snowflake-ml-python 1.6.4__tar.gz → 1.7.0__tar.gz

{snowflake_ml_python-1.6.4 → snowflake_ml_python-1.7.0}/CHANGELOG.md

@@ -1,6 +1,70 @@
 # Release History
 
-## 1.6.4
+## 1.7.0
+
+### Behavior Change
+
+- Generic: Require python >= 3.9.
+- Data Connector: Update `to_torch_dataset` and `to_torch_datapipe` to add a dimension for scalar data.
+This allows for more seamless integration with PyTorch `DataLoader`, which creates batches by stacking inputs of each batch.
+
+Examples:
+
+```python
+ds = connector.to_torch_dataset(shuffle=False, batch_size=3)
+```
+
+- Input: "col1": [10, 11, 12]
+  - Previous batch: array([10., 11., 12.]) with shape (3,)
+  - New batch: array([[10.], [11.], [12.]]) with shape (3, 1)
+
+- Input: "col2": [[0, 100], [1, 110], [2, 200]]
+  - Previous batch: array([[  0, 100], [  1, 110], [  2, 200]]) with shape (3,2)
+  - New batch: No change
+
+- Model Registry: External access integrations are optional when creating a model inference service in
+  Snowflake >= 8.40.0.
+- Model Registry: Deprecate `build_external_access_integration` with `build_external_access_integrations` in
+  `ModelVersion.create_service()`.
+
+### Bug Fixes
+
+- Registry: Updated `log_model` API to accept both signature and sample_input_data parameters.
+- Feature Store: ExampleHelper uses fully qualified path for table name. change weather features aggregation from 1d to 1h.
+- Data Connector: Return numpy array with appropriate object type instead of list for multi-dimensional
+data from `to_torch_dataset` and `to_torch_datapipe`
+- Model explainability: Incompatibility between SHAP 0.42.1 and XGB 2.1.1 resolved by using latest SHAP 0.46.0.
+
+### New Features
+
+- Registry: Provide pass keyworded variable length of arguments to class ModelContext. Example usage:
+
+```python
+mc = custom_model.ModelContext(
+    config = 'local_model_dir/config.json',
+    m1 = model1
+)
+
+class ExamplePipelineModel(custom_model.CustomModel):
+    def __init__(self, context: custom_model.ModelContext) -> None:
+      super().__init__(context)
+      v = open(self.context['config']).read()
+      self.bias = json.loads(v)['bias']
+
+    @custom_model.inference_api
+    def predict(self, input: pd.DataFrame) -> pd.DataFrame:
+      model_output = self.context['m1'].predict(input)
+      return pd.DataFrame({'output': model_output + self.bias})
+```
+
+- Model Development: Upgrade scikit-learn in UDTF backend for log_loss metric. As a result, `eps` argument is now ignored.
+- Data Connector: Add the option of passing a `None` sized batch to `to_torch_dataset` for better
+interoperability with PyTorch DataLoader.
+- Model Registry: Support [pandas.CategoricalDtype](https://pandas.pydata.org/docs/reference/api/pandas.CategoricalDtype.html#pandas-categoricaldtype)
+- Registry: It is now possible to pass `signatures` and `sample_input_data` at the same time to capture background
+data from explainablity and data lineage.
+
+## 1.6.4 (2024-10-17)
 
 ### Bug Fixes
 
@@ -18,6 +82,9 @@
 - Registry: Fix a bug that `ModelVersion.run` is called in a nested way.
 - Registry: Fix an issue that leads to `log_model` failure when local package version contains parts other than
   base version.
+- Fix issue where `sample_weights` were not being applied to search estimators.
+- Model explainability: Fix bug which creates explain as a function instead of table function when enabling by default.
+- Model explainability: Update lightgbm binary classification to return non-json values, from customer feedback.
 
