{
    "data_id": "351",
    "name": "codrna",
    "exact_name": "codrna",
    "version": 1,
    "version_label": null,
    "description": "**Author**: Andrew V Uzilov\",\"Joshua M Keegan\",\"David H Mathews.  \n**Source**: [original](http:\/\/www.csie.ntu.edu.tw\/~cjlin\/libsvmtools\/datasets) -   \n**Please cite**: [AVU06a]\nAndrew V Uzilov, Joshua M Keegan, and David H Mathews. \nDetection of non-coding RNAs on the basis of predicted secondary structure formation free energy change. \nBMC Bioinformatics, 7(173), 2006.  \n\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: \n-join test, train and rest datasets   \n-normalize each file columnwise according to the following rules:    \n-If a column only contains one value (constant feature), it will set to zero and thus removed by sparsity.    \n-If a column contains two values (binary feature), the value occuring more often will be set to zero, the other to one.    \n-If a column contains more than two values (multinary\/real feature), the column is divided by its std deviation.    \n\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!",
    "format": "Sparse_ARFF",
    "uploader": "aydin demircioglu",
    "uploader_id": 167,
    "visibility": "public",
    "creator": "Andrew V Uzilov,Joshua M Keegan,David H Mathews.",
    "contributor": null,
    "date": "2014-08-29 18:49:36",
    "update_comment": null,
    "last_update": "2014-08-29 18:49:36",
    "licence": "Public",
    "status": "active",
    "error_message": null,
    "url": "https:\/\/www.openml.org\/data\/download\/52254\/php89ntbG",
    "default_target_attribute": "Y",
    "row_id_attribute": null,
    "ignore_attribute": null,
    "runs": 31,
    "suggest": {
        "input": [
            "codrna",
            "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 following rules: -If a column only con "
        ],
        "weight": 5
    },
    "qualities": {
        "NumberOfInstances": 488565,
        "NumberOfFeatures": 9,
        "NumberOfClasses": 2,
        "NumberOfMissingValues": 0,
        "NumberOfInstancesWithMissingValues": 0,
        "NumberOfNumericFeatures": 8,
        "NumberOfSymbolicFeatures": 1,
        "Quartile2KurtosisOfNumericAtts": 1.948168765373243,
        "REPTreeDepth2Kappa": 0.9130768163684673,
        "ClassEntropy": 0.9182958340544896,
        "kNN1NKappa": 0.87717697538361,
        "MajorityClassSize": 325710,
        "MinAttributeEntropy": null,
        "Quartile2MeansOfNumericAtts": 4.59430480864909,
        "REPTreeDepth3AUC": 0.9847433511509635,
        "DecisionStumpAUC": 0.7548859393984904,
        "MaxAttributeEntropy": null,
        "MinKurtosisOfNumericAtts": -1.166479394004767,
        "Quartile2MutualInformation": null,
        "REPTreeDepth3ErrRate": 0.03890372826543039,
        "DecisionStumpErrRate": 0.2650844821057587,
        "MaxKurtosisOfNumericAtts": 4.297153713295439,
        "MinMeansOfNumericAtts": -2.3466154092775757,
        "Quartile2SkewnessOfNumericAtts": 0.8918455614925215,
        "REPTreeDepth3Kappa": 0.9130768163684673,
        "DecisionStumpKappa": 0.4603775786136006,
        "MaxMeansOfNumericAtts": 6.358384566393448,
        "MinMutualInformation": null,
        "PercentageOfBinaryFeatures": 11.11111111111111,
        "Quartile2StdDevOfNumericAtts": 1.0000000019653663,
        "RandomTreeDepth1AUC": 0.9581028529676425,
        "Dimensionality": 1.8421295017039696e-5,
        "MaxMutualInformation": null,
        "MinNominalAttDistinctValues": 2,
        "PercentageOfInstancesWithMissingValues": 0,
        "Quartile3AttributeEntropy": null,
        "RandomTreeDepth1ErrRate": 0.03637182360586616,
        "EquivalentNumberOfAtts": null,
        "MaxNominalAttDistinctValues": 2,
        "MinSkewnessOfNumericAtts": -1.0845536319565714,
        "PercentageOfMissingValues": 0,
        "Quartile3KurtosisOfNumericAtts": 3.5859215930908794,
        "AutoCorrelation": 0.9999774850377842,
        "RandomTreeDepth1Kappa": 0.9179889051957283,
        "J48.00001.AUC": 0.973580269998406,
        "MaxSkewnessOfNumericAtts": 1.645472676057296,
        "MinStdDevOfNumericAtts": 0.9999999695264041,
        "PercentageOfNumericFeatures": 88.88888888888889,
        "Quartile3MeansOfNumericAtts": 5.641623709844637,
        "CfsSubsetEval_DecisionStumpAUC": 0.789668876519815,
        "RandomTreeDepth2AUC": 0.9581028529676425,
        "J48.00001.ErrRate": 0.035305435305435305,
        "MaxStdDevOfNumericAtts": 1.0000000307172139,
        "MinorityClassPercentage": 33.33333333333333,
        "PercentageOfSymbolicFeatures": 11.11111111111111,
        "Quartile3MutualInformation": null,
        "CfsSubsetEval_DecisionStumpErrRate": 0.24564592224166693,
        "RandomTreeDepth2ErrRate": 0.03637182360586616,
        "J48.00001.Kappa": 0.9210934414555635,
        "MeanAttributeEntropy": null,
        "MinorityClassSize": 162855,
        "Quartile1AttributeEntropy": null,
        "Quartile3SkewnessOfNumericAtts": 1.466877889549969,
        "CfsSubsetEval_DecisionStumpKappa": 0.44116460128641316,
        "RandomTreeDepth2Kappa": 0.9179889051957283,
