Added precommit hooks (#63)

* Implemented new pre-commit hooks and removed the paper directory

The paper directory will be added in another PR after cleaning up

* Added tests to the dev branch

* Skipping tests until get the correct secrets to the repo

Author: maykcaldas

.github/workflows/build.yml

@@ -1,4 +1,3 @@
-
 name: publish
 
 on:
@@ -9,27 +8,26 @@ on:
 
 jobs:
   publish:
-
     runs-on: ubuntu-latest
 
     steps:
-    - uses: actions/checkout@v2
-    - name: Set up Python "3.10"
-      uses: actions/setup-python@v2
-      with:
-        python-version: "3.10"
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install flake8 pytest build
-        if [ -f dev-requirements.txt ]; then pip install -r dev-requirements.txt; fi
-    - name: Install
-      run: |
-        pip install .[gpr]
-    - name: Build a binary wheel and a source tarball
-      run: |
-        python -m build --sdist --wheel --outdir dist/ .
-    - name: Publish distribution 📦 to PyPI
-      uses: pypa/gh-action-pypi-publish@master
-      with:
-        password: ${{ secrets.PYPI_API_TOKEN }}
+      - uses: actions/checkout@v2
+      - name: Set up Python "3.10"
+        uses: actions/setup-python@v2
+        with:
+          python-version: "3.10"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install flake8 pytest build
+          if [ -f dev-requirements.txt ]; then pip install -r dev-requirements.txt; fi
+      - name: Install
+        run: |
+          pip install .[gpr]
+      - name: Build a binary wheel and a source tarball
+        run: |
+          python -m build --sdist --wheel --outdir dist/ .
+      - name: Publish distribution 📦 to PyPI
+        uses: pypa/gh-action-pypi-publish@master
+        with:
+          password: ${{ secrets.PYPI_API_TOKEN }}

.github/workflows/tests.yml

@@ -1,36 +1,52 @@
-
-name: test
-
-on:
-  push:
-    branches: [ main ]
-  pull_request:
-    branches: [ main ]
-
-jobs:
-  test:
-
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version: [3.9, "3.10", 3.11]
-
-    steps:
-    - uses: actions/checkout@v2
-    - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
-      with:
-        python-version: ${{ matrix.python-version }}
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install pytest  build
-        if [ -f dev-requirements.txt ]; then pip install -r dev-requirements.txt; fi
-    - name: Install
-      run: |
-        pip install .[gpr]
-    - name: Run Test
-      env:
-        OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
-      run: |
-         pytest tests
+name: test
+
+on:
+  push:
+    branches: [main, dev]
+  pull_request:
+    branches: [main, dev]
+
+jobs:
+  pre-commit:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: "3.10"
+      - name: Install pre-commit
+        run: |
+          python -m pip install --upgrade pip
+          pip install pre-commit
+      - name: Run pre-commit
+        run: |
+          pre-commit run --all-files
+
+  test:
+    # Skip this job for now - will be re-enabled later
+    if: false
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: [3.11]
+
+    steps:
+      - uses: actions/checkout@v2
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v2
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install pytest build
+          if [ -f dev-requirements.txt ]; then pip install -r dev-requirements.txt; fi
+      - name: Install
+        run: |
+          pip install .[gpr]
+      - name: Run Test
+        env:
+          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+        run: |
+          pytest tests

