snowflake-ml-python 1.6.4__py3-none-any.whl → 1.7.0__py3-none-any.whl

snowflake/ml/modeling/ensemble/bagging_regressor.py

@@ -164,9 +164,6 @@ class BaggingRegressor(BaseTransformer):
 
     verbose: int, default=0
         Controls the verbosity when fitting and predicting.
-
-    base_estimator: object, default="deprecated"
-        Use `estimator` instead.
     """
 
     def __init__(  # type: ignore[no-untyped-def]
@@ -183,7 +180,6 @@ class BaggingRegressor(BaseTransformer):
         n_jobs=None,
         random_state=None,
         verbose=0,
-        base_estimator="deprecated",
         input_cols: Optional[Union[str, Iterable[str]]] = None,
         output_cols: Optional[Union[str, Iterable[str]]] = None,
         label_cols: Optional[Union[str, Iterable[str]]] = None,
@@ -203,10 +199,8 @@ class BaggingRegressor(BaseTransformer):
         self._batch_size = -1        
         deps: Set[str] = set([f'numpy=={np.__version__}', f'scikit-learn=={sklearn.__version__}', f'cloudpickle=={cp.__version__}'])
         deps = deps | gather_dependencies(estimator)
-        deps = deps | gather_dependencies(base_estimator)
         self._deps = list(deps)
         estimator = transform_snowml_obj_to_sklearn_obj(estimator)
-        base_estimator = transform_snowml_obj_to_sklearn_obj(base_estimator)
         init_args = {'estimator':(estimator, None, False),
             'n_estimators':(n_estimators, 10, False),
             'max_samples':(max_samples, 1.0, False),
@@ -217,8 +211,7 @@ class BaggingRegressor(BaseTransformer):
             'warm_start':(warm_start, False, False),
             'n_jobs':(n_jobs, None, False),
             'random_state':(random_state, None, False),
-            'verbose':(verbose, 0, False),
-            'base_estimator':(base_estimator, "deprecated", False),}
+            'verbose':(verbose, 0, False),}
         cleaned_up_init_args = validate_sklearn_args(
             args=init_args,
             klass=sklearn.ensemble.BaggingRegressor

snowflake/ml/modeling/ensemble/extra_trees_classifier.py

@@ -219,7 +219,7 @@ class ExtraTreesClassifier(BaseTransformer):
         When set to ``True``, reuse the solution of the previous call to fit
         and add more estimators to the ensemble, otherwise, just fit a whole
         new forest. See :term:`Glossary <warm_start>` and
-        :ref:`gradient_boosting_warm_start` for details.
+        :ref:`tree_ensemble_warm_start` for details.
 
     class_weight: {"balanced", "balanced_subsample"}, dict or list of dicts,             default=None
         Weights associated with classes in the form ``{class_label: weight}``.
@@ -260,6 +260,23 @@ class ExtraTreesClassifier(BaseTransformer):
         - If int, then draw `max_samples` samples.
         - If float, then draw `max_samples * X.shape[0]` samples. Thus,
           `max_samples` should be in the interval `(0.0, 1.0]`.
+
+    monotonic_cst: array-like of int of shape (n_features), default=None
+        Indicates the monotonicity constraint to enforce on each feature.
+          - 1: monotonically increasing
+          - 0: no constraint
+          - -1: monotonically decreasing
+
+        If monotonic_cst is None, no constraints are applied.
+
+        Monotonicity constraints are not supported for:
+          - multiclass classifications (i.e. when `n_classes > 2`),
+          - multioutput classifications (i.e. when `n_outputs_ > 1`),
+          - classifications trained on data with missing values.
+
+        The constraints hold over the probability of the positive class.
+
+        Read more in the :ref:`User Guide <monotonic_cst_gbdt>`.
     """
 
