cross_genre_profiler.py 文件源码

def __init__(self, lang=None, method=None, features=None):
        fs = []
        if 'unigram' in features:
            fs.append(word_unigrams())
        if 'bigram' in features:
            fs.append(word_bigrams())
        if 'spelling' in features:
            fs.append(avg_spelling_error(lang=lang))
        if 'punctuation' in features:
            fs.append(punctuation_features())
        if 'char' in features:
            fs.append(char_ngrams())

        fu = FeatureUnion(fs, n_jobs=1)
        self.pipeline = Pipeline([('features', fu),
                                  ('scale', Normalizer()),
                                  ('classifier', get_classifier(method=method))])