nGramClassifier.py 文件源码

def __init__(self, ngram_range=(1, 1), analyzer='word', count=True,
                 n_features=200):
        """Initializes the classifier.

        Args:
            ngram_range (tuple): Pair of ints specifying the range of ngrams.
            analyzer (string): Determines what type of analyzer to be used.
            Setting it to 'word' will consider each word as a unit of language
            and 'char' will consider each character as a unit of language.
            count (boolean): Determines if features are counts of n-grams
            versus a binary value encoding if the n-gram is present or not.
            n_features (int): Maximum number of features used.
        """
        # checking what type of vectorizer to create
        if count:
            self.vectorizer = CountVectorizer(analyzer=analyzer,
                                              ngram_range=ngram_range,
                                              max_features=n_features)
        else:
            self.vectorizer = HashingVectorizer(analyzer=analyzer,
                                                ngram_range=ngram_range,
                                                n_features=n_features)