feat(core): implement get_params() API for steps

ibis_ml/core.py

@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import copy
+import inspect
 import os
 import pprint
 from collections import defaultdict
@@ -290,6 +291,77 @@ def categorize(df: pd.DataFrame, categories: dict[str, list[Any]]) -> pd.DataFra
 
 
 class Step:
+    @classmethod
+    def _get_param_names(cls) -> list[str]:
+        """Get parameter names for the estimator.
+
+        Notes
+        -----
+        Copied from [1]_.
+
+        References
+        ----------
+        .. [1] https://github.com/scikit-learn/scikit-learn/blob/ab2f539/sklearn/base.py#L148-L173
+        """
+        # fetch the constructor or the original constructor before
+        # deprecation wrapping if any
+        init = getattr(cls.__init__, "deprecated_original", cls.__init__)
+        if init is object.__init__:
+            # No explicit constructor to introspect
+            return []
+
+        # introspect the constructor arguments to find the model parameters
+        # to represent
+        init_signature = inspect.signature(init)
+        # Consider the constructor parameters excluding 'self'
+        parameters = [
+            p
+            for p in init_signature.parameters.values()
+            if p.name != "self" and p.kind != p.VAR_KEYWORD
+        ]
+        for p in parameters:
+            if p.kind == p.VAR_POSITIONAL:
+                raise RuntimeError(
+                    "scikit-learn estimators should always "
+                    "specify their parameters in the signature"
+                    " of their __init__ (no varargs)."
+                    f" {cls} with constructor {init_signature} doesn't "
+                    " follow this convention."
+                )
+        # Extract and sort argument names excluding 'self'
+        return sorted([p.name for p in parameters])
+
+    def get_params(self, deep=True) -> dict[str, Any]:
+        """Get parameters for this estimator.
+
+        Parameters
+        ----------
+        deep : bool, default=True
+            If True, will return the parameters for this estimator and
+            contained subobjects that are estimators.
+
+        Returns
+        -------
+        params : dict
+            Parameter names mapped to their values.
+
+        Notes
+        -----
+        Copied from [1]_.
+
+        References
+        ----------
+        .. [1] https://github.com/scikit-learn/scikit-learn/blob/626b460/sklearn/base.py#L145-L167
+        """
+        out = {}
+        for key in self._get_param_names():
+            value = getattr(self, key)
+            if deep and hasattr(value, "get_params") and not isinstance(value, type):
+                deep_items = value.get_params().items()
+                out.update((key + "__" + k, val) for k, val in deep_items)
+            out[key] = value
+        return out
+
     def __repr__(self) -> str:
         return pprint.pformat(self)
 

tests/test_core.py

@@ -365,6 +365,13 @@ def test_errors_nicely_if_not_fitted(table, method):
         getattr(r, method)(table)
 
 
+def test_get_params():
+    rec = ml.Recipe(ml.ExpandDateTime(ml.timestamp()))
+
+    assert "expanddatetime__components" in rec.get_params(deep=True)
+    assert "expanddatetime__components" not in rec.get_params(deep=False)
+
+
 @pytest.mark.parametrize(
     ("step", "url"),
     [