X = X[:,attribute_included].reshape(-1,1) attributeNames = attributeNames[attribute_included] N, M = X.shape C = len(classNames) # K-fold crossvalidation K = 2 CV = StratifiedKFold(K, shuffle=True) k=0 for train_index, test_index in CV.split(X,y): print(train_index) # extract training and test set for current CV fold X_train, y_train = X[train_index,:], y[train_index] X_test, y_test = X[test_index,:], y[test_index] logit_classifier = LogisticRegression() logit_classifier.fit(X_train, y_train) y_test_est = logit_classifier.predict(X_test).T p = logit_classifier.predict_proba(X_test)[:,1].T figure(k) rocplot(p,y_test) figure(k+1) confmatplot(y_test,y_test_est) k+=2 show()
X = X[:,attribute_included] attributeNames = attributeNames[attribute_included] N, M = X.shape C = len(classNames) # K-fold crossvalidation K = 2 CV = cross_validation.StratifiedKFold(y.A.ravel().tolist(),K) k=0 for train_index, test_index in CV: # extract training and test set for current CV fold X_train, y_train = X[train_index,:], y[train_index,:] X_test, y_test = X[test_index,:], y[test_index,:] logit_classifier = LogisticRegression() logit_classifier.fit(X_train, y_train.A.ravel()) y_test_est = np.mat(logit_classifier.predict(X_test)).T p = np.mat(logit_classifier.predict_proba(X_test)[:,1]).T figure(k) rocplot(p,y_test) figure(k+1) confmatplot(y_test,y_test_est) k+=2 show()