.pre-commit-config.yaml

@@ -1,19 +1,39 @@
-repos:
-  - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v2.2.3
-    hooks:
-      - id: trailing-whitespace
-      - id: check-yaml
-      - id: end-of-file-fixer
-      - id: mixed-line-ending
-  - repo: https://github.com/psf/black
-    rev: "22.3.0"
-    hooks:
-    - id: black
-  - repo: https://github.com/tomcatling/black-nb
-    rev: "0.7"
-    hooks:
-      - id: black-nb
-        description: strip output and black source
-        additional_dependencies: ['black[jupyter]']
-        args: ["--clear-output"]
+default_language_version:
+  python: python3
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v5.0.0
+    hooks:
+      - id: check-added-large-files
+      - id: fix-byte-order-marker
+      - id: check-case-conflict
+      - id: check-merge-conflict
+      - id: check-shebang-scripts-are-executable
+      - id: check-symlinks
+      - id: check-toml
+      - id: check-yaml
+      - id: debug-statements
+      - id: detect-private-key
+      - id: end-of-file-fixer
+      - id: mixed-line-ending
+      - id: trailing-whitespace
+  - repo: https://github.com/psf/black
+    rev: "22.3.0"
+    hooks:
+      - id: black
+  - repo: https://github.com/srstevenson/nb-clean
+    rev: 4.0.1
+    hooks:
+      - id: nb-clean
+        args: [--preserve-cell-outputs, --remove-empty-cells]
+  - repo: https://github.com/rbubley/mirrors-prettier
+    rev: v3.4.2
+    hooks:
+      - id: prettier
+  - repo: https://github.com/codespell-project/codespell
+    rev: v2.3.0
+    hooks:
+      - id: codespell
+        additional_dependencies: [".[toml]"]
+        exclude_types: [jupyter]
+        args: ["-L formate,Nd"]

README.md

@@ -1,17 +1,16 @@
 # 🤖 BO-LIFT: Bayesian Optimization using in-context learning
 
-
 ![version](https://img.shields.io/badge/version-0.0.1-brightgreen)
 [![paper](https://img.shields.io/badge/paper-arXiv-red)](https://arxiv.org/abs/2304.05341)
 [![MIT license](https://img.shields.io/badge/License-MIT-blue.svg)](https://lbesson.mit-license.org/)
 
-
 BO-LIFT does regression with uncertainties using frozen Large Language Models by using token probabilities.
 It uses LangChain to select examples to create in-context learning prompts from training data.
 By selecting examples, it can consider more training data than it fits in the model's context window.
 Being able to predict uncertainty, allow the employment of interesting techniques such as Bayesian Optimization.
 
 ## Table of content
+
 - [BO-LIFT](#-bo-lift-bayesian-optimization-using-in-context-learning)
   - [Install](#install-)
   - [Usage](#usage-)
@@ -48,6 +47,7 @@ os.environ["OPENAI_API_KEY"] = "<your-key-here>"
 ### Quickstart 🔥
 
 `bolift` provides a simple interface to use the model.
+
 ```py
 # Create the model object
 asktell = bolift.AskTellFewShotTopk()
@@ -62,9 +62,11 @@ asktell.tell("1-bromonaphthalene", -4.35)
 yhat = asktell.predict("1-bromobutane")
 print(yhat.mean(), yhat.std())
 ```
+
 This prediction returns $-2.92 \pm 1.27$.
 
 Further improvements can be done by using Bayesian Optimization.
+
 ```py
 # Create a list of examples
 pool_list = [
@@ -84,9 +86,11 @@ asktell.ask(pool)
 (['1-bromo-2-methylpropane'], [-1.284916344093158], [-1.92])
 
 ```
+
 Where the first value is the selected point, the second value is the value of the acquisition function, and the third value is the predicted mean.
 
 Let's tell this point to the model with its correct label and make a prediction:
+
 ```py
 asktell.tell("1-bromo-2-methylpropane", -2.430)
 
@@ -113,8 +117,10 @@ asktell = bolift.AskTellFewShotTopk(
   temperature=0.7,
 )
 ```
+
 Other arguments can be used to customize the prompt (`prefix`, `prompt_template`, `suffix`) and the in-context learning procedure (`use_quantiles`, `n_quantiles`).
 Additionally, we implemented other models. A brief list can be seen below:
+
 - AskTellFewShotMulti;
 - AskTellFewShotTopk;
 - AskTellFinetuning;
@@ -149,18 +155,21 @@ for i in range(n):
 
