MAINT Parameters validation for sklearn.linear_model.lars_path (sciki…

…t-learn#26381)

Co-authored-by: Guillaume Lemaitre <[email protected]>

sklearn/linear_model/_least_angle.py

@@ -23,13 +23,32 @@
 
 # mypy error: Module 'sklearn.utils' has no attribute 'arrayfuncs'
 from ..utils import arrayfuncs, as_float_array, check_random_state # type: ignore
-from ..utils._param_validation import Hidden, Interval, StrOptions
+from ..utils._param_validation import Hidden, Interval, StrOptions, validate_params
 from ..utils.parallel import Parallel, delayed
 from ._base import LinearModel, LinearRegression, _deprecate_normalize, _preprocess_data
 
 SOLVE_TRIANGULAR_ARGS = {"check_finite": False}
 
 
+@validate_params(
+ {
+ "X": [np.ndarray, None],
+ "y": [np.ndarray, None],
+ "Xy": [np.ndarray, None],
+ "Gram": [StrOptions({"auto"}), "boolean", np.ndarray, None],
+ "max_iter": [Interval(Integral, 0, None, closed="left")],
+ "alpha_min": [Interval(Real, 0, None, closed="left")],
+ "method": [StrOptions({"lar", "lasso"})],
+ "copy_X": ["boolean"],
+ "eps": [Interval(Real, 0, None, closed="neither"), None],
+ "copy_Gram": ["boolean"],
+ "verbose": ["verbose"],
+ "return_path": ["boolean"],
+ "return_n_iter": ["boolean"],
+ "positive": ["boolean"],
+ },
+ prefer_skip_nested_validation=True,
+)
 def lars_path(
  X,
  y,
@@ -60,21 +79,21 @@ def lars_path(
 
  Parameters
  ----------
- X : None or array-like of shape (n_samples, n_features)
+ X : None or ndarray of shape (n_samples, n_features)
  Input data. Note that if X is `None` then the Gram matrix must be
  specified, i.e., cannot be `None` or `False`.
 
- y : None or array-like of shape (n_samples,)
+ y : None or ndarray of shape (n_samples,)
  Input targets.
 
  Xy : array-like of shape (n_features,) or (n_features, n_targets), \
  default=None
- `Xy = np.dot(X.T, y)` that can be precomputed. It is useful
+ `Xy = X.T @ y` that can be precomputed. It is useful
  only when the Gram matrix is precomputed.
 
- Gram : None, 'auto', array-like of shape (n_features, n_features), \
+ Gram : None, 'auto', bool, ndarray of shape (n_features, n_features), \
  default=None
- Precomputed Gram matrix (X' * X), if `'auto'`, the Gram
+ Precomputed Gram matrix `X.T @ X`, if `'auto'`, the Gram
  matrix is precomputed from the given X, if there are more samples
  than features.
 
@@ -123,20 +142,20 @@ def lars_path(
 
  Returns
  -------
- alphas : array-like of shape (n_alphas + 1,)
+ alphas : ndarray of shape (n_alphas + 1,)
  Maximum of covariances (in absolute value) at each iteration.
  `n_alphas` is either `max_iter`, `n_features`, or the
  number of nodes in the path with `alpha >= alpha_min`, whichever
  is smaller.
 
- active : array-like of shape (n_alphas,)
+ active : ndarray of shape (n_alphas,)
  Indices of active variables at the end of the path.
 
- coefs : array-like of shape (n_features, n_alphas + 1)
+ coefs : ndarray of shape (n_features, n_alphas + 1)
  Coefficients along the path.
 
  n_iter : int
- Number of iterations run. Returned only if return_n_iter is set
+ Number of iterations run. Returned only if `return_n_iter` is set
  to True.
 
  See Also
@@ -1361,7 +1380,7 @@ def _lars_path_residues(
  y_test,
  Gram=None,
  copy=True,
- method="lars",
+ method="lar",
  verbose=False,
  fit_intercept=True,
  normalize=False,

sklearn/linear_model/tests/test_least_angle.py

@@ -132,7 +132,7 @@ def test_lars_path_gram_equivalent(method, return_path):
 def test_x_none_gram_none_raises_value_error():
  # Test that lars_path with no X and Gram raises exception
  Xy = np.dot(X.T, y)
- with pytest.raises(ValueError):
+ with pytest.raises(ValueError, match="X and Gram cannot both be unspecified"):
  linear_model.lars_path(None, y, Gram=None, Xy=Xy)
 
 
@@ -804,7 +804,7 @@ def test_lars_with_jitter(est):
 
 def test_X_none_gram_not_none():
  with pytest.raises(ValueError, match="X cannot be None if Gram is not None"):
- lars_path(X=None, y=[1], Gram="not None")
+ lars_path(X=None, y=np.array([1]), Gram=True)
 
 
 def test_copy_X_with_auto_gram():

sklearn/tests/test_public_functions.py

@@ -201,6 +201,7 @@ def _check_function_param_validation(
  "sklearn.isotonic.check_increasing",
  "sklearn.isotonic.isotonic_regression",
  "sklearn.linear_model.enet_path",
+ "sklearn.linear_model.lars_path",
  "sklearn.linear_model.lasso_path",
  "sklearn.linear_model.orthogonal_mp",
  "sklearn.linear_model.orthogonal_mp_gram",