sentenceClassifer.py 文件源码

def train(X, y, outpath=None, verbose=True):
    def build(X, y=None):
        """
        Inner build function that builds a single model.
        """
        model = Pipeline([
            ('preprocessor', NLTKPreprocessor()),
            ('vectorizer', TfidfVectorizer(
                tokenizer=identity, preprocessor=None, lowercase=False)),
            ('clf', OneVsRestClassifier(LinearSVC()))])

        model.fit(X, y)
        return model

    # Label encode the targets
    labels = preprocessing.MultiLabelBinarizer()
    y = labels.fit_transform(y)

    model = build(X, y)
    model.labels_ = labels

    if outpath:
        with open(outpath, 'wb') as f:
            pickle.dump(model, f)

            if verbose:
                print("Model written out to {}".format(outpath))

    return model