clean code

.flake8

@@ -0,0 +1,28 @@
+[flake8]
+ignore = 
+    # whitespace before ':'
+    E203,
+    # max length constraint
+    E501,
+    # breakline before binary operators
+    W503,
+    # import but not used (used in init files for convenient importing)
+    F401,
+    # do not assign a lambda expression, use a def
+    E731,
+    # too many comment symbols
+    E266,
+    # module level import not at top of file
+    E402
+exclude =
+    # No need to traverse our git directory
+    .git,
+    # There's no value in checking cache directories
+    __pycache__,
+    # This contains our built documentation
+    build,
+    # This contains builds of flake8 that we don't want to check
+    dist,
+    bak,
+    data,
+    debug*.py

.gitignore

@@ -0,0 +1,168 @@
+# 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/
+pip-wheel-metadata/
+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/
+
+# 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
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.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
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__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/
+
+# self-defined
+.vscode/
+debug*.py
+1.html
+data/bid_announcements/source/
+data/bid_announcements/refreshed/
+data/bid_announcements/annotated
+data/bid_announcements/title.txt
+data/bid_announcements/title100.txt
+data/credit_eval/
+data/fin_ann/
+data/bid_ann/
+data/mix_all/
+data/CreditEval_FinAnn/
+data/CreditEval_BidAnn/
+outputs/
+paper_outputs/
+
+news_data_pretrain/
+data/vertical_TextConcat_data_with_table/
+data/**/*.linejson
+data/**/*.json
+data/**/*.txt
+data/**/*.html
+data/**/*.jsonl
+data/**/filtered.lines
+# data/doc_tree_construct
+# data/text_concat
+# data/text_classification
+!/**/.gitkeep
+upload_files/*.json
+upload_predicted_results/*.json
+upload_predicted_results/**/*.json
+debug.py
+watchmen_server.pid
+pytorch_model.bin
+paper_debug/
+logs/