Warning: Declaration of action_plugin_tablewidth::register(&$controller) should be compatible with DokuWiki_Action_Plugin::register(Doku_Event_Handler $controller) in /s/bach/b/class/cs545/public_html/fall16/lib/plugins/tablewidth/action.php on line 93
"""classifier evaluation using scikit-learn more details at: http://scikit-learn.org/stable/modules/cross_validation.html http://scikit-learn.org/stable/tutorial/statistical_inference/model_selection.html """ import numpy as np from sklearn import cross_validation from sklearn import metrics import perceptron2 data=np.genfromtxt("../data/heart_scale.data", delimiter=",") X=data[:,1:] y=data[:,0] # let's train/test a perceptron on the heart dataset: X_train, X_test, y_train, y_test = cross_validation.train_test_split(X, y, test_size=0.4, random_state=0) classifier = perceptron2.Perceptron() classifier.fit(X_train, y_train) y_pred = classifier.predict(X_test) # let's comput the accuracy of the classifier: print (len(np.where(np.equal(y_pred, y_test))[0])/len(y_test)) # you can get the same result using scikit-learn: metrics.accuracy_score(y_test, y_pred) # now let's use cross-validation instead: print (cross_validation.cross_val_score(classifier, X, y, cv=5, scoring='accuracy')) # you can obtain accuracy for other metrics, such as area under the roc curve: print (cross_validation.cross_val_score(classifier, X, y, cv=5, scoring='roc_auc')) # you can also obtain the predictions by cross-validation and then compute the accuracy: y_predict = cross_validation.cross_val_predict(classifier, X, y, cv=5) print(metrics.accuracy_score(y, y_predict)) # here's an alternative way of doing cross-validation. # first divide the data into folds: cv = cross_validation.StratifiedKFold(y, 5) # now use these folds: print (cross_validation.cross_val_score(classifier, X, y, cv=cv, scoring='roc_auc')) # you can see how examples were divided into folds by looking at the test_folds attribute: print (cv.test_folds) # hmm... perhaps we should shuffle things a bit... cv = cross_validation.StratifiedKFold(y, 5, shuffle=True) print (cv.test_folds) # if you run division into folds multiple times you will get a different answer: cv = cross_validation.StratifiedKFold(y, 5, shuffle=True) print (cv.test_folds) # if you want to consistently get the same division into folds: cv = cross_validation.StratifiedKFold(y, 5, shuffle=True, random_state=0) # this sets the seed for the random number generator.