analyze.py 文件源码

def test_homonym(H, sent, features, C=1.0):
    X_0 = features(matching(sent, H[0]))
    X_1 = features(matching(sent, H[1]))
    y_0 = numpy.zeros(len(X_0))
    y_1 = numpy.ones(len(X_1))
    X = normalize(numpy.vstack([X_0, X_1]), norm='l2')
    y = numpy.hstack([y_0, y_1])
    classifier = LogisticRegression(C=C)
    fold = StratifiedKFold(y, n_folds=10)
    score = []
    count = []
    for tr, te in fold:
        X_tr, X_te = X[tr], X[te]
        y_tr, y_te = y[tr], y[te]
        classifier.fit(X_tr, y_tr)
        score.append(sum(classifier.predict(X_te) == y_te))
        count.append(len(y_te))
    score = numpy.array(score, dtype='float')
    count = numpy.array(count, dtype='float')
    result = {'word1_count': len(y_0),
              'word2_count': len(y_1),
              'majority': 1.0 * max(len(y_0),len(y_1))/len(y),
              'kfold_acc': score/count }
    return result