04_sent.py 文件源码

def train_model(clf, X, Y, name="NB ngram", plot=False):
    # create it again for plotting
    cv = ShuffleSplit(
        n=len(X), n_iter=10, test_size=0.3, indices=True, random_state=0)

    train_errors = []
    test_errors = []

    scores = []
    pr_scores = []
    precisions, recalls, thresholds = [], [], []

    clfs = []  # just to later get the median

    for train, test in cv:
        X_train, y_train = X[train], Y[train]
        X_test, y_test = X[test], Y[test]

        clf.fit(X_train, y_train)
        clfs.append(clf)

        train_score = clf.score(X_train, y_train)
        test_score = clf.score(X_test, y_test)

        train_errors.append(1 - train_score)
        test_errors.append(1 - test_score)

        scores.append(test_score)
        proba = clf.predict_proba(X_test)

        fpr, tpr, roc_thresholds = roc_curve(y_test, proba[:, 1])
        precision, recall, pr_thresholds = precision_recall_curve(
            y_test, proba[:, 1])

        pr_scores.append(auc(recall, precision))
        precisions.append(precision)
        recalls.append(recall)
        thresholds.append(pr_thresholds)

    if plot:
        scores_to_sort = pr_scores
        median = np.argsort(scores_to_sort)[len(scores_to_sort) / 2]

        plot_pr(pr_scores[median], name, phase, precisions[median],
                recalls[median], label=name)

        log_false_positives(clfs[median], X_test, y_test, name)

    summary = (np.mean(scores), np.std(scores),
               np.mean(pr_scores), np.std(pr_scores))
    print "%.3f\t%.3f\t%.3f\t%.3f\t" % summary

    return np.mean(train_errors), np.mean(test_errors)