=== Run information === Scheme: weka.classifiers.trees.J48 -C 0.25 -M 30 Relation: abalone Instances: 3675 Attributes: 9 sex length diameter height whole_weight shucked_weight viscera_weight shell_weight Age Test mode: 10-fold cross-validation === Classifier model (full training set) === J48 pruned tree ------------------ shell_weight <= 0.249 | shell_weight <= 0.154: Young (1140.0/147.0) | shell_weight > 0.154 | | shucked_weight <= 0.3025 | | | sex = M | | | | shell_weight <= 0.1775: Young (55.0/26.0) | | | | shell_weight > 0.1775: Old (77.0/17.0) | | | sex = F: Old (142.0/34.0) | | | sex = I | | | | whole_weight <= 0.6555 | | | | | shucked_weight <= 0.2105: Old (33.0/14.0) | | | | | shucked_weight > 0.2105: Young (101.0/15.0) | | | | whole_weight > 0.6555: Old (32.0/10.0) | | shucked_weight > 0.3025 | | | shucked_weight <= 0.376 | | | | whole_weight <= 0.788: Young (160.0/40.0) | | | | whole_weight > 0.788: Old (73.0/27.0) | | | shucked_weight > 0.376: Young (179.0/37.0) shell_weight > 0.249 | shucked_weight <= 0.3965: Old (356.0/55.0) | shucked_weight > 0.3965 | | shell_weight <= 0.2905 | | | shell_weight <= 0.2565: Young (42.0/11.0) | | | shell_weight > 0.2565 | | | | diameter <= 0.455: Old (69.0/24.0) | | | | diameter > 0.455 | | | | | height <= 0.15: Young (51.0/17.0) | | | | | height > 0.15 | | | | | | viscera_weight <= 0.2465: Young (33.0/12.0) | | | | | | viscera_weight > 0.2465: Old (30.0/10.0) | | shell_weight > 0.2905: Old (1102.0/192.0) Number of Leaves : 17 Size of the tree : 32 Time taken to build model: 0.04 seconds === Stratified cross-validation === === Summary === Correctly Classified Instances 2899 78.8844 % Incorrectly Classified Instances 776 21.1156 % Kappa statistic 0.5777 K&B Relative Info Score 158158.2797 % K&B Information Score 1581.5811 bits 0.4304 bits/instance Class complexity | order 0 3675.0001 bits 1 bits/instance Class complexity | scheme 2592.1979 bits 0.7054 bits/instance Complexity improvement (Sf) 1082.8022 bits 0.2946 bits/instance Mean absolute error 0.3035 Root mean squared error 0.3964 Relative absolute error 60.7071 % Root relative squared error 79.2864 % Coverage of cases (0.95 level) 100 % Mean rel. region size (0.95 level) 100 % Total Number of Instances 3675 === Detailed Accuracy By Class === TP Rate FP Rate Precision Recall F-Measure MCC ROC Area PRC Area Class 0.767 0.19 0.802 0.767 0.784 0.578 0.835 0.829 Young 0.81 0.233 0.777 0.81 0.793 0.578 0.835 0.789 Old Weighted Avg. 0.789 0.211 0.789 0.789 0.789 0.578 0.835 0.809 === Confusion Matrix === a b <-- classified as 1411 428 | a = Young 348 1488 | b = Old === Re-evaluation on test set === User supplied test set Relation: abalone-test Instances: unknown (yet). Reading incrementally Attributes: 9 === Summary === Correctly Classified Instances 388 77.6 % Incorrectly Classified Instances 112 22.4 % Kappa statistic 0.5518 Mean absolute error 0.3105 Root mean squared error 0.4029 Coverage of cases (0.95 level) 100 % Total Number of Instances 500 === Detailed Accuracy By Class === TP Rate FP Rate Precision Recall F-Measure MCC ROC Area PRC Area Class 0.777 0.225 0.783 0.777 0.78 0.552 0.835 0.812 Young 0.775 0.223 0.768 0.775 0.771 0.552 0.835 0.784 Old Weighted Avg. 0.776 0.224 0.776 0.776 0.776 0.552 0.835 0.798 === Confusion Matrix === a b <-- classified as 199 57 | a = Young 55 189 | b = Old