DEVELOPMENT... { "data_id": "163", "name": "lung-cancer", "exact_name": "lung-cancer", "version": 1, "version_label": "1", "description": "**Author**: \n**Source**: Unknown - \n**Please cite**: \n\n1. Title: Lung Cancer Data\n \n 2. Source Information:\n \t- Data was published in : \n \t Hong, Z.Q. and Yang, J.Y. \"Optimal Discriminant Plane for a Small\n \t Number of Samples and Design Method of Classifier on the Plane\",\n \t Pattern Recognition, Vol. 24, No. 4, pp. 317-324, 1991.\n \t- Donor: Stefan Aeberhard, stefan@coral.cs.jcu.edu.au\n \t- Date : May, 1992\n \n 3. Past Usage:\n \t- Hong, Z.Q. and Yang, J.Y. \"Optimal Discriminant Plane for a Small\n Number of Samples and Design Method of Classifier on the Plane\",\n Pattern Recognition, Vol. 24, No. 4, pp. 317-324, 1991.\n \t- Aeberhard, S., Coomans, D, De Vel, O. \"Comparisons of \n \t Classification Methods in High Dimensional Settings\", \n \t submitted to Technometrics.\n \t- Aeberhard, S., Coomans, D, De Vel, O. \"The Dangers of \n \t Bias in High Dimensional Settings\", submitted to\n \t pattern Recognition.\n \n 4. Relevant Information:\n \t- This data was used by Hong and Young to illustrate the \n \t power of the optimal discriminant plane even in ill-posed\n \t settings. Applying the KNN method in the resulting plane\t\n \t gave 77% accuracy. However, these results are strongly\n \t biased (See Aeberhard's second ref. above, or email to\n \t stefan@coral.cs.jcu.edu.au). Results obtained by\n \t Aeberhard et al. are : \n \t RDA : 62.5%, KNN 53.1%, Opt. Disc. Plane 59.4%\n \n \t The data described 3 types of pathological lung cancers.\n \t The Authors give no information on the individual\n \t variables nor on where the data was originally used.\n \n - In the original data 4 values for the fifth attribute were -1.\n These values have been changed to ? (unknown). (*)\n - In the original data 1 value for the 39 attribute was 4. This\n value has been changed to ? (unknown). (*)\n \n \t \n 5. Number of Instances: 32\n \n 6. Number of Attributes: 57 (1 class attribute, 56 predictive)\n \n 7. Attribute Information:\n \n \tattribute 1 is the class label.\n \t\n \t- All predictive attributes are nominal, taking on integer \n \t values 0-3\n \n 8. Missing Attribute Values: Attributes 5 and 39 (*)\n \n 9. Class Distribution:\n \t- 3 classes, \n \t\t1.)\t9 observations\n \t\t2.)\t13 \"\n \t\t3.)\t10 \"\n \n\n Information about the dataset\n CLASSTYPE: nominal\n CLASSINDEX: first", "format": "ARFF", "uploader": "Jason ", "uploader_id": 1, "visibility": "public", "creator": null, "contributor": null, "date": "2014-04-23 13:11:37", "update_comment": null, "last_update": "2014-04-23 13:11:37", "licence": "Public", "status": "active", "error_message": null, "url": "https:\/\/www.openml.org\/data\/download\/3584\/dataset_105_lung-cancer.arff", "default_target_attribute": "class", "row_id_attribute": null, "ignore_attribute": null, "runs": 1238, "suggest": { "input": [ "lung-cancer", "1. Title: Lung Cancer Data 2. Source Information: - Data was published in : Hong, Z.Q. and Yang, J.Y. \"Optimal Discriminant Plane for a Small Number of Samples and Design Method of Classifier on the Plane\", Pattern Recognition, Vol. 24, No. 4, pp. 317-324, 1991. - Donor: Stefan Aeberhard, stefan@coral.cs.jcu.edu.au - Date : May, 1992 3. Past Usage: - Hong, Z.Q. and Yang, J.Y. \"Optimal Discriminant Plane for a Small