Update

.dvcignore

@@ -0,0 +1,3 @@
+# Add patterns of files dvc should ignore, which could improve
+# the performance. Learn more at
+# https://dvc.org/doc/user-guide/dvcignore

.github/workflows/ci.yml

@@ -0,0 +1,34 @@
+name: CI
+
+on:
+  push:
+    branches: [ main, dev ]
+  pull_request:
+    branches: [ main ]
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.11", "3.12"]
+
+    steps:
+    - uses: actions/checkout@v4
+
+    - name: Install uv
+      uses: astral-sh/setup-uv@v3
+      with:
+        version: "latest"
+
+    - name: Set up Python ${{ matrix.python-version }}
+      run: uv python install ${{ matrix.python-version }}
+
+    - name: Install dependencies
+      run: make install
+
+    - name: Run code quality checks (Linting, Formatting Check, Type Check, Pre-commit hooks)
+      run: make check-all
+
+    - name: Run tests with coverage
+      run: make test-cov

.gitignore

@@ -1,34 +1,11 @@
-# folders
-
-## IDEs
-.idea/
-.vscode/
-
-## Cache
-__pycache__
-.ipynb_checkpoints
-
-## Project
-experiments/*
-models/*
-
-
-# files
-
 ## Mac OS
 .DS_Store
-
-## Configs
-.env
-config/*.json
-
+.venv/
 
 # Byte-compiled / optimized / DLL files
 __pycache__/
 *.py[cod]
-*$py.classdvc get https://github.com/iterative/dataset-registry \
-          use-cases/cats-dogs
-
+*$py.class
 
 # C extensions
 *.so
@@ -121,6 +98,12 @@ ipython_config.py
 #   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
@@ -133,8 +116,10 @@ ipython_config.py
 #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
+#   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__/
@@ -185,3 +170,23 @@ cython_debug/
 #  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/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer,
+#  you could uncomment the following to ignore the enitre vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore

.pre-commit-config.yaml

@@ -0,0 +1,63 @@
+# Pre-commit hooks to ensure code quality before commits
+# Install: uv run pre-commit install
+# Run manually: uv run pre-commit run --all-files
+
+repos:
+  # Basic file checks
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+      - id: check-toml
+      - id: check-added-large-files
+        args: ['--maxkb=2048']  # Allow up to 2MB files
+      - id: check-merge-conflict
+      - id: check-case-conflict
+      - id: debug-statements
+        exclude: ^tests/  # Allow debug statements in tests
+
+  # Python code formatting and linting
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.11.11
+    hooks:
+      - id: ruff
+        args: [--fix, --exit-non-zero-on-fix]
+        types_or: [python, pyi, jupyter]
+      - id: ruff-format
+        types_or: [python, pyi, jupyter]
+
+  # Type checking (with relaxed settings for MLOps course)
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.15.0
+    hooks:
+      - id: mypy
+        args: [
+          --config-file=pyproject.toml,
+          --explicit-package-bases,
+          --namespace-packages
+        ]
+        additional_dependencies: [
+          pandas-stubs>=2.0.0,
+          types-PyYAML>=6.0.0,
+          types-requests>=2.31.0,
+        ]
+        exclude: ^tests/  # Skip type checking for tests initially
+
+  # Security scanning
+  - repo: https://github.com/Yelp/detect-secrets
+    rev: v1.5.0
+    hooks:
+      - id: detect-secrets
+        args: ['--baseline', '.secrets.baseline']
+        exclude: ^(\.venv/|\.git/|htmlcov/|\.pytest_cache/|.*\.dvc$)
+
+  # Additional Python checks
+  - repo: https://github.com/pycqa/bandit
+    rev: 1.8.3
+    hooks:
+      - id: bandit
+        args: [--quiet]
+        files: ^src/.*\.py$
+        exclude: ^tests/