        "J48.0001.AUC": 0.973580269998406,
        "MeanKurtosisOfNumericAtts": 2.0082464917834963,
        "NaiveBayesAUC": 0.8209506262888236,
        "Quartile1KurtosisOfNumericAtts": 1.1300960254514656,
        "Quartile3StdDevOfNumericAtts": 1.0000000228919612,
        "CfsSubsetEval_NaiveBayesAUC": 0.789668876519815,
        "RandomTreeDepth3AUC": 0.9581028529676425,
        "J48.0001.ErrRate": 0.035305435305435305,
        "MeanMeansOfNumericAtts": 4.039429822081905,
        "NaiveBayesErrRate": 0.2553989745479107,
        "Quartile1MeansOfNumericAtts": 4.032599600505045,
        "REPTreeDepth1AUC": 0.9847433511509635,
        "CfsSubsetEval_NaiveBayesErrRate": 0.24564592224166693,
        "RandomTreeDepth3ErrRate": 0.03637182360586616,
        "J48.0001.Kappa": 0.9210934414555635,
        "MeanMutualInformation": null,
        "NaiveBayesKappa": 0.36553803598940354,
        "Quartile1MutualInformation": null,
        "REPTreeDepth1ErrRate": 0.03890372826543039,
        "CfsSubsetEval_NaiveBayesKappa": 0.44116460128641316,
        "RandomTreeDepth3Kappa": 0.9179889051957283,
        "J48.001.AUC": 0.973580269998406,
        "MeanNoiseToSignalRatio": null,
        "NumberOfBinaryFeatures": 1,
        "Quartile1SkewnessOfNumericAtts": -0.8986102075705807,
        "REPTreeDepth1Kappa": 0.9130768163684673,
        "CfsSubsetEval_kNN1NAUC": 0.789668876519815,
        "StdvNominalAttDistinctValues": 0,
        "J48.001.ErrRate": 0.035305435305435305,
        "MeanNominalAttDistinctValues": 2,
        "Quartile1StdDevOfNumericAtts": 0.9999999777120969,
        "REPTreeDepth2AUC": 0.9847433511509635,
        "CfsSubsetEval_kNN1NErrRate": 0.24564592224166693,
        "kNN1NAUC": 0.9315012774029311,
        "J48.001.Kappa": 0.9210934414555635,
        "MeanSkewnessOfNumericAtts": 0.41668060730399237,
        "Quartile2AttributeEntropy": null,
        "REPTreeDepth2ErrRate": 0.03890372826543039,
        "CfsSubsetEval_kNN1NKappa": 0.44116460128641316,
        "kNN1NErrRate": 0.05437147564807139,
        "MajorityClassPercentage": 66.66666666666666,
        "MeanStdDevOfNumericAtts": 1.0000000011526435
    },
    "tags": [
        {
            "uploader": "38960",
            "tag": "Life Science"
        },
        {
            "uploader": "38960",
            "tag": "Machine Learning"
        }
    ],
    "features": [
        {
            "name": "Y",
            "index": "0",
            "type": "nominal",
            "distinct": "2",
            "missing": "0",
            "target": "1",
            "distr": [
                [
                    "1",
                    "-1"
                ],
                [
                    [
                        "162855",
                        "0"
                    ],
                    [
                        "0",
                        "325710"
                    ]
                ]
            ]
        },
        {
            "name": "X1",
            "index": "1",
            "type": "numeric",
            "distinct": "1327",
            "missing": "0",
            "min": "-11",
            "max": "0",
            "mean": "-2",
            "stdev": "1"
        },
        {
            "name": "X2",
            "index": "2",
            "type": "numeric",
            "distinct": "43",
            "missing": "0",
            "min": "3",
            "max": "7",
            "mean": "4",
            "stdev": "1"
        },
        {
            "name": "X3",
            "index": "3",
            "type": "numeric",
            "distinct": "228",
            "missing": "0",
            "min": "2",
            "max": "8",
            "mean": "4",
            "stdev": "1"
        },
        {
            "name": "X4",
            "index": "4",
            "type": "numeric",
            "distinct": "228",
            "missing": "0",
            "min": "2",
            "max": "9",
            "mean": "5",
            "stdev": "1"
        },
        {
            "name": "X5",
            "index": "5",
            "type": "numeric",
            "distinct": "220",
            "missing": "0",
            "min": "2",
            "max": "8",
            "mean": "6",
            "stdev": "1"
        },
        {
            "name": "X6",
            "index": "6",
            "type": "numeric",
            "distinct": "228",
            "missing": "0",
            "min": "2",
            "max": "10",
            "mean": "4",
            "stdev": "1"
        },
        {
            "name": "X7",
            "index": "7",
            "type": "numeric",
            "distinct": "228",
            "missing": "0",
            "min": "2",
            "max": "9",
            "mean": "5",
            "stdev": "1"
        },
        {
            "name": "X8",
            "index": "8",
            "type": "numeric",
            "distinct": "220",
            "missing": "0",
            "min": "2",
            "max": "9",
            "mean": "6",
            "stdev": "1"
        }
    ],
    "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
}