project init

.editorconfig

@@ -0,0 +1,22 @@
+# EditorConfig is awesome!
+
+# Mark this as the root editorconfig file
+root = true
+
+# Base ruleset for all files
+[*]
+charset = utf-8
+end_of_line = lf
+indent_size = 2
+indent_style = space
+insert_final_newline = true
+trim_trailing_whitespace = true
+
+# Override rules for python
+[*.py]
+indent_size = 4
+
+# Override rules for markdown
+[*.md]
+# trailing whitespace is significant in markdown -> do not remove
+trim_trailing_whitespace = false

.gitattributes

@@ -0,0 +1,18 @@
+# Auto detect text files and perform LF normalization
+# https://pablorsk.medium.com/be-a-git-ninja-the-gitattributes-file-e58c07c9e915
+*                   text=auto
+*.zip               binary
+
+# Hide from GitHub's language detection
+data/**             linguist-documentation
+
+# Remove assets from github statistics
+data/**             linguist-vendored
+
+# Set the language for these files to ensure GitHub doesn't show the comments as errors
+.vscode/*.json     linguist-language=JSON5
+
+# Do not try and merge these files
+data/**            -diff
+archive.zip        -diff
+Pipfile.lock       -diff

.gitignore

@@ -0,0 +1,194 @@
+# Created by https://www.toptal.com/developers/gitignore/api/visualstudiocode,python
+# Edit at https://www.toptal.com/developers/gitignore?templates=visualstudiocode,python
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+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/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+### VisualStudioCode ###
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+!.vscode/*.code-snippets
+
+# Local History for Visual Studio Code
+.history/
+
+# Built Visual Studio Code Extensions
+*.vsix
+
+### VisualStudioCode Patch ###
+# Ignore all local history of files
+.history
+.ionide
+
+# End of https://www.toptal.com/developers/gitignore/api/visualstudiocode,python

.pre-commit-config.yaml

@@ -0,0 +1,19 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+      - id: check-ast
+      - id: check-case-conflict
+      - id: check-merge-conflict
+      - id: check-toml
+      - id: debug-statements
+      - id: end-of-file-fixer
+      - id: mixed-line-ending
+      - id: trailing-whitespace
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.4.4
+    hooks:
+      - id: ruff
+        args: [ --fix ]
+      - id: ruff-format

.vscode/settings.json

@@ -0,0 +1,27 @@
+{
+  "notebook.formatOnSave.enabled": true,
+  "notebook.codeActionsOnSave": {
+    "notebook.source.fixAll": "explicit",
+    "notebook.source.organizeImports": "explicit"
+  },
+  "[python]": {
+    "editor.formatOnSave": true,
+    "editor.codeActionsOnSave": {
+      "source.fixAll": "explicit",
+      "source.organizeImports": "explicit"
+    },
+    "editor.defaultFormatter": "charliermarsh.ruff"
+  },
+  "python.terminal.activateEnvironment": false,
+  "files.exclude": {
+    "**/.git": true,
+    "**/.svn": true,
+    "**/.hg": true,
+    "**/CVS": true,
+    "**/.DS_Store": true,
+    "**/Thumbs.db": true,
+    "**/__pycache__": true,
+    "**/.ruff_cache": true,
+    "**/.venv": true,
+  }
+}

