Restructure codebase

.github/workflows/code_checks.yaml

@@ -0,0 +1,51 @@
+name: code checks
+permissions:
+  contents: read
+  pull-requests: write
+
+on:
+  push:
+    branches:
+      - main
+    paths:
+      - .pre-commit-config.yaml
+      - .github/workflows/code_checks.yml
+      - '**.py'
+      - uv.lock
+      - pyproject.toml
+      - '**.ipynb'
+  pull_request:
+    branches:
+      - main
+    paths:
+      - .pre-commit-config.yaml
+      - .github/workflows/code_checks.yml
+      - '**.py'
+      - uv.lock
+      - pyproject.toml
+      - '**.ipynb'
+
+jobs:
+  run-code-check:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+        with:
+          version: "latest"
+          enable-cache: true
+
+      - name: "Set up Python"
+        uses: actions/setup-python@v5
+        with:
+          python-version-file: ".python-version"
+
+      - name: Install the project
+        run: uv sync --all-extras --dev
+
+      - name: Install dependencies and check code
+        run: |
+          source .venv/bin/activate
+          pre-commit run --all-files

.gitignore

@@ -81,9 +81,6 @@ target/
 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

.pre-commit-config.yaml

@@ -1,6 +1,6 @@
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.4.0  # Use the ref you want to point at
+    rev: v5.0.0  # Use the ref you want to point at
     hooks:
       - id: trailing-whitespace
       - id: check-ast
@@ -11,29 +11,19 @@ repos:
       - id: end-of-file-fixer
       - id: mixed-line-ending
         args: [--fix=lf]
-      - id: requirements-txt-fixer
-      - id: trailing-whitespace
+      - id: detect-private-key
+      - id: check-byte-order-marker
+      - id: check-merge-conflict
+      - id: check-symlinks
       - id: check-yaml
+        args: [--unsafe]
+      - id: check-toml
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.0.280
+    rev: v0.11.4
     hooks:
       - id: ruff
-
-  - repo: https://github.com/psf/black
-    rev: 23.7.0
-    hooks:
-      - id: black
-
-  - repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.4.1
-    hooks:
-      - id: mypy
-
-  - repo: https://github.com/nbQA-dev/nbQA
-    rev: 1.7.0
-    hooks:
-      - id: nbqa-black
-      - id: nbqa-ruff
-      - id: nbqa-check-ast
-      - id: nbqa-mypy
+        args: [--fix, --exit-non-zero-on-fix]
+        types_or: [ python, pyi, jupyter ]
+      - id: ruff-format
+        types_or: [ python, pyi, jupyter ]

.python-version

@@ -0,0 +1 @@
+3.9

README.md

@@ -2,27 +2,56 @@
 This repository contains reference implementations of three self-supervised learning
 techniques explored during the Vector Institute's Self-Supervised Learning (SSL) Bootcamp.
 
-# Installing dependencies
-```
-python3 -m venv /path/to/new/virtual/environment/ssl_env
-source /path/to/new/virtual/environment/ssl_env/bin/activate
-pip install --upgrade pip
-pip install -r requirements.txt
-```
+# Summary of Reference Implementations
 
-If you are on the Vector Institute's Vaughan cluster, the environment is already set up and can be activated with
+| Name | Description | Reference Implementation  |
+|------|-------------|-------|
+Internal Contrastive Learning (ICL) + Latent Outlier Exposure (LOE)| ICL learns to maximize the mutual information between two complementary subsets based on the assumption that the relation between a subset of features and the rest of the features is class-dependent. LOE extends ICL to work with contaminated datasets. | [Anomaly Detection in Tabular Data with ICL](src/contrastive_learning/ICL/ICL.ipynb), [Latent Outlier Exposure for Anomaly Detection with Contaminated Data](src/contrastive_learning/LatentOE/LatentOE_Notebook.ipynb)
+SimMTM | Reconstructs a time series signal from multiple randomly masked versions. Uses series-wise representation similarity to do a weighted aggregation of point-wise representations before reconstruction. | [Beijing PM2.5 Air Quality Forecasting](src/masked_modelling/simmtm/simmtm-BeijingPM25Quality-forecasting.ipynb)
+TabRet | TabRet is a pre-trainable Transformer-based model for tabular data and designed to work on a downstream task that contains columns not seen in pre-training. Unlike other methods, TabRet has an extra learning step before fine-tuning called retokenizing, which calibrates feature embeddings based on the masked autoencoding loss. | [Stroke Prediction with the BRFSS dataset](src/masked_modelling/tabret/TabRet.ipynb)
+Data2Vec | Combines masked prediction with self-distillation to predict contextualized latent representations (produced by the teacher network) based on a partial/masked view of the input (given to the student network). | [Image Classification with STL-10 dataset](src/self_distillation/data2vec_vision.ipynb)
 