 ### New Features
 

{snowflake_ml_python-1.6.4 → snowflake_ml_python-1.7.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: snowflake-ml-python
-Version: 1.6.4
+Version: 1.7.0
 Summary: The machine learning client library that is used for interacting with Snowflake to build machine learning solutions.
 Author-email: "Snowflake, Inc" <support@snowflake.com>
 License: 
@@ -220,7 +220,6 @@ Classifier: Intended Audience :: Information Technology
 Classifier: Intended Audience :: System Administrators
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Operating System :: OS Independent
-Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
@@ -230,7 +229,7 @@ Classifier: Topic :: Software Development :: Libraries
 Classifier: Topic :: Software Development :: Libraries :: Application Frameworks
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Topic :: Scientific/Engineering :: Information Analysis
-Requires-Python: <3.12,>=3.8
+Requires-Python: <3.12,>=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE.txt
 Requires-Dist: absl-py<2,>=0.15
@@ -247,13 +246,13 @@ Requires-Dist: pytimeparse<2,>=1.1.8
 Requires-Dist: pyyaml<7,>=6.0
 Requires-Dist: retrying<2,>=1.3.3
 Requires-Dist: s3fs<2024,>=2022.11
-Requires-Dist: scikit-learn<1.6,>=1.2.1
+Requires-Dist: scikit-learn<1.6,>=1.4
 Requires-Dist: scipy<2,>=1.9
 Requires-Dist: snowflake-connector-python[pandas]<4,>=3.5.0
 Requires-Dist: snowflake-snowpark-python<2,>=1.17.0
 Requires-Dist: sqlparse<1,>=0.4
 Requires-Dist: typing-extensions<5,>=4.1.0
-Requires-Dist: xgboost<2.1,>=1.7.3
+Requires-Dist: xgboost<3,>=1.7.3
 Provides-Extra: all
 Requires-Dist: catboost<2,>=1.2.0; extra == "all"
 Requires-Dist: lightgbm<5,>=3.3.5; extra == "all"
@@ -261,7 +260,7 @@ Requires-Dist: mlflow<2.4,>=2.1.0; extra == "all"
 Requires-Dist: peft<1,>=0.5.0; extra == "all"
 Requires-Dist: sentence-transformers<3,>=2.2.2; extra == "all"
 Requires-Dist: sentencepiece<1,>=0.1.95; extra == "all"
-Requires-Dist: shap<1,>=0.42.0; extra == "all"
+Requires-Dist: shap<1,>=0.46.0; extra == "all"
 Requires-Dist: tensorflow<3,>=2.10; extra == "all"
 Requires-Dist: tokenizers<1,>=0.10; extra == "all"
 Requires-Dist: torch<2.3.0,>=2.0.1; extra == "all"
@@ -276,7 +275,7 @@ Requires-Dist: peft<1,>=0.5.0; extra == "llm"
 Provides-Extra: mlflow
 Requires-Dist: mlflow<2.4,>=2.1.0; extra == "mlflow"
 Provides-Extra: shap
-Requires-Dist: shap<1,>=0.42.0; extra == "shap"
+Requires-Dist: shap<1,>=0.46.0; extra == "shap"
 Provides-Extra: tensorflow
 Requires-Dist: tensorflow<3,>=2.10; extra == "tensorflow"
 Provides-Extra: torch
@@ -336,7 +335,7 @@ If you don't have a Snowflake account yet, you can [sign up for a 30-day free tr
 Follow the [installation instructions](https://docs.snowflake.com/en/developer-guide/snowpark-ml/index#installing-snowpark-ml)
 in the Snowflake documentation.
 
-Python versions 3.8 to 3.11 are supported. You can use [miniconda](https://docs.conda.io/en/latest/miniconda.html) or
+Python versions 3.9 to 3.11 are supported. You can use [miniconda](https://docs.conda.io/en/latest/miniconda.html) or
 [anaconda](https://www.anaconda.com/) to create a Conda environment (recommended),
 or [virtualenv](https://docs.python.org/3/tutorial/venv.html) to create a virtual environment.
 
@@ -373,7 +372,71 @@ be compatibility issues. Server-side functionality that `snowflake-ml-python` de
 
