DEVELOPMENT... { "data_id": "1241", "name": "codrnaNorm", "exact_name": "codrnaNorm", "version": 1, "version_label": null, "description": "Normalized form of codrna (351)\r\n\r\n**Author**: Andrew V Uzilov\",\"Joshua M Keegan\",\"David H Mathews. \r\n**Source**: [original](http:\/\/www.csie.ntu.edu.tw\/~cjlin\/libsvmtools\/datasets) - \r\n**Please cite**: [AVU06a]\r\nAndrew V Uzilov, Joshua M Keegan, and David H Mathews. \r\nDetection of non-coding RNAs on the basis of predicted secondary structure formation free energy change. \r\nBMC Bioinformatics, 7(173), 2006. \r\n\r\nThis is the cod-rna dataset, retrieved 2014-11-14 from the libSVM site. Additional to the preprocessing done there (see LibSVM site for details), this dataset was created as follows: \r\n-join test, train and rest datasets \r\n-normalize each file columnwise according to the following rules: \r\n-If a column only contains one value (constant feature), it will set to zero and thus removed by sparsity. \r\n-If a column contains two values (binary feature), the value occuring more often will be set to zero, the other to one. \r\n-If a column contains more than two values (multinary\/real feature), the column is divided by its std deviation. \r\n\r\nNOTE: please keep in mind that cod-rna has many duplicated data points, within each file (train,test,rest) and also accross these files. these duplicated points have not been removed!\r\n\r\n", "format": "Sparse_ARFF", "uploader": "unknown", "uploader_id": 1, "visibility": "public", "creator": null, "contributor": null, "date": "2015-02-14 02:50:40", "update_comment": null, "last_update": "2015-02-14 02:50:40", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/522888\/codrnaNorm.arff", "default_target_attribute": "codrna_Y", "row_id_attribute": null, "ignore_attribute": null, "runs": 309, "suggest": { "input": [ "codrnaNorm", "Normalized form of codrna (351) Andrew V Uzilov, Joshua M Keegan, and David H Mathews. Detection of non-coding RNAs on the basis of predicted secondary structure formation free energy change. BMC Bioinformatics, 7(173), 2006. This is the cod-rna dataset, retrieved 2014-11-14 from the libSVM site. Additional to the preprocessing done there (see LibSVM site for details), this dataset was created as follows: -join test, train and rest datasets -normalize each file columnwise according to the follow " ], "weight": 5 }, "qualities": { "NumberOfInstances": 488565, "NumberOfFeatures": 9, "NumberOfClasses": 2, "NumberOfMissingValues": 0, "NumberOfInstancesWithMissingValues": 0, "NumberOfNumericFeatures": 8, "NumberOfSymbolicFeatures": 1, "AutoCorrelation": 0.5552476236480789, "CfsSubsetEval_DecisionStumpAUC": 0.7752703142174981, "CfsSubsetEval_DecisionStumpErrRate": 0.24510761106505788, "CfsSubsetEval_DecisionStumpKappa": 0.45920147643914433, "CfsSubsetEval_NaiveBayesAUC": 0.7752703142174981, "CfsSubsetEval_NaiveBayesErrRate": 0.24510761106505788, "CfsSubsetEval_NaiveBayesKappa": 0.45920147643914433, "CfsSubsetEval_kNN1NAUC": 0.7752703142174981, "CfsSubsetEval_kNN1NErrRate": 0.24510761106505788, "CfsSubsetEval_kNN1NKappa": 0.45920147643914433, "ClassEntropy": 0.9182958340544896, "DecisionStumpAUC": 0.7540330261244507, "DecisionStumpErrRate": 0.26571899337856786, "DecisionStumpKappa": 0.4598391429835523, "Dimensionality": 1.8421295017039696e-5, "EquivalentNumberOfAtts": null, "J48.00001.AUC": 0.9731723657940493, "J48.00001.ErrRate": 0.03539958859107795, "J48.00001.Kappa": 0.9208494591341571, "J48.0001.AUC": 0.9731723657940493, "J48.0001.ErrRate": 0.03539958859107795, "J48.0001.Kappa": 0.9208494591341571, "J48.001.AUC": 0.9731723657940493, "J48.001.ErrRate": 0.03539958859107795, "J48.001.Kappa": 0.9208494591341571, "MajorityClassPercentage": 66.66666666666666, "MajorityClassSize": 325710, "MaxAttributeEntropy": null, "MaxKurtosisOfNumericAtts": 4.297151636317367, "MaxMeansOfNumericAtts": 0.7813438706640877, "MaxMutualInformation": null, "MaxNominalAttDistinctValues": 2, "MaxSkewnessOfNumericAtts": 1.6454722514215625, "MaxStdDevOfNumericAtts": 0.2984731067341398, "MeanAttributeEntropy": null, "MeanKurtosisOfNumericAtts": 