README.md

@@ -0,0 +1,2 @@
+Movie Recommendation System
+---

pyproject.toml

@@ -0,0 +1,117 @@
+[tool.poetry]
+name = "movie-recommender"
+package-mode = false
+
+[tool.poetry.dependencies]
+python = "^3.12"
+
+[tool.poetry.group.dev.dependencies]
+ruff = "^0.4.1"
+pre-commit = "^3.7.0"
+ipykernel = "^6.29.4"
+ipympl = "^0.9.4"
+
+[tool.poetry.plugins.dotenv]
+location = ".env"
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.ruff]
+extend-include = ["*.ipynb"]
+line-length = 120
+indent-width = 4
+
+[tool.ruff.lint]
+fixable = ["ALL"]
+# select = [
+#   "E",   # pycodestyle
+#   "F",   # Pyflakes
+#   "UP",  # pyupgrade
+#   "B",   # flake8-bugbear
+#   "SIM", # flake8-simplify
+#   "I",   # isort
+# ]
+# ignore = [
+#   # Conflicting rules with the formatter
+#   "W191",   # tab-indentation
+#   "E111",   # indentation-with-invalid-multiple
+#   "E114",   # indentation-with-invalid-multiple-comment
+#   "E117",   # over-indented
+#   "D206",   # indent-with-spaces
+#   "D300",   # triple-single-quotes
+#   "Q000",   # bad-quotes-inline-string
+#   "Q001",   # bad-quotes-multiline-string
+#   "Q002",   # bad-quotes-docstring
+#   "Q003",   # avoidable-escaped-quote
+#   "COM812", # missing-trailing-comma
+#   "COM819", # prohibited-trailing-comma
+#   "ISC001", # single-line-implicit-string-concatenation
+#   "ISC002", # multi-line-implicit-string-concatenation
+#   "E501",   # line-too-long
+# ]
+ignore = [
+  "E501",    # pycodestyle line too long, handled by black
+  "D100",    # pydocstyle - missing docstring in public module
+  "D101",    # pydocstyle - missing docstring in public class
+  "D102",    # pydocstyle - missing docstring in public method
+  "D103",    # pydocstyle - missing docstring in public function
+  "D104",    # pydocstyle - missing docstring in public package
+  "D105",    # pydocstyle - missing docstring in magic method
+  "D106",    # pydocstyle - missing docstring in public nested class
+  "D107",    # pydocstyle - missing docstring in __init__
+  "D202",    # pydocstyle - no blank lines allowed after function docstring
+  "D205",    # pydocstyle - 1 blank line required between summary line and description
+  "D415",    # pydocstyle - first line should end with a period, question mark, or exclamation point
+  "UP037",   # pyupgrade - removes quotes from type annotation
+  "A003",    # flake8-builtins - class attribute {name} is shadowing a python builtin
+  "B010",    # flake8-bugbear - do not call setattr with a constant attribute value
+  "B008",    #  flake8-bugbear - Do not perform function call `Parameter` in argument defaultsRuff(B008)
+  "RUF012",  # ruff - mutable class attributes should be annotated with `typing.ClassVar`
+  "ANN401",  # ruff - Dynamically typed expressions (typing.Any) are disallowed
+  "ANN102",
+  "ANN101",  # ruff - Missing type annotation for `self` in method
+  "PLR0913", # ruff - Too many arguments to function call
+  "PLR2004", # Magic value used in comparison
+  "FBT001",  # Boolean typed positional argument in function definition
+  "FBT002",  # Boolean default positional argument in function definition
+  "FBT003",  # Boolean Boolean default positional argument in function definition
+  "ARG002",  # Unused method argument
+  "ARG001",  #  Unused function argument
+  "TD002",
+  "TD003",
+  "FIX002",
+  "PGH003",
+  "RUF006",
+  "SLF001",
+  "PT007",
+  'PT004',
+  'PT005',
+  'S603',
+  "E501",    # pycodestyle line too long, handled by black
+  "PLW2901", # pylint - for loop variable overwritten by assignment target
+  "ANN401",
+  "ANN102",
+  "ANN101",
+  "FBT",
+  "PLR0913", # too many arguments
+  "PT",
+  "TD",
+  "PERF203", # ignore for now; investigate
+]
+select = ["ALL"]
+# Allow unused variables when underscore-prefixed
+dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"
+
+[tool.ruff.lint.pydocstyle]
+convention = "google"
+
+[tool.ruff.lint.mccabe]
+max-complexity = 12
+
+[tool.ruff.format]
+docstring-code-format = true
+
+[tool.ruff.lint.per-file-ignores]
+"__init__.py" = ["E402"]