mean": "39", "stdev": "0" }, { "name": "longitude", "index": "18", "type": "numeric", "distinct": "11745", "missing": "0", "min": "-9", "max": "0", "mean": "-9", "stdev": "0" }, { "name": "location", "index": "19", "type": "string", "distinct": "13578", "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 }