naivebayes.py 文件源码

def train_model(documents, labels, sample_size=.3, verbose=True):

    if verbose:
        print('starting to generate training data...', end='', flush=True)

    labeled_feature_set = list()
    for n, doc in enumerate(documents):
        feature = word_tokenize(' '.join(doc))
        label = labels[n]
        resampled = resample(feature, label, sample_size)
        labeled_feature_set += resampled

    if verbose:
        print('done', flush=True)
        print('training model...this may take a few minutes.',
              flush=True, end='')

    trained_model = NaiveBayesClassifier.train(iter(labeled_feature_set))

    if verbose:
        print('done', flush=True)
    return trained_model