版本更新

.gitignore

@@ -0,0 +1,162 @@
+cache
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+# Usually these files are written by a python script from a template
+# before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+# For a library or package, you might want to ignore these files since the code is
+# intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+# However, in case of collaboration, if having platform-specific dependencies or dependencies
+# having no cross-platform support, pipenv may install dependencies that don't work, or not
+# install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+# This is especially recommended for binary packages to ensure reproducibility, and is more
+# commonly ignored for libraries.
+# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+# in version control.
+# https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+# and can be added to the global gitignore or merged into this file. For a more nuclear
+# option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

data_helper.py

@@ -1,9 +1,9 @@
-from collections import Counter
-from torchtext.vocab import Vocab
+import re
+
+import torch
 from torch.utils.data import DataLoader
 from torchtext.data.utils import get_tokenizer
-import torch
-import re
+from torchtext.vocab import build_vocab_from_iterator
 from tqdm import tqdm
 
 
@@ -29,12 +29,18 @@ def build_vocab(tokenizer, filepath, min_freq, specials=None):
  """
  if specials is None:
  specials = ['<unk>', '<pad>']
- counter = Counter()
- with open(filepath, encoding='utf8') as f:
- for string_ in tqdm(f):
- string_ = string_.strip().split('","')[-1][:-1] # 新闻描述
- counter.update(tokenizer(clean_str(string_)))
- return Vocab(counter, min_freq=min_freq, specials=specials)
+
+ def yield_tokens(filepath):
+ with open(filepath, encoding='utf8') as f:
+ for string_ in f:
+ yield tokenizer(string_)
+
+ vocab_obj = build_vocab_from_iterator(yield_tokens(
+ filepath), specials=specials, min_freq=min_freq)
+
+ vocab_obj.set_default_index(vocab_obj['<unk>'])
+
+ return vocab_obj
 
 
 def pad_sequence(sequences, batch_first=False, max_len=None, padding_value=0):
@@ -96,7 +102,7 @@ def data_process(self, filepath):
  :return:
  """
 
- raw_iter = open(filepath,encoding='utf8').readlines()
+ raw_iter = open(filepath, encoding='utf8').readlines()
  data = []
  max_len = 0
  for raw in tqdm(raw_iter, ncols=80):
@@ -111,7 +117,8 @@ def data_process(self, filepath):
  return data, max_len
 
  def load_train_val_test_data(self, train_file_paths, test_file_paths):
- train_data, max_sen_len = self.data_process(train_file_paths) # 得到处理好的所有样本
+ train_data, max_sen_len = self.data_process(
+ train_file_paths) # 得到处理好的所有样本
  if self.max_sen_len == 'same':
  self.max_sen_len = max_sen_len
  test_data, _ = self.data_process(test_file_paths)