Number of Samples and Design Method of Classifier on the Plane\", Pattern Recognit " ], "weight": 5 }, "qualities": { "NumberOfInstances": 32, "NumberOfFeatures": 57, "NumberOfClasses": 3, "NumberOfMissingValues": 5, "NumberOfInstancesWithMissingValues": 5, "NumberOfNumericFeatures": 0, "NumberOfSymbolicFeatures": 57, "AutoCorrelation": 0.9354838709677419, "CfsSubsetEval_DecisionStumpAUC": 0.5504505148741419, "CfsSubsetEval_DecisionStumpErrRate": 0.625, "CfsSubsetEval_DecisionStumpKappa": 0.05604719764011799, "CfsSubsetEval_NaiveBayesAUC": 0.6473534688995215, "CfsSubsetEval_NaiveBayesErrRate": 0.5, "CfsSubsetEval_NaiveBayesKappa": 0.22658610271903323, "CfsSubsetEval_kNN1NAUC": 0.6280408128770543, "CfsSubsetEval_kNN1NErrRate": 0.5625, "CfsSubsetEval_kNN1NKappa": 0.13122171945701358, "ClassEntropy": 1.5670524281972305, "DecisionStumpAUC": 0.5504505148741419, "DecisionStumpErrRate": 0.625, "DecisionStumpKappa": 0.05604719764011799, "Dimensionality": 1.78125, "EquivalentNumberOfAtts": 10.217733049754147, "J48.00001.AUC": 0.5454480445184107, "J48.00001.ErrRate": 0.59375, "J48.00001.Kappa": 0.01935483870967742, "J48.0001.AUC": 0.5466880980861244, "J48.0001.ErrRate": 0.59375, "J48.0001.Kappa": 0.01935483870967742, "J48.001.AUC": 0.5940604197004369, "J48.001.ErrRate": 0.5625, "J48.001.Kappa": 0.12195121951219512, "MajorityClassPercentage": 40.625, "MajorityClassSize": 13, "MaxAttributeEntropy": 1.8075167455986105, "MaxKurtosisOfNumericAtts": null, "MaxMeansOfNumericAtts": null, "MaxMutualInformation": 0.46668169862682, "MaxNominalAttDistinctValues": 4, "MaxSkewnessOfNumericAtts": null, "MaxStdDevOfNumericAtts": null, "MeanAttributeEntropy": 1.0665622249946334, "MeanKurtosisOfNumericAtts": null, "MeanMeansOfNumericAtts": null, "MeanMutualInformation": 0.15336595902110947, "MeanNoiseToSignalRatio": 5.954360875139381, "MeanNominalAttDistinctValues": 2.807017543859649, "MeanSkewnessOfNumericAtts": null, "MeanStdDevOfNumericAtts": null, "MinAttributeEntropy": 0.20062232431271465, "MinKurtosisOfNumericAtts": null, "MinMeansOfNumericAtts": null, "MinMutualInformation": 0.00505028512406, "MinNominalAttDistinctValues": 2, "MinSkewnessOfNumericAtts": null, "MinStdDevOfNumericAtts": null, "MinorityClassPercentage": 28.125, "MinorityClassSize": 9, "NaiveBayesAUC": 0.6909487466195132, "NaiveBayesErrRate": 0.4375, "NaiveBayesKappa": 0.3392330383480826, "NumberOfBinaryFeatures": 13, "PercentageOfBinaryFeatures": 22.807017543859647, "PercentageOfInstancesWithMissingValues": 15.625, "PercentageOfMissingValues": 0.2741228070175438, "PercentageOfNumericFeatures": 0, "PercentageOfSymbolicFeatures": 100, "Quartile1AttributeEntropy": 0.8227457027014425, "Quartile1KurtosisOfNumericAtts": null, "Quartile1MeansOfNumericAtts": null, "Quartile1MutualInformation": 0.09299463140802999, "Quartile1SkewnessOfNumericAtts": null, "Quartile1StdDevOfNumericAtts": null, "Quartile2AttributeEntropy": 1.0555823748247535, "Quartile2KurtosisOfNumericAtts": null, "Quartile2MeansOfNumericAtts": null, "Quartile2MutualInformation": 0.117069797372545, "Quartile2SkewnessOfNumericAtts": null, "Quartile2StdDevOfNumericAtts": null, "Quartile3AttributeEntropy": 1.387082418920817, "Quartile3KurtosisOfNumericAtts": null, "Quartile3MeansOfNumericAtts": null, "Quartile3MutualInformation": 0.208345204047035, "Quartile3SkewnessOfNumericAtts": null, "Quartile3StdDevOfNumericAtts": null, "REPTreeDepth1AUC": 