     def __init__(  # type: ignore[no-untyped-def]
@@ -283,6 +300,7 @@ class ExtraTreesClassifier(BaseTransformer):
         class_weight=None,
         ccp_alpha=0.0,
         max_samples=None,
+        monotonic_cst=None,
         input_cols: Optional[Union[str, Iterable[str]]] = None,
         output_cols: Optional[Union[str, Iterable[str]]] = None,
         label_cols: Optional[Union[str, Iterable[str]]] = None,
@@ -321,7 +339,8 @@ class ExtraTreesClassifier(BaseTransformer):
             'warm_start':(warm_start, False, False),
             'class_weight':(class_weight, None, False),
             'ccp_alpha':(ccp_alpha, 0.0, False),
-            'max_samples':(max_samples, None, False),}
+            'max_samples':(max_samples, None, False),
+            'monotonic_cst':(monotonic_cst, None, False),}
         cleaned_up_init_args = validate_sklearn_args(
             args=init_args,
             klass=sklearn.ensemble.ExtraTreesClassifier

snowflake/ml/modeling/ensemble/extra_trees_regressor.py

@@ -225,7 +225,7 @@ class ExtraTreesRegressor(BaseTransformer):
         When set to ``True``, reuse the solution of the previous call to fit
         and add more estimators to the ensemble, otherwise, just fit a whole
         new forest. See :term:`Glossary <warm_start>` and
-        :ref:`gradient_boosting_warm_start` for details.
+        :ref:`tree_ensemble_warm_start` for details.
 
     ccp_alpha: non-negative float, default=0.0
         Complexity parameter used for Minimal Cost-Complexity Pruning. The
@@ -241,6 +241,20 @@ class ExtraTreesRegressor(BaseTransformer):
         - If int, then draw `max_samples` samples.
         - If float, then draw `max_samples * X.shape[0]` samples. Thus,
           `max_samples` should be in the interval `(0.0, 1.0]`.
+
+    monotonic_cst: array-like of int of shape (n_features), default=None
+        Indicates the monotonicity constraint to enforce on each feature.
+          - 1: monotonically increasing
+          - 0: no constraint
+          - -1: monotonically decreasing
+
+        If monotonic_cst is None, no constraints are applied.
+
+        Monotonicity constraints are not supported for:
+          - multioutput regressions (i.e. when `n_outputs_ > 1`),
+          - regressions trained on data with missing values.
+
+        Read more in the :ref:`User Guide <monotonic_cst_gbdt>`.
     """
 
     def __init__(  # type: ignore[no-untyped-def]
@@ -263,6 +277,7 @@ class ExtraTreesRegressor(BaseTransformer):
         warm_start=False,
         ccp_alpha=0.0,
         max_samples=None,
+        monotonic_cst=None,
         input_cols: Optional[Union[str, Iterable[str]]] = None,
         output_cols: Optional[Union[str, Iterable[str]]] = None,
         label_cols: Optional[Union[str, Iterable[str]]] = None,
@@ -300,7 +315,8 @@ class ExtraTreesRegressor(BaseTransformer):
             'verbose':(verbose, 0, False),
             'warm_start':(warm_start, False, False),
             'ccp_alpha':(ccp_alpha, 0.0, False),
-            'max_samples':(max_samples, None, False),}
+            'max_samples':(max_samples, None, False),
+            'monotonic_cst':(monotonic_cst, None, False),}
         cleaned_up_init_args = validate_sklearn_args(
             args=init_args,
             klass=sklearn.ensemble.ExtraTreesRegressor

snowflake/ml/modeling/ensemble/gradient_boosting_classifier.py

@@ -255,6 +255,8 @@ class GradientBoostingClassifier(BaseTransformer):
         improving in all of the previous ``n_iter_no_change`` numbers of
         iterations. The split is stratified.
         Values must be in the range `[1, inf)`.
+        See
+        :ref:`sphx_glr_auto_examples_ensemble_plot_gradient_boosting_early_stopping.py`.
 