+
+# Setting up the environment
+Prior to installing the dependencies for this project, it is recommended to install
+[uv](https://github.com/astral-sh/uv?tab=readme-ov-file#installation) and create
+a virtual environment. You may use whatever virtual environment management tool
+that you like, including uv, conda, and virtualenv.
+
+With uv, you can create a virtual environment with the following command:
+
+```bash
+uv venv -n --seed --python 3.9 /path/to/new/virtual/environment/ssl_env
 ```
-source /ssd003/projects/aieng/public/ssl_bootcamp_resources/venv/bin/activate
-```
+This will create a new virtual environment in the specified path.
+
+**Note**: If you are using the Vector Institute's Vaughan cluster, a virtual
+environment has already been created for you at `/ssd003/projects/aieng/public/ssl_bootcamp_resources/venv`.
+
+Once you have created a virtual environment, you can activate it with the command:
 
-# Using pre-commit hooks
-To check your code at commit time
 ```
-pre-commit install
+source /path/to/new/virtual/environment/ssl_env/bin/activate
 ```
 
-You can also get pre-commit to fix your code
+Then, you can install the dependencies for this project with the following command:
+
+```bash
+git clone https://github.com/VectorInstitute/SSL-Bootcamp.git
+cd SSL-Bootcamp
+uv sync --no-cache --active --dev
+```
+**Note**: The `--active` flag in the above command assumes that you have already
+activated your virtual environment. If you prefer not to create a new virtual
+environment yourself, you can omit the `--active` flag and uv will create a new virtual environment
+for you in the `.venv` directory inside the project root.
+
+## Using pre-commit hooks
+To ensure that your code adheres to the project's style and formatting guidelines,
+you can use pre-commit hooks to check for common issues, such as code formatting,
+linting, and security vulnerabilities. Run the following command before pushing
+your code to the repository:
+
 ```
 pre-commit run --all-files
 ```

pyproject.toml

@@ -1,33 +1,66 @@
-[build-system]
-requires = ["setuptools", "wheel"]
-build-backend = "setuptools.build_meta"
-
-[tool.black]
-line-length = 88
-
-[tool.mypy]
-ignore_missing_imports = true
-install_types = true
-pretty = true
-non_interactive = true
-disallow_untyped_defs = true
-no_implicit_optional = true
-check_untyped_defs = true
+[project]
+name = "ssl-bootcamp"
+version = "0.1.0"
+description = "Reference implementations for the Vector Institute's self-supervised learning (SSL) bootcamp (2023)"
+readme = "README.md"
+authors = [{name = "Vector AI Engineering", email = "[email protected]"}]
+license = "MIT"
+repository = "https://github.com/VectorInstitute/SSL-Bootcamp"
+requires-python = ">=3.9"
+dependencies = [
+    "copulas>=0.12.0",
+    "deepod>=0.4.1",
+    "ipykernel>=6.29.5",
+    "lightning==2.0.6",
+    "lightning-bolts>=0.7.0",
+    "matplotlib>=3.7.5",
+    "notebook>=7.3.3",
+    "numpy>=1.24.4",
+    "optuna>=4.2.1",
+    "pandas>=2.0.3",
+    "pyod>=2.0.4",
+    "pytorch-tabular==1.0.2",
+    "rtdl==0.0.13",
+    "scikit-learn>=1.3.2",
+    "scipy>=1.10.1",
+    "timm==0.9.2",
+    "toml>=0.10.2",
+    "torch==1.13.0",
+    "torchvision==0.14.0",
+    "transformers==4.31.0",
+    "transtab>=0.0.5",
+    "wandb>=0.19.9",
+    "xgboost>=2.1.4",
+]
+
+[dependency-groups]
+dev = [
+    "pre-commit>=3.5.0",
+    "ruff>=0.11.4",
+]
 
 [tool.ruff]
-select = ["B", "C", "D", "E", "F", "I", "W"]
-line-length = 88
+include = ["*.py", "pyproject.toml", "*.ipynb"]
+line-length = 119
+
+[tool.ruff.format]
+quote-style = "double"
+indent-style = "space"
+docstring-code-format = true
 
-[tool.ruff.isort]
+[tool.ruff.lint]
+select = ["A", "B", "C", "E", "F", "I", "W"]
+fixable = ["A", "B", "COM", "C", "C4", "RET", "SIM", "ICN", "Q", "RSE", "E", "F", "I", "W", "PL"]
+ignore = ["E501", "C901"]
+
+[tool.ruff.lint.isort]
 lines-after-imports = 2
 
-[tool.nbqa.addopts]
-ruff = [
-    "--ignore=D100,D203,D211,D212,D213,D401",
-    "--fix",
-    "--line-length=119",
-]
-black = ["--line-length=119"]
+[tool.ruff.lint.pycodestyle]
+max-doc-length = 119
+
+[tool.ruff.lint.pydocstyle]
+convention = "numpy"
 
 [tool.nbqa.md]
 blacken-docs = true