.gitignore

@@ -1,3 +1,5 @@
+data
+
 # ---> VisualStudioCode
 .vscode/*
 !.vscode/settings.json

lab_8/.devcontainer/devcontainer.json

@@ -0,0 +1,22 @@
+// For format details, see https://aka.ms/devcontainer.json. For config options, see the
+// README at: https://github.com/devcontainers/templates/tree/main/src/python
+{
+	"name": "Python 3",
+	// Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile
+	"image": "mcr.microsoft.com/devcontainers/python:1-3.9-bullseye"
+
+	// Features to add to the dev container. More info: https://containers.dev/features.
+	// "features": {},
+
+	// Use 'forwardPorts' to make a list of ports inside the container available locally.
+	// "forwardPorts": [],
+
+	// Use 'postCreateCommand' to run commands after the container is created.
+	// "postCreateCommand": "pip3 install --user -r requirements.txt",
+
+	// Configure tool-specific properties.
+	// "customizations": {},
+
+	// Uncomment to connect as root instead. More info: https://aka.ms/dev-containers-non-root.
+	// "remoteUser": "root"
+}

lab_8/.gitignore

@@ -0,0 +1,174 @@
+# 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
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.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/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# 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/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc

lab_8/README.md

@@ -0,0 +1,3 @@
+# Вычисляем похожие работы
+
+> Использовался Python 3.9.21

lab_8/requirements.txt

@@ -0,0 +1,113 @@
+annotated-types==0.7.0
+argcomplete==1.10.3
+asttokens==3.0.0
+beautifulsoup4==4.8.2
+blis==1.3.0
+catalogue==2.0.10
+certifi==2025.1.31
+chardet==3.0.4
+charset-normalizer==3.4.1
+click==8.1.8
+cloudpathlib==0.21.0
+comm==0.2.2
+compressed-rtf==1.0.7
+confection==0.1.5
+contourpy==1.3.0
+cycler==0.12.1
+cymem==2.0.11
+DAWG2-Python==0.9.0
+debugpy==1.8.14
+decorator==5.2.1
+docx2txt==0.9
+ebcdic==1.1.1
+exceptiongroup==1.2.2
+executing==2.2.0
+extract-msg==0.28.7
+fonttools==4.57.0
+idna==3.10
+IMAPClient==2.1.0
+importlib_metadata==8.6.1
+importlib_resources==6.5.2
+ipykernel==6.29.5
+ipython==8.18.1
+jedi==0.19.2
+Jinja2==3.1.6
+joblib==1.4.2
+jupyter_client==8.6.3
+jupyter_core==5.7.2
+kiwisolver==1.4.7
+langcodes==3.5.0
+language_data==1.3.0
+lxml==5.3.2
+marisa-trie==1.2.1
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+matplotlib==3.9.4
+matplotlib-inline==0.1.7
+mdurl==0.1.2
+murmurhash==1.0.12
+nest-asyncio==1.6.0
+nltk==3.9.1
+numpy==2.0.2
+olefile==0.47
+packaging==24.2
+pandas==2.2.3
+parso==0.8.4
+pdfminer.six==20191110
+pexpect==4.9.0
+pillow==11.1.0
+platformdirs==4.3.7
+preshed==3.0.9
+prompt_toolkit==3.0.50
+psutil==7.0.0
+ptyprocess==0.7.0
+pure_eval==0.2.3
+pycryptodome==3.22.0
+pydantic==2.11.3
+pydantic_core==2.33.1
+Pygments==2.19.1
+pymorphy3==2.0.3
+pymorphy3-dicts-ru==2.4.417150.4580142
+pyparsing==3.2.3
+python-dateutil==2.9.0.post0
+python-docx==1.1.2
+python-pptx==0.6.23
+pytz==2025.2
+pyzmq==26.4.0
+regex==2024.11.6
+requests==2.32.3
+rich==14.0.0
+ru_core_news_sm @ https://github.com/explosion/spacy-models/releases/download/ru_core_news_sm-3.8.0/ru_core_news_sm-3.8.0-py3-none-any.whl
+scikit-learn==1.6.1
+scipy==1.13.1
+seaborn==0.13.2
+shellingham==1.5.4
+six==1.12.0
+smart-open==7.1.0
+sortedcontainers==2.4.0
+soupsieve==2.6
+spacy==3.8.5
+spacy-legacy==3.0.12
+spacy-loggers==1.0.5
+SpeechRecognition==3.8.1
+srsly==2.5.1
+stack-data==0.6.3
+textract==1.6.5
+thinc==8.3.6
+threadpoolctl==3.6.0
+tornado==6.4.2
+tqdm==4.67.1
+traitlets==5.14.3
+typer==0.15.2
+typing-inspection==0.4.0
+typing_extensions==4.13.2
+tzdata==2025.2
+tzlocal==5.3.1
+urllib3==2.4.0
+wasabi==1.1.3
+wcwidth==0.2.13
+weasel==0.4.1
+wrapt==1.17.2
+xlrd==1.2.0
+XlsxWriter==3.2.2
+zipp==3.21.0