transitionparser.py 文件源码

def train(self, depgraphs):
        """
        :param depgraphs : list of DependencyGraph as the training data
        :type depgraphs : DependencyGraph
        """

        try:
            input_file = tempfile.NamedTemporaryFile(
                prefix='transition_parse.train',
                dir=tempfile.gettempdir(),
                delete=False)

            self._create_training_examples_arc_eager(depgraphs, input_file)

            input_file.close()
            # Using the temporary file to train the libsvm classifier
            x_train, y_train = load_svmlight_file(input_file.name)
            # The parameter is set according to the paper:
            # Algorithms for Deterministic Incremental Dependency Parsing by Joakim Nivre
            # this is very slow.
            self._model = svm.SVC(
                kernel='poly',
                degree=2,
                coef0=0,
                gamma=0.2,
                C=0.5,
                verbose=False,
                probability=True)

            print('Training support vector machine...')
            self._model.fit(x_train, y_train)
            print('done!')
        finally:
            os.remove(input_file.name)