classifier.py 文件源码

def classify(self, data):
        if 'version' not in self._model.config:
            logging.error('Trying to use MetadataClassifier without learning first')
            return utility.get_zero_class_dict()

        if self._model.config['version'] != sklearn.__version__:
            logging.error('Using MetadataClassifier with different scikit learn version (trained on: {}, used: {}) - relearn classifier first'.format(self._model.config['version'], sklearn.__version__))
            return utility.get_zero_class_dict()

        if self._tree is None:
            self._tree = pickle.loads(base64.b64decode(self._model.config['tree']))

        probability = self._tree.predict_proba([self._get_input(data)])
        result = utility.get_zero_class_dict()
        for i in range(len(self._tree.classes_)):
            result[self._tree.classes_[i]] = probability[0][i]
        return result

    ##
    # \brief Trains a <em>Decision Tree</em> based on the provided repositories.
    #
    # \param learn List containing Tupel (GITHUB, CLASS), where GITHUB is the repository as a github.Github class and
    #              CLASS is the class label of the repository as a string.