Instances: 14
Attributes: 5
outlook
temperature
humidity
windy
play
Test mode: 3-fold cross-validation
=== Classifier model (full training set) ===
Logistic Regression with ridge parameter of 1.0E-8
Coefficients...
Variable Coeff.
1 -6.4257
2 13.5922
3 -5.6562
4 -0.0776
5 -0.1556
6 3.7317
Intercept 22.234
Odds Ratios...
Variable O.R.
1 0.0016
2 799848.4264
3 0.0035
4 0.9254
5 0.8559
6 41.7508
Time taken to build model: 0 seconds
=== Stratified cross-validation ===
=== Summary ===
Correctly Classified Instances 9 64.2857 %
Incorrectly Classified Instances 5 35.7143 %
Kappa statistic 0.2553
Mean absolute error 0.3571
Root mean squared error 0.5976
Relative absolute error 76.2124 %
Root relative squared error 123.5728 %
Total Number of Instances 14
=== Detailed Accuracy By Class ===
TP Rate FP Rate Precision Recall F-Measure Class
0.667 0.4 0.75 0.667 0.706 yes
0.6 0.333 0.5 0.6 0.545 no
=== Confusion Matrix ===
a b <-- classified as
6 3 | a = yes
2 3 | b = no
После выбора значения процентного разделителя, результат выглядит следующим образом:
Percent split=30%
Scheme: weka.classifiers.functions.Logistic -R 1.0E-8 -M -1
Relation: weather
Instances: 14
Attributes: 5
outlook
temperature
humidity
windy
play
Test mode: split 30% train, remainder test
=== Classifier model (full training set) ===
Logistic Regression with ridge parameter of 1.0E-8
Coefficients...
Variable Coeff.
1 -6.4257
2 13.5922
3 -5.6562
4 -0.0776
5 -0.1556
6 3.7317
Intercept 22.234
Odds Ratios...
Variable O.R.
1 0.0016
2 799848.4264
3 0.0035
4 0.9254
5 0.8559
6 41.7508
Time taken to build model: 0 seconds
=== Evaluation on test split ===
=== Summary ===
Correctly Classified Instances 7 70 %
Incorrectly Classified Instances 3 30 %
Kappa statistic 0.4444
Mean absolute error 0.3359
Root mean squared error 0.554
Relative absolute error 67.1804 %
Root relative squared error 110.8036 %
Total Number of Instances 10
=== Detailed Accuracy By Class ===
TP Rate FP Rate Precision Recall F-Measure Class
0.571 0 1 0.571 0.727 yes
1 0.429 0.5 1 0.667 no
=== Confusion Matrix ===
a b <-- classified as
4 3 | a = yes
0 3 | b = no
Таким образом, видно, что в последнем случае алгоритм дал менее точный резултат.
-
Алгоритмы кластеризации:
COBWEB
Устанавливаем split 35%.
Scheme: weka.clusterers.Cobweb -A 1.0 -C 0.0028209479177387815
Relation: weather