{ "data_id": "43375", "name": "Towards-Data-Science-articles-dataset-(2010-2021)", "exact_name": "Towards-Data-Science-articles-dataset-(2010-2021)", "version": 1, "version_label": "v1.0", "description": "Context\nTowards Data Science Inc. is a corporation registered in Canada as a platform for thousands of people to exchange ideas and to expand understanding of data science.\nThis dataset contains data for the Towards Data Science article since 2010. It will be updated on a monthly basis. The data in this dataset was extracted from https:\/\/towardsdatascience.com\/archive\nContent\nAs of now, the dataset consists of 40 133 articles and 8 features:\n\nPublication date\nTitle\nAuthor\nArticle URL\nNumber of claps\nNumber of responses\nAmount of time spent on reading based on the average reading speed of an adult (roughly 265 WPM).\nPaid or free (Participation in Medium Partner Program)", "format": "arff", "uploader": "Elif Ceren Gok", "uploader_id": 30125, "visibility": "public", "creator": null, "contributor": null, "date": "2022-03-23 12:43:55", "update_comment": null, "last_update": "2022-03-23 12:43:55", "licence": "CC0: Public Domain", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/22102200\/dataset", "default_target_attribute": null, "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "Towards-Data-Science-articles-dataset-(2010-2021)", "Context Towards Data Science Inc. is a corporation registered in Canada as a platform for thousands of people to exchange ideas and to expand understanding of data science. This dataset contains data for the Towards Data Science article since 2010. It will be updated on a monthly basis. The data in this dataset was extracted from https:\/\/towardsdatascience.com\/archive Content As of now, the dataset consists of 40 133 articles and 8 features: Publication date Title Author Article URL Number of cl " ], "weight": 5 }, "qualities": { "NumberOfInstances": 46079, "NumberOfFeatures": 8, "NumberOfClasses": null, "NumberOfMissingValues": 3, "NumberOfInstancesWithMissingValues": 3, "NumberOfNumericFeatures": 4, "NumberOfSymbolicFeatures": 0, "Dimensionality": 0.00017361487879511274, "PercentageOfNumericFeatures": 50, "MajorityClassPercentage": null, "PercentageOfSymbolicFeatures": 0, "MajorityClassSize": null, "MinorityClassPercentage": null, "MinorityClassSize": null, "NumberOfBinaryFeatures": 0, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 0.006510557954816728, "AutoCorrelation": null, "PercentageOfMissingValues": 0.000813819744352091 }, "tags": [ { "uploader": "38960", "tag": "Computer Systems" }, { "uploader": "38960", "tag": "Machine Learning" } ], "features": [ { "name": "publish_date", "index": "0", "type": "string", "distinct": "1720", "missing": "0" }, { "name": "title", "index": "1", "type": "string", "distinct": "45821", "missing": "2" }, { "name": "author", "index": "2", "type": "string", "distinct": "12134", "missing": "1" }, { "name": "url", "index": "3", "type": "string", "distinct": "46079", "missing": "0" }, { "name": "claps", "index": "4", "type": "numeric", "distinct": "1138", "missing": "0", "min": "0", "max": "52000", "mean": "266", "stdev": "862" }, { "name": "responses", "index": "5", "type": "numeric", "distinct": "92", "missing": "0", "min": "0", "max": "298", "mean": "2", "stdev": "5" }, { "name": "reading_time", "index": "6", "type": "numeric", "distinct": "58", "missing": "0", "min": "0", "max": "67", "mean": "7", "stdev": "4" }, { "name": "paid", "index": "7", "type": "numeric", "distinct": "2", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "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 }