{ "data_id": "40886", "name": "Annthyroid", "exact_name": "Annthyroid", "version": 1, "version_label": null, "description": "The original thyroid disease (ann-thyroid) dataset from UCI machine learning repository is a classification dataset, which is suited for training ANNs. It has 3772 training instances and 3428 testing instances. It has 15 categorical and 6 real attributes. The problem is to determine whether a patient referred to the clinic is hypothyroid. Therefore three classes are built: normal (not hypothyroid), hyperfunction and subnormal functioning. For outlier detection, both training and testing instances are used, with only 6 real attributes. The hyperfunction and subnormal classes are treated as outlier class and the other one as inliers class. This dataset is not the original dataset. The target variable "Target" is relabeled into "Normal" and "Anomaly" and the categorial variables are deleted.", "format": "ARFF", "uploader": "Minh-Anh Le", "uploader_id": 3768, "visibility": "public", "creator": null, "contributor": null, "date": "2017-09-22 16:50:21", "update_comment": null, "last_update": "2017-09-22 16:50:21", "licence": "Public", "status": "in_preparation", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/16787449\/phpgtTkZa", "default_target_attribute": "Target", "row_id_attribute": null, "ignore_attribute": null, "runs": 0, "suggest": { "input": [ "Annthyroid", "The original thyroid disease (ann-thyroid) dataset from UCI machine learning repository is a classification dataset, which is suited for training ANNs. It has 3772 training instances and 3428 testing instances. It has 15 categorical and 6 real attributes. The problem is to determine whether a patient referred to the clinic is hypothyroid. Therefore three classes are built: normal (not hypothyroid), hyperfunction and subnormal functioning. For outlier detection, both training and testing instance " ], "weight": 5 }, "qualities": { "NumberOfInstances": 7200, "NumberOfFeatures": 7, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 6, "NumberOfSymbolicFeatures": 1, "ClassEntropy": 0.3812838896631388, "MeanNoiseToSignalRatio": null, "Quartile2AttributeEntropy": null, "Dimensionality": 0.0009722222222222222, "MeanNominalAttDistinctValues": 2, "Quartile2KurtosisOfNumericAtts": 16.90781943712377, "EquivalentNumberOfAtts": null, "MeanSkewnessOfNumericAtts": 3.8249341750077632, "Quartile2MeansOfNumericAtts": 0.10363402430555557, "MajorityClassPercentage": 92.58333333333333, "MeanStdDevOfNumericAtts": 0.051823080031399696, "Quartile2MutualInformation": null, "MajorityClassSize": 6666, "MinAttributeEntropy": null, "Quartile2SkewnessOfNumericAtts": 1.9504937087205372, "MaxAttributeEntropy": null, "MinKurtosisOfNumericAtts": -0.8762368326035763, "PercentageOfBinaryFeatures": 14.285714285714285, "Quartile2StdDevOfNumericAtts": 0.0294739246949774, "MaxKurtosisOfNumericAtts": 261.9477142845789, "MinMeansOfNumericAtts": 0.004861402777777778, "PercentageOfInstancesWithMissingValues": 0, "Quartile3AttributeEntropy": null, "MaxMeansOfNumericAtts": 0.5205181527777778, "MinMutualInformation": null, "PercentageOfMissingValues": 0, "Quartile3KurtosisOfNumericAtts": 99.88244897108726, "MaxMutualInformation": null, "MinNominalAttDistinctValues": 2, "PercentageOfNumericFeatures": 85.71428571428571, "Quartile3MeansOfNumericAtts": 0.21504055173611114, "MaxNominalAttDistinctValues": 2, "MinSkewnessOfNumericAtts": -0.212572347692324, "PercentageOfSymbolicFeatures": 14.285714285714285, "Quartile3MutualInformation": null, "MaxSkewnessOfNumericAtts": 14.525564126070142, "MinStdDevOfNumericAtts": 0.007539165112330409, "Quartile1AttributeEntropy": null, "Quartile3SkewnessOfNumericAtts": 6.247151069401445, "MaxStdDevOfNumericAtts": 0.18926936479888193, "MinorityClassPercentage": 7.416666666666667, "Quartile1KurtosisOfNumericAtts": 3.452503856371688, "Quartile3StdDevOfNumericAtts": 0.07439052151125479, "MeanAttributeEntropy": null, "MinorityClassSize": 534, "Quartile1MeansOfNumericAtts": 0.016197934027777774, "StdvNominalAttDistinctValues": 0, "MeanKurtosisOfNumericAtts": 57.60720460202939, "NumberOfBinaryFeatures": 1, "Quartile1MutualInformation": null, "MeanMeansOfNumericAtts": 0.14430651111111112, "Quartile1SkewnessOfNumericAtts": 0.8828162658637742, "AutoCorrelation": 0.8647034310320878, "MeanMutualInformation": null, "Quartile1StdDevOfNumericAtts": 0.016198186631971565 }, "tags": [], "features": [ { "name": "Target", "index": "6", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "Normal", "Anomaly" ], [ [ "6666", "0" ], [ "0", "534" ] ] ] }, { "name": "V1", "index": "0", "type": "numeric", "distinct": "98", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "V2", "index": "1", "type": "numeric", "distinct": "326", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V3", "index": "2", "type": "numeric", "distinct": "85", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V4", "index": "3", "type": "numeric", "distinct": "272", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "V5", "index": "4", "type": "numeric", "distinct": "161", "missing": "0", "min": "0", "max": "0", "mean": "0", "stdev": "0" }, { "name": "V6", "index": "5", "type": "numeric", "distinct": "466", "missing": "0", "min": "0", "max": "1", "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 }