2.008245877424671, "MeanMeansOfNumericAtts": 0.4709931774523348, "MeanMutualInformation": null, "MeanNoiseToSignalRatio": null, "MeanNominalAttDistinctValues": 2, "MeanSkewnessOfNumericAtts": 0.41668060167671883, "MeanStdDevOfNumericAtts": 0.1608717658315541, "MinAttributeEntropy": null, "MinKurtosisOfNumericAtts": -1.1664793375781841, "MinMeansOfNumericAtts": 0.3066706468146511, "MinMutualInformation": null, "MinNominalAttDistinctValues": 2, "MinSkewnessOfNumericAtts": -1.084552706018174, "MinStdDevOfNumericAtts": 0.09317936604191648, "MinorityClassPercentage": 33.33333333333333, "MinorityClassSize": 162855, "NaiveBayesAUC": 0.8207851261773921, "NaiveBayesErrRate": 0.25530686807282554, "NaiveBayesKappa": 0.36572277046473856, "NumberOfBinaryFeatures": 1, "PercentageOfBinaryFeatures": 11.11111111111111, "PercentageOfInstancesWithMissingValues": 0, "PercentageOfMissingValues": 0, "PercentageOfNumericFeatures": 88.88888888888889, "PercentageOfSymbolicFeatures": 11.11111111111111, "Quartile1AttributeEntropy": null, "Quartile1KurtosisOfNumericAtts": 1.1300959755347857, "Quartile1MeansOfNumericAtts": 0.3157025961960024, "Quartile1MutualInformation": null, "Quartile1SkewnessOfNumericAtts": -0.8986100236476178, "Quartile1StdDevOfNumericAtts": 0.13712425024405978, "Quartile2AttributeEntropy": null, "Quartile2KurtosisOfNumericAtts": 1.9481686322071594, "Quartile2MeansOfNumericAtts": 0.377065957809094, "Quartile2MutualInformation": null, "Quartile2SkewnessOfNumericAtts": 0.8918457702480338, "Quartile2StdDevOfNumericAtts": 0.1502212213929145, "Quartile3AttributeEntropy": null, "Quartile3KurtosisOfNumericAtts": 3.585921009468714, "Quartile3MeansOfNumericAtts": 0.6474900833809216, "Quartile3MutualInformation": null, "Quartile3SkewnessOfNumericAtts": 1.4668772213687997, "Quartile3StdDevOfNumericAtts": 0.15835603615085453, "REPTreeDepth1AUC": 0.9843994491310175, "REPTreeDepth1ErrRate": 0.039466601168728827, "REPTreeDepth1Kappa": 0.9118553260740375, "REPTreeDepth2AUC": 0.9843994491310175, "REPTreeDepth2ErrRate": 0.039466601168728827, "REPTreeDepth2Kappa": 0.9118553260740375, "REPTreeDepth3AUC": 0.9843994491310175, "REPTreeDepth3ErrRate": 0.039466601168728827, "REPTreeDepth3Kappa": 0.9118553260740375, "RandomTreeDepth1AUC": 0.9582343845545545, "RandomTreeDepth1ErrRate": 0.03627971713078096, "RandomTreeDepth1Kappa": 0.9181964607950674, "RandomTreeDepth2AUC": 0.9582343845545545, "RandomTreeDepth2ErrRate": 0.03627971713078096, "RandomTreeDepth2Kappa": 0.9181964607950674, "RandomTreeDepth3AUC": 0.9582343845545545, "RandomTreeDepth3ErrRate": 0.03627971713078096, "RandomTreeDepth3Kappa": 0.9181964607950674, "StdvNominalAttDistinctValues": 0, "kNN1NAUC": 0.9316298655598791, "kNN1NErrRate": 0.05422001166682018, "kNN1NKappa": 0.8775176163790711 }, "tags": [ { "tag": "study_16", "uploader": "1" } ], "features": [ { "name": "codrna_Y", "index": "8", "type": "nominal", "distinct": "2", "missing": "0", "target": "1", "distr": [ [ "1", "-1" ], [ [ "162855", "0" ], [ "0", "325710" ] ] ] }, { "name": "codrna_X1", "index": "0", "type": "numeric", "distinct": "1327", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "codrna_X2", "index": "1", "type": "numeric", "distinct": "43", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "codrna_X3", "index": "2", "type": "numeric", "distinct": "228", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "codrna_X4", "index": "3", "type": "numeric", "distinct": "228", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "codrna_X5", "index": "4", "type": "numeric", "distinct": "220", "missing": "0", "min": "0", "max": "1", "mean": "1", "stdev": "0" }, { "name": "codrna_X6", "index": "5", "type": "numeric", "distinct": "228", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "codrna_X7", "index": "6", "type": "numeric", "distinct": "228", "missing": "0", "min": "0", "max": "1", "mean": "0", "stdev": "0" }, { "name": "codrna_X8", "index": "7", "type": "numeric", "distinct": "220", "missing": "0", "min": "0", "max": "1", "mean": "1", "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 }