snowflake-ml-python 1.8.2__py3-none-any.whl → 1.8.4__py3-none-any.whl

snowflake/ml/modeling/metrics/ranking.py

@@ -1,4 +1,4 @@
-from typing import List, Optional, Tuple, Union
+from typing import Optional, Union
 
 import cloudpickle
 import numpy as np
@@ -26,7 +26,7 @@ def precision_recall_curve(
     probas_pred_col_name: str,
     pos_label: Optional[Union[str, int]] = None,
     sample_weight_col_name: Optional[str] = None,
-) -> Tuple[npt.NDArray[np.float_], npt.NDArray[np.float_], npt.NDArray[np.float_]]:
+) -> tuple[npt.NDArray[np.float_], npt.NDArray[np.float_], npt.NDArray[np.float_]]:
     """
     Compute precision-recall pairs for different probability thresholds.
 
@@ -125,7 +125,7 @@ def precision_recall_curve(
 
     kwargs = telemetry.get_sproc_statement_params_kwargs(precision_recall_curve_anon_sproc, statement_params)
     result_object = result.deserialize(session, precision_recall_curve_anon_sproc(session, **kwargs))
-    res: Tuple[npt.NDArray[np.float_], npt.NDArray[np.float_], npt.NDArray[np.float_]] = result_object
+    res: tuple[npt.NDArray[np.float_], npt.NDArray[np.float_], npt.NDArray[np.float_]] = result_object
     return res
 
 
@@ -133,8 +133,8 @@ def precision_recall_curve(
 def roc_auc_score(
     *,
     df: snowpark.DataFrame,
-    y_true_col_names: Union[str, List[str]],
-    y_score_col_names: Union[str, List[str]],
+    y_true_col_names: Union[str, list[str]],
+    y_score_col_names: Union[str, list[str]],
     average: Optional[str] = "macro",
     sample_weight_col_name: Optional[str] = None,
     max_fpr: Optional[float] = None,
@@ -289,7 +289,7 @@ def roc_curve(
     pos_label: Optional[Union[str, int]] = None,
     sample_weight_col_name: Optional[str] = None,
     drop_intermediate: bool = True,
-) -> Tuple[npt.NDArray[np.float_], npt.NDArray[np.float_], npt.NDArray[np.float_]]:
+) -> tuple[npt.NDArray[np.float_], npt.NDArray[np.float_], npt.NDArray[np.float_]]:
     """
     Compute Receiver operating characteristic (ROC).
 
@@ -380,6 +380,6 @@ def roc_curve(
     kwargs = telemetry.get_sproc_statement_params_kwargs(roc_curve_anon_sproc, statement_params)
     result_object = result.deserialize(session, roc_curve_anon_sproc(session, **kwargs))
 
-    res: Tuple[npt.NDArray[np.float_], npt.NDArray[np.float_], npt.NDArray[np.float_]] = result_object
+    res: tuple[npt.NDArray[np.float_], npt.NDArray[np.float_], npt.NDArray[np.float_]] = result_object
 
     return res

snowflake/ml/modeling/metrics/regression.py

@@ -1,5 +1,5 @@
 import inspect
-from typing import List, Optional, Union
+from typing import Optional, Union
 