 # Release History
 
-## 1.6.4
+## 1.7.0
+
+### Behavior Change
+
+- Generic: Require python >= 3.9.
+- Data Connector: Update `to_torch_dataset` and `to_torch_datapipe` to add a dimension for scalar data.
+This allows for more seamless integration with PyTorch `DataLoader`, which creates batches by stacking inputs of each batch.
+
+Examples:
+
+```python
+ds = connector.to_torch_dataset(shuffle=False, batch_size=3)
+```
+
+- Input: "col1": [10, 11, 12]
+  - Previous batch: array([10., 11., 12.]) with shape (3,)
+  - New batch: array([[10.], [11.], [12.]]) with shape (3, 1)
+
+- Input: "col2": [[0, 100], [1, 110], [2, 200]]
+  - Previous batch: array([[  0, 100], [  1, 110], [  2, 200]]) with shape (3,2)
+  - New batch: No change
+
+- Model Registry: External access integrations are optional when creating a model inference service in
+  Snowflake >= 8.40.0.
+- Model Registry: Deprecate `build_external_access_integration` with `build_external_access_integrations` in
+  `ModelVersion.create_service()`.
+
+### Bug Fixes
+
+- Registry: Updated `log_model` API to accept both signature and sample_input_data parameters.
+- Feature Store: ExampleHelper uses fully qualified path for table name. change weather features aggregation from 1d to 1h.
+- Data Connector: Return numpy array with appropriate object type instead of list for multi-dimensional
+data from `to_torch_dataset` and `to_torch_datapipe`
+- Model explainability: Incompatibility between SHAP 0.42.1 and XGB 2.1.1 resolved by using latest SHAP 0.46.0.
+
+### New Features
+
+- Registry: Provide pass keyworded variable length of arguments to class ModelContext. Example usage:
+
+```python
+mc = custom_model.ModelContext(
+    config = 'local_model_dir/config.json',
+    m1 = model1
+)
+
+class ExamplePipelineModel(custom_model.CustomModel):
+    def __init__(self, context: custom_model.ModelContext) -> None:
+      super().__init__(context)
+      v = open(self.context['config']).read()
+      self.bias = json.loads(v)['bias']
+
+    @custom_model.inference_api
+    def predict(self, input: pd.DataFrame) -> pd.DataFrame:
+      model_output = self.context['m1'].predict(input)
+      return pd.DataFrame({'output': model_output + self.bias})
+```
+
+- Model Development: Upgrade scikit-learn in UDTF backend for log_loss metric. As a result, `eps` argument is now ignored.
+- Data Connector: Add the option of passing a `None` sized batch to `to_torch_dataset` for better
+interoperability with PyTorch DataLoader.
+- Model Registry: Support [pandas.CategoricalDtype](https://pandas.pydata.org/docs/reference/api/pandas.CategoricalDtype.html#pandas-categoricaldtype)
+- Registry: It is now possible to pass `signatures` and `sample_input_data` at the same time to capture background
+data from explainablity and data lineage.
+
+## 1.6.4 (2024-10-17)
 
 ### Bug Fixes
 
@@ -391,6 +454,9 @@ be compatibility issues. Server-side functionality that `snowflake-ml-python` de
 - Registry: Fix a bug that `ModelVersion.run` is called in a nested way.
 - Registry: Fix an issue that leads to `log_model` failure when local package version contains parts other than
   base version.
+- Fix issue where `sample_weights` were not being applied to search estimators.
+- Model explainability: Fix bug which creates explain as a function instead of table function when enabling by default.
+- Model explainability: Update lightgbm binary classification to return non-json values, from customer feedback.
 
 ### New Features
 

{snowflake_ml_python-1.6.4 → snowflake_ml_python-1.7.0}/README.md

@@ -46,7 +46,7 @@ If you don't have a Snowflake account yet, you can [sign up for a 30-day free tr
 Follow the [installation instructions](https://docs.snowflake.com/en/developer-guide/snowpark-ml/index#installing-snowpark-ml)
 in the Snowflake documentation.
 
-Python versions 3.8 to 3.11 are supported. You can use [miniconda](https://docs.conda.io/en/latest/miniconda.html) or
+Python versions 3.9 to 3.11 are supported. You can use [miniconda](https://docs.conda.io/en/latest/miniconda.html) or
 [anaconda](https://www.anaconda.com/) to create a Conda environment (recommended),
 or [virtualenv](https://docs.python.org/3/tutorial/venv.html) to create a virtual environment.
 

