snowflake-ml-python 1.1.2__py3-none-any.whl → 1.2.1__py3-none-any.whl

snowflake/ml/modeling/neural_network/mlp_classifier.py

@@ -54,6 +54,18 @@ _PROJECT = "ModelDevelopment"
 _SUBPROJECT = "".join([s.capitalize() for s in "sklearn.neural_network".replace("sklearn.", "").split("_")])
 
 
+def _is_fit_predict_method_enabled() -> Callable[[Any], bool]:
+    def check(self: BaseTransformer) -> TypeGuard[Callable[..., object]]:
+        return False and callable(getattr(self._sklearn_object, "fit_predict", None))
+    return check
+
+
+def _is_fit_transform_method_enabled() -> Callable[[Any], bool]:
+    def check(self: BaseTransformer) -> TypeGuard[Callable[..., object]]:
+        return False and callable(getattr(self._sklearn_object, "fit_transform", None))
+    return check
+
+
 class MLPClassifier(BaseTransformer):
     r"""Multi-layer Perceptron classifier
     For more details on this class, see [sklearn.neural_network.MLPClassifier]
@@ -297,7 +309,9 @@ class MLPClassifier(BaseTransformer):
         self.set_label_cols(label_cols)
         self.set_passthrough_cols(passthrough_cols)
         self.set_drop_input_cols(drop_input_cols)
-        self.set_sample_weight_col(sample_weight_col)        
+        self.set_sample_weight_col(sample_weight_col)
+        self._use_external_memory_version = False
+        self._batch_size = -1        
         deps: Set[str] = set([f'numpy=={np.__version__}', f'scikit-learn=={sklearn.__version__}', f'cloudpickle=={cp.__version__}'])
         
         self._deps = list(deps)
@@ -395,11 +409,6 @@ class MLPClassifier(BaseTransformer):
         if isinstance(dataset, DataFrame):
             session = dataset._session
             assert session is not None  # keep mypy happy
-            # Validate that key package version in user workspace are supported in snowflake conda channel
-            # If customer doesn't have package in conda channel, replace the ones have the closest versions
-            self._deps = pkg_version_utils.get_valid_pkg_versions_supported_in_snowflake_conda_channel(
-                pkg_versions=self._get_dependencies(), session=session, subproject=_SUBPROJECT)
-            
             # Specify input columns so column pruning will be enforced
             selected_cols = self._get_active_columns()
             if len(selected_cols) > 0:
@@ -427,7 +436,9 @@ class MLPClassifier(BaseTransformer):
             label_cols=self.label_cols,
             sample_weight_col=self.sample_weight_col,
             autogenerated=self._autogenerated,
-            subproject=_SUBPROJECT
+            subproject=_SUBPROJECT,
+            use_external_memory_version=self._use_external_memory_version,
+            batch_size=self._batch_size,
         )
         self._sklearn_object = model_trainer.train()
         self._is_fitted = True
@@ -698,6 +709,22 @@ class MLPClassifier(BaseTransformer):
                 # each row containing a list of values.
                 expected_dtype = "ARRAY"
 
+            # If we were unable to assign a type to this transform in the factory, infer the type here.
+            if expected_dtype == "":
+                # If this is a clustering transformer, if the number of output columns does not equal the number of clusters the response will be an "ARRAY"
+                if hasattr(self._sklearn_object, "n_clusters") and getattr(self._sklearn_object, "n_clusters") != len(self.output_cols):
+                    expected_dtype = "ARRAY"
+                # If this is a decomposition transformer, if the number of output columns does not equal the number of components the response will be an "ARRAY"
+                elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
+                    expected_dtype = "ARRAY"
+                else:
+                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(dataset[self.input_cols], "output", use_snowflake_identifiers=True)]
+                    # We can only infer the output types from the input types if the following two statemetns are true:
+                    # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
+                    # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
+                    if all(x == output_types[0] for x in output_types) and len(output_types) == len(self.output_cols):
+                        expected_dtype = convert_sp_to_sf_type(output_types[0])
+            
             output_df = self._batch_inference(
                 dataset=dataset,
                 inference_method="transform",
@@ -713,8 +740,8 @@ class MLPClassifier(BaseTransformer):
 
         return output_df
     
-    @available_if(original_estimator_has_callable("fit_predict"))  # type: ignore[misc]
-    def fit_predict(self, dataset: Union[DataFrame, pd.DataFrame]) -> npt.NDArray[Any]:
+    @available_if(_is_fit_predict_method_enabled())  # type: ignore[misc]
+    def fit_predict(self, dataset: Union[DataFrame, pd.DataFrame]) -> Union[Any, npt.NDArray[Any]]:
         """ Method not supported for this class.
 
