{ "data_id": "471", "name": "analcatdata_draft", "exact_name": "analcatdata_draft", "version": 1, "version_label": null, "description": "**Author**: \n**Source**: Unknown - Date unknown \n**Please cite**: \n\nanalcatdata A collection of data sets used in the book \"Analyzing Categorical Data,\"\nby Jeffrey S. Simonoff, Springer-Verlag, New York, 2003. The submission\nconsists of a zip file containing two versions of each of 84 data sets,\nplus this README file. Each data set is given in comma-delimited ASCII\n(.csv) form, and Microsoft Excel (.xls) form.\n\nNOTICE: These data sets may be used freely for scientific, educational and\/or\nnoncommercial purposes, provided suitable acknowledgment is given (by citing\nthe above-named reference).\n\nFurther details concerning the book, including information on statistical software\n(including sample S-PLUS\/R and SAS code), are available at the web site\n\nhttp:\/\/www.stern.nyu.edu\/~jsimonof\/AnalCatData\n\n\nInformation about the dataset\nCLASSTYPE: nominal\nCLASSINDEX: none specific\n\n\nNote: Quotes, Single-Quotes and Backslashes were removed, Blanks replaced\nwith Underscores", "format": "ARFF", "uploader": "Joaquin Vanschoren", "uploader_id": 2, "visibility": "public", "creator": null, "contributor": null, "date": "2014-09-28 23:51:28", "update_comment": "Actual.date is a row id", "last_update": "2015-04-15 17:36:25", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/52583\/analcatdata_draft.arff", "default_target_attribute": "", "row_id_attribute": "Actual.date", "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "analcatdata_draft", "analcatdata A collection of data sets used in the book \"Analyzing Categorical Data,\" by Jeffrey S. Simonoff, Springer-Verlag, New York, 2003. The submission consists of a zip file containing two versions of each of 84 data sets, plus this README file. Each data set is given in comma-delimited ASCII (.csv) form, and Microsoft Excel (.xls) form. NOTICE: These data sets may be used freely for scientific, educational and\/or noncommercial purposes, provided suitable acknowledgment is given (by citing " ], "weight": 5 }, "qualities": { "NumberOfInstances": 366, "NumberOfFeatures": 5, "NumberOfClasses": null, "NumberOfMissingValues": 2, "NumberOfInstancesWithMissingValues": 2, "NumberOfNumericFeatures": 2, "NumberOfSymbolicFeatures": 3, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 0.546448087431694, "AutoCorrelation": null, "PercentageOfMissingValues": 0.1092896174863388, "Dimensionality": 0.01366120218579235, "PercentageOfNumericFeatures": 40, "MajorityClassPercentage": null, "PercentageOfSymbolicFeatures": 60, "MajorityClassSize": null, "MinorityClassPercentage": null, "MinorityClassSize": null, "NumberOfBinaryFeatures": 0 }, "tags": [], "features": [ { "name": "Actual.date", "index": "0", "type": "numeric", "distinct": "366", "missing": "0", "identifier": "1", "min": "1", "max": "366", "mean": "184", "stdev": "106" }, { "name": "Lottery.pick.1970", "index": "1", "type": "numeric", "distinct": "366", "missing": "0", "min": "1", "max": "366", "mean": "184", "stdev": "106" }, { "name": "Lottery.pick.1971", "index": "2", "type": "numeric", "distinct": "365", "missing": "1", "min": "1", "max": "365", "mean": "183", "stdev": "106" }, { "name": "Month", "index": "3", "type": "nominal", "distinct": "12", "missing": "0", "distr": [] }, { "name": "Month.ordered.picks.1970", "index": "4", "type": "nominal", "distinct": "12", "missing": "0", "distr": [] }, { "name": "Month.ordered.picks.1971", "index": "5", "type": "nominal", "distinct": "12", "missing": "1", "distr": [] } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 2, "total_downloads": 3, "reach": 2, "reuse": 11, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 11 }