0.4759725400457666, "REPTreeDepth1ErrRate": 0.59375, "REPTreeDepth1Kappa": 0, "REPTreeDepth2AUC": 0.4759725400457666, "REPTreeDepth2ErrRate": 0.59375, "REPTreeDepth2Kappa": 0, "REPTreeDepth3AUC": 0.4759725400457666, "REPTreeDepth3ErrRate": 0.59375, "REPTreeDepth3Kappa": 0, "RandomTreeDepth1AUC": 0.6178635973580195, "RandomTreeDepth1ErrRate": 0.65625, "RandomTreeDepth1Kappa": 0.03724928366762178, "RandomTreeDepth2AUC": 0.5949949292698149, "RandomTreeDepth2ErrRate": 0.625, "RandomTreeDepth2Kappa": 0.07514450867052024, "RandomTreeDepth3AUC": 0.5351326841065114, "RandomTreeDepth3ErrRate": 0.625, "RandomTreeDepth3Kappa": 0.06841339155749636, "StdvNominalAttDistinctValues": 0.4795308902320235, "kNN1NAUC": 0.5676747451633035, "kNN1NErrRate": 0.59375, "kNN1NKappa": 0.12265512265512266 }, "tags": [ { "tag": "mythbusting_1", "uploader": "1" }, { "tag": "study_1", "uploader": "2" }, { "tag": "study_123", "uploader": "3886" }, { "tag": "study_15", "uploader": "939" }, { "tag": "study_20", "uploader": "939" }, { "tag": "study_41", "uploader": "1" }, { "tag": "uci", "uploader": "9180" } ], "features": [ { "name": "class", "index": "0", "type": "nominal", "distinct": "3", "missing": "0", "target": "1", "distr": [ [ "1", "2", "3" ], [ [ "9", "0", "0" ], [ "0", "13", "0" ], [ "0", "0", "10" ] ] ] }, { "name": "attribute44", "index": "43", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "0", "0", "1" ], [ "9", "13", "6" ], [ "0", "0", "3" ] ] ] }, { "name": "attribute31", "index": "30", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "7", "9", "6" ], [ "2", "1", "3" ], [ "0", "3", "1" ] ] ] }, { "name": "attribute32", "index": "31", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "3", "4", "2" ], [ "0", "1", "3" ], [ "6", "8", "5" ] ] ] }, { "name": "attribute33", "index": "32", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "3", "4", "2" ], [ "0", "1", "3" ], [ "6", "8", "5" ] ] ] }, { "name": "attribute34", "index": "33", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "0", "1", "2" ], [ "0", "0", "3" ], [ "9", "12", "5" ] ] ] }, { "name": "attribute35", "index": "34", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "2", "8", "4" ], [ "4", "4", "5" ], [ "3", "1", "1" ] ] ] }, { "name": "attribute36", "index": "35", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "4", "6", "6" ], [ "5", "4", "3" ], [ "0", "3", "1" ] ] ] }, { "name": "attribute37", "index": "36", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "3", "5", "3" ], [ "6", "8", "6" ], [ "0", "0", "1" ] ] ] }, { "name": "attribute38", "index": "37", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "4", "8", "2" ], [ "5", "5", "4" ], [ "0", "0", "4" ] ] ] }, { "name": "attribute39", "index": "38", "type": "nominal", "distinct": "3", "missing": "1", "distr": [ [ "1", "2", "3" ], [ [ "4", "4", "3" ], [ "5", "9", "4" ], [ "0", "0", "2" ] ] ] }, { "name": "attribute40", "index": "39", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "1", "2", "1" ], [ "8", "11", "6" ], [ "0", "0", "3" ] ] ] }, { "name": "attribute41", "index": "40", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "0", "0", "3" ], [ "9", "13", "4" ], [ "0", "0", "3" ] ] ] }, { "name": "attribute42", "index": "41", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "5", "6", "4" ], [ "4", "7", "4" ], [ "0", "0", "2" ] ] ] }, { "name": "attribute43", "index": "42", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "4", "5", "2" ], [ "5", "7", "6" ], [ "0", "1", "2" ] ] ] }, { "name": "attribute29", "index": "28", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "2", "0", "2" ], [ "5", "10", "7" ], [ "2", "3", "1" ] ] ] }, { "name": "attribute45", "index": "44", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "2", "3", "1" ], [ "7", "10", "7" ], [ "0", "0", "2" ] ] ] }, { "name": "attribute46", "index": "45", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "2", "1", "0" ], [ "7", "12", "8" ], [ "0", "0", "2" ] ] ] }, { "name": "attribute47", "index": "46", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "2", "0", "2" ], [ "7", "13", "6" ], [ "0", "0", "2" ] ] ] }, { "name": "attribute48", "index": "47", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "2", "3" ], [ [ "9", "13", "8" ], [ "0", "0", "2" ] ] ] }, { "name": "attribute49", "index": "48", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "2", "3" ], [ [ "9", "13", "8" ], [ "0", "0", "2" ] ] ] }, { "name": "attribute50", "index": "49", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "1", "1", "0" ], [ "8", "12", "8" ], [ "0", "0", "2" ] ] ] }, { "name": "attribute51", "index": "50", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "0", "1", "1" ], [ "9", "12", "7" ], [ "0", "0", "2" ] ] ] }, { "name": "attribute52", "index": "51", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "1", "1", "2" ], [ "8", "11", "5" ], [ "0", "1", "3" ] ] ] }, { "name": "attribute53", "index": "52", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "1", "4", "1" ], [ "8", "9", "8" ], [ "0", "0", "1" ] ] ] }, { "name": "attribute54", "index": "53", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "1", "5", "0" ], [ "8", "8", "9" ], [ "0", "0", "1" ] ] ] }, { "name": "attribute55", "index": "54", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "2" ], [ [ "5", "7", "2" ], [ "4", "6", "8" ] ] ] }, { "name": "attribute56", "index": "55", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "2" ], [ [ "3", "2", "1" ], [ "6", "11", "9" ] ] ] }, { "name": "attribute57", "index": "56", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "2" ], [ [ "0", "3", "6" ], [ "9", "10", "4" ] ] ] }, { "name": "attribute15", "index": "14", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "0", "3", "3" ], [ "2", "5", "7" ], [ "7", "5", "0" ] ] ] }, { "name": "attribute2", "index": "1", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "9", "12", "10" ], [ "0", "1", "0" ] ] ] }, { "name": "attribute3", "index": "2", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "0", "1", "0" ], [ "2", "8", "8" ], [ "7", "4", "2" ] ] ] }, { "name": "attribute4", "index": "3", "type": "nominal", "distinct": "4", "missing": "0", "distr": [ [ "0", "1", "2", "3" ], [ [ "1", "3", "0" ], [ "1", "2", "1" ], [ "3", "5", "3" ], [ "4", "3", "6" ] ] ] }, { "name": "attribute5", "index": "4", "type": "nominal", "distinct": "3", "missing": "4", "distr": [ [ "0", "1", "2" ], [ [ "0", "1", "0" ], [ "5", "4", "6" ], [ "3", "5", "4" ] ] ] }, { "name": "attribute6", "index": "5", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "0", "1" ], [ [ "7", "9", "7" ], [ "2", "4", "3" ] ] ] }, { "name": "attribute7", "index": "6", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "0", "4", "2" ], [ "1", "6", "7" ], [ "8", "3", "1" ] ] ] }, { "name": "attribute8", "index": "7", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "3", "3", "1" ], [ "1", "6", "7" ], [ "5", "4", "2" ] ] ] }, { "name": "attribute9", "index": "8", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "0", "1", "4" ], [ "1", "4", "4" ], [ "8", "8", "2" ] ] ] }, { "name": "attribute10", "index": "9", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "7", "12", "10" ], [ "1", "0", "0" ], [ "1", "1", "0" ] ] ] }, { "name": "attribute11", "index": "10", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "4", "7", "9" ], [ "4", "6", "1" ], [ "1", "0", "0" ] ] ] }, { "name": "attribute12", "index": "11", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "6", "8", "5" ], [ "2", "3", "5" ], [ "1", "2", "0" ] ] ] }, { "name": "attribute13", "index": "12", "type": "nominal", "distinct": "4", "missing": "0", "distr": [ [ "0", "1", "2", "3" ], [ [ "3", "4", "4" ], [ "3", "7", "5" ], [ "2", "1", "1" ], [ "1", "1", "0" ] ] ] }, { "name": "attribute14", "index": "13", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "3", "3", "5" ], [ "1", "6", "5" ], [ "5", "4", "0" ] ] ] }, { "name": "attribute30", "index": "29", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "2", "1", "2" ], [ "4", "7", "6" ], [ "3", "5", "2" ] ] ] }, { "name": "attribute16", "index": "15", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "1", "3", "2" ], [ "2", "4", "7" ], [ "6", "6", "1" ] ] ] }, { "name": "attribute17", "index": "16", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "6", "11", "6" ], [ "2", "2", "4" ], [ "1", "0", "0" ] ] ] }, { "name": "attribute18", "index": "17", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "2" ], [ [ "0", "1", "3" ], [ "9", "12", "7" ] ] ] }, { "name": "attribute19", "index": "18", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "2" ], [ [ "2", "1", "1" ], [ "7", "12", "9" ] ] ] }, { "name": "attribute20", "index": "19", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "9", "12", "3" ], [ "0", "0", "1" ], [ "0", "1", "6" ] ] ] }, { "name": "attribute21", "index": "20", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "0", "1", "2" ], [ [ "8", "5", "0" ], [ "0", "2", "1" ], [ "1", "6", "9" ] ] ] }, { "name": "attribute22", "index": "21", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "2" ], [ [ "2", "2", "4" ], [ "7", "11", "6" ] ] ] }, { "name": "attribute23", "index": "22", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "2" ], [ [ "1", "2", "3" ], [ "8", "11", "7" ] ] ] }, { "name": "attribute24", "index": "23", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "1", "2" ], [ [ "0", "2", "6" ], [ "9", "11", "4" ] ] ] }, { "name": "attribute25", "index": "24", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "6", "10", "8" ], [ "3", "1", "1" ], [ "0", "2", "1" ] ] ] }, { "name": "attribute26", "index": "25", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "4", "3", "4" ], [ "5", "9", "5" ], [ "0", "1", "1" ] ] ] }, { "name": "attribute27", "index": "26", "type": "nominal", "distinct": "3", "missing": "0", "distr": [ [ "1", "2", "3" ], [ [ "3", "5", "3" ], [ "3", "4", "5" ], [ "3", "4", "2" ] ] ] }, { "name": "attribute28", "index": "27", "type": "nominal", "distinct": "2", "missing": "0", "distr": [ [ "2", "3" ], [ [ "4", "9", "9" ], [ "5", "4", "1" ] ] ] } ], "nr_of_issues": 0, "nr_of_downvotes": 0, "nr_of_likes": 0, "nr_of_downloads": 19, "total_downloads": 19, "reach": 19, "reuse": 13, "impact_of_reuse": 0, "reach_of_reuse": 0, "impact": 13 }