 
@@ -727,13 +754,21 @@ class MLPClassifier(BaseTransformer):
         Returns:
             Predicted dataset.
         """
-        if False:
-            self.fit(dataset)
-            assert self._sklearn_object is not None
-            labels : npt.NDArray[Any] = self._sklearn_object.labels_
-            return labels
-        else:
-            raise NotImplementedError
+        self.fit(dataset)
+        assert self._sklearn_object is not None
+        return self._sklearn_object.labels_
+
+
+    @available_if(_is_fit_transform_method_enabled())  # type: ignore[misc]
+    def fit_transform(self, dataset: Union[DataFrame, pd.DataFrame]) -> Union[Any, npt.NDArray[Any]]:
+        """ 
+        Returns:
+            Transformed dataset.
+        """
+        self.fit(dataset)
+        assert self._sklearn_object is not None
+        return self._sklearn_object.embedding_
+
 
     def _get_output_column_names(self, output_cols_prefix: str, output_cols: Optional[List[str]] = None) -> List[str]:
         """ Returns the list of output columns for predict_proba(), decision_function(), etc.. functions.

snowflake/ml/modeling/neural_network/mlp_regressor.py

@@ -54,6 +54,18 @@ _PROJECT = "ModelDevelopment"
 _SUBPROJECT = "".join([s.capitalize() for s in "sklearn.neural_network".replace("sklearn.", "").split("_")])
 
 
+def _is_fit_predict_method_enabled() -> Callable[[Any], bool]:
+    def check(self: BaseTransformer) -> TypeGuard[Callable[..., object]]:
+        return False and callable(getattr(self._sklearn_object, "fit_predict", None))
+    return check
+
+
+def _is_fit_transform_method_enabled() -> Callable[[Any], bool]:
+    def check(self: BaseTransformer) -> TypeGuard[Callable[..., object]]:
+        return False and callable(getattr(self._sklearn_object, "fit_transform", None))
+    return check
+
+
 class MLPRegressor(BaseTransformer):
     r"""Multi-layer Perceptron regressor
     For more details on this class, see [sklearn.neural_network.MLPRegressor]
@@ -293,7 +305,9 @@ class MLPRegressor(BaseTransformer):
         self.set_label_cols(label_cols)
         self.set_passthrough_cols(passthrough_cols)
         self.set_drop_input_cols(drop_input_cols)
-        self.set_sample_weight_col(sample_weight_col)        
+        self.set_sample_weight_col(sample_weight_col)
+        self._use_external_memory_version = False
+        self._batch_size = -1        
         deps: Set[str] = set([f'numpy=={np.__version__}', f'scikit-learn=={sklearn.__version__}', f'cloudpickle=={cp.__version__}'])
         
         self._deps = list(deps)
@@ -391,11 +405,6 @@ class MLPRegressor(BaseTransformer):
         if isinstance(dataset, DataFrame):
             session = dataset._session
             assert session is not None  # keep mypy happy
-            # Validate that key package version in user workspace are supported in snowflake conda channel
-            # If customer doesn't have package in conda channel, replace the ones have the closest versions
-            self._deps = pkg_version_utils.get_valid_pkg_versions_supported_in_snowflake_conda_channel(
-                pkg_versions=self._get_dependencies(), session=session, subproject=_SUBPROJECT)
-            
             # Specify input columns so column pruning will be enforced
             selected_cols = self._get_active_columns()
             if len(selected_cols) > 0:
@@ -423,7 +432,9 @@ class MLPRegressor(BaseTransformer):
             label_cols=self.label_cols,
             sample_weight_col=self.sample_weight_col,
             autogenerated=self._autogenerated,
-            subproject=_SUBPROJECT
+            subproject=_SUBPROJECT,
+            use_external_memory_version=self._use_external_memory_version,
+            batch_size=self._batch_size,
         )
         self._sklearn_object = model_trainer.train()
         self._is_fitted = True
@@ -694,6 +705,22 @@ class MLPRegressor(BaseTransformer):
                 # each row containing a list of values.
                 expected_dtype = "ARRAY"
 