     tol: float, default=1e-4
         Tolerance for the early stopping. When the loss is not improving

snowflake/ml/modeling/ensemble/gradient_boosting_regressor.py

@@ -262,6 +262,8 @@ class GradientBoostingRegressor(BaseTransformer):
         improving in all of the previous ``n_iter_no_change`` numbers of
         iterations.
         Values must be in the range `[1, inf)`.
+        See
+        :ref:`sphx_glr_auto_examples_ensemble_plot_gradient_boosting_early_stopping.py`.
 
     tol: float, default=1e-4
         Tolerance for the early stopping. When the loss is not improving

snowflake/ml/modeling/ensemble/hist_gradient_boosting_classifier.py

@@ -142,7 +142,15 @@ class HistGradientBoostingClassifier(BaseTransformer):
         than a few hundred samples, it is recommended to lower this value
         since only very shallow trees would be built.
     l2_regularization: float, default=0
-        The L2 regularization parameter. Use 0 for no regularization.
+        The L2 regularization parameter penalizing leaves with small hessians.
+        Use ``0`` for no regularization (default).
+    max_features: float, default=1.0
+        Proportion of randomly chosen features in each and every node split.
+        This is a form of regularization, smaller values make the trees weaker
+        learners and might prevent overfitting.
+        If interaction constraints from `interaction_cst` are present, only allowed
+        features are taken into account for the subsampling.
+
     max_bins: int, default=255
         The maximum number of bins to use for non-missing values. Before
         training, each feature of the input array `X` is binned into
@@ -159,13 +167,16 @@ class HistGradientBoostingClassifier(BaseTransformer):
           features.
         - str array-like: names of categorical features (assuming the training
           data has feature names).
+        - `"from_dtype"`: dataframe columns with dtype "category" are
+          considered to be categorical features. The input must be an object
+          exposing a ``__dataframe__`` method such as pandas or polars
+          DataFrames to use this feature.
 
         For each categorical feature, there must be at most `max_bins` unique
-        categories, and each categorical value must be less then `max_bins - 1`.
-        Negative values for categorical features are treated as missing values.
-        All categorical values are converted to floating point numbers.
-        This means that categorical values of 1.0 and 1 are treated as
-        the same category.
+        categories. Negative values for categorical features encoded as numeric
+        dtypes are treated as missing values. All categorical values are
+        converted to floating point numbers. This means that categorical values
+        of 1.0 and 1 are treated as the same category.
 
         Read more in the :ref:`User Guide <categorical_support_gbdt>`.
 
@@ -261,8 +272,9 @@ class HistGradientBoostingClassifier(BaseTransformer):
         max_depth=None,
         min_samples_leaf=20,
         l2_regularization=0.0,
+        max_features=1.0,
         max_bins=255,
-        categorical_features=None,
+        categorical_features="warn",
         monotonic_cst=None,
         interaction_cst=None,
         warm_start=False,
@@ -302,8 +314,9 @@ class HistGradientBoostingClassifier(BaseTransformer):
             'max_depth':(max_depth, None, False),
             'min_samples_leaf':(min_samples_leaf, 20, False),
             'l2_regularization':(l2_regularization, 0.0, False),
+            'max_features':(max_features, 1.0, False),
             'max_bins':(max_bins, 255, False),
-            'categorical_features':(categorical_features, None, False),
+            'categorical_features':(categorical_features, "warn", False),
             'monotonic_cst':(monotonic_cst, None, False),
             'interaction_cst':(interaction_cst, None, False),
             'warm_start':(warm_start, False, False),

snowflake/ml/modeling/ensemble/hist_gradient_boosting_regressor.py

@@ -140,8 +140,15 @@ class HistGradientBoostingRegressor(BaseTransformer):
         than a few hundred samples, it is recommended to lower this value
         since only very shallow trees would be built.
     l2_regularization: float, default=0
-        The L2 regularization parameter. Use ``0`` for no regularization
-        (default).
+        The L2 regularization parameter penalizing leaves with small hessians.
+        Use ``0`` for no regularization (default).
+    max_features: float, default=1.0
+        Proportion of randomly chosen features in each and every node split.
+        This is a form of regularization, smaller values make the trees weaker
+        learners and might prevent overfitting.
+        If interaction constraints from `interaction_cst` are present, only allowed
+        features are taken into account for the subsampling.
+
     max_bins: int, default=255
         The maximum number of bins to use for non-missing values. Before
         training, each feature of the input array `X` is binned into
@@ -158,13 +165,16 @@ class HistGradientBoostingRegressor(BaseTransformer):
           features.
         - str array-like: names of categorical features (assuming the training
           data has feature names).
+        - `"from_dtype"`: dataframe columns with dtype "category" are
+          considered to be categorical features. The input must be an object
+          exposing a ``__dataframe__`` method such as pandas or polars
+          DataFrames to use this feature.
 
