Merge branch 'master' into fix-cluster-manager

.github/workflows/CI_conda_forge.yml

@@ -16,26 +16,12 @@ jobs:
     timeout-minutes: 60
     defaults:
       run:
-        shell: bash -l {0}
+        shell: bash -el {0}
     strategy:
       fail-fast: false
       matrix:
-        python-version: ['3.10', '3.11', '3.12']
-        os: ['ubuntu-latest']
-        use-mamba: [true, false]
-        include:
-          - python-version: '3.10'
-            os: 'windows-latest'
-            use-mamba: true
-          - python-version: '3.12'
-            os: 'windows-latest'
-            use-mamba: true
-          - python-version: '3.10'
-            os: 'macos-latest'
-            use-mamba: true
-          - python-version: '3.12'
-            os: 'macos-latest'
-            use-mamba: true
+        python-version: ['3.10', '3']
+        os: ['ubuntu-latest', 'windows-latest', 'macos-latest']
 
     steps:
       - name: "Set up Conda"
@@ -46,13 +32,14 @@ jobs:
           auto-activate-base: true
           python-version: ${{ matrix.python-version }}
           activate-environment: pysr-test
-      - name: "Install pysr with mamba"
-        run: conda activate pysr-test && mamba install pysr
-        if: ${{ matrix.use-mamba }}
-      - name: "Install pysr with conda"
-        run: conda activate pysr-test && conda install pysr
-        if: ${{ !matrix.use-mamba }}
+      - name: "Install pysr"
+        run: |
+          conda install -y pysr
+          python -c "import pysr"
+          echo "Finished."
       - name: "Run tests"
         run: |
+          echo "Running tests"
           pip install pytest nbval
           python -m pysr test main,startup
+          echo "Finished."

.github/workflows/update_backend_version.py

@@ -20,7 +20,7 @@
 major, minor, patch, *dev = pyproject_data["project"]["version"].split(".")
 pyproject_data["project"]["version"] = f"{major}.{minor}.{int(patch)+1}"
 
-juliapkg_data["packages"]["SymbolicRegression"]["version"] = f"={new_backend_version}"
+juliapkg_data["packages"]["SymbolicRegression"]["version"] = f"~{new_backend_version}"
 
 with open(pyproject_toml, "w") as toml_file:
     toml_file.write(tomlkit.dumps(pyproject_data))

.pre-commit-config.yaml

@@ -9,25 +9,25 @@ repos:
       - id: check-added-large-files
   # General formatting
   - repo: https://github.com/psf/black
-    rev: 24.10.0
+    rev: 25.1.0
     hooks:
       - id: black
       - id: black-jupyter
         exclude: pysr/test/test_nb.ipynb
   # Stripping notebooks
   - repo: https://github.com/kynan/nbstripout
-    rev: 0.8.0
+    rev: 0.8.1
     hooks:
       - id: nbstripout
         exclude: pysr/test/test_nb.ipynb
   # Unused imports
   - repo: https://github.com/hadialqattan/pycln
-    rev: "v2.4.0"
+    rev: "v2.5.0"
     hooks:
       - id: pycln
   # Sorted imports
   - repo: https://github.com/PyCQA/isort
-    rev: "5.13.2"
+    rev: "6.0.0"
     hooks:
       - id: isort
         additional_dependencies: [toml]

README.md

@@ -27,7 +27,7 @@ If you've finished a project with PySR, please submit a PR to showcase your work
 - [Why PySR?](#why-pysr)
 - [Installation](#installation)
 - [Quickstart](#quickstart)
-- [→ Documentation](https://ai.damtp.cam.ac.uk/PySR)
+- [→ Documentation](https://ai.damtp.cam.ac.uk/pysr)
 - [Contributors](#contributors-)
 
 <div align="center">

docs/examples.md

@@ -546,8 +546,9 @@ y = np.sin(X[:, 0] + X[:, 1]) + X[:, 2]**2
 
 # Define template: we want sin(f(x1, x2)) + g(x3)
 template = TemplateExpressionSpec(
-    function_symbols=["f", "g"],
-    combine="((; f, g), (x1, x2, x3)) -> sin(f(x1, x2)) + g(x3)",
+    expressions=["f", "g"],
+    variable_names=["x1", "x2", "x3"],
+    combine="sin(f(x1, x2)) + g(x3)",
 )
 
 model = PySRRegressor(
@@ -559,15 +560,23 @@ model = PySRRegressor(
 model.fit(X, y)
 ```
 
-You can also use no argument-functions for learning constants, like:
+You can also use parameters in your template expressions, which will be optimized during the search:
 
 ```python
 template = TemplateExpressionSpec(
-    function_symbols=["a", "f"],
-    combine="((; a, f), (x, y)) -> a() * sin(f(x, y))",
+    expressions=["f", "g"],
+    variable_names=["x1", "x2", "x3"],
+    parameters={"p1": 2, "p2": 1},  # p1 has length 2, p2 has length 1
+    combine="p1[1] * sin(f(x1, x2)) + p1[2] * g(x3) + p2[1]",
 )
 ```
 
+This will learn an equation of the form:
+
+$$ y = \alpha_1 \sin(f(x_1, x_2)) + \alpha_2 g(x_3) + \beta $$
+
+where $\alpha_1, \alpha_2$ are stored in `p1` and $\beta$ is stored in `p2`. The parameters will be optimized during the search.
+
 ### Parametric Expressions
 
 When your data has categories with shared equation structure but different parameters,
@@ -609,6 +618,20 @@ model.fit(X, y, category=category)
 
 See [Expression Specifications](/api/#expression-specifications) for more details.
 
+You can also use `TemplateExpressionSpec` in the same way, passing
+the category as a column of `X`:
+
+```python
+spec = TemplateExpressionSpec(
+    expressions=["f", "g"],
+    variable_names=["x1", "x2", "class"],
+    combine="p1[class] * sin(f(x1, x2)) + p2[class]",
+)
+```
+
+this column will automatically be converted to integers.
+
+
 ## 12. Using TensorBoard for Logging
 
 You can use TensorBoard to visualize the search progress, as well as

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "pysr"
-version = "1.3.1"
+version = "1.5.0"
 authors = [
     {name = "Miles Cranmer", email = "miles.cranmer@gmail.com"},
 ]
@@ -22,7 +22,7 @@ dependencies = [
     "pandas>=0.21.0,<3.0.0",
     "numpy>=1.13.0,<3.0.0",
     "scikit_learn>=1.0.0,<2.0.0",
-    "juliacall==0.9.23",
+    "juliacall==0.9.24",
     "click>=7.0.0,<9.0.0",
     "setuptools>=50.0.0",
 ]

pysr/__init__.py

@@ -1,5 +1,12 @@
+import logging
 import os
 
+pysr_logger = logging.getLogger("pysr")
+pysr_logger.setLevel(logging.INFO)
+handler = logging.StreamHandler()
+handler.setLevel(logging.INFO)
+pysr_logger.addHandler(handler)
+
 if os.environ.get("PYSR_USE_BEARTYPE", "0") == "1":
     from beartype.claw import beartype_this_package