{ "data_id": "43369", "name": "U.S.-Airbnb-Open-Data", "exact_name": "U.S.-Airbnb-Open-Data", "version": 1, "version_label": "v1.0", "description": "**Author**: Kritik Seth\n\n### Context\nSince its inception in 2008, Airbnb has disrupted the traditional hospitality industry as more travellers decide to use Airbnb as their primary means of accommodation. Airbnb offers travellers a more unique and personalized way of accommodation and experience.\n\n### Content\nThis dataset has columns describing features such as host id, hostname, listing id, listing name, latitude and longitude of listing, the neighbourhood, price, room type, minimum number of nights, number of reviews, last review date, reviews per month, availability, host listings and city.\n\n### Acknowledgements\nThis dataset is a compilation of multiple datasets found on Inside Airbnb.\n\n### Inspiration\n* Can we predict the price of each house in different regions? \n* Can we describe a region using the names of listings in that region? \n* What can we learn about different regions from the data? \n* Based on different factors is it possible to recommend a title to the host for his\/her listing? \n* Can we estimate the popularity of a listing based on given features?", "format": "arff", "uploader": "Onur Yildirim", "uploader_id": 30126, "visibility": "public", "creator": null, "contributor": null, "date": "2022-03-23 12:43:10", "update_comment": null, "last_update": "2022-03-23 12:43:10", "licence": "CC0: Public Domain", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/22102194\/dataset", "default_target_attribute": null, "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "U.S.-Airbnb-Open-Data", "### Context Since its inception in 2008, Airbnb has disrupted the traditional hospitality industry as more travellers decide to use Airbnb as their primary means of accommodation. Airbnb offers travellers a more unique and personalized way of accommodation and experience. ### Content This dataset has columns describing features such as host id, hostname, listing id, listing name, latitude and longitude of listing, the neighbourhood, price, room type, minimum number of nights, number of reviews, " ], "weight": 5 }, "qualities": { "NumberOfInstances": 226030, "NumberOfFeatures": 17, "NumberOfClasses": null, "NumberOfMissingValues": 213880, "NumberOfInstancesWithMissingValues": 141316, "NumberOfNumericFeatures": 10, "NumberOfSymbolicFeatures": 0, "MajorityClassSize": null, "MinorityClassPercentage": null, "MinorityClassSize": null, "NumberOfBinaryFeatures": 0, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 62.52090430473831, "AutoCorrelation": null, "PercentageOfMissingValues": 5.566153373706249, "Dimensionality": 7.52112551431226e-5, "PercentageOfNumericFeatures": 58.82352941176471, "MajorityClassPercentage": null, "PercentageOfSymbolicFeatures": 0 }, "tags": [ { "uploader": "38960", "tag": "Computer Systems" }, { "uploader": "38960", "tag": "Machine Learning" } ], "features": [ { "name": "id", "index": "0", "type": "numeric", "distinct": "226029", "missing": "0", "min": "109", "max": "45560850", "mean": "25471759", "stdev": "13178142" }, { "name": "name", "index": "1", "type": "string", "distinct": "217702", "missing": "481" }, { "name": "host_id", "index": "2", "type": "numeric", "distinct": "130425", "missing": "0", "min": "23", "max": "367917574", "mean": "93523849", "stdev": "98274222" }, { "name": "host_name", "index": "3", "type": "string", "distinct": "30305", "missing": "350" }, { "name": "neighbourhood_group", "index": "4", "type": "string", "distinct": "34", "missing": "115845" }, { "name": "neighbourhood", "index": "5", "type": "string", "distinct": "1450", "missing": "0" }, { "name": "latitude", "index": "6", "type": "numeric", "distinct": "145091", "missing": "0", "min": "19", "max": "48", "mean": "36", "stdev": "7" }, { "name": "longitude", "index": "7", "type": "numeric", "distinct": "145243", "missing": "0", "min": "-160", "max": "0", "mean": "-103", "stdev": "26" }, { "name": "room_type", "index": "8", "type": "string", "distinct": "4", "missing": "0" }, { "name": "price", "index": "9", "type": "numeric", "distinct": "1975", "missing": "0", "min": "0", "max": "24999", "mean": "220", "stdev": "570" }, { "name": "minimum_nights", "index": "10", "type": "numeric", "distinct": "169", "missing": "0", "min": "1", "max": "100000000", "mean": "453", "stdev": "210338" }, { "name": "number_of_reviews", "index": "11", "type": "numeric", "distinct": "660", "missing": "0", "min": "0", "max": "966", "mean": "35", "stdev": "64" }, { "name": "last_review", "index": "12", "type": "string", "distinct": "2377", "missing": "48602" }, { "name": "reviews_per_month", "index": "13", "type": "numeric", "distinct": "1242", "missing": "48602", "min": "0", "max": "44", "mean": "1", "stdev": "2" }, { "name": "calculated_host_listings_count", "index": "14", "type": "numeric", "distinct": "142", "missing": "0", "min": "1", "max": "593", "mean": "17", "stdev": "51" }, { "name": "availability_365", "index": "15", "type": "numeric", "distinct": "366", "missing": "0", "min": "0", "max": "365", "mean": "159", "stdev": "140" }, { "name": "city", "index": "16", "type": "string", "distinct": "28", "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 }