Add pre-commit hooks: whitespace, eof, yaml

.github/ISSUE_TEMPLATE/feature_request.yml

@@ -19,4 +19,3 @@ body:
     attributes:
       value: |
         Be sure to check out the [PySR forums](https://github.com/MilesCranmer/PySR/discussions) to chat with other users about PySR use-cases!
-

.github/workflows/CI.yml

@@ -32,7 +32,7 @@ jobs:
         julia-version: ['1.9']
         python-version: ['3.10']
         os: [ubuntu-latest]
-    
+
     steps:
       - uses: actions/checkout@v3
       - name: "Set up Julia"
@@ -96,7 +96,7 @@ jobs:
       matrix:
         python-version: ['3.9']
         os: ['ubuntu-latest']
-    
+
     steps:
       - uses: actions/checkout@v3
       - name: "Cache conda"
@@ -129,7 +129,7 @@ jobs:
 
   coveralls:
     name: Indicate completion to coveralls.io
-    needs: 
+    needs:
       - test
     runs-on: ubuntu-latest
     defaults:

.github/workflows/CI_Windows.yml

@@ -32,7 +32,7 @@ jobs:
         julia-version: ['1.9']
         python-version: ['3.10']
         os: [windows-latest]
-    
+
     steps:
       - uses: actions/checkout@v3
       - name: "Set up Julia"

.github/workflows/CI_conda_forge.yml

@@ -23,7 +23,7 @@ jobs:
         python-version: ['3.8', '3.9', '3.10', '3.11']
         os: ['ubuntu-latest', 'macos-latest']
         use-mamba: [true, false]
-    
+
     steps:
       - name: "Set up Conda"
         uses: conda-incubator/setup-miniconda@v2

.github/workflows/CI_docker_large_nightly.yml

@@ -22,8 +22,8 @@ jobs:
         python-version: ['3.10']
         os: [ubuntu-latest]
         arch: ['linux/amd64', 'linux/arm64']
-      
-    
+
+
     steps:
       - uses: actions/checkout@v3
       - name: Set up QEMU

.github/workflows/CI_large_nightly.yml

@@ -26,7 +26,7 @@ jobs:
         julia-version: ['1.6', '1.8', '1.9']
         python-version: ['3.7', '3.8', '3.9', '3.10', '3.11']
         os: [ubuntu-latest, macos-latest, windows-latest]
-    
+
     steps:
       - uses: actions/checkout@v3
       - name: "Set up Julia"

.github/workflows/CI_mac.yml

@@ -32,7 +32,7 @@ jobs:
         julia-version: ['1.9']
         python-version: ['3.10']
         os: [macos-latest]
-    
+
     steps:
       - uses: actions/checkout@v3
       - name: "Set up Julia"

.github/workflows/codeql-analysis.yml

@@ -37,11 +37,11 @@ jobs:
         # If you wish to specify custom queries, you can do so here or in a config file.
         # By default, queries listed here will override any specified in a config file.
         # Prefix the list here with "+" to use these queries and those in the config file.
-        
+
         # Details on CodeQL's query packs refer to : https://docs.github.com/en/code-security/code-scanning/automatically-scanning-your-code-for-vulnerabilities-and-errors/configuring-code-scanning#using-queries-in-ql-packs
         # queries: security-extended,security-and-quality
 
-        
+
     # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
     # If this step fails, then you should remove it and run the build manually (see below)
     - name: Autobuild
@@ -50,7 +50,7 @@ jobs:
     # ℹ️ Command-line programs to run using the OS shell.
     # 📚 See https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions#jobsjob_idstepsrun
 
-    #   If the Autobuild fails above, remove it and uncomment the following three lines. 
+    #   If the Autobuild fails above, remove it and uncomment the following three lines.
     #   modify them (or add more) to build your code if your project, please refer to the EXAMPLE below for guidance.
 