 asktell.inv_predict(20.0)
 ```
+
 The data for that is available in the paper directory.
 This generated the following procedure:
+
 ```
 the synthesis procedure:"A 30 wt% tungsten carbide catalyst was prepared with Cu dopant metal at 5 wt% and carburized at 835 C. The reaction was run at 350 ºC"
 ```
 
 ### Citation
 
 Please, cite [Ramos et al.](https://arxiv.org/abs/2304.05341):
+
 ```
 @misc{ramos2023bayesian,
-      title={Bayesian Optimization of Catalysts With In-context Learning}, 
+      title={Bayesian Optimization of Catalysts With In-context Learning},
       author={Mayk Caldas Ramos and Shane S. Michtavy and Marc D. Porosoff and Andrew D. White},
       year={2023},
       eprint={2304.05341},

bolift/__init__.py

@@ -19,5 +19,5 @@
     "AskTellRidgeKernelRegression",
     "AskTellNearestNeighbor",
     "Pool",
-    "BOLiftTool"
-    ]
+    "BOLiftTool",
+]

bolift/aqfxns.py

@@ -10,13 +10,15 @@ def expected_improvement(dist, best):
     elif isinstance(dist, GaussDist):
         return expected_improvement_g(dist.mean(), dist.std(), best)
 
+
 def log_expected_improvement(dist, best):
     """Log Expected improvement for the given discrete distribution"""
     if isinstance(dist, DiscreteDist):
         return log_expected_improvement_d(dist.probs, dist.values, best)
     elif isinstance(dist, GaussDist):
         return log_expected_improvement_g(dist.mean(), dist.std(), best)
- 
+
+
 # I think it's just taking the log of the final EI computation. Will test this later
 # def log_expected_improvement(dist, best):
 #     """Log Expected improvement for the given discrete distribution"""
@@ -25,6 +27,7 @@ def log_expected_improvement(dist, best):
 #     elif isinstance(dist, GaussDist):
 #         return np.log(expected_improvement_g(dist.mean(), dist.std(), best))
 
+
 def probability_of_improvement(dist, best):
     """Probability of improvement for the given discrete distribution"""
     if isinstance(dist, DiscreteDist):
@@ -54,12 +57,14 @@ def expected_improvement_d(probs, values, best):
     ei = np.sum(np.maximum(values - best, 0) * probs)
     return ei
 
+
 def log_expected_improvement_d(probs, values, best):
     """Log Expected improvement for the given discrete distribution"""
     # ei = np.sum(np.maximum(values - best, 0) * probs)
-    log_ei = np.log(np.sum(np.maximum(values - best, 0) * probs)+1e-15)
+    log_ei = np.log(np.sum(np.maximum(values - best, 0) * probs) + 1e-15)
     return log_ei
 
+
 def probability_of_improvement_d(probs, values, best):
     """Probability of improvement for the given discrete distribution"""
     pi = np.sum(np.cast[float](values > best) * probs)
@@ -80,32 +85,34 @@ def greedy_d(probs, values, best):
 
 def expected_improvement_g(mean, std, best):
     """Expected improvement for the given Gaussian distribution"""
-    eps=1e-15
-    z = (mean - best) / (std+eps)
+    eps = 1e-15
+    z = (mean - best) / (std + eps)
     ei = (mean - best) * norm.cdf(z) + std * norm.pdf(z)
     return ei
 
+
 def log_expected_improvement_g(mean, std, best):
     """Log Expected improvement for the given Gaussian distribution"""
-    eps=1e-15
-    z = (mean - best) / (std+eps)
+    eps = 1e-15
+    z = (mean - best) / (std + eps)
     # ei = std * h(z)
     # ei = std * (norm.pdf(z) + z * norm.cdf(z))
     log_ei = np.log(std) + np.log((norm.pdf(z) + z * norm.cdf(z)))
     return log_ei
 
+
 def probability_of_improvement_g(mean, std, best):
     """Probability of improvement for the given Gaussian distribution"""
-    eps=1e-15
-    z = (mean - best) / (std+eps)
+    eps = 1e-15
+    z = (mean - best) / (std + eps)
     pi = norm.cdf(z)
     return pi
 
 
 def upper_confidence_bound_g(mean, std, best, _lambda):
     """Upper confidence bound for the given Gaussian distribution"""
-    eps=1e-15
-    return mean + _lambda * (std+eps)
+    eps = 1e-15
+    return mean + _lambda * (std + eps)
 
 
 def greedy_g(mean, std, best):