本文整理汇总了Python中skip_thoughts.data.special_words.UNK_ID属性的典型用法代码示例。如果您正苦于以下问题：Python special_words.UNK_ID属性的具体用法？Python special_words.UNK_ID怎么用？Python special_words.UNK_ID使用的例子？那么恭喜您, 这里精选的属性代码示例或许可以为您提供帮助。您也可以进一步了解该属性所在类skip_thoughts.data.special_words的用法示例。
在下文中一共展示了special_words.UNK_ID属性的3个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: _sentence_to_ids
# 需要导入模块: from skip_thoughts.data import special_words [as 别名]
# 或者: from skip_thoughts.data.special_words import UNK_ID [as 别名]
def _sentence_to_ids(sentence, vocab):
"""Helper for converting a sentence (list of words) to a list of ids."""
ids = [vocab.get(w, special_words.UNK_ID) for w in sentence]
if FLAGS.add_eos:
ids.append(special_words.EOS_ID)
return ids 示例2: _build_vocabulary
# 需要导入模块: from skip_thoughts.data import special_words [as 别名]
# 或者: from skip_thoughts.data.special_words import UNK_ID [as 别名]
def _build_vocabulary(input_files):
"""Loads or builds the model vocabulary.
Args:
input_files: List of pre-tokenized input .txt files.
Returns:
vocab: A dictionary of word to id.
"""
if FLAGS.vocab_file:
tf.logging.info("Loading existing vocab file.")
vocab = collections.OrderedDict()
with tf.gfile.GFile(FLAGS.vocab_file, mode="r") as f:
for i, line in enumerate(f):
word = line.decode("utf-8").strip()
assert word not in vocab, "Attempting to add word twice: %s" % word
vocab[word] = i
tf.logging.info("Read vocab of size %d from %s",
len(vocab), FLAGS.vocab_file)
return vocab
tf.logging.info("Creating vocabulary.")
num = 0
wordcount = collections.Counter()
for input_file in input_files:
tf.logging.info("Processing file: %s", input_file)
for sentence in tf.gfile.FastGFile(input_file):
wordcount.update(sentence.split())
num += 1
if num % 1000000 == 0:
tf.logging.info("Processed %d sentences", num)
tf.logging.info("Processed %d sentences total", num)
words = wordcount.keys()
freqs = wordcount.values()
sorted_indices = np.argsort(freqs)[::-1]
vocab = collections.OrderedDict()
vocab[special_words.EOS] = special_words.EOS_ID
vocab[special_words.UNK] = special_words.UNK_ID
for w_id, w_index in enumerate(sorted_indices[0:FLAGS.num_words - 2]):
vocab[words[w_index]] = w_id + 2 # 0: EOS, 1: UNK.
tf.logging.info("Created vocab with %d words", len(vocab))
vocab_file = os.path.join(FLAGS.output_dir, "vocab.txt")
with tf.gfile.FastGFile(vocab_file, "w") as f:
f.write("\n".join(vocab.keys()))
tf.logging.info("Wrote vocab file to %s", vocab_file)
word_counts_file = os.path.join(FLAGS.output_dir, "word_counts.txt")
with tf.gfile.FastGFile(word_counts_file, "w") as f:
for i in sorted_indices:
f.write("%s %d\n" % (words[i], freqs[i]))
tf.logging.info("Wrote word counts file to %s", word_counts_file)
return vocab 示例3: _build_vocabulary
# 需要导入模块: from skip_thoughts.data import special_words [as 别名]
# 或者: from skip_thoughts.data.special_words import UNK_ID [as 别名]
def _build_vocabulary(input_files):
"""Loads or builds the model vocabulary.
Args:
input_files: List of pre-tokenized input .txt files.
Returns:
vocab: A dictionary of word to id.
"""
if FLAGS.vocab_file:
tf.logging.info("Loading existing vocab file.")
vocab = collections.OrderedDict()
with tf.gfile.GFile(FLAGS.vocab_file, mode="r") as f:
for i, line in enumerate(f):
word = line.decode("utf-8").strip()
assert word not in vocab, "Attempting to add word twice: %s" % word
vocab[word] = i
tf.logging.info("Read vocab of size %d from %s",
len(vocab), FLAGS.vocab_file)
return vocab
tf.logging.info("Creating vocabulary.")
num = 0
wordcount = collections.Counter()
for input_file in input_files:
tf.logging.info("Processing file: %s", input_file)
for sentence in tf.gfile.FastGFile(input_file):
wordcount.update(sentence.split())
num += 1
if num % 1000000 == 0:
tf.logging.info("Processed %d sentences", num)
tf.logging.info("Processed %d sentences total", num)
words = list(wordcount)
freqs = list(wordcount.values())
sorted_indices = np.argsort(freqs)[::-1]
vocab = collections.OrderedDict()
vocab[special_words.EOS] = special_words.EOS_ID
vocab[special_words.UNK] = special_words.UNK_ID
for w_id, w_index in enumerate(sorted_indices[0:FLAGS.num_words - 2]):
vocab[words[w_index]] = w_id + 2 # 0: EOS, 1: UNK.
tf.logging.info("Created vocab with %d words", len(vocab))
vocab_file = os.path.join(FLAGS.output_dir, "vocab.txt")
with tf.gfile.FastGFile(vocab_file, "w") as f:
f.write("\n".join(vocab.keys()))
tf.logging.info("Wrote vocab file to %s", vocab_file)
word_counts_file = os.path.join(FLAGS.output_dir, "word_counts.txt")
with tf.gfile.FastGFile(word_counts_file, "w") as f:
for i in sorted_indices:
f.write("%s %d\n" % (words[i], freqs[i]))
tf.logging.info("Wrote word counts file to %s", word_counts_file)
return vocab