     # - run: |

.github/workflows/docker_deploy.yml

@@ -9,7 +9,7 @@ on:
     tags:
       - "v*.*.*"
   workflow_dispatch:
-  
+
 
 jobs:
   docker:

.github/workflows/docs.yml

@@ -18,7 +18,7 @@ jobs:
     defaults:
       run:
         shell: bash
-    
+
     steps:
       - uses: actions/checkout@v3
       - name: "Set up Python"
@@ -33,4 +33,4 @@ jobs:
       - name: "Build API docs"
         run: cd docs && ./gen_docs.sh
       - name: "Deploy documentation"
-        run: mkdocs gh-deploy --force
+        run: mkdocs gh-deploy --force

.github/workflows/update_backend.yml

@@ -48,7 +48,7 @@ jobs:
           CURRENT_PYSR_PATCH_VERSION=$(python -c 'import pysr; print(pysr.version.__version__.split(".")[-1], end="")' 2>/dev/null)
           NEW_PYSR_PATCH_VERSION=$((CURRENT_PYSR_PATCH_VERSION + 1))
           sed -i "s/^__version__ = .*/__version__ = \"$(python -c 'import pysr; print(".".join(pysr.version.__version__.split(".")[:-1]), end="")' 2>/dev/null).${NEW_PYSR_PATCH_VERSION}\"/" pysr/version.py
-          
+
           # Set SymbolicRegression.jl version:
           sed -i "s/^__symbolic_regression_jl_version__ = .*/__symbolic_regression_jl_version__ = \"${{ steps.get-latest.outputs.version }}\"/" pysr/version.py
 

.pre-commit-config.yaml

@@ -0,0 +1,9 @@
+repos:
+  # General linting:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v3.2.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+      - id: check-added-large-files

CONTRIBUTORS.md

@@ -121,4 +121,4 @@ Thanks for being part of the PySR community!
 <!-- prettier-ignore-end -->
 
 <!-- ALL-CONTRIBUTORS-LIST:END -->
-</div>
+</div>

README.md

@@ -155,7 +155,7 @@ The PySR build in conda includes all required dependencies, so you can install i
 conda install -c conda-forge pysr
 ```
 
-from within your target conda environment. 
+from within your target conda environment.
 
 However, note that the conda install does not support precompilation of Julia libraries, so the
 start time may be slightly slower as the JIT-compilation will be running.
@@ -305,7 +305,7 @@ model = PySRRegressor(
     # ^ 2 populations per core, so one is always running.
     population_size=50,
     # ^ Slightly larger populations, for greater diversity.
-    ncyclesperiteration=500, 
+    ncyclesperiteration=500,
     # ^ Generations between migrations.
     niterations=10000000,  # Run forever
     early_stop_condition=(

benchmarks/README.md

@@ -21,7 +21,7 @@ v0.3.6 | 25900
 v0.3.7 | 26600
 v0.3.8 | 7470
 v0.3.9 | 6760
-v0.3.10 | 
+v0.3.10 |
 v0.3.11 | 19500
 v0.3.12 | 19000
 v0.3.13 | 15200

datasets/FeynmanEquations.csv

@@ -98,4 +98,4 @@ III.15.14,10,96,m,(h/(2*pi))**2/(2*E_n*d**2),3,h,1,5,E_n,1,5,d,1,5,,,,,,,,,,,,,,
 III.15.27,10,97,k,2*pi*alpha/(n*d),3,alpha,1,5,n,1,5,d,1,5,,,,,,,,,,,,,,,,,,,,,
 III.17.37,10,98,f,beta*(1+alpha*cos(theta)),3,beta,1,5,alpha,1,5,theta,1,5,,,,,,,,,,,,,,,,,,,,,
 III.19.51,10,99,E_n,-m*q**4/(2*(4*pi*epsilon)**2*(h/(2*pi))**2)*(1/n**2),5,m,1,5,q,1,5,h,1,5,n,1,5,epsilon,1,5,,,,,,,,,,,,,,,
-III.21.20,10,100,j,-rho_c_0*q*A_vec/m,4,rho_c_0,1,5,q,1,5,A_vec,1,5,m,1,5,,,,,,,,,,,,,,,,,,
+III.21.20,10,100,j,-rho_c_0*q*A_vec/m,4,rho_c_0,1,5,q,1,5,A_vec,1,5,m,1,5,,,,,,,,,,,,,,,,,,

docs/.gitignore

@@ -1,4 +1,4 @@
 build
 api.md
 index.md.bak
-papers.md
+papers.md

docs/_api.md

@@ -6,7 +6,7 @@ Let's look at them below.
 PARAMSKEY
 
 ## PySRRegressor Functions
-        
+
 ::: pysr.PySRRegressor.fit
     options:
         show_root_heading: true
@@ -60,5 +60,3 @@ PARAMSKEY
         show_root_heading: true
         heading_level: 3
         show_root_full_path: false
-
-

docs/backend.md

@@ -12,7 +12,7 @@ Generally you can do this as follows:
 git clone https://github.com/MilesCranmer/SymbolicRegression.jl
 ```
 2. Edit the source code in `src/` to your requirements:
-    -  The documentation for the backend is given [here](https://astroautomata.com/SymbolicRegression.jl/dev/). 
+    -  The documentation for the backend is given [here](https://astroautomata.com/SymbolicRegression.jl/dev/).
     - Throughout the package, you will often see template functions which typically use a symbol `T` (such as in the string `where {T<:Real}`). Here, `T` is simply the datatype of the input data and stored constants, such as `Float32` or `Float64`. Writing functions in this way lets us write functions generic to types, while still having access to the specific type specified at compilation time.
     - Expressions are stored as binary trees, using the `Node{T}` type, described [here](https://astroautomata.com/SymbolicRegression.jl/dev/types/#SymbolicRegression.CoreModule.EquationModule.Node).
     - Parts of the code which are typically edited by users include:
@@ -26,4 +26,4 @@ git clone https://github.com/MilesCranmer/SymbolicRegression.jl
 