.python-version

@@ -0,0 +1 @@
+3.11.6

.secrets.baseline

@@ -0,0 +1,127 @@
+{
+  "version": "1.5.0",
+  "plugins_used": [
+    {
+      "name": "ArtifactoryDetector"
+    },
+    {
+      "name": "AWSKeyDetector"
+    },
+    {
+      "name": "AzureStorageKeyDetector"
+    },
+    {
+      "name": "Base64HighEntropyString",
+      "limit": 4.5
+    },
+    {
+      "name": "BasicAuthDetector"
+    },
+    {
+      "name": "CloudantDetector"
+    },
+    {
+      "name": "DiscordBotTokenDetector"
+    },
+    {
+      "name": "GitHubTokenDetector"
+    },
+    {
+      "name": "GitLabTokenDetector"
+    },
+    {
+      "name": "HexHighEntropyString",
+      "limit": 3.0
+    },
+    {
+      "name": "IbmCloudIamDetector"
+    },
+    {
+      "name": "IbmCosHmacDetector"
+    },
+    {
+      "name": "IPPublicDetector"
+    },
+    {
+      "name": "JwtTokenDetector"
+    },
+    {
+      "name": "KeywordDetector",
+      "keyword_exclude": ""
+    },
+    {
+      "name": "MailchimpDetector"
+    },
+    {
+      "name": "NpmDetector"
+    },
+    {
+      "name": "OpenAIDetector"
+    },
+    {
+      "name": "PrivateKeyDetector"
+    },
+    {
+      "name": "PypiTokenDetector"
+    },
+    {
+      "name": "SendGridDetector"
+    },
+    {
+      "name": "SlackDetector"
+    },
+    {
+      "name": "SoftlayerDetector"
+    },
+    {
+      "name": "SquareOAuthDetector"
+    },
+    {
+      "name": "StripeDetector"
+    },
+    {
+      "name": "TelegramBotTokenDetector"
+    },
+    {
+      "name": "TwilioKeyDetector"
+    }
+  ],
+  "filters_used": [
+    {
+      "path": "detect_secrets.filters.allowlist.is_line_allowlisted"
+    },
+    {
+      "path": "detect_secrets.filters.common.is_ignored_due_to_verification_policies",
+      "min_level": 2
+    },
+    {
+      "path": "detect_secrets.filters.heuristic.is_indirect_reference"
+    },
+    {
+      "path": "detect_secrets.filters.heuristic.is_likely_id_string"
+    },
+    {
+      "path": "detect_secrets.filters.heuristic.is_lock_file"
+    },
+    {
+      "path": "detect_secrets.filters.heuristic.is_not_alphanumeric_string"
+    },
+    {
+      "path": "detect_secrets.filters.heuristic.is_potential_uuid"
+    },
+    {
+      "path": "detect_secrets.filters.heuristic.is_prefixed_with_dollar_sign"
+    },
+    {
+      "path": "detect_secrets.filters.heuristic.is_sequential_string"
+    },
+    {
+      "path": "detect_secrets.filters.heuristic.is_swagger_file"
+    },
+    {
+      "path": "detect_secrets.filters.heuristic.is_templated_secret"
+    }
+  ],
+  "results": {},
+  "generated_at": "2025-05-29T13:17:00Z"
+}

Makefile

@@ -0,0 +1,67 @@
+.PHONY: help install test lint format clean run-pipeline tutorial-setup tutorial-clean tutorial-init tutorial-file tutorial-directory tutorial-changes tutorial-versions tutorial-remotes tutorial-advanced tutorial-pipelines tutorial-full tutorial-reset
+
+help: ## Show this help message
+	@echo "Available commands:"
+	@grep -E '^[a-zA-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | sort | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[36m%-20s\033[0m %s\n", $$1, $$2}'
+
+setup-hooks: ## Install pre-commit hooks
+	uv run pre-commit install
+	@echo "Pre-commit hooks installed!
+
+install: ## Install dependencies
+	uv sync --group dev
+	uv run pre-commit install
+
+pre-commit: ## Run pre-commit on all files
+	uv run pre-commit run --all-files
+
+autofix: lint-fix format ## Automatically fix linting issues and then format code
+	@echo "Code auto-fixing and formatting complete."
+
+type-check: ## Run mypy type checking separately
+	uv run mypy src/ --config-file=pyproject.toml
+
+check-all: lint format-check type-check test pre-commit ## Run all checks (lint + test)
+	@echo "All checks complete."
+
+
+tutorial-clean: ## Clean up all DVC-related files and data (reset to initial state)
+	@echo "🧹 Cleaning up DVC tutorial state..."
+	@# Remove DVC directory and config
+	rm -rf .dvc/
+	@# Remove all .dvc files
+	find . -name "*.dvc" -type f -delete
+	@# Remove data directories and files created during tutorial
+	rm -rf data/
+	rm -rf datadir/
+	rm -rf cats-dogs-untracked/
+	rm -rf imported_data.xml* external_data.xml*
+	@# Remove pipeline files
+	rm -rf dvc.yaml dvc.lock
+	rm -rf model.weights.h5 metrics.csv
+	@# Remove temporary remote storage
+	rm -rf /tmp/dvc_remote_storage
+	@# Clean git index of any staged DVC files
+	-git reset HEAD *.dvc .dvc/ dvc.yaml 2>/dev/null || true
+	@# Remove any DVC-related entries from .gitignore that might have been added
+	@if [ -f .gitignore ]; then \
+		grep -v "^/data" .gitignore > .gitignore.tmp && mv .gitignore.tmp .gitignore || true; \
+		grep -v "^/datadir" .gitignore > .gitignore.tmp && mv .gitignore.tmp .gitignore || true; \
+	fi
+	@# Remove Git branches created during tutorial
+	@echo "Switching to a safe branch before cleanup..."
+	@if git show-ref --verify --quiet refs/heads/main; then \
+		git checkout main; \
+	elif git show-ref --verify --quiet refs/heads/master; then \
+		git checkout master; \
+	else \
+		git checkout -b cleanup-temp; \
+	fi
+	@echo "Removing tutorial branches..."
+	@for branch in cats-dogs-v1 cats-dogs-v2 tutorial cleanup-temp; do \
+		if git show-ref --verify --quiet refs/heads/$$branch && [ "$$branch" != "$$(git branch --show-current)" ]; then \
+			echo "Deleting branch $$branch"; \
+			git branch -D $$branch 2>/dev/null || true; \
+		fi; \
+	done
+	@echo "✅ DVC tutorial cleanup complete! Repository reset to initial state."