{ "data_id": "40908", "name": "Pen_global", "exact_name": "Pen_global", "version": 1, "version_label": null, "description": ""This UCI dataset contains the hand- written digits 0–9 of 45 different writers. Here, in the “global” task, we only keep the digit 8 as the normal class and sample the 10 digits from all of the other classes as anomalies. This results in one big normal cluster and global anomalies sparsely distributed. The resulting pen-global dataset has 16 dimensions and 809 instances including a large amount of anomalies (11.1%)." (cite from Goldstein, Markus, and Seiichi Uchida. "A comparative evaluation of unsupervised anomaly detection algorithms for multivariate data." PloS one 11.4 (2016): e0152173). This dataset is not the original dataset. The target variable "Target" is relabeled into "Normal" and "Anomaly".", "format": "ARFF", "uploader": "Minh-Anh Le", "uploader_id": 3768, "visibility": "public", "creator": "\"Markus Goldstein\"", "contributor": "\"\"F. Alimoglu (1996) Combining Multiple Classifiers for Pen-Based Handwritten Digit Recognition\",\"MSc Thesis\",\"Institute of Graduate Studies in Science and Engineering\",\"Bogazici University.\"\"", "date": "2017-09-22 19:50:55", "update_comment": null, "last_update": "2017-09-22 19:50:55", "licence": "Public", "status": "in_preparation", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/16787471\/phpHY9mJK", "default_target_attribute": "Target", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "Pen_global", ""This UCI dataset contains the hand- written digits 0–9 of 45 different writers. Here, in the “global” task, we only keep the digit 8 as the normal class and sample the 10 digits from all of the other classes as anomalies. This results in one big normal cluster and global anomalies sparsely distributed. The resulting pen-global dataset has 16 dimensions and 809 instances including a large amount of anomalies (11.1%)." (cite from Goldstein, Markus, and Seiichi Uchida. " ], "weight": 5 }, "qualities": { "NumberOfInstances": 809, "NumberOfFeatures": 17, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 16, "NumberOfSymbolicFeatures": 1, "ClassEntropy": 0.5036702283687591, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.021013597033374538, "MeanNominalAttDistinctValues": 2, "Quartile2KurtosisOfNumericAtts": -0.9449325986357755, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": -0.10622766355602077, "Quartile2MeansOfNumericAtts": 50.35599505562424, "MajorityClassPercentage": 88.87515451174289, "MeanStdDevOfNumericAtts": 28.984067953065548, "Quartile2MutualInformation": null, "MajorityClassSize": 719, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": -0.0736720455121458, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.419044439985841, "PercentageOfBinaryFeatures": 5.88235294117647, "Quartile2StdDevOfNumericAtts": 29.537437572773626, "MaxKurtosisOfNumericAtts": 2.2567249014179236, "MinMeansOfNumericAtts": 20.913473423980218, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 80.64276885043265, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": -0.5566396412441224, "MaxMutualInformation": null, "MinNominalAttDistinctValues": 2, "PercentageOfNumericFeatures": 94.11764705882352, "Quartile3MeansOfNumericAtts": 65.46260815822001, "MaxNominalAttDistinctValues": 2, "MinSkewnessOfNumericAtts": -1.3246115210888576, "PercentageOfSymbolicFeatures": 5.88235294117647, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 0.8891969889251996, "MinStdDevOfNumericAtts": 18.006316280331912, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 0.36599739496347167, "MaxStdDevOfNumericAtts": 38.53771346697613, "MinorityClassPercentage": 11.124845488257108, "Quartile1KurtosisOfNumericAtts": -1.160794124892091, "Quartile3StdDevOfNumericAtts": 31.865669718461973, "MeanAttributeEntropy": null, "MinorityClassSize": 90, "Quartile1MeansOfNumericAtts": 38.08220024721878, "StdvNominalAttDistinctValues": 0, "MeanKurtosisOfNumericAtts": -0.6344729615775281, "NumberOfBinaryFeatures": 1, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 51.5798825710754, "Quartile1SkewnessOfNumericAtts": -0.39478843686789045, "AutoCorrelation": 0.9727722772277227, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 27.060753237293483 }, "tags": [ { "tag": "derived", "uploader": "1" } ], "features": [ { "name": "Target", "index": "16", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "Normal", "Anomaly" ], [ [ "719", "0" ], [ "0", "90" ] ] ] }, { "name": "V1", "index": "0", "type": "numeric", "distinct": "101", "missing": "0", "min": "0", "max": "100", "mean": "52", "stdev": "31" }, { "name": "V2", "index": "1", "type": "numeric", "distinct": "84", "missing": "0", "min": "0", "max": "100", "mean": "81", "stdev": "18" }, { "name": "V3", "index": "2", "type": "numeric", "distinct": "99", "missing": "0", "min": "0", "max": "100", "mean": "40", "stdev": "28" }, { "name": "V4", "index": "3", "type": "numeric", "distinct": "76", "missing": "0", "min": "0", "max": "100", "mean": "79", "stdev": "21" }, { "name": "V5", "index": "4", "type": "numeric", "distinct": "101", "missing": "0", "min": "0", "max": "100", "mean": "54", "stdev": "35" }, { "name": "V6", "index": "5", "type": "numeric", "distinct": "101", "missing": "0", "min": "0", "max": "100", "mean": "55", "stdev": "29" }, { "name": "V7", "index": "6", "type": "numeric", "distinct": "101", "missing": "0", "min": "0", "max": "100", "mean": "49", "stdev": "30" }, { "name": "V8", "index": "7", "type": "numeric", "distinct": "97", "missing": "0", "min": "0", "max": "100", "mean": "29", "stdev": "30" }, { "name": "V9", "index": "8", "type": "numeric", "distinct": "99", "missing": "0", "min": "0", "max": "100", "mean": "37", "stdev": "30" }, { "name": "V10", "index": "9", "type": "numeric", "distinct": "79", "missing": "0", "min": "0", "max": "86", "mean": "21", "stdev": "21" }, { "name": "V11", "index": "10", "type": "numeric", "distinct": "101", "missing": "0", "min": "0", "max": "100", "mean": "46", "stdev": "36" }, { "name": "V12", "index": "11", "type": "numeric", "distinct": "93", "missing": "0", "min": "0", "max": "100", "mean": "36", "stdev": "27" }, { "name": "V13", "index": "12", "type": "numeric", "distinct": "91", "missing": "0", "min": "0", "max": "100", "mean": "66", "stdev": "29" }, { "name": "V14", "index": "13", "type": "numeric", "distinct": "99", "missing": "0", "min": "0", "max": "100", "mean": "64", "stdev": "32" }, { "name": "V15", "index": "14", "type": "numeric", "distinct": "96", "missing": "0", "min": "0", "max": "100", "mean": "43", "stdev": "39" }, { "name": "V16", "index": "15", "type": "numeric", "distinct": "94", "missing": "0", "min": "0", "max": "100", "mean": "73", "stdev": "28" } ], "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 }