p2fa_helper.py 文件源码

def load_w2v(self):
        """
        Load Word2Vec embeddings from P2FA files and pre-trained Word2Vec 
        KeyedVectors text file and store them in the 
        directory path mentioned in self.embedding_dir.
        :returns segment wise feature dictionary for embeddings
        :Note: Do not provide KeyedVector file in binary format
        """
        from gensim.models.keyedvectors import KeyedVectors
        from gensim.models import Word2Vec

        is_binary = True if self.embed_model_type == "binary" else False
        model = KeyedVectors.load_word2vec_format(self.embed_model_path, 
                                                  binary = is_binary )
        print "Word2Vec model Loaded"
        self.embed_model = model
        self.embed_length = model.vector_size
        if not self.word_dict:
            self.load_words()

        features = {}
        system("mkdir -p "+self.embedding_dir)
        for video_id, video_word_data in self.word_dict.iteritems():
            video_feats = {}
            for segment_id, segment_word_data in video_word_data.iteritems():
                video_feats[segment_id] = []
                for word_feat in segment_word_data:
                    start, end, word = word_feat
                    try:
                        embed = self.embed_model[word]
                    except:
                        embed = np.zeros(self.embed_length)
                    video_feats[segment_id].append((start, end, embed))

                fname = video_id+"_"+segment_id+".csv"
                fpath = join(self.embedding_dir, fname)
                with open(fpath,"wb") as fh:
                    # Writing each feature in csv file for segment
                    for f in video_feats[segment_id]:
                        f_start = str(f[0])
                        f_end = str(f[1])
                        f_val = [str(val) for val in f[2].tolist()]
                        str2write = ",".join([f_start, f_end] + f_val)
                        str2write += "\n"
                        fh.write(str2write)
            features[video_id] = video_feats
        return features