{ "data_id": "530", "name": "analcatdata_olympic2000", "exact_name": "analcatdata_olympic2000", "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: numeric\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": "2014-09-29 00:08:05", "update_comment": "set target feature", "last_update": "2014-10-07 01:26:08", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/52642\/analcatdata_olympic2000.arff", "default_target_attribute": "GDP", "row_id_attribute": null, "ignore_attribute": "\"Country\"", "runs": 2, "suggest": { "input": [ "analcatdata_olympic2000", "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": 66, "NumberOfFeatures": 12, "NumberOfClasses": 0, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 12, "NumberOfSymbolicFeatures": 0, "PercentageOfBinaryFeatures": 0, "PercentageOfInstancesWithMissingValues": 0, "AutoCorrelation": -518039.90769230766, "PercentageOfMissingValues": 0, "Dimensionality": 0.18181818181818182, "PercentageOfNumericFeatures": 100, "MajorityClassPercentage": null, "PercentageOfSymbolicFeatures": 0, "MajorityClassSize": null, "MinorityClassPercentage": null, "MinorityClassSize": null, "NumberOfBinaryFeatures": 0 }, "tags": [ { "tag": "study_239", "uploader": "0" } ], "features": [ { "name": "GDP", "index": "7", "type": "numeric", "distinct": "66", "missing": "0", "target": "1", "min": "1472", "max": "7567100", "mean": "430534", "stdev": "1149215" }, { "name": "Country", "index": "0", "type": "nominal", "distinct": "66", "missing": "0", "ignore": "1", "distr": [] }, { "name": "Gold2000", "index": "1", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "39", "mean": "5", "stdev": "8" }, { "name": "Silver2000", "index": "2", "type": "numeric", "distinct": "16", "missing": "0", "min": "0", "max": "28", "mean": "4", "stdev": "6" }, { "name": "Bronze2000", "index": "3", "type": "numeric", "distinct": "18", "missing": "0", "min": "0", "max": "33", "mean": "5", "stdev": "7" }, { "name": "Total2000", "index": "4", "type": "numeric", "distinct": "28", "missing": "0", "min": "1", "max": "97", "mean": "14", "stdev": "19" }, { "name": "Population", "index": "5", "type": "numeric", "distinct": "66", "missing": "0", "min": "296", "max": "1255698", "mean": "69262", "stdev": "195302" }, { "name": "Athletes", "index": "6", "type": "numeric", "distinct": "57", "missing": "0", "min": "5", "max": "664", "mean": "155", "stdev": "147" }, { "name": "Total1996", "index": "8", "type": "numeric", "distinct": "26", "missing": "0", "min": "1", "max": "101", "mean": "13", "stdev": "18" }, { "name": "Log1996", "index": "9", "type": "numeric", "distinct": "26", "missing": "0", "min": "0", "max": "5", "mean": "2", "stdev": "1" }, { "name": "Log.population", "index": "10", "type": "numeric", "distinct": "66", "missing": "0", "min": "6", "max": "14", "mean": "10", "stdev": "2" }, { "name": "Log.GDP", "index": "11", "type": "numeric", "distinct": "66", "missing": "0", "min": "7", "max": "16", "mean": "11", "stdev": "2" }, { "name": "Log.athletes", "index": "12", "type": "numeric", "distinct": "57", "missing": "0", "min": "2", "max": "6", "mean": "5", "stdev": "1" } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 0, "total_downloads": 0, "reach": 0, "reuse": 14, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 14 }