features_nn.py 文件源码

def extract_instances(self, train_instances):
        sentences = []
        for idx, train_instance in enumerate(train_instances):
            sa, sb = train_instance.get_word(type='lemma', lower=True)
            sentences.append(TaggedDocument(words=sa, tags=['sa_%d' % idx]))
            sentences.append(TaggedDocument(words=sb, tags=['sb_%d' % idx]))

        model = Doc2Vec(sentences, size=25, window=3, min_count=0, workers=10, iter=1000)

        features = []
        infos = []
        for idx in range(len(train_instances)):
            vec_a = model.docvecs['sa_%d' % idx]
            vec_b = model.docvecs['sb_%d' % idx]
            feature, info = vk.get_all_kernel(vec_a, vec_b)
            features.append(feature)
            infos.append([])
            # infos.append([vec_a, vec_b])

        return features, infos

    # def load_instances(self, train_instances):
    #     """
    #     extract cosine distance from already trained feature file
    #     without modify the feature_file
    #     this function's priority is higher that the above extract_instances
    #     """
    #
    #     _features, _n_dim, _n_instance = Feature.load_feature_from_file(self.feature_file)
    #     features = []
    #     infos = []
    #     ''' get features from train instances'''
    #     for _feature in _features:
    #         feature = Feature._feat_string_to_list(_feature, _n_dim)
    #         features.append([feature[1]])
    #         infos.append(['cosine'])
    #
    #     features = [ Feature._feat_list_to_string(feature) for feature in features ]
    #
    #     return features, 1, _n_instance