{ "data_id": "43819", "name": "Boston-Airbnb-Listings", "exact_name": "Boston-Airbnb-Listings", "version": 1, "version_label": "v1.0", "description": "Context\nSince 2008, guests and hosts have used Airbnb to travel in a more unique, personalized way. As part of the Airbnb Inside initiative, this dataset describes the listing activity of homestays in Boston, MA. \nContent\nThis data file includes all needed information to about the listing details, the host, geographical availability, and necessary metrics to make predictions and draw conclusions. Basic data cleaning has been done, such as dropping redundant features (ex: city) and converting amenities into a dictionary. The data includes both numerical and categorical data, as well as natural language descriptions. \nAcknowledgements\nThis dataset is part of Airbnb Inside, and the original source can be found here.\nInspiration\n\nListing visualization\nWhat features drive the price of a listing up?\nWhat can we learn about different hosts and areas?\nWhat can we learn from predictions? (ex: locations, prices, reviews, etc)\nWhich hosts are the busiest and why?\nIs there any noticeable difference of traffic among different areas and what could be the reason for it?", "format": "arff", "uploader": "Elif Ceren Gok", "uploader_id": 30125, "visibility": "public", "creator": null, "contributor": null, "date": "2022-03-24 15:30:20", "update_comment": null, "last_update": "2022-03-24 15:30:20", "licence": "CC0: Public Domain", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/22102644\/dataset", "default_target_attribute": null, "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "Boston-Airbnb-Listings", "Context Since 2008, guests and hosts have used Airbnb to travel in a more unique, personalized way. As part of the Airbnb Inside initiative, this dataset describes the listing activity of homestays in Boston, MA. Content This data file includes all needed information to about the listing details, the host, geographical availability, and necessary metrics to make predictions and draw conclusions. Basic data cleaning has been done, such as dropping redundant features (ex: city) and converting amen " ], "weight": 5 }, "qualities": { "NumberOfInstances": 3845, "NumberOfFeatures": 51, "NumberOfClasses": null, "NumberOfMissingValues": 14267, "NumberOfInstancesWithMissingValues": 2984, "NumberOfNumericFeatures": 22, "NumberOfSymbolicFeatures": 0, "Dimensionality": 0.013263979193758128, "PercentageOfNumericFeatures": 43.13725490196079, "MajorityClassPercentage": null, "PercentageOfSymbolicFeatures": 0, "MajorityClassSize": null, "MinorityClassPercentage": null, "MinorityClassSize": null, "NumberOfBinaryFeatures": 0, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 77.6072821846554, "AutoCorrelation": null, "PercentageOfMissingValues": 7.275555215584283 }, "tags": [ { "uploader": "38960", "tag": "Machine Learning" }, { "uploader": "38960", "tag": "Medicine" } ], "features": [ { "name": "id", "index": "0", "type": "numeric", "distinct": "3845", "missing": "0", "min": "3781", "max": "43176358", "mean": "25290888", "stdev": "12563132" }, { "name": "name", "index": "1", "type": "string", "distinct": "3679", "missing": "3" }, { "name": "summary", "index": "2", "type": "string", "distinct": "2721", "missing": "80" }, { "name": "access", "index": "3", "type": "string", "distinct": "1492", "missing": "1637" }, { "name": "interaction", "index": "4", "type": "string", "distinct": "1404", "missing": "1257" }, { "name": "house_rules", "index": "5", "type": "string", "distinct": "1530", "missing": "990" }, { "name": "host_id", "index": "6", "type": "numeric", "distinct": "1331", "missing": "0", "min": "4804", "max": "342693771", "mean": "92878271", "stdev": "100346111" }, { "name": "host_since", "index": "7", "type": "string", "distinct": "1080", "missing": "0" }, { "name": "host_location", "index": "8", "type": "string", "distinct": "123", "missing": "3" }, { "name": "host_response_time", "index": "9", "type": "string", "distinct": "4", "missing": "562" }, { "name": "host_response_rate", "index": "10", "type": "string", "distinct": "35", "missing": "562" }, { "name": "host_acceptance_rate", "index": "11", "type": "string", "distinct": "73", "missing": "260" }, { "name": "host_is_superhost", "index": "12", "type": "string", "distinct": "2", "missing": "0" }, { "name": "host_neighbourhood", "index": "13", "type": "string", "distinct": "65", "missing": "221" }, { "name": "host_total_listings_count", "index": "14", "type": "numeric", "distinct": "51", "missing": "0", "min": "0", "max": "2324", "mean": "186", "stdev": "428" }, { "name": "host_verifications", "index": "15", "type": "string", "distinct": "152", "missing": "0" }, { "name": "host_identity_verified", "index": "16", "type": "string", "distinct": "2", "missing": "0" }, { "name": "neighbourhood", "index": "17", "type": "string", "distinct": "31", "missing": "0" }, { "name": "neighbourhood_cleansed", "index": "18", "type": "string", "distinct": "25", "missing": "0" }, { "name": "zipcode", "index": "19", "type": "string", "distinct": "54", "missing": "14" }, { "name": "latitude", "index": "20", "type": "numeric", "distinct": "2838", "missing": "0", "min": "42", "max": "42", "mean": "42", "stdev": "0" }, { "name": "longitude", "index": "21", "type": "numeric", "distinct": "2968", "missing": "0", "min": "-71", "max": "0", "mean": "-71", "stdev": "0" }, { "name": "is_location_exact", "index": "22", "type": "string", "distinct": "2", "missing": "0" }, { "name": "property_type", "index": "23", "type": "string", "distinct": "21", "missing": "0" }, { "name": "room_type", "index": "24", "type": "string", "distinct": "4", "missing": "0" }, { "name": "accommodates", "index": "25", "type": "numeric", "distinct": "19", "missing": "0", "min": "1", "max": "29", "mean": "3", "stdev": "2" }, { "name": "bathrooms", "index": "26", "type": "numeric", "distinct": "12", "missing": "3", "min": "0", "max": "6", "mean": "1", "stdev": "1" }, { "name": "bedrooms", "index": "27", "type": "numeric", "distinct": "10", "missing": "4", "min": "0", "max": "13", "mean": "1", "stdev": "1" }, { "name": "beds", "index": "28", "type": "numeric", "distinct": "16", "missing": "20", "min": "0", "max": "22", "mean": "2", "stdev": "1" }, { "name": "bed_type", "index": "29", "type": "string", "distinct": "5", "missing": "1" }, { "name": "amenities_dict", "index": "30", "type": "string", "distinct": "2908", "missing": "0" }, { "name": "price", "index": "31", "type": "string", "distinct": "345", "missing": "0" }, { "name": "cleaning_fee", "index": "32", "type": "string", "distinct": "119", "missing": "399" }, { "name": "availability_30", "index": "33", "type": "numeric", "distinct": "31", "missing": "0", "min": "0", "max": "30", "mean": "16", "stdev": "13" }, { "name": "availability_60", "index": "34", "type": "numeric", "distinct": "61", "missing": "0", "min": "0", "max": "60", "mean": "35", "stdev": "24" }, { "name": "availability_90", "index": "35", "type": "numeric", "distinct": "91", "missing": "0", "min": "0", "max": "90", "mean": "54", "stdev": "35" }, { "name": "availability_365", "index": "36", "type": "numeric", "distinct": "364", "missing": "0", "min": "0", "max": "365", "mean": "185", "stdev": "133" }, { "name": "number_of_reviews", "index": "37", "type": "numeric", "distinct": "289", "missing": "0", "min": "0", "max": "615", "mean": "40", "stdev": "68" }, { "name": "review_scores_rating", "index": "38", "type": "numeric", "distinct": "46", "missing": "839", "min": "20", "max": "100", "mean": "93", "stdev": "9" }, { "name": "review_scores_accuracy", "index": "39", "type": "numeric", "distinct": "9", "missing": "841", "min": "2", "max": "10", "mean": "10", "stdev": "1" }, { "name": "review_scores_cleanliness", "index": "40", "type": "numeric", "distinct": "9", "missing": "840", "min": "2", "max": "10", "mean": "9", "stdev": "1" }, { "name": "review_scores_checkin", "index": "41", "type": "numeric", "distinct": "8", "missing": "842", "min": "2", "max": "10", "mean": "10", "stdev": "1" }, { "name": "review_scores_communication", "index": "42", "type": "numeric", "distinct": "8", "missing": "839", "min": "2", "max": "10", "mean": "10", "stdev": "1" }, { "name": "review_scores_location", "index": "43", "type": "numeric", "distinct": "8", "missing": "841", "min": "2", "max": "10", "mean": "10", "stdev": "1" }, { "name": "review_scores_value", "index": "44", "type": "numeric", "distinct": "9", "missing": "841", "min": "2", "max": "10", "mean": "9", "stdev": "1" }, { "name": "requires_license", "index": "45", "type": "string", "distinct": "2", "missing": "0" }, { "name": "license", "index": "46", "type": "string", "distinct": "895", "missing": "1543" }, { "name": "instant_bookable", "index": "47", "type": "string", "distinct": "2", "missing": "0" }, { "name": "is_business_travel_ready", "index": "48", "type": "string", "distinct": "1", "missing": "0" }, { "name": "cancellation_policy", "index": "49", "type": "string", "distinct": "6", "missing": "0" }, { "name": "reviews_per_month", "index": "50", "type": "numeric", "distinct": "617", "missing": "825", "min": "0", "max": "19", "mean": "2", "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 }