classifier.py 文件源码

def trainModel(xtrain, xtest, ytrain, ytest):
    classifiers = [
        # KNeighborsClassifier(3),
        # SVC(kernel="linear",  probability=True),
        # NuSVC(probability=True),
        # DecisionTreeClassifier(),
        RandomForestClassifier(),
        # AdaBoostClassifier(),
        # GradientBoostingClassifier(loss='deviance', learning_rate=0.1, n_estimators=200,
        #          subsample=1.0, criterion='friedman_mse', min_samples_split=2,
        #          min_samples_leaf=1, min_weight_fraction_leaf=0.,
        #          max_depth=5),
        # GradientBoostingClassifier(),
        # GaussianNB(),
        # LinearDiscriminantAnalysis(),
        # QuadraticDiscriminantAnalysis()
        ]

    log_cols = ["Classifier", "Accuracy", "Log Loss"]
    log = pd.DataFrame(columns=log_cols)
    for clf in classifiers:
        clf.fit(xtrain, ytrain)
        name = clf.__class__.__name__

        print("=" * 30)
        print(name)

        print('****Results****')
        train_predictions = clf.predict(xtest)
        # acc = accuracy_score(ytest, train_predictions)
        # print("Accuracy: {:.4%}".format(acc))


        train_porb_predictions = clf.predict_proba(xtest)
        ll = log_loss(ytest, train_porb_predictions)
        print("Log Loss: {}".format(ll))

        # printResult(ytest, train_predictions)
        # result.printMultiResult(ytest, train_predictions)

        save_path = "doc/result.txt"
        desc = "sentiment by tfidf "
        result_str = result.printMultiResult(ytest, train_predictions)
        result.saveResult(save_path, desc, result_str)


        #
        # log_entry = pd.DataFrame([[name, acc * 100, ll]], columns=log_cols)
        # log = log.append(log_entry)


    print("=" * 30)