         For each categorical feature, there must be at most `max_bins` unique
-        categories, and each categorical value must be less then `max_bins - 1`.
-        Negative values for categorical features are treated as missing values.
-        All categorical values are converted to floating point numbers.
-        This means that categorical values of 1.0 and 1 are treated as
-        the same category.
+        categories. Negative values for categorical features encoded as numeric
+        dtypes are treated as missing values. All categorical values are
+        converted to floating point numbers. This means that categorical values
+        of 1.0 and 1 are treated as the same category.
 
         Read more in the :ref:`User Guide <categorical_support_gbdt>`.
 
@@ -180,8 +190,6 @@ class HistGradientBoostingRegressor(BaseTransformer):
         If an array, the features are mapped to constraints by position. See
         :ref:`monotonic_cst_features_names` for a usage example.
 
-        The constraints are only valid for binary classifications and hold
-        over the probability of the positive class.
         Read more in the :ref:`User Guide <monotonic_cst_gbdt>`.
 
     interaction_cst: {"pairwise", "no_interactions"} or sequence of lists/tuples/sets             of int, default=None
@@ -253,8 +261,9 @@ class HistGradientBoostingRegressor(BaseTransformer):
         max_depth=None,
         min_samples_leaf=20,
         l2_regularization=0.0,
+        max_features=1.0,
         max_bins=255,
-        categorical_features=None,
+        categorical_features="warn",
         monotonic_cst=None,
         interaction_cst=None,
         warm_start=False,
@@ -294,8 +303,9 @@ class HistGradientBoostingRegressor(BaseTransformer):
             'max_depth':(max_depth, None, False),
             'min_samples_leaf':(min_samples_leaf, 20, False),
             'l2_regularization':(l2_regularization, 0.0, False),
+            'max_features':(max_features, 1.0, False),
             'max_bins':(max_bins, 255, False),
-            'categorical_features':(categorical_features, None, False),
+            'categorical_features':(categorical_features, "warn", False),
             'monotonic_cst':(monotonic_cst, None, False),
             'interaction_cst':(interaction_cst, None, False),
             'warm_start':(warm_start, False, False),

snowflake/ml/modeling/ensemble/random_forest_classifier.py

@@ -215,7 +215,7 @@ class RandomForestClassifier(BaseTransformer):
         When set to ``True``, reuse the solution of the previous call to fit
         and add more estimators to the ensemble, otherwise, just fit a whole
         new forest. See :term:`Glossary <warm_start>` and
-        :ref:`gradient_boosting_warm_start` for details.
+        :ref:`tree_ensemble_warm_start` for details.
 
     class_weight: {"balanced", "balanced_subsample"}, dict or list of dicts,             default=None
         Weights associated with classes in the form ``{class_label: weight}``.
@@ -256,6 +256,23 @@ class RandomForestClassifier(BaseTransformer):
         - If int, then draw `max_samples` samples.
         - If float, then draw `max(round(n_samples * max_samples), 1)` samples. Thus,
           `max_samples` should be in the interval `(0.0, 1.0]`.
+
+    monotonic_cst: array-like of int of shape (n_features), default=None
+        Indicates the monotonicity constraint to enforce on each feature.
+          - 1: monotonic increase
+          - 0: no constraint
+          - -1: monotonic decrease
+
+        If monotonic_cst is None, no constraints are applied.
+
+        Monotonicity constraints are not supported for:
+          - multiclass classifications (i.e. when `n_classes > 2`),
+          - multioutput classifications (i.e. when `n_outputs_ > 1`),
+          - classifications trained on data with missing values.
+
+        The constraints hold over the probability of the positive class.
+
+        Read more in the :ref:`User Guide <monotonic_cst_gbdt>`.
     """
 