 If you get comfortable enough with the backend, you might consider using the Julia package directly: the API is given on the [SymbolicRegression.jl documentation](https://astroautomata.com/SymbolicRegression.jl/dev/).
 
-If you make a change that you think could be useful to other users, don't hesitate to open a pull request on either the PySR or SymbolicRegression.jl repositories! Contributions are very appreciated.
+If you make a change that you think could be useful to other users, don't hesitate to open a pull request on either the PySR or SymbolicRegression.jl repositories! Contributions are very appreciated.

docs/generate_papers.py

@@ -49,7 +49,7 @@ with open(output_file, "w") as f:
 
 <center>
 {authors}
-    
+
 <small>{affiliations}</small>
 </center>
 

docs/operators.md

@@ -64,5 +64,3 @@ instead of `1.5e3`, if you write any constant numbers.
 Your operator should work with the entire real line (you can use
 abs(x) for operators requiring positive input - see `log_abs`); otherwise
 the search code will experience domain errors.
-
-

docs/options.md

@@ -265,7 +265,7 @@ PySRRegressor(..., loss="loss(x, y) = abs(x * y)")
 With weights:
 
 ```python
-model = PySRRegressor(..., loss="myloss(x, y, w) = w * abs(x - y)") 
+model = PySRRegressor(..., loss="myloss(x, y, w) = w * abs(x - y)")
 model.fit(..., weights=weights)
 ```
 

docs/papers.yml

@@ -151,7 +151,6 @@ papers:
     abstract: "We present an approach for using machine learning to automatically discover the governing equations and hidden properties of real physical systems from observations. We train a \"graph neural network\" to simulate the dynamics of our solar system's Sun, planets, and large moons from 30 years of trajectory data. We then use symbolic regression to discover an analytical expression for the force law implicitly learned by the neural network, which our results showed is equivalent to Newton's law of gravitation. The key assumptions that were required were translational and rotational equivariance, and Newton's second and third laws of motion. Our approach correctly discovered the form of the symbolic force law. Furthermore, our approach did not require any assumptions about the masses of planets and moons or physical constants. They, too, were accurately inferred through our methods. Though, of course, the classical law of gravitation has been known since Isaac Newton, our result serves as a validation that our method can discover unknown laws and hidden properties from observed data. More broadly this work represents a key step toward realizing the potential of machine learning for accelerating scientific discovery."
     image: rediscovering_gravity.png
     date: 2022-02-04
-    link: https://arxiv.org/abs/2202.02306
   - title: (Thesis) On Neural Differential Equations - Section 6.1
     authors:
       - Patrick Kidger (1)

docs/requirements.txt

@@ -1,4 +1,4 @@
 mkdocs-material
 mkdocs-autorefs
 mkdocstrings[python]
-docstring_parser
+docstring_parser

docs/stylesheets/extra.css

@@ -2,4 +2,4 @@
     --md-primary-fg-color:        #C13245;
     --md-primary-fg-color--light: #D35364;
     --md-primary-fg-color--dark:  #982736;
-}
+}

docs/stylesheets/papers_header.txt

@@ -6,4 +6,3 @@ These are sorted by the date of release, with most recent papers at the top.
 