{snowflake_ml_python-1.6.4 → snowflake_ml_python-1.7.0}/pyproject.toml

@@ -5,10 +5,10 @@ build-backend = "setuptools.build_meta"
 [project]
 name = "snowflake-ml-python"
 description = "The machine learning client library that is used for interacting with Snowflake to build machine learning solutions."
-classifiers = [ "Development Status :: 5 - Production/Stable", "Environment :: Console", "Environment :: Other Environment", "Intended Audience :: Developers", "Intended Audience :: Education", "Intended Audience :: Information Technology", "Intended Audience :: System Administrators", "License :: OSI Approved :: Apache Software License", "Operating System :: OS Independent", "Programming Language :: Python :: 3.8", "Programming Language :: Python :: 3.9", "Programming Language :: Python :: 3.10", "Programming Language :: Python :: 3.11", "Topic :: Database", "Topic :: Software Development", "Topic :: Software Development :: Libraries", "Topic :: Software Development :: Libraries :: Application Frameworks", "Topic :: Software Development :: Libraries :: Python Modules", "Topic :: Scientific/Engineering :: Information Analysis",]
-requires-python = ">=3.8, <3.12"
+classifiers = [ "Development Status :: 5 - Production/Stable", "Environment :: Console", "Environment :: Other Environment", "Intended Audience :: Developers", "Intended Audience :: Education", "Intended Audience :: Information Technology", "Intended Audience :: System Administrators", "License :: OSI Approved :: Apache Software License", "Operating System :: OS Independent", "Programming Language :: Python :: 3.9", "Programming Language :: Python :: 3.10", "Programming Language :: Python :: 3.11", "Topic :: Database", "Topic :: Software Development", "Topic :: Software Development :: Libraries", "Topic :: Software Development :: Libraries :: Application Frameworks", "Topic :: Software Development :: Libraries :: Python Modules", "Topic :: Scientific/Engineering :: Information Analysis",]
+requires-python = ">=3.9, <3.12"
 dynamic = [ "version", "readme",]
-dependencies = [ "absl-py>=0.15,<2", "anyio>=3.5.0,<4", "cachetools>=3.1.1,<6", "cloudpickle>=2.0.0", "fsspec[http]>=2022.11,<2024", "importlib_resources>=6.1.1, <7", "numpy>=1.23,<2", "packaging>=20.9,<24", "pandas>=1.0.0,<3", "pyarrow", "pytimeparse>=1.1.8,<2", "pyyaml>=6.0,<7", "retrying>=1.3.3,<2", "s3fs>=2022.11,<2024", "scikit-learn>=1.2.1,<1.6", "scipy>=1.9,<2", "snowflake-connector-python[pandas]>=3.5.0,<4", "snowflake-snowpark-python>=1.17.0,<2", "sqlparse>=0.4,<1", "typing-extensions>=4.1.0,<5", "xgboost>=1.7.3,<2.1",]
+dependencies = [ "absl-py>=0.15,<2", "anyio>=3.5.0,<4", "cachetools>=3.1.1,<6", "cloudpickle>=2.0.0", "fsspec[http]>=2022.11,<2024", "importlib_resources>=6.1.1, <7", "numpy>=1.23,<2", "packaging>=20.9,<24", "pandas>=1.0.0,<3", "pyarrow", "pytimeparse>=1.1.8,<2", "pyyaml>=6.0,<7", "retrying>=1.3.3,<2", "s3fs>=2022.11,<2024", "scikit-learn>=1.4,<1.6", "scipy>=1.9,<2", "snowflake-connector-python[pandas]>=3.5.0,<4", "snowflake-snowpark-python>=1.17.0,<2", "sqlparse>=0.4,<1", "typing-extensions>=4.1.0,<5", "xgboost>=1.7.3,<3",]
 [[project.authors]]
 name = "Snowflake, Inc"
 email = "support@snowflake.com"
@@ -24,12 +24,12 @@ Issues = "https://github.com/snowflakedb/snowflake-ml-python/issues"
 Changelog = "https://github.com/snowflakedb/snowflake-ml-python/blob/master/CHANGELOG.md"
 
 [project.optional-dependencies]
-all = [ "catboost>=1.2.0, <2", "lightgbm>=3.3.5,<5", "mlflow>=2.1.0,<2.4", "peft>=0.5.0,<1", "sentence-transformers>=2.2.2,<3", "sentencepiece>=0.1.95,<1", "shap>=0.42.0,<1", "tensorflow>=2.10,<3", "tokenizers>=0.10,<1", "torch>=2.0.1,<2.3.0", "torchdata>=0.4,<1", "transformers>=4.32.1,<5",]
+all = [ "catboost>=1.2.0, <2", "lightgbm>=3.3.5,<5", "mlflow>=2.1.0,<2.4", "peft>=0.5.0,<1", "sentence-transformers>=2.2.2,<3", "sentencepiece>=0.1.95,<1", "shap>=0.46.0,<1", "tensorflow>=2.10,<3", "tokenizers>=0.10,<1", "torch>=2.0.1,<2.3.0", "torchdata>=0.4,<1", "transformers>=4.32.1,<5",]
 catboost = [ "catboost>=1.2.0, <2",]
 lightgbm = [ "lightgbm>=3.3.5,<5",]
 llm = [ "peft>=0.5.0,<1",]
 mlflow = [ "mlflow>=2.1.0,<2.4",]
-shap = [ "shap>=0.42.0,<1",]
+shap = [ "shap>=0.46.0,<1",]
 tensorflow = [ "tensorflow>=2.10,<3",]
 torch = [ "torch>=2.0.1,<2.3.0", "torchdata>=0.4,<1",]
 transformers = [ "sentence-transformers>=2.2.2,<3", "sentencepiece>=0.1.95,<1", "tokenizers>=0.10,<1", "transformers>=4.32.1,<5",]

