eric-haibin-lin commented on a change in pull request #10025: [MXNET-96] Language model with Google's billion words dataset URL: https://github.com/apache/incubator-mxnet/pull/10025#discussion_r174650752
########## File path: example/rnn/large_word_lm/data.py ########## @@ -0,0 +1,202 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license agreements. See the NOTICE file +# distributed with this work for additional information +# regarding copyright ownership. The ASF licenses this file +# to you under the Apache License, Version 2.0 (the +# "License"); you may not use this file except in compliance +# with the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, +# software distributed under the License is distributed on an +# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +# KIND, either express or implied. See the License for the +# specific language governing permissions and limitations +# under the License. + +import mxnet as mx +import numpy as np +import codecs, glob, random, logging + +class Vocabulary(object): + """ A dictionary for words. + Adapeted from @rafaljozefowicz's implementation. + """ + def __init__(self): + self._token_to_id = {} + self._token_to_count = {} + self._id_to_token = [] + self._num_tokens = 0 + self._total_count = 0 + self._s_id = None + self._unk_id = None + + @property + def num_tokens(self): + return self._num_tokens + + @property + def unk(self): + return "<UNK>" + + @property + def unk_id(self): + return self._unk_id + + @property + def s(self): + return "<S>" + + @property + def s_id(self): + return self._s_id + + def add(self, token, count): + self._token_to_id[token] = self._num_tokens + self._token_to_count[token] = count + self._id_to_token.append(token) + self._num_tokens += 1 + self._total_count += count + + def finalize(self): + self._s_id = self.get_id(self.s) + self._unk_id = self.get_id(self.unk) + + def get_id(self, token): + # Unseen token are mapped to UNK + return self._token_to_id.get(token, self.unk_id) + + def get_token(self, id_): + return self._id_to_token[id_] + + @staticmethod + def from_file(filename): + vocab = Vocabulary() + with codecs.open(filename, "r", "utf-8") as f: + for line in f: + word, count = line.strip().split() + vocab.add(word, int(count)) + vocab.finalize() + return vocab + +class Dataset(object): + """ A dataset for truncated bptt with multiple sentences. + Adapeted from @rafaljozefowicz's implementation. + """ + def __init__(self, vocab, file_pattern, deterministic=False): Review comment: ok ---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: us...@infra.apache.org With regards, Apache Git Services
