{ "data_id": "43438", "name": "Goodreads-Books---31-Features", "exact_name": "Goodreads-Books---31-Features", "version": 1, "version_label": "v1.0", "description": "Context\nThe official Goodread's API limits retrievable data, so I decided to scrape the actual HTTP pages and grab additional details on each book.\nContent\nBooks are scraped from a list titles the \"Best Books Ever\" which can be found here https:\/\/www.goodreads.com\/list\/show\/1.Best_Books_Ever\nAcknowledgements\nThanks to Goodreads for housing the data.", "format": "arff", "uploader": "Onur Yildirim", "uploader_id": 30126, "visibility": "public", "creator": null, "contributor": null, "date": "2022-03-23 13:21:01", "update_comment": null, "last_update": "2022-03-23 13:21:01", "licence": "CC0: Public Domain", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/22102263\/dataset", "default_target_attribute": null, "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "Goodreads-Books---31-Features", "Context The official Goodread's API limits retrievable data, so I decided to scrape the actual HTTP pages and grab additional details on each book. Content Books are scraped from a list titles the \"Best Books Ever\" which can be found here https:\/\/www.goodreads.com\/list\/show\/1.Best_Books_Ever Acknowledgements Thanks to Goodreads for housing the data. " ], "weight": 5 }, "qualities": { "NumberOfInstances": 52199, "NumberOfFeatures": 31, "NumberOfClasses": null, "NumberOfMissingValues": 285951, "NumberOfInstancesWithMissingValues": 52199, "NumberOfNumericFeatures": 10, "NumberOfSymbolicFeatures": 0, "Dimensionality": 0.0005938811088335025, "PercentageOfNumericFeatures": 32.25806451612903, "MajorityClassPercentage": null, "PercentageOfSymbolicFeatures": 0, "MajorityClassSize": null, "MinorityClassPercentage": null, "MinorityClassSize": null, "NumberOfBinaryFeatures": 0, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 100, "AutoCorrelation": null, "PercentageOfMissingValues": 17.671269193761592 }, "tags": [ { "uploader": "38960", "tag": "Computer Systems" }, { "uploader": "38960", "tag": "Machine Learning" } ], "features": [ { "name": "id", "index": "0", "type": "numeric", "distinct": "52199", "missing": "0", "min": "1", "max": "54442989", "mean": "10154425", "stdev": "11644432" }, { "name": "title", "index": "1", "type": "string", "distinct": "48145", "missing": "224" }, { "name": "link", "index": "2", "type": "string", "distinct": "52199", "missing": "0" }, { "name": "series", "index": "3", "type": "string", "distinct": "22477", "missing": "28880" }, { "name": "cover_link", "index": "4", "type": "string", "distinct": "51592", "missing": "607" }, { "name": "author", "index": "5", "type": "string", "distinct": "27233", "missing": "6" }, { "name": "author_link", "index": "6", "type": "string", "distinct": "23009", "missing": "0" }, { "name": "rating_count", "index": "7", "type": "numeric", "distinct": "19267", "missing": "0", "min": "0", "max": "6801077", "mean": "18874", "stdev": "116398" }, { "name": "review_count", "index": "8", "type": "numeric", "distinct": "5627", "missing": "0", "min": "0", "max": "169511", "mean": "1013", "stdev": "4055" }, { "name": "average_rating", "index": "9", "type": "numeric", "distinct": "262", "missing": "0", "min": "0", "max": "5", "mean": "4", "stdev": "0" }, { "name": "five_star_ratings", "index": "10", "type": "numeric", "distinct": "12808", "missing": "0", "min": "0", "max": "4414877", "mean": "7817", "stdev": "58764" }, { "name": "four_star_ratings", "index": "11", "type": "numeric", "distinct": "12399", "missing": "0", "min": "0", "max": "1868421", "mean": "6251", "stdev": "34735" }, { "name": "three_star_ratings", "index": "12", "type": "numeric", "distinct": "9597", "missing": "0", "min": "0", "max": "980183", "mean": "3457", "stdev": "18249" }, { "name": "two_star_ratings", "index": "13", "type": "numeric", "distinct": "4904", "missing": "0", "min": "0", "max": "529060", "mean": "935", "stdev": "5890" }, { "name": "one_star_ratings", "index": "14", "type": "numeric", "distinct": "3118", "missing": "0", "min": "0", "max": "537793", "mean": "414", "stdev": "3843" }, { "name": "number_of_pages", "index": "15", "type": "numeric", "distinct": "1367", "missing": "2330", "min": "0", "max": "14777", "mean": "329", "stdev": "253" }, { "name": "date_published", "index": "16", "type": "string", "distinct": "9120", "missing": "860" }, { "name": "publisher", "index": "17", "type": "string", "distinct": "10369", "missing": "3935" }, { "name": "original_title", "index": "18", "type": "string", "distinct": "36190", "missing": "13266" }, { "name": "genre_and_votes", "index": "19", "type": "string", "distinct": "47301", "missing": "2840" }, { "name": "isbn", "index": "20", "type": "string", "distinct": "40316", "missing": "11883" }, { "name": "isbn13", "index": "21", "type": "string", "distinct": "39507", "missing": "12692" }, { "name": "asin", "index": "22", "type": "string", "distinct": "5236", "missing": "46963" }, { "name": "settings", "index": "23", "type": "string", "distinct": "5335", "missing": "40687" }, { "name": "characters", "index": "24", "type": "string", "distinct": "12260", "missing": "38509" }, { "name": "awards", "index": "25", "type": "string", "distinct": "9148", "missing": "41574" }, { "name": "amazon_redirect_link", "index": "26", "type": "string", "distinct": "52199", "missing": "0" }, { "name": "worldcat_redirect_link", "index": "27", "type": "string", "distinct": "48214", "missing": "3985" }, { "name": "recommended_books", "index": "28", "type": "string", "distinct": "48047", "missing": "3994" }, { "name": "books_in_series", "index": "29", "type": "string", "distinct": "20318", "missing": "30121" }, { "name": "description", "index": "30", "type": "string", "distinct": "49164", "missing": "2595" } ], "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 }