{ "data_id": "40906", "name": "Aloi", "exact_name": "Aloi", "version": 2, "version_label": null, "description": "**Author**: Markus Goldstein \r\nE. Schubert\",\"R. Wojdanowski\",\"A. Zimek\",\"H.-P. Kriegel\",\"On Evaluation of Outlier Rankings and Outlier Scores\",\"In Proceedings of the 12th SIAM International Conference on Data Mining (SDM)\",\"Anaheim\",\"CA\",\"2012. \r\n**Source**: [original](https:\/\/dataverse.harvard.edu\/dataset.xhtml?persistentId=doi:10.7910\/DVN\/OPQMVF) - Date unknown \r\n**Please cite**: "J. M. Geusebroek, G. J. Burghouts, and A. W. M. Smeulders, The Amsterdam \r\nlibrary of object images, Int. J. Comput. Vision, 61(1), 103-112, January, \r\n2005." \r\n\r\n"The aloi dataset is derived from the “Amsterdam Library of Object Images” collection (see citation request). The original dataset contains about 110 images of 1000 small objects taken under different light conditions and viewing angles. From the original images, a 27 dimensional feature vector was extracted using HSB color histograms. Some objects were chosen as anomalies and the data was down-sampled such that the resulting dataset contains 50,000 instances including 3.02% anomalies. (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 from the provided URL. The target variable is renamed into "Target" and relabeled into "Normal" and "Anomaly".", "format": "ARFF", "uploader": "Minh-Anh Le", "uploader_id": 3768, "visibility": "public", "creator": "\"Markus Goldstein\"", "contributor": "\"\"E. Schubert\",\"R. Wojdanowski\",\"A. Zimek\",\"H.-P. Kriegel\",\"On Evaluation of Outlier Rankings and Outlier Scores\",\"In Proceedings of the 12th SIAM International Conference on Data Mining (SDM)\",\"Anaheim\",\"CA\",\"2012.\"\"", "date": "2017-09-22 19:46:19", "update_comment": null, "last_update": "2017-09-22 19:46:19", "licence": "Public", "status": "in_preparation", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/16787469\/phpYaqmhm", "default_target_attribute": "Target", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "Aloi", "E. Schubert\",\"R. Wojdanowski\",\"A. Zimek\",\"H.-P. Kriegel\",\"On Evaluation of Outlier Rankings and Outlier Scores\",\"In Proceedings of the 12th SIAM International Conference on Data Mining (SDM)\",\"Anaheim\",\"CA\",\"2012. library of object images, Int. J. Comput. Vision, 61(1), 103-112, January, 2005." "The aloi dataset is derived from the “Amsterdam Library of Object Images” collection (see citation request). The original dataset contains about 110 images of 1000 small objects tak " ], "weight": 5 }, "qualities": { "NumberOfInstances": 49999, "NumberOfFeatures": 28, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 27, "NumberOfSymbolicFeatures": 1, "ClassEntropy": 0.19509648464300827, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.0005600112002240045, "MeanNominalAttDistinctValues": 2, "Quartile2KurtosisOfNumericAtts": 234.40835095025705, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 20.66838215413329, "Quartile2MeansOfNumericAtts": 0.0008101731316309865, "MajorityClassPercentage": 96.98593971879438, "MeanStdDevOfNumericAtts": 0.011802856324325225, "Quartile2MutualInformation": null, "MajorityClassSize": 48492, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 13.313574907906158, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": 1.105657885585917, "PercentageOfBinaryFeatures": 3.571428571428571, "Quartile2StdDevOfNumericAtts": 0.004881111134319973, "MaxKurtosisOfNumericAtts": 30995.609836413983, "MinMeansOfNumericAtts": 2.145496468956765e-6, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 0.8998692838259252, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 661.7662698461936, "MaxMutualInformation": null, "MinNominalAttDistinctValues": 2, "PercentageOfNumericFeatures": 96.42857142857143, "Quartile3MeansOfNumericAtts": 0.008979558750607906, "MaxNominalAttDistinctValues": 2, "MinSkewnessOfNumericAtts": -1.137984955552159, "PercentageOfSymbolicFeatures": 3.571428571428571, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 160.05167157744597, "MinStdDevOfNumericAtts": 9.50254833925126e-5, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 21.721830652755408, "MaxStdDevOfNumericAtts": 0.08088240344026507, "MinorityClassPercentage": 3.014060281205624, "Quartile1KurtosisOfNumericAtts": 31.509630561233447, "Quartile3StdDevOfNumericAtts": 0.017662716414159226, "MeanAttributeEntropy": null, "MinorityClassSize": 1507, "Quartile1MeansOfNumericAtts": 0.0001415275339650167, "StdvNominalAttDistinctValues": 0, "MeanKurtosisOfNumericAtts": 1768.0791428576638, "NumberOfBinaryFeatures": 1, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 0.037037037037037014, "Quartile1SkewnessOfNumericAtts": 4.508484065530033, "AutoCorrelation": 0.999979999199968, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.0015259499974248525 }, "tags": [], "features": [ { "name": "Target", "index": "27", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "Normal", "Anomaly" ], [ [ "48492", "0" ], [ "0", "1507" ] ] ] }, { "name": "X0.8728117766203703", "index": "0", "type": "numeric", "distinct": "39004", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "X4.521122685185185E.6", "index": "1", "type": "numeric", "distinct": "6027", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X0.0", "index": "2", "type": "numeric", "distinct": "1103", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X3.616898148148148E.5", "index": "3", "type": "numeric", "distinct": "5337", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X0.0.1", "index": "4", "type": "numeric", "distinct": "4592", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X0.0.2", "index": "5", "type": "numeric", "distinct": "2396", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X0.0.3", "index": "6", "type": "numeric", "distinct": "551", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X0.0.4", "index": "7", "type": "numeric", "distinct": "744", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X0.0.5", "index": "8", "type": "numeric", "distinct": "889", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X0.05032687717013889", "index": "9", "type": "numeric", "distinct": "19960", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X4.521122685185185E.6.1", "index": "10", "type": "numeric", "distinct": "1914", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X0.0.6", "index": "11", "type": "numeric", "distinct": "303", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X0.005631058304398148", "index": "12", "type": "numeric", "distinct": "14611", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X0.004163953993055556", "index": "13", "type": "numeric", "distinct": "13334", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X0.0.7", "index": "14", "type": "numeric", "distinct": "2910", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X2.2605613425925925E.6", "index": "15", "type": "numeric", "distinct": "1873", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X2.0345052083333332E.5", "index": "16", "type": "numeric", "distinct": "2435", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X0.0.8", "index": "17", "type": "numeric", "distinct": "3230", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X0.01421214916087963", "index": "18", "type": "numeric", "distinct": "9045", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X1.0398582175925926E.4", "index": "19", "type": "numeric", "distinct": "1107", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X0.0.9", "index": "20", "type": "numeric", "distinct": "101", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X0.025490089699074073", "index": "21", "type": "numeric", "distinct": "12626", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X0.004937065972222222", "index": "22", "type": "numeric", "distinct": "8464", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X1.1302806712962962E.5", "index": "23", "type": "numeric", "distinct": "1085", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X5.425347222222222E.5", "index": "24", "type": "numeric", "distinct": "8950", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X0.006804289641203704", "index": "25", "type": "numeric", "distinct": "13233", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "X0.015385380497685185", "index": "26", "type": "numeric", "distinct": "15994", "missing": "0", "min": "0", "max": "0", "mean": "0", "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 }