     def __init__(  # type: ignore[no-untyped-def]
@@ -279,6 +296,7 @@ class RandomForestClassifier(BaseTransformer):
         class_weight=None,
         ccp_alpha=0.0,
         max_samples=None,
+        monotonic_cst=None,
         input_cols: Optional[Union[str, Iterable[str]]] = None,
         output_cols: Optional[Union[str, Iterable[str]]] = None,
         label_cols: Optional[Union[str, Iterable[str]]] = None,
@@ -317,7 +335,8 @@ class RandomForestClassifier(BaseTransformer):
             'warm_start':(warm_start, False, False),
             'class_weight':(class_weight, None, False),
             'ccp_alpha':(ccp_alpha, 0.0, False),
-            'max_samples':(max_samples, None, False),}
+            'max_samples':(max_samples, None, False),
+            'monotonic_cst':(monotonic_cst, None, False),}
         cleaned_up_init_args = validate_sklearn_args(
             args=init_args,
             klass=sklearn.ensemble.RandomForestClassifier

snowflake/ml/modeling/ensemble/random_forest_regressor.py

@@ -221,7 +221,7 @@ class RandomForestRegressor(BaseTransformer):
         When set to ``True``, reuse the solution of the previous call to fit
         and add more estimators to the ensemble, otherwise, just fit a whole
         new forest. See :term:`Glossary <warm_start>` and
-        :ref:`gradient_boosting_warm_start` for details.
+        :ref:`tree_ensemble_warm_start` for details.
 
     ccp_alpha: non-negative float, default=0.0
         Complexity parameter used for Minimal Cost-Complexity Pruning. The
@@ -237,6 +237,20 @@ class RandomForestRegressor(BaseTransformer):
         - If int, then draw `max_samples` samples.
         - If float, then draw `max(round(n_samples * max_samples), 1)` samples. Thus,
           `max_samples` should be in the interval `(0.0, 1.0]`.
+
+    monotonic_cst: array-like of int of shape (n_features), default=None
+        Indicates the monotonicity constraint to enforce on each feature.
+          - 1: monotonically increasing
+          - 0: no constraint
+          - -1: monotonically decreasing
+
+        If monotonic_cst is None, no constraints are applied.
+
+        Monotonicity constraints are not supported for:
+          - multioutput regressions (i.e. when `n_outputs_ > 1`),
+          - regressions trained on data with missing values.
+
+        Read more in the :ref:`User Guide <monotonic_cst_gbdt>`.
     """
 
     def __init__(  # type: ignore[no-untyped-def]
@@ -259,6 +273,7 @@ class RandomForestRegressor(BaseTransformer):
         warm_start=False,
         ccp_alpha=0.0,
         max_samples=None,
+        monotonic_cst=None,
         input_cols: Optional[Union[str, Iterable[str]]] = None,
         output_cols: Optional[Union[str, Iterable[str]]] = None,
         label_cols: Optional[Union[str, Iterable[str]]] = None,
@@ -296,7 +311,8 @@ class RandomForestRegressor(BaseTransformer):
             'verbose':(verbose, 0, False),
             'warm_start':(warm_start, False, False),
             'ccp_alpha':(ccp_alpha, 0.0, False),
-            'max_samples':(max_samples, None, False),}
+            'max_samples':(max_samples, None, False),
+            'monotonic_cst':(monotonic_cst, None, False),}
         cleaned_up_init_args = validate_sklearn_args(
             args=init_args,
             klass=sklearn.ensemble.RandomForestRegressor

snowflake/ml/modeling/feature_selection/generic_univariate_select.py

@@ -116,7 +116,8 @@ class GenericUnivariateSelect(BaseTransformer):
         a single array scores.
 