+            # If we were unable to assign a type to this transform in the factory, infer the type here.
+            if expected_dtype == "":
+                # If this is a clustering transformer, if the number of output columns does not equal the number of clusters the response will be an "ARRAY"
+                if hasattr(self._sklearn_object, "n_clusters") and getattr(self._sklearn_object, "n_clusters") != len(self.output_cols):
+                    expected_dtype = "ARRAY"
+                # If this is a decomposition transformer, if the number of output columns does not equal the number of components the response will be an "ARRAY"
+                elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
+                    expected_dtype = "ARRAY"
+                else:
+                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(dataset[self.input_cols], "output", use_snowflake_identifiers=True)]
+                    # We can only infer the output types from the input types if the following two statemetns are true:
+                    # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
+                    # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
+                    if all(x == output_types[0] for x in output_types) and len(output_types) == len(self.output_cols):
+                        expected_dtype = convert_sp_to_sf_type(output_types[0])
+            
             output_df = self._batch_inference(
                 dataset=dataset,
                 inference_method="transform",
@@ -709,8 +736,8 @@ class MLPRegressor(BaseTransformer):
 
         return output_df
     
-    @available_if(original_estimator_has_callable("fit_predict"))  # type: ignore[misc]
-    def fit_predict(self, dataset: Union[DataFrame, pd.DataFrame]) -> npt.NDArray[Any]:
+    @available_if(_is_fit_predict_method_enabled())  # type: ignore[misc]
+    def fit_predict(self, dataset: Union[DataFrame, pd.DataFrame]) -> Union[Any, npt.NDArray[Any]]:
         """ Method not supported for this class.
 
 
@@ -723,13 +750,21 @@ class MLPRegressor(BaseTransformer):
         Returns:
             Predicted dataset.
         """
-        if False:
-            self.fit(dataset)
-            assert self._sklearn_object is not None
-            labels : npt.NDArray[Any] = self._sklearn_object.labels_
-            return labels
-        else:
-            raise NotImplementedError
+        self.fit(dataset)
+        assert self._sklearn_object is not None
+        return self._sklearn_object.labels_
+
+
+    @available_if(_is_fit_transform_method_enabled())  # type: ignore[misc]
+    def fit_transform(self, dataset: Union[DataFrame, pd.DataFrame]) -> Union[Any, npt.NDArray[Any]]:
+        """ 
+        Returns:
+            Transformed dataset.
+        """
+        self.fit(dataset)
+        assert self._sklearn_object is not None
+        return self._sklearn_object.embedding_
+
 
     def _get_output_column_names(self, output_cols_prefix: str, output_cols: Optional[List[str]] = None) -> List[str]:
         """ Returns the list of output columns for predict_proba(), decision_function(), etc.. functions.

snowflake/ml/modeling/preprocessing/min_max_scaler.py

@@ -8,8 +8,9 @@ from sklearn.preprocessing import _data as sklearn_preprocessing_data
 
 from snowflake import snowpark
 from snowflake.ml._internal import telemetry
+from snowflake.ml._internal.exceptions import error_codes, exceptions
 from snowflake.ml.modeling.framework import _utils, base
-from snowflake.snowpark import functions as F
+from snowflake.snowpark import functions as F, types as T
 
 
 class MinMaxScaler(base.BaseTransformer):
@@ -125,6 +126,18 @@ class MinMaxScaler(base.BaseTransformer):
             self.data_max_ = {}
             self.data_range_ = {}
 
+    def _check_input_column_types(self, dataset: snowpark.DataFrame) -> None:
+        for field in dataset.schema.fields:
+            if field.name in self.input_cols:
+                if not issubclass(type(field.datatype), T._NumericType):
+                    raise exceptions.SnowflakeMLException(
+                        error_code=error_codes.INVALID_DATA_TYPE,
+                        original_exception=TypeError(
+                            f"Non-numeric input column {field.name} datatype {field.datatype} "
+                            "is not supported by the MinMaxScaler."
+                        ),
+                    )
+
     @telemetry.send_api_usage_telemetry(
         project=base.PROJECT,
         subproject=base.SUBPROJECT,
@@ -169,6 +182,7 @@ class MinMaxScaler(base.BaseTransformer):
             self.data_range_[input_col] = float(sklearn_scaler.data_range_[i])
 
     def _fit_snowpark(self, dataset: snowpark.DataFrame) -> None:
+        self._check_input_column_types(dataset)
         computed_states = self._compute(dataset, self.input_cols, self.custom_states)
 
