mlcomp_sparse_document_classification.py 文件源码

def benchmark(clf_class, params, name):
    print("parameters:", params)
    t0 = time()
    clf = clf_class(**params).fit(X_train, y_train)
    print("done in %fs" % (time() - t0))

    if hasattr(clf, 'coef_'):
        print("Percentage of non zeros coef: %f"
              % (np.mean(clf.coef_ != 0) * 100))
    print("Predicting the outcomes of the testing set")
    t0 = time()
    pred = clf.predict(X_test)
    print("done in %fs" % (time() - t0))

    print("Classification report on test set for classifier:")
    print(clf)
    print()
    print(classification_report(y_test, pred,
                                target_names=news_test.target_names))

    cm = confusion_matrix(y_test, pred)
    print("Confusion matrix:")
    print(cm)

    # Show confusion matrix
    pl.matshow(cm)
    pl.title('Confusion matrix of the %s classifier' % name)
    pl.colorbar()