log_reg.py 文件源码

def sklearn_logit(self,Xtrain,ytrain, Xtest, ytest):
            clf = linear_model.LogisticRegressionCV(penalty='l2', class_weight='balanced', intercept_scaling=1e3, cv=5)
            clf.fit (Xtrain, ytrain)
            coeffients = clf.coef_
            print "coefficients:", coeffients
            print "intercept:", clf.intercept_
            # predict train labels
            train_predictions = clf.predict(Xtrain)
            train_accuracy = self.calculate_accuracy(train_predictions, ytrain)
            print "train accuracy: ", train_accuracy * 100
            MSE_train = self.calculate_MSE(train_predictions, ytrain)
            print "train MSE: ", MSE_train
            AIC_train = len(ytrain) * np.log(MSE_train) + 2 * (p + 1)
            print "train AIC:", AIC_train
            for i in range(len(train_predictions)):
                train_predictions[i] = round(train_predictions[i])
            train_confMatrix = confusion_matrix(ytrain, train_predictions, labels = [1.0, 0.0])
            print "train confusion matrix:", train_confMatrix
            # predict test labels
            test_predictions = clf.predict(Xtest)
            test_accuracy = self.calculate_accuracy(test_predictions, ytest)
            print "test accuracy: ", test_accuracy * 100
            MSE_test = self.calculate_MSE(test_predictions, ytest)
            print "test MSE: ", MSE_test
            for i in range(len(test_predictions)):
                test_predictions[i] = round(test_predictions[i])
            test_confMatrix = confusion_matrix(ytest, test_predictions, labels = [1.0, 0.0])
            print "test confusion matrix:", test_confMatrix