{snowflake_ml_python-1.6.4 → snowflake_ml_python-1.7.0}/snowflake/ml/_internal/telemetry.py

@@ -544,7 +544,7 @@ def send_api_usage_telemetry(
                 if not isinstance(e, snowml_exceptions.SnowflakeMLException):
                     # already handled via a nested decorated function
                     if getattr(e, "_snowflake_ml_handled", False):
-                        raise e
+                        raise
                     if isinstance(e, snowpark_exceptions.SnowparkClientException):
                         me = snowml_exceptions.SnowflakeMLException(
                             error_code=error_codes.INTERNAL_SNOWPARK_ERROR, original_exception=e
@@ -558,7 +558,9 @@ def send_api_usage_telemetry(
                 telemetry_args["error"] = repr(me)
                 telemetry_args["error_code"] = me.error_code
                 me.original_exception._snowflake_ml_handled = True  # type: ignore[attr-defined]
-                if me.suppress_source_trace:
+                if e is not me:
+                    raise  # Directly raise non-wrapped exceptions to preserve original stacktrace
+                elif me.suppress_source_trace:
                     raise me.original_exception from None
                 else:
                     raise me.original_exception from e

{snowflake_ml_python-1.6.4 → snowflake_ml_python-1.7.0}/snowflake/ml/_internal/utils/import_utils.py

@@ -19,6 +19,33 @@ class MissingOptionalDependency:
         raise ImportError(f"Unable to import {self._dep_name}.")
 
 
+def import_with_fallbacks(*targets: str) -> Any:
+    """Import a module which may be located in different locations.
+
+    This method will iterate through the provided targets, returning the first available import target.
+    If none of the requested import targets are available, ImportError will be raised.
+
+    Args:
+        targets: Strings representing the target which needs to be imported. It should be a list of symbol name
+            joined by dot. Some valid examples:
+                - <some_package>
+                - <some_module>
+                - <some_package>.<some_module>
+                - <some_module>.<some_symbol>
+
+    Returns:
+        The imported target.
+
+    Raises:
+        ImportError: None of the requested targets are available
+    """
+    for target in targets:
+        result, success = import_or_get_dummy(target)
+        if success:
+            return result
+    raise ImportError(f"None of the requested targets could be imported. Requested: {', '.join(targets)}")
+
+
 def import_or_get_dummy(target: str) -> Tuple[Any, bool]:
     """Try to import the the given target or return a dummy object.
 
@@ -43,6 +70,10 @@ def import_or_get_dummy(target: str) -> Tuple[Any, bool]:
     except ImportError:
         pass
 
+    # Don't try symbol resolution if target doesn't contain '.'
+    if "." not in target:
+        return (MissingOptionalDependency(target), False)
+
     # Try to import the target as a symbol
     try:
         res = _try_import_symbol(target)

{snowflake_ml_python-1.6.4 → snowflake_ml_python-1.7.0}/snowflake/ml/_internal/utils/snowpark_dataframe_utils.py

@@ -121,3 +121,16 @@ def cast_snowpark_dataframe_column_types(df: snowpark.DataFrame) -> snowpark.Dat
             selected_cols.append(functions.col(src))
     df = df.select(selected_cols)
     return df
+
+
+def is_single_query_snowpark_dataframe(df: snowpark.DataFrame) -> bool:
+    """Check if dataframe only has a single query.
+
+    Args:
+        df: A snowpark dataframe.
+
+    Returns:
+        true if there is only on query in the dataframe and no post_actions,
+        false otherwise.
+    """
+    return len(df.queries["queries"]) == 1 and len(df.queries["post_actions"]) == 0

{snowflake_ml_python-1.6.4 → snowflake_ml_python-1.7.0}/snowflake/ml/data/_internal/arrow_ingestor.py

@@ -198,7 +198,15 @@ def _record_batch_to_arrays(rb: pa.RecordBatch) -> Dict[str, npt.NDArray[Any]]:
     for column, column_schema in zip(rb, rb.schema):
         # zero_copy_only=False because of nans. Ideally nans should have been imputed in feature engineering.
         array = column.to_numpy(zero_copy_only=False)
+        # If this column is a list, use the underlying type from the list values. Since this is just one column,
+        # there should only be one type within the list.
+        # TODO: Refactor to reduce data copies.
+        if isinstance(column_schema.type, pa.ListType):
+            # Update dtype of outer array:
+            array = np.array(array.tolist(), dtype=column_schema.type.value_type.to_pandas_dtype())
+
         batch_dict[column_schema.name] = array
+
     return batch_dict
 