         # assign states to the object

snowflake/ml/modeling/preprocessing/polynomial_features.py

@@ -54,6 +54,18 @@ _PROJECT = "ModelDevelopment"
 _SUBPROJECT = "".join([s.capitalize() for s in "sklearn.preprocessing".replace("sklearn.", "").split("_")])
 
 
+def _is_fit_predict_method_enabled() -> Callable[[Any], bool]:
+    def check(self: BaseTransformer) -> TypeGuard[Callable[..., object]]:
+        return False and callable(getattr(self._sklearn_object, "fit_predict", None))
+    return check
+
+
+def _is_fit_transform_method_enabled() -> Callable[[Any], bool]:
+    def check(self: BaseTransformer) -> TypeGuard[Callable[..., object]]:
+        return False and callable(getattr(self._sklearn_object, "fit_transform", None))
+    return check
+
+
 class PolynomialFeatures(BaseTransformer):
     r"""Generate polynomial and interaction features
     For more details on this class, see [sklearn.preprocessing.PolynomialFeatures]
@@ -151,7 +163,9 @@ class PolynomialFeatures(BaseTransformer):
         self.set_label_cols(label_cols)
         self.set_passthrough_cols(passthrough_cols)
         self.set_drop_input_cols(drop_input_cols)
-        self.set_sample_weight_col(sample_weight_col)        
+        self.set_sample_weight_col(sample_weight_col)
+        self._use_external_memory_version = False
+        self._batch_size = -1        
         deps: Set[str] = set([f'numpy=={np.__version__}', f'scikit-learn=={sklearn.__version__}', f'cloudpickle=={cp.__version__}'])
         
         self._deps = list(deps)
@@ -230,11 +244,6 @@ class PolynomialFeatures(BaseTransformer):
         if isinstance(dataset, DataFrame):
             session = dataset._session
             assert session is not None  # keep mypy happy
-            # Validate that key package version in user workspace are supported in snowflake conda channel
-            # If customer doesn't have package in conda channel, replace the ones have the closest versions
-            self._deps = pkg_version_utils.get_valid_pkg_versions_supported_in_snowflake_conda_channel(
-                pkg_versions=self._get_dependencies(), session=session, subproject=_SUBPROJECT)
-            
             # Specify input columns so column pruning will be enforced
             selected_cols = self._get_active_columns()
             if len(selected_cols) > 0:
@@ -262,7 +271,9 @@ class PolynomialFeatures(BaseTransformer):
             label_cols=self.label_cols,
             sample_weight_col=self.sample_weight_col,
             autogenerated=self._autogenerated,
-            subproject=_SUBPROJECT
+            subproject=_SUBPROJECT,
+            use_external_memory_version=self._use_external_memory_version,
+            batch_size=self._batch_size,
         )
         self._sklearn_object = model_trainer.train()
         self._is_fitted = True
@@ -533,6 +544,22 @@ class PolynomialFeatures(BaseTransformer):
                 # each row containing a list of values.
                 expected_dtype = "ARRAY"
 
+            # If we were unable to assign a type to this transform in the factory, infer the type here.
+            if expected_dtype == "":
+                # If this is a clustering transformer, if the number of output columns does not equal the number of clusters the response will be an "ARRAY"
+                if hasattr(self._sklearn_object, "n_clusters") and getattr(self._sklearn_object, "n_clusters") != len(self.output_cols):
+                    expected_dtype = "ARRAY"
+                # If this is a decomposition transformer, if the number of output columns does not equal the number of components the response will be an "ARRAY"
+                elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
+                    expected_dtype = "ARRAY"
+                else:
+                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(dataset[self.input_cols], "output", use_snowflake_identifiers=True)]
+                    # We can only infer the output types from the input types if the following two statemetns are true:
+                    # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
+                    # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
+                    if all(x == output_types[0] for x in output_types) and len(output_types) == len(self.output_cols):
+                        expected_dtype = convert_sp_to_sf_type(output_types[0])
+            
             output_df = self._batch_inference(
                 dataset=dataset,
                 inference_method="transform",
@@ -548,8 +575,8 @@ class PolynomialFeatures(BaseTransformer):
 
         return output_df
     
-    @available_if(original_estimator_has_callable("fit_predict"))  # type: ignore[misc]
-    def fit_predict(self, dataset: Union[DataFrame, pd.DataFrame]) -> npt.NDArray[Any]:
+    @available_if(_is_fit_predict_method_enabled())  # type: ignore[misc]
+    def fit_predict(self, dataset: Union[DataFrame, pd.DataFrame]) -> Union[Any, npt.NDArray[Any]]:
         """ Method not supported for this class.
 
