Results for the updated "Redskins Rules" (http://en.wikipedia.org/wiki/Redskins_Rule) with the C4.5 decision tree algorithm.

gistfile1.txt

=== Run information ===

Scheme:weka.classifiers.trees.J48 -C 0.25 -M 2

Relation:     Dataset0 - Sheet1-weka.filters.unsupervised.attribute.Remove-R1-weka.filters.supervised.attribute.NominalToBinary-weka.filters.supervised.attribute.NominalToBinary-weka.filters.supervised.attribute.NominalToBinary-weka.filters.unsupervised.attribute.NumericToNominal-Rfirst-last

Instances:    21

Attributes:   3

             United_States_presidential_election

             Incumbant

             Washington_Redskins

Test mode:10-fold cross-validation

=== Classifier model (full training set) ===

J48 pruned tree

------------------

Washington_Redskins = 0: 0 (9.0/1.0)

Washington_Redskins = 1: 1 (12.0/1.0)

Number of Leaves  :     2

Size of the tree :     3


Time taken to build model: 0.01 seconds

=== Stratified cross-validation ===

=== Summary ===

Correctly Classified Instances          19               90.4762 %

Incorrectly Classified Instances         2                9.5238 %

Kappa statistic                          0.8056

Mean absolute error                      0.1819

Root mean squared error                  0.3236

Relative absolute error                 36.7267 %

Root relative squared error             64.764  %

Total Number of Instances               21     

=== Detailed Accuracy By Class ===

              TP Rate   FP Rate   Precision   Recall  F-Measure   ROC Area  Class

                0.889     0.083      0.889     0.889     0.889      0.824    0

                0.917     0.111      0.917     0.917     0.917      0.824    1

Weighted Avg.    0.905     0.099      0.905     0.905     0.905      0.824

=== Confusion Matrix ===

 a  b   <-- classified as

 8  1 |  a = 0

 1 11 |  b = 1