 

{snowflake_ml_python-1.6.4 → snowflake_ml_python-1.7.0}/snowflake/ml/data/data_connector.py

@@ -159,7 +159,7 @@ class DataConnector:
         func_params_to_log=["batch_size", "shuffle", "drop_last_batch"],
     )
     def to_torch_dataset(
-        self, *, batch_size: int = 1, shuffle: bool = False, drop_last_batch: bool = True
+        self, *, batch_size: Optional[int] = None, shuffle: bool = False, drop_last_batch: bool = True
     ) -> "torch_data.IterableDataset":  # type: ignore[type-arg]
         """Transform the Snowflake data into a PyTorch Iterable Dataset to be used with a DataLoader.
 

{snowflake_ml_python-1.6.4 → snowflake_ml_python-1.7.0}/snowflake/ml/data/torch_utils.py

@@ -1,4 +1,4 @@
-from typing import Any, Dict, Iterator, List, Union
+from typing import Any, Dict, Iterator, List, Optional, Union
 
 import numpy as np
 import numpy.typing as npt
@@ -14,17 +14,21 @@ class TorchDatasetWrapper(torch.utils.data.IterableDataset[Dict[str, Any]]):
         self,
         ingestor: data_ingestor.DataIngestor,
         *,
-        batch_size: int,
+        batch_size: Optional[int],
         shuffle: bool = False,
         drop_last: bool = False,
-        squeeze_outputs: bool = True
     ) -> None:
         """Not intended for direct usage. Use DataConnector.to_torch_dataset() instead"""
+        squeeze = False
+        if batch_size is None:
+            batch_size = 1
+            squeeze = True
+
         self._ingestor = ingestor
         self._batch_size = batch_size
         self._shuffle = shuffle
         self._drop_last = drop_last
-        self._squeeze_outputs = squeeze_outputs
+        self._squeeze_outputs = squeeze
 
     def __iter__(self) -> Iterator[Dict[str, Union[npt.NDArray[Any], List[Any]]]]:
         max_idx = 0
@@ -43,15 +47,7 @@ class TorchDatasetWrapper(torch.utils.data.IterableDataset[Dict[str, Any]]):
         ):
             # Skip indices during multi-process data loading to prevent data duplication
             if counter == filter_idx:
-                # Basic preprocessing on batch values: squeeze away extra dimensions
-                # and convert object arrays (e.g. strings) to lists
-                if self._squeeze_outputs:
-                    yield {
-                        k: (v.squeeze().tolist() if v.dtype == np.object_ else v.squeeze()) for k, v in batch.items()
-                    }
-                else:
-                    yield batch  # type: ignore[misc]
-
+                yield {k: _preprocess_array(v, squeeze=self._squeeze_outputs) for k, v in batch.items()}
             if counter < max_idx:
                 counter += 1
             else:
@@ -65,4 +61,27 @@ class TorchDataPipeWrapper(TorchDatasetWrapper, torch.utils.data.IterDataPipe[Di
         self, ingestor: data_ingestor.DataIngestor, *, batch_size: int, shuffle: bool = False, drop_last: bool = False
     ) -> None:
         """Not intended for direct usage. Use DataConnector.to_torch_datapipe() instead"""
-        super().__init__(ingestor, batch_size=batch_size, shuffle=shuffle, drop_last=drop_last, squeeze_outputs=False)
+        super().__init__(ingestor, batch_size=batch_size, shuffle=shuffle, drop_last=drop_last)
+
+
+def _preprocess_array(arr: npt.NDArray[Any], squeeze: bool = False) -> Union[npt.NDArray[Any], List[np.object_]]:
+    """Preprocesses batch column values."""
+    single_dimensional = arr.ndim < 2 and not arr.dtype == np.object_
+
+    # Squeeze away all extra dimensions. This is only used when batch_size = None.
+    if squeeze:
+        arr = arr.squeeze(axis=0)
+
+    # For single dimensional data,
+    if single_dimensional:
+        axis = 0 if arr.ndim == 0 else 1
+        arr = np.expand_dims(arr, axis=axis)
+
+    # Handle object arrays.
+    if arr.dtype == np.object_:
+        array_list = arr.tolist()
+        # If this is an array of arrays, convert the dtype to match the underlying array.
+        # Otherwise, if this is a numpy array of strings, convert the array to a list.
+        arr = np.array(array_list, dtype=arr.flat[0].dtype) if isinstance(arr.flat[0], np.ndarray) else array_list
+
+    return arr