 
@@ -562,13 +589,21 @@ class PolynomialFeatures(BaseTransformer):
         Returns:
             Predicted dataset.
         """
-        if False:
-            self.fit(dataset)
-            assert self._sklearn_object is not None
-            labels : npt.NDArray[Any] = self._sklearn_object.labels_
-            return labels
-        else:
-            raise NotImplementedError
+        self.fit(dataset)
+        assert self._sklearn_object is not None
+        return self._sklearn_object.labels_
+
+
+    @available_if(_is_fit_transform_method_enabled())  # type: ignore[misc]
+    def fit_transform(self, dataset: Union[DataFrame, pd.DataFrame]) -> Union[Any, npt.NDArray[Any]]:
+        """ 
+        Returns:
+            Transformed dataset.
+        """
+        self.fit(dataset)
+        assert self._sklearn_object is not None
+        return self._sklearn_object.embedding_
+
 
     def _get_output_column_names(self, output_cols_prefix: str, output_cols: Optional[List[str]] = None) -> List[str]:
         """ Returns the list of output columns for predict_proba(), decision_function(), etc.. functions.

snowflake/ml/modeling/semi_supervised/label_propagation.py

@@ -54,6 +54,18 @@ _PROJECT = "ModelDevelopment"
 _SUBPROJECT = "".join([s.capitalize() for s in "sklearn.semi_supervised".replace("sklearn.", "").split("_")])
 
 
+def _is_fit_predict_method_enabled() -> Callable[[Any], bool]:
+    def check(self: BaseTransformer) -> TypeGuard[Callable[..., object]]:
+        return False and callable(getattr(self._sklearn_object, "fit_predict", None))
+    return check
+
+
+def _is_fit_transform_method_enabled() -> Callable[[Any], bool]:
+    def check(self: BaseTransformer) -> TypeGuard[Callable[..., object]]:
+        return False and callable(getattr(self._sklearn_object, "fit_transform", None))
+    return check
+
+
 class LabelPropagation(BaseTransformer):
     r"""Label Propagation classifier
     For more details on this class, see [sklearn.semi_supervised.LabelPropagation]
@@ -155,7 +167,9 @@ class LabelPropagation(BaseTransformer):
         self.set_label_cols(label_cols)
         self.set_passthrough_cols(passthrough_cols)
         self.set_drop_input_cols(drop_input_cols)
-        self.set_sample_weight_col(sample_weight_col)        
+        self.set_sample_weight_col(sample_weight_col)
+        self._use_external_memory_version = False
+        self._batch_size = -1        
         deps: Set[str] = set([f'numpy=={np.__version__}', f'scikit-learn=={sklearn.__version__}', f'cloudpickle=={cp.__version__}'])
         
         self._deps = list(deps)
@@ -236,11 +250,6 @@ class LabelPropagation(BaseTransformer):
         if isinstance(dataset, DataFrame):
             session = dataset._session
             assert session is not None  # keep mypy happy
-            # Validate that key package version in user workspace are supported in snowflake conda channel
-            # If customer doesn't have package in conda channel, replace the ones have the closest versions
-            self._deps = pkg_version_utils.get_valid_pkg_versions_supported_in_snowflake_conda_channel(
-                pkg_versions=self._get_dependencies(), session=session, subproject=_SUBPROJECT)
-            
             # Specify input columns so column pruning will be enforced
             selected_cols = self._get_active_columns()
             if len(selected_cols) > 0:
@@ -268,7 +277,9 @@ class LabelPropagation(BaseTransformer):
             label_cols=self.label_cols,
             sample_weight_col=self.sample_weight_col,
             autogenerated=self._autogenerated,
-            subproject=_SUBPROJECT
+            subproject=_SUBPROJECT,
+            use_external_memory_version=self._use_external_memory_version,
+            batch_size=self._batch_size,
         )
         self._sklearn_object = model_trainer.train()
         self._is_fitted = True
@@ -539,6 +550,22 @@ class LabelPropagation(BaseTransformer):
                 # each row containing a list of values.
                 expected_dtype = "ARRAY"
 