 If you have used PySR in your research,
 please submit a pull request to add your paper to [this file](https://github.com/MilesCranmer/PySR/blob/master/docs/papers.yml).
-

docs/tuning.md

@@ -17,7 +17,7 @@ I run from IPython (Jupyter Notebooks don't work as well[^1]) on the head node o
 5. Set `ncyclesperiteration` to maybe `5000` or so, until the head node occupation is under `10%`.
 6. Set `constraints` and `nested_constraints` as strict as possible. These can help quite a bit with exploration. Typically, if I am using `pow`, I would set `constraints={"pow": (9, 1)}`, so that power laws can only have a variable or constant as their exponent. If I am using `sin` and `cos`, I also like to set `nested_constraints={"sin": {"sin": 0, "cos": 0}, "cos": {"sin": 0, "cos": 0}}`, so that sin and cos can't be nested, which seems to happen frequently. (Although in practice I would just use `sin`, since the search could always add a phase offset!)
 7. Set `maxsize` a bit larger than the final size you want. e.g., if you want a final equation of size `30`, you might set this to `35`, so that it has a bit of room to explore.
-8. Set `maxdepth` strictly, but leave a bit of room for exploration. e.g., if you want a final equation limited to a depth of `5`, you might set this to `6` or `7`, so that it has a bit of room to explore. 
+8. Set `maxdepth` strictly, but leave a bit of room for exploration. e.g., if you want a final equation limited to a depth of `5`, you might set this to `6` or `7`, so that it has a bit of room to explore.
 9.  Set `parsimony` equal to about the minimum loss you would expect, divided by 5-10. e.g., if you expect the final equation to have a loss of `0.001`, you might set `parsimony=0.0001`.
 10. Set `weight_optimize` to some larger value, maybe `0.001`. This is very important if `ncyclesperiteration` is large, so that optimization happens more frequently.
 11. Set `turbo` to `True`. This may or not work, if there's an error just turn it off (some operators are not SIMD-capable). If it does work, it should give you a nice 20% speedup.
@@ -31,7 +31,7 @@ Some things I try out to see if they help:
 2. Try setting `adaptive_parsimony_scaling` a bit larger, maybe up to `1000`.
 3. Sometimes I try using `warmup_maxsize_by`. This is useful if you find that the search finds a very complex equation very quickly, and then gets stuck. It basically forces it to start at the simpler equations and build up complexity slowly.
 4. Play around with different losses:
-    - I typically try `L2DistLoss()` and `L1DistLoss()`. L1 loss is more robust to outliers compared to L2 (L1 finds the median, while L2 finds the mean of a random variable), so is often a good choice for a noisy dataset. 
+    - I typically try `L2DistLoss()` and `L1DistLoss()`. L1 loss is more robust to outliers compared to L2 (L1 finds the median, while L2 finds the mean of a random variable), so is often a good choice for a noisy dataset.
     - I might also provide the `weights` parameter to `fit` if there is some reasonable choice of weighting. For example, maybe I know the signal-to-noise of a particular row of `y` - I would set that SNR equal to the weights. Or, perhaps I do some sort of importance sampling, and weight the rows by importance.
 
 Very rarely I might also try tuning the mutation weights, the crossover probability, or the optimization parameters. I never use `denoise` or `select_k_features` as I find they aren't very useful.

environment.yml

@@ -10,4 +10,4 @@ dependencies:
   - pyjulia
   - openlibm
   - openspecfun
-  - click
+  - click

mkdocs.yml

@@ -13,7 +13,7 @@ theme:
       toggle:
         icon: material/toggle-switch-off-outline
         name: Switch to light mode
-    
+
 
   features:
     - navigation.expand