 import cloudpickle
 import numpy as np
@@ -25,8 +25,8 @@ _MULTIOUTPUT_RAW_VALUES = "raw_values"
 def d2_absolute_error_score(
     *,
     df: snowpark.DataFrame,
-    y_true_col_names: Union[str, List[str]],
-    y_pred_col_names: Union[str, List[str]],
+    y_true_col_names: Union[str, list[str]],
+    y_pred_col_names: Union[str, list[str]],
     sample_weight_col_name: Optional[str] = None,
     multioutput: Union[str, npt.ArrayLike] = "uniform_average",
 ) -> Union[float, npt.NDArray[np.float_]]:
@@ -119,8 +119,8 @@ def d2_absolute_error_score(
 def d2_pinball_score(
     *,
     df: snowpark.DataFrame,
-    y_true_col_names: Union[str, List[str]],
-    y_pred_col_names: Union[str, List[str]],
+    y_true_col_names: Union[str, list[str]],
+    y_pred_col_names: Union[str, list[str]],
     sample_weight_col_name: Optional[str] = None,
     alpha: float = 0.5,
     multioutput: Union[str, npt.ArrayLike] = "uniform_average",
@@ -219,8 +219,8 @@ def d2_pinball_score(
 def explained_variance_score(
     *,
     df: snowpark.DataFrame,
-    y_true_col_names: Union[str, List[str]],
-    y_pred_col_names: Union[str, List[str]],
+    y_true_col_names: Union[str, list[str]],
+    y_pred_col_names: Union[str, list[str]],
     sample_weight_col_name: Optional[str] = None,
     multioutput: Union[str, npt.ArrayLike] = "uniform_average",
     force_finite: bool = True,
@@ -334,8 +334,8 @@ def explained_variance_score(
 def mean_absolute_error(
     *,
     df: snowpark.DataFrame,
-    y_true_col_names: Union[str, List[str]],
-    y_pred_col_names: Union[str, List[str]],
+    y_true_col_names: Union[str, list[str]],
+    y_pred_col_names: Union[str, list[str]],
     sample_weight_col_name: Optional[str] = None,
     multioutput: Union[str, npt.ArrayLike] = "uniform_average",
 ) -> Union[float, npt.NDArray[np.float_]]:
@@ -407,8 +407,8 @@ def mean_absolute_error(
 def mean_absolute_percentage_error(
     *,
     df: snowpark.DataFrame,
-    y_true_col_names: Union[str, List[str]],
-    y_pred_col_names: Union[str, List[str]],
+    y_true_col_names: Union[str, list[str]],
+    y_pred_col_names: Union[str, list[str]],
     sample_weight_col_name: Optional[str] = None,
     multioutput: Union[str, npt.ArrayLike] = "uniform_average",
 ) -> Union[float, npt.NDArray[np.float_]]:
@@ -490,8 +490,8 @@ def mean_absolute_percentage_error(
 def mean_squared_error(
     *,
     df: snowpark.DataFrame,
-    y_true_col_names: Union[str, List[str]],
-    y_pred_col_names: Union[str, List[str]],
+    y_true_col_names: Union[str, list[str]],
+    y_pred_col_names: Union[str, list[str]],
     sample_weight_col_name: Optional[str] = None,
     multioutput: Union[str, npt.ArrayLike] = "uniform_average",
     squared: bool = True,

snowflake/ml/modeling/mixture/bayesian_gaussian_mixture.py

@@ -11,7 +11,7 @@ import cloudpickle as cp
 import numpy as np
 import pandas as pd
 from numpy import typing as npt
-
+from packaging import version
 
 import numpy
 import sklearn
@@ -60,6 +60,14 @@ DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
 INFER_SIGNATURE_MAX_ROWS = 100
 
+SKLEARN_LOWER, SKLEARN_UPPER = ('1.4', '1.6')
+# Modeling library estimators require a smaller sklearn version range.
+if not version.Version(SKLEARN_LOWER) <= version.Version(sklearn.__version__) < version.Version(SKLEARN_UPPER):
+    raise Exception(
+        f"To use the modeling library, install scikit-learn version >= {SKLEARN_LOWER} and < {SKLEARN_UPPER}"
+    )
+
+
 class BayesianGaussianMixture(BaseTransformer):
     r"""Variational Bayesian estimation of a Gaussian mixture
     For more details on this class, see [sklearn.mixture.BayesianGaussianMixture]

snowflake/ml/modeling/mixture/gaussian_mixture.py

@@ -11,7 +11,7 @@ import cloudpickle as cp
 import numpy as np
 import pandas as pd
 from numpy import typing as npt
-
+from packaging import version
 
 import numpy
 import sklearn
@@ -60,6 +60,14 @@ DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
 INFER_SIGNATURE_MAX_ROWS = 100
 
+SKLEARN_LOWER, SKLEARN_UPPER = ('1.4', '1.6')
+# Modeling library estimators require a smaller sklearn version range.
+if not version.Version(SKLEARN_LOWER) <= version.Version(sklearn.__version__) < version.Version(SKLEARN_UPPER):
+    raise Exception(
+        f"To use the modeling library, install scikit-learn version >= {SKLEARN_LOWER} and < {SKLEARN_UPPER}"
+    )
+
+
 class GaussianMixture(BaseTransformer):
     r"""Gaussian Mixture
     For more details on this class, see [sklearn.mixture.GaussianMixture]

snowflake/ml/modeling/model_selection/__init__.py

@@ -2,7 +2,7 @@ import os
 
 from snowflake.ml._internal import init_utils
 
-pkg_dir = os.path.dirname(os.path.abspath(__file__))
+pkg_dir = os.path.dirname(__file__)
 pkg_name = __name__
 exportable_classes = init_utils.fetch_classes_from_modules_in_pkg_dir(pkg_dir=pkg_dir, pkg_name=pkg_name)
 for k, v in exportable_classes.items():

snowflake/ml/modeling/model_selection/grid_search_cv.py

@@ -2,7 +2,7 @@
 # This code is auto-generated using the sklearn_wrapper_template.py_template template.
 # Do not modify the auto-generated code(except automatic reformatting by precommit hooks).
 #
-from typing import Any, Dict, Iterable, List, Optional, Set, Union
+from typing import Any, Iterable, Optional, Union
 
 import cloudpickle as cp
 import numpy as np
@@ -244,7 +244,7 @@ class GridSearchCV(BaseTransformer):
         sample_weight_col: Optional[str] = None,
     ) -> None:
         super().__init__()
-        deps: Set[str] = {
+        deps: set[str] = {
             f"numpy=={np.__version__}",
             f"scikit-learn=={sklearn.__version__}",
             f"cloudpickle=={cp.__version__}",
@@ -268,7 +268,7 @@ class GridSearchCV(BaseTransformer):
         self._sklearn_object: Any = sklearn.model_selection.GridSearchCV(
             **cleaned_up_init_args,
         )
-        self._model_signature_dict: Optional[Dict[str, ModelSignature]] = None
+        self._model_signature_dict: Optional[dict[str, ModelSignature]] = None
         self.set_input_cols(input_cols)
         self.set_output_cols(output_cols)
         self.set_label_cols(label_cols)
@@ -281,7 +281,7 @@ class GridSearchCV(BaseTransformer):
         self._class_name = GridSearchCV.__class__.__name__
         self._subproject = _SUBPROJECT
 
-    def _get_active_columns(self) -> List[str]:
+    def _get_active_columns(self) -> list[str]:
         """ "Get the list of columns that are relevant to the transformer."""
         selected_cols = (
             self.input_cols + self.label_cols + ([self.sample_weight_col] if self.sample_weight_col is not None else [])
@@ -805,7 +805,7 @@ class GridSearchCV(BaseTransformer):
         assert self._sklearn_object is not None
         return self._sklearn_object
 
-    def _get_dependencies(self) -> List[str]:
+    def _get_dependencies(self) -> list[str]:
         return self._deps
 
     def _generate_model_signatures(self, dataset: Union[DataFrame, pd.DataFrame]) -> None:
@@ -820,7 +820,7 @@ class GridSearchCV(BaseTransformer):
                 use_snowflake_identifiers=True,
             )
         )
-        outputs: List[BaseFeatureSpec] = []
+        outputs: list[BaseFeatureSpec] = []
         if hasattr(self, "predict"):
             # keep mypy happy
             assert self._sklearn_object is not None and hasattr(self._sklearn_object, "_estimator_type")
@@ -863,7 +863,7 @@ class GridSearchCV(BaseTransformer):
             self._model_signature_dict[method] = signature
 
     @property
-    def model_signatures(self) -> Dict[str, ModelSignature]:
+    def model_signatures(self) -> dict[str, ModelSignature]:
         """Returns model signature of current class.
 
         Raises:

snowflake/ml/modeling/model_selection/randomized_search_cv.py

@@ -1,4 +1,4 @@
-from typing import Any, Dict, Iterable, List, Optional, Set, Union
+from typing import Any, Iterable, Optional, Union
 
 import cloudpickle as cp
 import numpy as np
@@ -254,7 +254,7 @@ class RandomizedSearchCV(BaseTransformer):
         sample_weight_col: Optional[str] = None,
     ) -> None:
         super().__init__()
-        deps: Set[str] = {
+        deps: set[str] = {
             f"numpy=={np.__version__}",
             f"scikit-learn=={sklearn.__version__}",
             f"cloudpickle=={cp.__version__}",
@@ -280,7 +280,7 @@ class RandomizedSearchCV(BaseTransformer):
         self._sklearn_object: Any = sklearn.model_selection.RandomizedSearchCV(
             **cleaned_up_init_args,
         )
-        self._model_signature_dict: Optional[Dict[str, ModelSignature]] = None
+        self._model_signature_dict: Optional[dict[str, ModelSignature]] = None
         self.set_input_cols(input_cols)
         self.set_output_cols(output_cols)
         self.set_label_cols(label_cols)
@@ -294,7 +294,7 @@ class RandomizedSearchCV(BaseTransformer):
         self._class_name = RandomizedSearchCV.__class__.__name__
         self._subproject = _SUBPROJECT
 
-    def _get_active_columns(self) -> List[str]:
+    def _get_active_columns(self) -> list[str]:
         """ "Get the list of columns that are relevant to the transformer."""
         selected_cols = (
             self.input_cols + self.label_cols + ([self.sample_weight_col] if self.sample_weight_col is not None else [])
@@ -820,7 +820,7 @@ class RandomizedSearchCV(BaseTransformer):
         assert self._sklearn_object is not None
         return self._sklearn_object
 
-    def _get_dependencies(self) -> List[str]:
+    def _get_dependencies(self) -> list[str]:
         return self._deps
 
     def _generate_model_signatures(self, dataset: Union[DataFrame, pd.DataFrame]) -> None:
@@ -835,7 +835,7 @@ class RandomizedSearchCV(BaseTransformer):
                 use_snowflake_identifiers=True,
             )
         )
-        outputs: List[BaseFeatureSpec] = []
+        outputs: list[BaseFeatureSpec] = []
         if hasattr(self, "predict"):
             # keep mypy happy
             assert self._sklearn_object is not None and hasattr(self._sklearn_object, "_estimator_type")
@@ -878,7 +878,7 @@ class RandomizedSearchCV(BaseTransformer):
             self._model_signature_dict[method] = signature
 
     @property
-    def model_signatures(self) -> Dict[str, ModelSignature]:
+    def model_signatures(self) -> dict[str, ModelSignature]:
         """Returns model signature of current class.
 
         Raises:

snowflake/ml/modeling/multiclass/one_vs_one_classifier.py

@@ -11,7 +11,7 @@ import cloudpickle as cp
 import numpy as np
 import pandas as pd
 from numpy import typing as npt
-
+from packaging import version
 
 import numpy
 import sklearn
@@ -60,6 +60,14 @@ DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
 INFER_SIGNATURE_MAX_ROWS = 100
 
+SKLEARN_LOWER, SKLEARN_UPPER = ('1.4', '1.6')
+# Modeling library estimators require a smaller sklearn version range.
+if not version.Version(SKLEARN_LOWER) <= version.Version(sklearn.__version__) < version.Version(SKLEARN_UPPER):
+    raise Exception(
+        f"To use the modeling library, install scikit-learn version >= {SKLEARN_LOWER} and < {SKLEARN_UPPER}"
+    )
+
+
 class OneVsOneClassifier(BaseTransformer):
     r"""One-vs-one multiclass strategy
     For more details on this class, see [sklearn.multiclass.OneVsOneClassifier]

snowflake/ml/modeling/multiclass/one_vs_rest_classifier.py

@@ -11,7 +11,7 @@ import cloudpickle as cp
 import numpy as np
 import pandas as pd
 from numpy import typing as npt
-
+from packaging import version
 
 import numpy
 import sklearn
@@ -60,6 +60,14 @@ DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
 INFER_SIGNATURE_MAX_ROWS = 100
 
+SKLEARN_LOWER, SKLEARN_UPPER = ('1.4', '1.6')
+# Modeling library estimators require a smaller sklearn version range.
+if not version.Version(SKLEARN_LOWER) <= version.Version(sklearn.__version__) < version.Version(SKLEARN_UPPER):
+    raise Exception(
+        f"To use the modeling library, install scikit-learn version >= {SKLEARN_LOWER} and < {SKLEARN_UPPER}"
+    )
+
+
 class OneVsRestClassifier(BaseTransformer):
     r"""One-vs-the-rest (OvR) multiclass strategy
     For more details on this class, see [sklearn.multiclass.OneVsRestClassifier]

snowflake/ml/modeling/multiclass/output_code_classifier.py

@@ -11,7 +11,7 @@ import cloudpickle as cp
 import numpy as np
 import pandas as pd
 from numpy import typing as npt
-
+from packaging import version
 
 import numpy
 import sklearn
@@ -60,6 +60,14 @@ DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
 INFER_SIGNATURE_MAX_ROWS = 100
 
+SKLEARN_LOWER, SKLEARN_UPPER = ('1.4', '1.6')
+# Modeling library estimators require a smaller sklearn version range.
+if not version.Version(SKLEARN_LOWER) <= version.Version(sklearn.__version__) < version.Version(SKLEARN_UPPER):
+    raise Exception(
+        f"To use the modeling library, install scikit-learn version >= {SKLEARN_LOWER} and < {SKLEARN_UPPER}"
+    )
+
+
 class OutputCodeClassifier(BaseTransformer):
     r"""(Error-Correcting) Output-Code multiclass strategy
     For more details on this class, see [sklearn.multiclass.OutputCodeClassifier]

snowflake/ml/modeling/naive_bayes/bernoulli_nb.py

@@ -11,7 +11,7 @@ import cloudpickle as cp
 import numpy as np
 import pandas as pd
 from numpy import typing as npt
-
+from packaging import version
 
 import numpy
 import sklearn
@@ -60,6 +60,14 @@ DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
 INFER_SIGNATURE_MAX_ROWS = 100
 
+SKLEARN_LOWER, SKLEARN_UPPER = ('1.4', '1.6')
+# Modeling library estimators require a smaller sklearn version range.
+if not version.Version(SKLEARN_LOWER) <= version.Version(sklearn.__version__) < version.Version(SKLEARN_UPPER):
+    raise Exception(
+        f"To use the modeling library, install scikit-learn version >= {SKLEARN_LOWER} and < {SKLEARN_UPPER}"
+    )
+
+
 class BernoulliNB(BaseTransformer):
     r"""Naive Bayes classifier for multivariate Bernoulli models
     For more details on this class, see [sklearn.naive_bayes.BernoulliNB]

snowflake/ml/modeling/naive_bayes/categorical_nb.py

@@ -11,7 +11,7 @@ import cloudpickle as cp
 import numpy as np
 import pandas as pd
 from numpy import typing as npt
-
+from packaging import version
 
 import numpy
 import sklearn
@@ -60,6 +60,14 @@ DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
 INFER_SIGNATURE_MAX_ROWS = 100
 
+SKLEARN_LOWER, SKLEARN_UPPER = ('1.4', '1.6')
+# Modeling library estimators require a smaller sklearn version range.
+if not version.Version(SKLEARN_LOWER) <= version.Version(sklearn.__version__) < version.Version(SKLEARN_UPPER):
+    raise Exception(
+        f"To use the modeling library, install scikit-learn version >= {SKLEARN_LOWER} and < {SKLEARN_UPPER}"
+    )
+
+
 class CategoricalNB(BaseTransformer):
     r"""Naive Bayes classifier for categorical features
     For more details on this class, see [sklearn.naive_bayes.CategoricalNB]

snowflake/ml/modeling/naive_bayes/complement_nb.py

@@ -11,7 +11,7 @@ import cloudpickle as cp
 import numpy as np
 import pandas as pd
 from numpy import typing as npt
-
+from packaging import version
 
 import numpy
 import sklearn
@@ -60,6 +60,14 @@ DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
 INFER_SIGNATURE_MAX_ROWS = 100
 
+SKLEARN_LOWER, SKLEARN_UPPER = ('1.4', '1.6')
+# Modeling library estimators require a smaller sklearn version range.
+if not version.Version(SKLEARN_LOWER) <= version.Version(sklearn.__version__) < version.Version(SKLEARN_UPPER):
+    raise Exception(
+        f"To use the modeling library, install scikit-learn version >= {SKLEARN_LOWER} and < {SKLEARN_UPPER}"
+    )
+
+
 class ComplementNB(BaseTransformer):
     r"""The Complement Naive Bayes classifier described in Rennie et al
     For more details on this class, see [sklearn.naive_bayes.ComplementNB]

snowflake/ml/modeling/naive_bayes/gaussian_nb.py

@@ -11,7 +11,7 @@ import cloudpickle as cp
 import numpy as np
 import pandas as pd
 from numpy import typing as npt
-
+from packaging import version
 
 import numpy
 import sklearn
@@ -60,6 +60,14 @@ DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
 INFER_SIGNATURE_MAX_ROWS = 100
 
+SKLEARN_LOWER, SKLEARN_UPPER = ('1.4', '1.6')
+# Modeling library estimators require a smaller sklearn version range.
+if not version.Version(SKLEARN_LOWER) <= version.Version(sklearn.__version__) < version.Version(SKLEARN_UPPER):
+    raise Exception(
+        f"To use the modeling library, install scikit-learn version >= {SKLEARN_LOWER} and < {SKLEARN_UPPER}"
+    )
+
+
 class GaussianNB(BaseTransformer):
     r"""Gaussian Naive Bayes (GaussianNB)
     For more details on this class, see [sklearn.naive_bayes.GaussianNB]

snowflake/ml/modeling/naive_bayes/multinomial_nb.py

@@ -11,7 +11,7 @@ import cloudpickle as cp
 import numpy as np
 import pandas as pd
 from numpy import typing as npt
-
+from packaging import version
 
 import numpy
 import sklearn
@@ -60,6 +60,14 @@ DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
 INFER_SIGNATURE_MAX_ROWS = 100
 
+SKLEARN_LOWER, SKLEARN_UPPER = ('1.4', '1.6')
+# Modeling library estimators require a smaller sklearn version range.
+if not version.Version(SKLEARN_LOWER) <= version.Version(sklearn.__version__) < version.Version(SKLEARN_UPPER):
+    raise Exception(
+        f"To use the modeling library, install scikit-learn version >= {SKLEARN_LOWER} and < {SKLEARN_UPPER}"
+    )
+
+
 class MultinomialNB(BaseTransformer):
     r"""Naive Bayes classifier for multinomial models
     For more details on this class, see [sklearn.naive_bayes.MultinomialNB]

snowflake/ml/modeling/neighbors/k_neighbors_classifier.py

@@ -11,7 +11,7 @@ import cloudpickle as cp
 import numpy as np
 import pandas as pd
 from numpy import typing as npt
-
+from packaging import version
 
 import numpy
 import sklearn
@@ -60,6 +60,14 @@ DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
 INFER_SIGNATURE_MAX_ROWS = 100
 
+SKLEARN_LOWER, SKLEARN_UPPER = ('1.4', '1.6')
+# Modeling library estimators require a smaller sklearn version range.
+if not version.Version(SKLEARN_LOWER) <= version.Version(sklearn.__version__) < version.Version(SKLEARN_UPPER):
+    raise Exception(
+        f"To use the modeling library, install scikit-learn version >= {SKLEARN_LOWER} and < {SKLEARN_UPPER}"
+    )
+
+
 class KNeighborsClassifier(BaseTransformer):
     r"""Classifier implementing the k-nearest neighbors vote
     For more details on this class, see [sklearn.neighbors.KNeighborsClassifier]

snowflake/ml/modeling/neighbors/k_neighbors_regressor.py

@@ -11,7 +11,7 @@ import cloudpickle as cp
 import numpy as np
 import pandas as pd
 from numpy import typing as npt
-
+from packaging import version
 
 import numpy
 import sklearn
@@ -60,6 +60,14 @@ DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
 INFER_SIGNATURE_MAX_ROWS = 100
 
+SKLEARN_LOWER, SKLEARN_UPPER = ('1.4', '1.6')
+# Modeling library estimators require a smaller sklearn version range.
+if not version.Version(SKLEARN_LOWER) <= version.Version(sklearn.__version__) < version.Version(SKLEARN_UPPER):
+    raise Exception(
+        f"To use the modeling library, install scikit-learn version >= {SKLEARN_LOWER} and < {SKLEARN_UPPER}"
+    )
+
+
 class KNeighborsRegressor(BaseTransformer):
     r"""Regression based on k-nearest neighbors
     For more details on this class, see [sklearn.neighbors.KNeighborsRegressor]

snowflake/ml/modeling/neighbors/kernel_density.py

@@ -11,7 +11,7 @@ import cloudpickle as cp
 import numpy as np
 import pandas as pd
 from numpy import typing as npt
-
+from packaging import version
 
 import numpy
 import sklearn
@@ -60,6 +60,14 @@ DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
 INFER_SIGNATURE_MAX_ROWS = 100
 
+SKLEARN_LOWER, SKLEARN_UPPER = ('1.4', '1.6')
+# Modeling library estimators require a smaller sklearn version range.
+if not version.Version(SKLEARN_LOWER) <= version.Version(sklearn.__version__) < version.Version(SKLEARN_UPPER):
+    raise Exception(
+        f"To use the modeling library, install scikit-learn version >= {SKLEARN_LOWER} and < {SKLEARN_UPPER}"
+    )
+
+
 class KernelDensity(BaseTransformer):
     r"""Kernel Density Estimation
     For more details on this class, see [sklearn.neighbors.KernelDensity]

snowflake/ml/modeling/neighbors/local_outlier_factor.py

@@ -11,7 +11,7 @@ import cloudpickle as cp
 import numpy as np
 import pandas as pd
 from numpy import typing as npt
-
+from packaging import version
 
 import numpy
 import sklearn
@@ -60,6 +60,14 @@ DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
 INFER_SIGNATURE_MAX_ROWS = 100
 
+SKLEARN_LOWER, SKLEARN_UPPER = ('1.4', '1.6')
+# Modeling library estimators require a smaller sklearn version range.
+if not version.Version(SKLEARN_LOWER) <= version.Version(sklearn.__version__) < version.Version(SKLEARN_UPPER):
+    raise Exception(
+        f"To use the modeling library, install scikit-learn version >= {SKLEARN_LOWER} and < {SKLEARN_UPPER}"
+    )
+
+
 class LocalOutlierFactor(BaseTransformer):
     r"""Unsupervised Outlier Detection using the Local Outlier Factor (LOF)
     For more details on this class, see [sklearn.neighbors.LocalOutlierFactor]

snowflake/ml/modeling/neighbors/nearest_centroid.py

@@ -11,7 +11,7 @@ import cloudpickle as cp
 import numpy as np
 import pandas as pd
 from numpy import typing as npt
-
+from packaging import version
 
 import numpy
 import sklearn
@@ -60,6 +60,14 @@ DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
 INFER_SIGNATURE_MAX_ROWS = 100
 
+SKLEARN_LOWER, SKLEARN_UPPER = ('1.4', '1.6')
+# Modeling library estimators require a smaller sklearn version range.
+if not version.Version(SKLEARN_LOWER) <= version.Version(sklearn.__version__) < version.Version(SKLEARN_UPPER):
+    raise Exception(
+        f"To use the modeling library, install scikit-learn version >= {SKLEARN_LOWER} and < {SKLEARN_UPPER}"
+    )
+
+
 class NearestCentroid(BaseTransformer):
     r"""Nearest centroid classifier
     For more details on this class, see [sklearn.neighbors.NearestCentroid]

snowflake/ml/modeling/neighbors/nearest_neighbors.py

@@ -11,7 +11,7 @@ import cloudpickle as cp
 import numpy as np
 import pandas as pd
 from numpy import typing as npt
-
+from packaging import version
 
 import numpy
 import sklearn
@@ -60,6 +60,14 @@ DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
 INFER_SIGNATURE_MAX_ROWS = 100
 
+SKLEARN_LOWER, SKLEARN_UPPER = ('1.4', '1.6')
+# Modeling library estimators require a smaller sklearn version range.
+if not version.Version(SKLEARN_LOWER) <= version.Version(sklearn.__version__) < version.Version(SKLEARN_UPPER):
+    raise Exception(
+        f"To use the modeling library, install scikit-learn version >= {SKLEARN_LOWER} and < {SKLEARN_UPPER}"
+    )
+
+
 class NearestNeighbors(BaseTransformer):
     r"""Unsupervised learner for implementing neighbor searches
     For more details on this class, see [sklearn.neighbors.NearestNeighbors]

snowflake/ml/modeling/neighbors/neighborhood_components_analysis.py

@@ -11,7 +11,7 @@ import cloudpickle as cp
 import numpy as np
 import pandas as pd
 from numpy import typing as npt
-
+from packaging import version
 
 import numpy
 import sklearn
@@ -60,6 +60,14 @@ DATAFRAME_TYPE = Union[DataFrame, pd.DataFrame]
 
 INFER_SIGNATURE_MAX_ROWS = 100
 
+SKLEARN_LOWER, SKLEARN_UPPER = ('1.4', '1.6')
+# Modeling library estimators require a smaller sklearn version range.
+if not version.Version(SKLEARN_LOWER) <= version.Version(sklearn.__version__) < version.Version(SKLEARN_UPPER):
+    raise Exception(
+        f"To use the modeling library, install scikit-learn version >= {SKLEARN_LOWER} and < {SKLEARN_UPPER}"
+    )
+
+
 class NeighborhoodComponentsAnalysis(BaseTransformer):
     r"""Neighborhood Components Analysis
     For more details on this class, see [sklearn.neighbors.NeighborhoodComponentsAnalysis]