+            # If we were unable to assign a type to this transform in the factory, infer the type here.
+            if expected_dtype == "":
+                # If this is a clustering transformer, if the number of output columns does not equal the number of clusters the response will be an "ARRAY"
+                if hasattr(self._sklearn_object, "n_clusters") and getattr(self._sklearn_object, "n_clusters") != len(self.output_cols):
+                    expected_dtype = "ARRAY"
+                # If this is a decomposition transformer, if the number of output columns does not equal the number of components the response will be an "ARRAY"
+                elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
+                    expected_dtype = "ARRAY"
+                else:
+                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(dataset[self.input_cols], "output", use_snowflake_identifiers=True)]
+                    # We can only infer the output types from the input types if the following two statemetns are true:
+                    # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
+                    # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
+                    if all(x == output_types[0] for x in output_types) and len(output_types) == len(self.output_cols):
+                        expected_dtype = convert_sp_to_sf_type(output_types[0])
+            
             output_df = self._batch_inference(
                 dataset=dataset,
                 inference_method="transform",
@@ -554,8 +581,8 @@ class LabelPropagation(BaseTransformer):
 
         return output_df
     
-    @available_if(original_estimator_has_callable("fit_predict"))  # type: ignore[misc]
-    def fit_predict(self, dataset: Union[DataFrame, pd.DataFrame]) -> npt.NDArray[Any]:
+    @available_if(_is_fit_predict_method_enabled())  # type: ignore[misc]
+    def fit_predict(self, dataset: Union[DataFrame, pd.DataFrame]) -> Union[Any, npt.NDArray[Any]]:
         """ Method not supported for this class.
 
 
@@ -568,13 +595,21 @@ class LabelPropagation(BaseTransformer):
         Returns:
             Predicted dataset.
         """
-        if False:
-            self.fit(dataset)
-            assert self._sklearn_object is not None
-            labels : npt.NDArray[Any] = self._sklearn_object.labels_
-            return labels
-        else:
-            raise NotImplementedError
+        self.fit(dataset)
+        assert self._sklearn_object is not None
+        return self._sklearn_object.labels_
+
+
+    @available_if(_is_fit_transform_method_enabled())  # type: ignore[misc]
+    def fit_transform(self, dataset: Union[DataFrame, pd.DataFrame]) -> Union[Any, npt.NDArray[Any]]:
+        """ 
+        Returns:
+            Transformed dataset.
+        """
+        self.fit(dataset)
+        assert self._sklearn_object is not None
+        return self._sklearn_object.embedding_
+
 
     def _get_output_column_names(self, output_cols_prefix: str, output_cols: Optional[List[str]] = None) -> List[str]:
         """ Returns the list of output columns for predict_proba(), decision_function(), etc.. functions.

snowflake/ml/modeling/semi_supervised/label_spreading.py

@@ -54,6 +54,18 @@ _PROJECT = "ModelDevelopment"
 _SUBPROJECT = "".join([s.capitalize() for s in "sklearn.semi_supervised".replace("sklearn.", "").split("_")])
 
 
+def _is_fit_predict_method_enabled() -> Callable[[Any], bool]:
+    def check(self: BaseTransformer) -> TypeGuard[Callable[..., object]]:
+        return False and callable(getattr(self._sklearn_object, "fit_predict", None))
+    return check
+
+
+def _is_fit_transform_method_enabled() -> Callable[[Any], bool]:
+    def check(self: BaseTransformer) -> TypeGuard[Callable[..., object]]:
+        return False and callable(getattr(self._sklearn_object, "fit_transform", None))
+    return check
+
+
 class LabelSpreading(BaseTransformer):
     r"""LabelSpreading model for semi-supervised learning
     For more details on this class, see [sklearn.semi_supervised.LabelSpreading]
@@ -163,7 +175,9 @@ class LabelSpreading(BaseTransformer):
         self.set_label_cols(label_cols)
         self.set_passthrough_cols(passthrough_cols)
         self.set_drop_input_cols(drop_input_cols)
-        self.set_sample_weight_col(sample_weight_col)        
+        self.set_sample_weight_col(sample_weight_col)
+        self._use_external_memory_version = False
+        self._batch_size = -1        
         deps: Set[str] = set([f'numpy=={np.__version__}', f'scikit-learn=={sklearn.__version__}', f'cloudpickle=={cp.__version__}'])
         
