snowflake-ml-python 1.6.3__py3-none-any.whl → 1.7.0__py3-none-any.whl

snowflake/ml/registry/registry.py

@@ -14,11 +14,8 @@ from snowflake.ml.model import (
     type_hints as model_types,
 )
 from snowflake.ml.model._client.model import model_version_impl
-from snowflake.ml.monitoring._client import (
-    model_monitor,
-    model_monitor_manager,
-    model_monitor_version,
-)
+from snowflake.ml.monitoring import model_monitor, model_monitor_version
+from snowflake.ml.monitoring._manager import model_monitor_manager
 from snowflake.ml.monitoring.entities import model_monitor_config
 from snowflake.ml.registry._manager import model_manager
 from snowflake.snowpark import session
@@ -107,6 +104,7 @@ class Registry:
         metrics: Optional[Dict[str, Any]] = None,
         conda_dependencies: Optional[List[str]] = None,
         pip_requirements: Optional[List[str]] = None,
+        target_platforms: Optional[List[model_types.SupportedTargetPlatformType]] = None,
         python_version: Optional[str] = None,
         signatures: Optional[Dict[str, model_signature.ModelSignature]] = None,
         sample_input_data: Optional[model_types.SupportedDataType] = None,
@@ -128,14 +126,17 @@ class Registry:
             metrics: A JSON serializable dictionary containing metrics linked to the model version. Defaults to None.
             signatures: Model data signatures for inputs and outputs for various target methods. If it is None,
                 sample_input_data would be used to infer the signatures for those models that cannot automatically
-                infer the signature. If not None, sample_input_data should not be specified. Defaults to None.
-            sample_input_data: Sample input data to infer model signatures from. Defaults to None.
+                infer the signature. Defaults to None.
+            sample_input_data: Sample input data to infer model signatures from.
+                It would also be used as background data in explanation and to capture data lineage. Defaults to None.
             conda_dependencies: List of Conda package specifications. Use "[channel::]package [operator version]" syntax
                 to specify a dependency. It is a recommended way to specify your dependencies using conda. When channel
                 is not specified, Snowflake Anaconda Channel will be used. Defaults to None.
             pip_requirements: List of Pip package specifications. Defaults to None.
                 Currently it is not supported since Model can only executed in Snowflake Warehouse where all
                 dependencies are required to be retrieved from Snowflake Anaconda Channel.
+            target_platforms: List of target platforms to run the model. The only acceptable inputs are a combination of
+                {"WAREHOUSE", "SNOWPARK_CONTAINER_SERVICES"}. Defaults to None.
             python_version: Python version in which the model is run. Defaults to None.
             code_paths: List of directories containing code to import. Defaults to None.
             ext_modules: List of external modules to pickle with the model object.
@@ -190,6 +191,7 @@ class Registry:
             "metrics",
             "conda_dependencies",
             "pip_requirements",
+            "target_platforms",
             "python_version",
             "signatures",
         ],
@@ -204,6 +206,7 @@ class Registry:
         metrics: Optional[Dict[str, Any]] = None,
         conda_dependencies: Optional[List[str]] = None,
         pip_requirements: Optional[List[str]] = None,
+        target_platforms: Optional[List[model_types.SupportedTargetPlatformType]] = None,
         python_version: Optional[str] = None,
         signatures: Optional[Dict[str, model_signature.ModelSignature]] = None,
         sample_input_data: Optional[model_types.SupportedDataType] = None,
@@ -229,13 +232,16 @@ class Registry:
             signatures: Model data signatures for inputs and outputs for various target methods. If it is None,
                 sample_input_data would be used to infer the signatures for those models that cannot automatically
                 infer the signature. If not None, sample_input_data should not be specified. Defaults to None.
-            sample_input_data: Sample input data to infer model signatures from. Defaults to None.
+            sample_input_data: Sample input data to infer model signatures from.
+                It would also be used as background data in explanation and to capture data lineage. Defaults to None.
             conda_dependencies: List of Conda package specifications. Use "[channel::]package [operator version]" syntax
                 to specify a dependency. It is a recommended way to specify your dependencies using conda. When channel
                 is not specified, Snowflake Anaconda Channel will be used. Defaults to None.
             pip_requirements: List of Pip package specifications. Defaults to None.
                 Currently it is not supported since Model can only executed in Snowflake Warehouse where all
                 dependencies are required to be retrieved from Snowflake Anaconda Channel.
+            target_platforms: List of target platforms to run the model. The only acceptable inputs are a combination of
+                {"WAREHOUSE", "SNOWPARK_CONTAINER_SERVICES"}. Defaults to None.
             python_version: Python version in which the model is run. Defaults to None.
             code_paths: List of directories containing code to import. Defaults to None.
             ext_modules: List of external modules to pickle with the model object.
@@ -287,6 +293,7 @@ class Registry:
             metrics=metrics,
             conda_dependencies=conda_dependencies,
             pip_requirements=pip_requirements,
+            target_platforms=target_platforms,
             python_version=python_version,
             signatures=signatures,
             sample_input_data=sample_input_data,

snowflake/ml/version.py

@@ -1 +1 @@
-VERSION="1.6.3"
+VERSION="1.7.0"

{snowflake_ml_python-1.6.3.dist-info → snowflake_ml_python-1.7.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: snowflake-ml-python
-Version: 1.6.3
+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 +372,77 @@ be compatibility issues. Server-side functionality that `snowflake-ml-python` de
 
 # Release History
 
-## 1.6.3
+## 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
+
+- Registry: Fix an issue that leads to incident when using `ModelVersion.run` with service.
+
+## 1.6.3 (2024-10-07)
 
 - Model Registry (PrPr) has been removed.
 
@@ -385,6 +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