How to use the sense2vec.word2vec.Vocab function in sense2vec

# Discard words less-frequent than min_count
        if not dry_run:
            self.index2word = []
            # make stored settings match these applied settings
            self.min_count = min_count
            self.sample = sample
            self.vocab = {}
        drop_unique, drop_total, retain_total, original_total = 0, 0, 0, 0
        retain_words = []
        for word, v in iteritems(self.raw_vocab):
            if keep_vocab_item(word, v, min_count, trim_rule=trim_rule):
                retain_words.append(word)
                retain_total += v
                original_total += v
                if not dry_run:
                    self.vocab[word] = Vocab(count=v, index=len(self.index2word))
                    self.index2word.append(word)
            else:
                drop_unique += 1
                drop_total += v
                original_total += v
        logger.info("min_count=%d retains %i unique words (drops %i)",
                    min_count, len(retain_words), drop_unique)
        logger.info("min_count leaves %i word corpus (%i%% of original %i)",
                    retain_total, retain_total * 100 / max(original_total, 1), original_total)

        # Precalculate each vocabulary item's threshold for sampling
        if not sample:
            # no words downsampled
            threshold_count = retain_total
        elif sample < 1.0:
            # traditional meaning: set parameter as proportion of total

def create_binary_tree(self):
        """
        Create a binary Huffman tree using stored vocabulary word counts. Frequent words
        will have shorter binary codes. Called internally from `build_vocab()`.

        """
        logger.info("constructing a huffman tree from %i words", len(self.vocab))

        # build the huffman tree
        heap = list(itervalues(self.vocab))
        heapq.heapify(heap)
        for i in xrange(len(self.vocab) - 1):
            min1, min2 = heapq.heappop(heap), heapq.heappop(heap)
            heapq.heappush(heap, Vocab(count=min1.count + min2.count, index=i + len(self.vocab), left=min1, right=min2))

        # recurse over the tree, assigning a binary code to each vocabulary word
        if heap:
            max_depth, stack = 0, [(heap[0], [], [])]
            while stack:
                node, codes, points = stack.pop()
                if node.index < len(self.vocab):
                    # leaf node => store its path from the root
                    node.code, node.point = codes, points
                    max_depth = max(len(codes), max_depth)
                else:
                    # inner node => continue recursion
                    points = array(list(points) + [node.index - len(self.vocab)], dtype=uint32)
                    stack.append((node.left, array(list(codes) + [0], dtype=uint8), points))
                    stack.append((node.right, array(list(codes) + [1], dtype=uint8), points))

def finalize_vocab(self):
        """Build tables and model weights based on final vocabulary settings."""
        if not self.index2word:
            self.scale_vocab()
        if self.sorted_vocab:
            self.sort_vocab()
        if self.hs:
            # add info about each word's Huffman encoding
            self.create_binary_tree()
        if self.negative:
            # build the table for drawing random words (for negative sampling)
            self.make_cum_table()
        if self.null_word:
            # create null pseudo-word for padding when using concatenative L1 (run-of-words)
            # this word is only ever input – never predicted – so count, huffman-point, etc doesn't matter
            word, v = '\0', Vocab(count=1, sample_int=0)
            v.index = len(self.vocab)
            self.index2word.append(word)
            self.vocab[word] = v
        # set initial input/projection and hidden weights
        self.reset_weights()

def add_word(word, weights):
                word_id = len(result.vocab)
                if word in result.vocab:
                    logger.warning("duplicate word '%s' in %s, ignoring all but first", word, fname)
                    return
                if counts is None:
                    # most common scenario: no vocab file given. just make up some bogus counts, in descending order
                    result.vocab[word] = Vocab(index=word_id, count=vocab_size - word_id)
                elif word in counts:
                    # use count from the vocab file
                    result.vocab[word] = Vocab(index=word_id, count=counts[word])
                else:
                    # vocab file given, but word is missing -- set count to None (TODO: or raise?)
                    logger.warning("vocabulary file is incomplete: '%s' is missing", word)
                    result.vocab[word] = Vocab(index=word_id, count=None)
                result.syn0[word_id] = weights
                result.index2word.append(word)