         self._deps = list(deps)
@@ -245,11 +259,6 @@ class LabelSpreading(BaseTransformer):
         if isinstance(dataset, DataFrame):
             session = dataset._session
             assert session is not None  # keep mypy happy
-            # Validate that key package version in user workspace are supported in snowflake conda channel
-            # If customer doesn't have package in conda channel, replace the ones have the closest versions
-            self._deps = pkg_version_utils.get_valid_pkg_versions_supported_in_snowflake_conda_channel(
-                pkg_versions=self._get_dependencies(), session=session, subproject=_SUBPROJECT)
-            
             # Specify input columns so column pruning will be enforced
             selected_cols = self._get_active_columns()
             if len(selected_cols) > 0:
@@ -277,7 +286,9 @@ class LabelSpreading(BaseTransformer):
             label_cols=self.label_cols,
             sample_weight_col=self.sample_weight_col,
             autogenerated=self._autogenerated,
-            subproject=_SUBPROJECT
+            subproject=_SUBPROJECT,
+            use_external_memory_version=self._use_external_memory_version,
+            batch_size=self._batch_size,
         )
         self._sklearn_object = model_trainer.train()
         self._is_fitted = True
@@ -548,6 +559,22 @@ class LabelSpreading(BaseTransformer):
                 # each row containing a list of values.
                 expected_dtype = "ARRAY"
 
+            # If we were unable to assign a type to this transform in the factory, infer the type here.
+            if expected_dtype == "":
+                # If this is a clustering transformer, if the number of output columns does not equal the number of clusters the response will be an "ARRAY"
+                if hasattr(self._sklearn_object, "n_clusters") and getattr(self._sklearn_object, "n_clusters") != len(self.output_cols):
+                    expected_dtype = "ARRAY"
+                # If this is a decomposition transformer, if the number of output columns does not equal the number of components the response will be an "ARRAY"
+                elif hasattr(self._sklearn_object, "n_components") and getattr(self._sklearn_object, "n_components") != len(self.output_cols):
+                    expected_dtype = "ARRAY"
+                else:
+                    output_types = [signature.as_snowpark_type() for signature in _infer_signature(dataset[self.input_cols], "output", use_snowflake_identifiers=True)]
+                    # We can only infer the output types from the input types if the following two statemetns are true:
+                    # 1) All of the output types are the same. Otherwise, we still have to fall back to variant because `_sklearn_inference` only accepts one type.
+                    # 2) The length of the input columns equals the length of the output columns. Otherwise the transform will likely result in an `ARRAY`.
+                    if all(x == output_types[0] for x in output_types) and len(output_types) == len(self.output_cols):
+                        expected_dtype = convert_sp_to_sf_type(output_types[0])
+            
             output_df = self._batch_inference(
                 dataset=dataset,
                 inference_method="transform",
@@ -563,8 +590,8 @@ class LabelSpreading(BaseTransformer):
 
         return output_df
     
-    @available_if(original_estimator_has_callable("fit_predict"))  # type: ignore[misc]
-    def fit_predict(self, dataset: Union[DataFrame, pd.DataFrame]) -> npt.NDArray[Any]:
+    @available_if(_is_fit_predict_method_enabled())  # type: ignore[misc]
+    def fit_predict(self, dataset: Union[DataFrame, pd.DataFrame]) -> Union[Any, npt.NDArray[Any]]:
         """ Method not supported for this class.
 
 
@@ -577,13 +604,21 @@ class LabelSpreading(BaseTransformer):
         Returns:
             Predicted dataset.
         """
-        if False:
-            self.fit(dataset)
-            assert self._sklearn_object is not None
-            labels : npt.NDArray[Any] = self._sklearn_object.labels_
-            return labels
-        else:
-            raise NotImplementedError
+        self.fit(dataset)
+        assert self._sklearn_object is not None
+        return self._sklearn_object.labels_
+
+
+    @available_if(_is_fit_transform_method_enabled())  # type: ignore[misc]
+    def fit_transform(self, dataset: Union[DataFrame, pd.DataFrame]) -> Union[Any, npt.NDArray[Any]]:
+        """ 
+        Returns:
+            Transformed dataset.
+        """
+        self.fit(dataset)
+        assert self._sklearn_object is not None
+        return self._sklearn_object.embedding_
+
 
     def _get_output_column_names(self, output_cols_prefix: str, output_cols: Optional[List[str]] = None) -> List[str]:
         """ Returns the list of output columns for predict_proba(), decision_function(), etc.. functions.