{snowflake_ml_python-1.6.4 → snowflake_ml_python-1.7.0}/snowflake/ml/feature_store/examples/airline_features/features/plane_features.py

@@ -6,15 +6,17 @@ from snowflake.snowpark import DataFrame, Session
 
 
 # This function will be invoked by example_helper.py. Do not change the name.
-def create_draft_feature_view(session: Session, source_dfs: List[DataFrame], source_tables: List[str]) -> FeatureView:
+def create_draft_feature_view(
+    session: Session, source_dfs: List[DataFrame], source_tables: List[str], database: str, schema: str
+) -> FeatureView:
     """Create a feature view about airplane model."""
     query = session.sql(
-        """
+        f"""
         select
            PLANE_MODEL,
            SEATING_CAPACITY
         from
-            PLANE_MODEL_ATTRIBUTES
+            {database}.{schema}.PLANE_MODEL_ATTRIBUTES
         """
     )
 

{snowflake_ml_python-1.6.4 → snowflake_ml_python-1.7.0}/snowflake/ml/feature_store/examples/airline_features/features/weather_features.py

@@ -6,10 +6,12 @@ from snowflake.snowpark import DataFrame, Session
 
 
 # This function will be invoked by example_helper.py. Do not change the name.
-def create_draft_feature_view(session: Session, source_dfs: List[DataFrame], source_tables: List[str]) -> FeatureView:
+def create_draft_feature_view(
+    session: Session, source_dfs: List[DataFrame], source_tables: List[str], database: str, schema: str
+) -> FeatureView:
     """Create a feature view about airport weather."""
     query = session.sql(
-        """
+        f"""
         select
             DATETIME_UTC AS TS,
             AIRPORT_ZIP_CODE,
@@ -21,9 +23,9 @@ def create_draft_feature_view(session: Session, source_dfs: List[DataFrame], sou
             sum(RAIN_MM_H) over (
                 partition by AIRPORT_ZIP_CODE
                 order by DATETIME_UTC
-                range between interval '1 day' preceding and current row
+                range between interval '60 minutes' preceding and current row
             ) RAIN_SUM_60M
-        from AIRPORT_WEATHER_STATION
+        from {database}.{schema}.AIRPORT_WEATHER_STATION
         """
     )
 
@@ -37,6 +39,6 @@ def create_draft_feature_view(session: Session, source_dfs: List[DataFrame], sou
     ).attach_feature_desc(
         {
             "RAIN_SUM_30M": "The sum of rain fall over past 30 minutes for one zipcode.",
-            "RAIN_SUM_60M": "The sum of rain fall over past 1 day for one zipcode.",
+            "RAIN_SUM_60M": "The sum of rain fall over past 1 hour for one zipcode.",
         }
     )

{snowflake_ml_python-1.6.4 → snowflake_ml_python-1.7.0}/snowflake/ml/feature_store/examples/citibike_trip_features/features/station_feature.py

@@ -8,7 +8,9 @@ from snowflake.snowpark import DataFrame, Session
 
 
 # This function will be invoked by example_helper.py. Do not change the name.
-def create_draft_feature_view(session: Session, source_dfs: List[DataFrame], source_tables: List[str]) -> FeatureView:
+def create_draft_feature_view(
+    session: Session, source_dfs: List[DataFrame], source_tables: List[str], database: str, schema: str
+) -> FeatureView:
     """Create a feature view about trip station."""
     query = session.sql(
         f"""
@@ -17,7 +19,7 @@ def create_draft_feature_view(session: Session, source_dfs: List[DataFrame], sou
             count(end_station_id) as f_count,
             avg(end_station_latitude) as f_avg_latitude,
             avg(end_station_longitude) as f_avg_longtitude
-        from {source_tables[0]}
+        from {database}.{schema}.{source_tables[0]}
         group by end_station_id
         """
     )

{snowflake_ml_python-1.6.4 → snowflake_ml_python-1.7.0}/snowflake/ml/feature_store/examples/citibike_trip_features/features/trip_feature.py

@@ -6,7 +6,9 @@ from snowflake.snowpark import DataFrame, Session, functions as F
 
 
 # This function will be invoked by example_helper.py. Do not change the name.
-def create_draft_feature_view(session: Session, source_dfs: List[DataFrame], source_tables: List[str]) -> FeatureView:
+def create_draft_feature_view(
+    session: Session, source_dfs: List[DataFrame], source_tables: List[str], database: str, schema: str
+) -> FeatureView:
     """Create a feature view about trip."""
     feature_df = source_dfs[0].select(
         "trip_id",