     mode: {'percentile', 'k_best', 'fpr', 'fdr', 'fwe'}, default='percentile'
-        Feature selection mode.
+        Feature selection mode. Note that the `'percentile'` and `'kbest'`
+        modes are supporting unsupervised feature selection (when `y` is `None`).
 
     param: "all", float or int, default=1e-5
         Parameter of the corresponding mode.

snowflake/ml/modeling/feature_selection/sequential_feature_selector.py

@@ -154,9 +154,11 @@ class SequentialFeatureSelector(BaseTransformer):
         - An iterable yielding (train, test) splits as arrays of indices.
 
         For integer/None inputs, if the estimator is a classifier and ``y`` is
-        either binary or multiclass, :class:`StratifiedKFold` is used. In all
-        other cases, :class:`KFold` is used. These splitters are instantiated
-        with `shuffle=False` so the splits will be the same across calls.
+        either binary or multiclass,
+        :class:`~sklearn.model_selection.StratifiedKFold` is used. In all other
+        cases, :class:`~sklearn.model_selection.KFold` is used. These splitters
+        are instantiated with `shuffle=False` so the splits will be the same
+        across calls.
 
         Refer :ref:`User Guide <cross_validation>` for the various
         cross-validation strategies that can be used here.

snowflake/ml/modeling/kernel_ridge/kernel_ridge.py

@@ -121,7 +121,7 @@ class KernelRidge(BaseTransformer):
 
     kernel: str or callable, default="linear"
         Kernel mapping used internally. This parameter is directly passed to
-        :class:`~sklearn.metrics.pairwise.pairwise_kernel`.
+        :class:`~sklearn.metrics.pairwise.pairwise_kernels`.
         If `kernel` is a string, it must be one of the metrics
         in `pairwise.PAIRWISE_KERNEL_FUNCTIONS` or "precomputed".
         If `kernel` is "precomputed", X is assumed to be a kernel matrix.
@@ -139,7 +139,7 @@ class KernelRidge(BaseTransformer):
         the kernel; see the documentation for sklearn.metrics.pairwise.
         Ignored by other kernels.
 
-    degree: int, default=3
+    degree: float, default=3
         Degree of the polynomial kernel. Ignored by other kernels.
 
     coef0: float, default=1

snowflake/ml/modeling/linear_model/ard_regression.py

@@ -109,8 +109,8 @@ class ARDRegression(BaseTransformer):
     drop_input_cols: Optional[bool], default=False
         If set, the response of predict(), transform() methods will not contain input columns.
 
-    max_iter: int, default=None
-        Maximum number of iterations. If `None`, it corresponds to `max_iter=300`.
+    max_iter: int, default=300
+        Maximum number of iterations.
 
     tol: float, default=1e-3
         Stop the algorithm if w has converged.
@@ -148,15 +148,12 @@ class ARDRegression(BaseTransformer):
 
     verbose: bool, default=False
         Verbose mode when fitting the model.
-
-    n_iter: int
-        Maximum number of iterations.
     """
 
     def __init__(  # type: ignore[no-untyped-def]
         self,
         *,
-        max_iter=None,
+        max_iter=300,
         tol=0.001,
         alpha_1=1e-06,
         alpha_2=1e-06,
@@ -167,7 +164,6 @@ class ARDRegression(BaseTransformer):
         fit_intercept=True,
         copy_X=True,
         verbose=False,
-        n_iter="deprecated",
         input_cols: Optional[Union[str, Iterable[str]]] = None,
         output_cols: Optional[Union[str, Iterable[str]]] = None,
         label_cols: Optional[Union[str, Iterable[str]]] = None,
@@ -189,7 +185,7 @@ class ARDRegression(BaseTransformer):
         
         self._deps = list(deps)
         
