p-final.py 文件源码

def do_ml(ticker):
    X, y, df = extract_featuresets(ticker)

    X_train, X_test, y_train, y_test = cross_validation.train_test_split(X,
                                                        y,
                                                        test_size=0.25)

    #clf = neighbors.KNeighborsClassifier()

    clf = VotingClassifier([('lsvc',svm.LinearSVC()),
                            ('knn',neighbors.KNeighborsClassifier()),
                            ('rfor',RandomForestClassifier())])


    clf.fit(X_train, y_train)
    confidence = clf.score(X_test, y_test)
    print('accuracy:',confidence)
    predictions = clf.predict(X_test)
    print('predicted class counts:',Counter(predictions))
    print()
    print()
    return confidence

# examples of running: