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

snowflake/ml/modeling/preprocessing/ordinal_encoder.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python3
 import numbers
 import uuid
-from typing import Any, Dict, Iterable, List, Optional, Union
+from typing import Any, Iterable, Optional, Union
 
 import numpy as np
 import pandas as pd
@@ -102,7 +102,7 @@ class OrdinalEncoder(base.BaseTransformer):
     def __init__(
         self,
         *,
-        categories: Union[str, List[type_utils.LiteralNDArrayType], Dict[str, type_utils.LiteralNDArrayType]] = "auto",
+        categories: Union[str, list[type_utils.LiteralNDArrayType], dict[str, type_utils.LiteralNDArrayType]] = "auto",
         handle_unknown: str = "error",
         unknown_value: Optional[Union[int, float]] = None,
         encoded_missing_value: Union[int, float] = np.nan,
@@ -161,9 +161,9 @@ class OrdinalEncoder(base.BaseTransformer):
         self.unknown_value = unknown_value
         self.encoded_missing_value = encoded_missing_value
 
-        self.categories_: Dict[str, type_utils.LiteralNDArrayType] = {}
-        self._categories_list: List[type_utils.LiteralNDArrayType] = []
-        self._missing_indices: Dict[int, int] = {}
+        self.categories_: dict[str, type_utils.LiteralNDArrayType] = {}
+        self._categories_list: list[type_utils.LiteralNDArrayType] = []
+        self._missing_indices: dict[int, int] = {}
         self._infrequent_enabled = False
         self._vocab_table_name = snowpark_utils.random_name_for_temp_object(snowpark_utils.TempObjectType.TABLE)
 
@@ -221,7 +221,7 @@ class OrdinalEncoder(base.BaseTransformer):
 
         self._categories_list = sklearn_encoder.categories_
 
-        _state_pandas_ordinals: List[pd.DataFrame] = []
+        _state_pandas_ordinals: list[pd.DataFrame] = []
         for idx, input_col in enumerate(sorted(self.input_cols)):
             self.categories_[input_col] = self._categories_list[idx]
             # A column with values [a, b, b, None, a] will get mapped into a `_column_ordinals`
@@ -673,7 +673,7 @@ class OrdinalEncoder(base.BaseTransformer):
     def _check_unknown(
         self,
         dataset: snowpark.DataFrame,
-        statement_params: Dict[str, Any],
+        statement_params: dict[str, Any],
         batch: bool = False,
     ) -> None:
         """
@@ -690,8 +690,8 @@ class OrdinalEncoder(base.BaseTransformer):
 
         def create_unknown_df(
             dataset: snowpark.DataFrame,
-            input_cols: List[str],
-            output_cols: List[str],
+            input_cols: list[str],
+            output_cols: list[str],
         ) -> snowpark.DataFrame:
             # dataframe with unknown values
             # columns: COLUMN_NAME, UNKNOWN_VALUE

snowflake/ml/modeling/preprocessing/polynomial_features.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 PolynomialFeatures(BaseTransformer):
     r"""Generate polynomial and interaction features
     For more details on this class, see [sklearn.preprocessing.PolynomialFeatures]

snowflake/ml/modeling/preprocessing/robust_scaler.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-from typing import Dict, Iterable, List, Optional, Tuple, Union
+from typing import Iterable, Optional, Union
 
 import numpy as np
 import pandas as pd
@@ -70,7 +70,7 @@ class RobustScaler(base.BaseTransformer):
         *,
         with_centering: bool = True,
         with_scaling: bool = True,
-        quantile_range: Tuple[float, float] = (25.0, 75.0),
+        quantile_range: tuple[float, float] = (25.0, 75.0),
         unit_variance: bool = False,
         input_cols: Optional[Union[str, Iterable[str]]] = None,
         output_cols: Optional[Union[str, Iterable[str]]] = None,
@@ -112,12 +112,12 @@ class RobustScaler(base.BaseTransformer):
         self.unit_variance = unit_variance
 
         self._state_is_set = False
-        self._center: Dict[str, float] = {}
-        self._scale: Dict[str, float] = {}
+        self._center: dict[str, float] = {}
+        self._scale: dict[str, float] = {}
 
         l_range = self.quantile_range[0] / 100.0
         r_range = self.quantile_range[1] / 100.0
-        self.custom_states: List[str] = [
+        self.custom_states: list[str] = [
             _utils.NumericStatistics.MEDIAN,
             "SQL>>>percentile_cont(" + str(l_range) + ") within group (order by {col_name})",
             "SQL>>>percentile_cont(" + str(r_range) + ") within group (order by {col_name})",
@@ -140,11 +140,11 @@ class RobustScaler(base.BaseTransformer):
         self._state_is_set = False
 
     @property
-    def center_(self) -> Optional[Dict[str, float]]:
+    def center_(self) -> Optional[dict[str, float]]:
         return None if (not self.with_centering or not self._state_is_set) else self._center
 
     @property
-    def scale_(self) -> Optional[Dict[str, float]]:
+    def scale_(self) -> Optional[dict[str, float]]:
         return None if (not self.with_scaling or not self._state_is_set) else self._scale
 
     def _fit(self, dataset: Union[snowpark.DataFrame, pd.DataFrame]) -> "RobustScaler":

snowflake/ml/modeling/preprocessing/standard_scaler.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-from typing import Dict, Iterable, List, Optional, Union
+from typing import Iterable, Optional, Union
 
 import numpy as np
 import pandas as pd
@@ -106,11 +106,11 @@ class StandardScaler(base.BaseTransformer):
         self.with_mean = with_mean
         self.with_std = with_std
 
-        self.scale_: Optional[Dict[str, float]] = {} if with_std else None
-        self.mean_: Optional[Dict[str, float]] = {} if with_mean else None
-        self.var_: Optional[Dict[str, float]] = {} if with_std else None
+        self.scale_: Optional[dict[str, float]] = {} if with_std else None
+        self.mean_: Optional[dict[str, float]] = {} if with_mean else None
+        self.var_: Optional[dict[str, float]] = {} if with_std else None
 
-        self.custom_states: List[str] = []
+        self.custom_states: list[str] = []
         if with_mean:
             self.custom_states.append(_utils.NumericStatistics.MEAN)
         if with_std:

snowflake/ml/modeling/semi_supervised/label_propagation.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 LabelPropagation(BaseTransformer):
     r"""Label Propagation classifier
     For more details on this class, see [sklearn.semi_supervised.LabelPropagation]

snowflake/ml/modeling/semi_supervised/label_spreading.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 LabelSpreading(BaseTransformer):
     r"""LabelSpreading model for semi-supervised learning
     For more details on this class, see [sklearn.semi_supervised.LabelSpreading]

snowflake/ml/modeling/svm/linear_svc.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 LinearSVC(BaseTransformer):
     r"""Linear Support Vector Classification
     For more details on this class, see [sklearn.svm.LinearSVC]

snowflake/ml/modeling/svm/linear_svr.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 LinearSVR(BaseTransformer):
     r"""Linear Support Vector Regression
     For more details on this class, see [sklearn.svm.LinearSVR]

snowflake/ml/modeling/svm/nu_svc.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 NuSVC(BaseTransformer):
     r"""Nu-Support Vector Classification
     For more details on this class, see [sklearn.svm.NuSVC]

snowflake/ml/modeling/svm/nu_svr.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 NuSVR(BaseTransformer):
     r"""Nu Support Vector Regression
     For more details on this class, see [sklearn.svm.NuSVR]

snowflake/ml/modeling/svm/svc.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 SVC(BaseTransformer):
     r"""C-Support Vector Classification
     For more details on this class, see [sklearn.svm.SVC]

snowflake/ml/modeling/svm/svr.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 SVR(BaseTransformer):
     r"""Epsilon-Support Vector Regression
     For more details on this class, see [sklearn.svm.SVR]

snowflake/ml/modeling/tree/decision_tree_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 DecisionTreeClassifier(BaseTransformer):
     r"""A decision tree classifier
     For more details on this class, see [sklearn.tree.DecisionTreeClassifier]

snowflake/ml/modeling/tree/decision_tree_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 DecisionTreeRegressor(BaseTransformer):
     r"""A decision tree regressor
     For more details on this class, see [sklearn.tree.DecisionTreeRegressor]

snowflake/ml/modeling/tree/extra_tree_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 ExtraTreeClassifier(BaseTransformer):
     r"""An extremely randomized tree classifier
     For more details on this class, see [sklearn.tree.ExtraTreeClassifier]

snowflake/ml/modeling/tree/extra_tree_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 ExtraTreeRegressor(BaseTransformer):
     r"""An extremely randomized tree regressor
     For more details on this class, see [sklearn.tree.ExtraTreeRegressor]

snowflake/ml/modeling/xgboost/xgb_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 XGBClassifier(BaseTransformer):
     r"""Implementation of the scikit-learn API for XGBoost classification
     For more details on this class, see [xgboost.XGBClassifier]

snowflake/ml/modeling/xgboost/xgb_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 XGBRegressor(BaseTransformer):
     r"""Implementation of the scikit-learn API for XGBoost regression
     For more details on this class, see [xgboost.XGBRegressor]

snowflake/ml/modeling/xgboost/xgbrf_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 XGBRFClassifier(BaseTransformer):
     r"""scikit-learn API for XGBoost random forest classification
     For more details on this class, see [xgboost.XGBRFClassifier]

snowflake/ml/modeling/xgboost/xgbrf_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 XGBRFRegressor(BaseTransformer):
     r"""scikit-learn API for XGBoost random forest regression
     For more details on this class, see [xgboost.XGBRFRegressor]