{snowflake_ml_python-1.6.4 → snowflake_ml_python-1.7.0}/snowflake/ml/feature_store/examples/example_helper.py

@@ -66,7 +66,9 @@ class ExampleHelper:
                 continue
             mod_path = f"{__package__}.{self._selected_example}.features.{f_name.rstrip('.py')}"
             mod = importlib.import_module(mod_path)
-            fv = mod.create_draft_feature_view(self._session, self._source_dfs, self._source_tables)
+            fv = mod.create_draft_feature_view(
+                self._session, self._source_dfs, self._source_tables, self._database_name, self._dataset_schema
+            )
             fvs.append(fv)
 
         return fvs
@@ -140,7 +142,7 @@ class ExampleHelper:
             """
         ).collect()
 
-        return [destination_table]
+        return [schema_dict["destination_table_name"]]
 
     def _load_parquet(self, schema_dict: Dict[str, str], temp_stage_name: str) -> List[str]:
         regex_pattern = schema_dict["load_files_pattern"]
@@ -173,13 +175,14 @@ class ExampleHelper:
                 dest_table_name = (
                     f"{self._database_name}.{self._dataset_schema}.{schema_dict['destination_table_name']}"
                 )
+                result.append(schema_dict["destination_table_name"])
             else:
                 regex_pattern = schema_dict["destination_table_name"]
                 dest_table_name = re.match(regex_pattern, file_name).group("table_name")  # type: ignore[union-attr]
+                result.append(dest_table_name)
                 dest_table_name = f"{self._database_name}.{self._dataset_schema}.{dest_table_name}"
 
             df.write.mode("overwrite").save_as_table(dest_table_name)
-            result.append(dest_table_name)
 
         return result
 

{snowflake_ml_python-1.6.4 → snowflake_ml_python-1.7.0}/snowflake/ml/feature_store/examples/new_york_taxi_features/features/location_features.py

@@ -8,7 +8,9 @@ from snowflake.snowpark import DataFrame, Session
 
 
 # This function will be invoked by example_helper.py. Do not change the name.
-def create_draft_feature_view(session: Session, source_dfs: List[DataFrame], source_tables: List[str]) -> FeatureView:
+def create_draft_feature_view(
+    session: Session, source_dfs: List[DataFrame], source_tables: List[str], database: str, schema: str
+) -> FeatureView:
     """Create a draft feature view."""
     feature_df = session.sql(
         f"""
@@ -25,7 +27,7 @@ def create_draft_feature_view(session: Session, source_dfs: List[DataFrame], sou
                 order by TPEP_DROPOFF_DATETIME
                 range between interval '10 hours' preceding and current row
             ) AVG_FARE_10h
-        from {source_tables[0]}
+        from {database}.{schema}.{source_tables[0]}
     """
     )
 

{snowflake_ml_python-1.6.4 → snowflake_ml_python-1.7.0}/snowflake/ml/feature_store/examples/new_york_taxi_features/features/trip_features.py

@@ -6,7 +6,9 @@ from snowflake.snowpark import DataFrame, Session
 
 
 # This function will be invoked by example_helper.py. Do not change the name.
-def create_draft_feature_view(session: Session, source_dfs: List[DataFrame], source_tables: List[str]) -> FeatureView:
+def create_draft_feature_view(
+    session: Session, source_dfs: List[DataFrame], source_tables: List[str], database: str, schema: str
+) -> FeatureView:
     """Create a draft feature view."""
     feature_df = session.sql(
         f"""
@@ -16,7 +18,7 @@ def create_draft_feature_view(session: Session, source_dfs: List[DataFrame], sou
             TRIP_DISTANCE,
             FARE_AMOUNT
         from
-            {source_tables[0]}
+            {database}.{schema}.{source_tables[0]}
         """
     )
 

{snowflake_ml_python-1.6.4 → snowflake_ml_python-1.7.0}/snowflake/ml/feature_store/examples/wine_quality_features/features/managed_wine_features.py

@@ -6,7 +6,9 @@ from snowflake.snowpark import DataFrame, Session, functions as F
 
 
 # This function will be invoked by example_helper.py. Do not change the name.
-def create_draft_feature_view(session: Session, source_dfs: List[DataFrame], source_tables: List[str]) -> FeatureView:
+def create_draft_feature_view(
+    session: Session, source_dfs: List[DataFrame], source_tables: List[str], database: str, schema: str
+) -> FeatureView:
     """Create a feature view about trip station."""
     feature_df = source_dfs[0].select(
         "WINE_ID",