-        init_args = {'max_iter':(max_iter, None, False),
+        init_args = {'max_iter':(max_iter, 300, False),
             'tol':(tol, 0.001, False),
             'alpha_1':(alpha_1, 1e-06, False),
             'alpha_2':(alpha_2, 1e-06, False),
@@ -199,8 +195,7 @@ class ARDRegression(BaseTransformer):
             'threshold_lambda':(threshold_lambda, 10000.0, False),
             'fit_intercept':(fit_intercept, True, False),
             'copy_X':(copy_X, True, False),
-            'verbose':(verbose, False, False),
-            'n_iter':(n_iter, "deprecated", False),}
+            'verbose':(verbose, False, False),}
         cleaned_up_init_args = validate_sklearn_args(
             args=init_args,
             klass=sklearn.linear_model.ARDRegression

snowflake/ml/modeling/linear_model/bayesian_ridge.py

@@ -109,10 +109,9 @@ class BayesianRidge(BaseTransformer):
     drop_input_cols: Optional[bool], default=False
         If set, the response of predict(), transform() methods will not contain input columns.
 
-    max_iter: int, default=None
+    max_iter: int, default=300
         Maximum number of iterations over the complete dataset before
-        stopping independently of any early stopping criterion. If `None`, it
-        corresponds to `max_iter=300`.
+        stopping independently of any early stopping criterion.
 
     tol: float, default=1e-3
         Stop the algorithm if w has converged.
@@ -157,15 +156,12 @@ class BayesianRidge(BaseTransformer):
 
     verbose: bool, default=False
         Verbose mode when fitting the model.
-
-    n_iter: int
-        Maximum number of iterations. Should be greater than or equal to 1.
     """
 
     def __init__(  # type: ignore[no-untyped-def]
         self,
         *,
-        max_iter=None,
+        max_iter=300,
         tol=0.001,
         alpha_1=1e-06,
         alpha_2=1e-06,
@@ -177,7 +173,6 @@ class BayesianRidge(BaseTransformer):
         fit_intercept=True,
         copy_X=True,
         verbose=False,
-        n_iter="deprecated",
         input_cols: Optional[Union[str, Iterable[str]]] = None,
         output_cols: Optional[Union[str, Iterable[str]]] = None,
         label_cols: Optional[Union[str, Iterable[str]]] = None,
@@ -199,7 +194,7 @@ class BayesianRidge(BaseTransformer):
         
         self._deps = list(deps)
         
-        init_args = {'max_iter':(max_iter, None, False),
+        init_args = {'max_iter':(max_iter, 300, False),
             'tol':(tol, 0.001, False),
             'alpha_1':(alpha_1, 1e-06, False),
             'alpha_2':(alpha_2, 1e-06, False),
@@ -210,8 +205,7 @@ class BayesianRidge(BaseTransformer):
             'compute_score':(compute_score, False, False),
             'fit_intercept':(fit_intercept, True, False),
             'copy_X':(copy_X, True, False),
-            'verbose':(verbose, False, False),
-            'n_iter':(n_iter, "deprecated", False),}
+            'verbose':(verbose, False, False),}
         cleaned_up_init_args = validate_sklearn_args(
             args=init_args,
             klass=sklearn.linear_model.BayesianRidge

snowflake/ml/modeling/linear_model/elastic_net.py

@@ -131,6 +131,9 @@ class ElasticNet(BaseTransformer):
         Whether to use a precomputed Gram matrix to speed up
         calculations. The Gram matrix can also be passed as argument.
         For sparse input this option is always ``False`` to preserve sparsity.
+        Check :ref:`an example on how to use a precomputed Gram Matrix in ElasticNet
+        <sphx_glr_auto_examples_linear_model_plot_elastic_net_precomputed_gram_matrix_with_weighted_samples.py>`
+        for details.
 
     max_iter: int, default=1000
         The maximum number of iterations.

snowflake/ml/modeling/linear_model/elastic_net_cv.py

@@ -160,7 +160,7 @@ class ElasticNetCV(BaseTransformer):
         - :term:`CV splitter`,
         - An iterable yielding (train, test) splits as arrays of indices.
 
-        For int/None inputs, :class:`KFold` is used.
+        For int/None inputs, :class:`~sklearn.model_selection.KFold` is used.
 
