new_data_mlp.py 文件源码

def SVMbanchmark(X_train, y_train, X_test, y_test):
    # optimial c is 10.0, f1 = 0.52
    print("Training LinearSVC with l1-based feature selection")
    X_valid, y_valid = X_test[:10000], y_test[:10000]
    score_list = []
    CList = [0.1, 0.5, 1, 10, 50, 100]
    for c in CList:
        clf = OneVsRestClassifier(LinearSVC(C=c, penalty='l1', dual=False))
        clf.fit(X_train, y_train)

        pred = clf.predict(X_valid)
        score = metrics.f1_score(y_valid, pred, average="macro")
        score_list.append(score)
        print("f1-score: {:f}, c is {:f}".format(score, c))
    clf = OneVsRestClassifier(LinearSVC(penality="l1", dual=False, C=CList[np.argmax(score_list)]))
    clf.fit(X_train, y_train)
    pred = clf.predict(X_test)
    score = metrics.f1_score(y_test, pred, average="micro")
    print("f1-score for test set: {:f}".format(score))