         Refer :ref:`User Guide <cross_validation>` for the various
         cross-validation strategies that can be used here.

snowflake/ml/modeling/linear_model/lars.py

@@ -117,14 +117,6 @@ class Lars(BaseTransformer):
     verbose: bool or int, default=False
         Sets the verbosity amount.
 
-    normalize: bool, default=False
-        This parameter is ignored when ``fit_intercept`` is set to False.
-        If True, the regressors X will be normalized before regression by
-        subtracting the mean and dividing by the l2-norm.
-        If you wish to standardize, please use
-        :class:`~sklearn.preprocessing.StandardScaler` before calling ``fit``
-        on an estimator with ``normalize=False``.
-
     precompute: bool, 'auto' or array-like , default='auto'
         Whether to use a precomputed Gram matrix to speed up
         calculations. If set to ``'auto'`` let us decide. The Gram
@@ -165,7 +157,6 @@ class Lars(BaseTransformer):
         *,
         fit_intercept=True,
         verbose=False,
-        normalize="deprecated",
         precompute="auto",
         n_nonzero_coefs=500,
         eps=2.220446049250313e-16,
@@ -196,7 +187,6 @@ class Lars(BaseTransformer):
         
         init_args = {'fit_intercept':(fit_intercept, True, False),
             'verbose':(verbose, False, False),
-            'normalize':(normalize, "deprecated", False),
             'precompute':(precompute, "auto", False),
             'n_nonzero_coefs':(n_nonzero_coefs, 500, False),
             'eps':(eps, 2.220446049250313e-16, False),

snowflake/ml/modeling/linear_model/lars_cv.py

@@ -120,14 +120,6 @@ class LarsCV(BaseTransformer):
     max_iter: int, default=500
         Maximum number of iterations to perform.
 
-    normalize: bool, default=False
-        This parameter is ignored when ``fit_intercept`` is set to False.
-        If True, the regressors X will be normalized before regression by
-        subtracting the mean and dividing by the l2-norm.
-        If you wish to standardize, please use
-        :class:`~sklearn.preprocessing.StandardScaler` before calling ``fit``
-        on an estimator with ``normalize=False``.
-
     precompute: bool, 'auto' or array-like , default='auto'
         Whether to use a precomputed Gram matrix to speed up
         calculations. If set to ``'auto'`` let us decide. The Gram matrix
@@ -142,7 +134,7 @@ class LarsCV(BaseTransformer):
         - :term:`CV splitter`,
         - An iterable yielding (train, test) splits as arrays of indices.
 
-        For integer/None inputs, :class:`KFold` is used.
+        For integer/None inputs, :class:`~sklearn.model_selection.KFold` is used.
 
         Refer :ref:`User Guide <cross_validation>` for the various
         cross-validation strategies that can be used here.
@@ -174,7 +166,6 @@ class LarsCV(BaseTransformer):
         fit_intercept=True,
         verbose=False,
         max_iter=500,
-        normalize="deprecated",
         precompute="auto",
         cv=None,
         max_n_alphas=1000,
@@ -205,7 +196,6 @@ class LarsCV(BaseTransformer):
         init_args = {'fit_intercept':(fit_intercept, True, False),
             'verbose':(verbose, False, False),
             'max_iter':(max_iter, 500, False),
-            'normalize':(normalize, "deprecated", False),
             'precompute':(precompute, "auto", False),
             'cv':(cv, None, False),
             'max_n_alphas':(max_n_alphas, 1000, False),

snowflake/ml/modeling/linear_model/lasso_cv.py

@@ -151,7 +151,7 @@ class LassoCV(BaseTransformer):
         - :term:`CV splitter`,
         - An iterable yielding (train, test) splits as arrays of indices.
 
-        For int/None inputs, :class:`KFold` is used.
+        For int/None inputs, :class:`~sklearn.model_selection.KFold` is used.
 
         Refer :ref:`User Guide <cross_validation>` for the various
         cross-validation strategies that can be used here.