Project import generated by Copybara. (#116)

GitOrigin-RevId: 6fc3ce416ce5843fc01936fc61bf5480ae9f791f

Co-authored-by: Snowflake Authors <[email protected]>

Author: sfc-gh-anavalos

BUILD.bazel

@@ -3,6 +3,8 @@ load("//:packages.bzl", "PACKAGES")
 load("//bazel:py_rules.bzl", "py_wheel")
 load("//bazel/requirements:rules.bzl", "generate_pyproject_file")
 
+package(default_visibility = ["//visibility:public"])
+
 exports_files([
     "CHANGELOG.md",
     "README.md",

CHANGELOG.md

@@ -1,6 +1,26 @@
 # Release History
 
-## 1.6.1 (TBD)
+## 1.6.2 (TBD)
+
+### Bug Fixes
+
+- Modeling: Support XGBoost version that is larger than 2.
+
+- Data: Fix multiple epoch iteration over `DataConnector.to_torch_datapipe()` DataPipes.
+- Generic: Fix a bug that when an invalid name is provided to argument where fully qualified name is expected, it will
+  be parsed wrongly. Now it raises an exception correctly.
+- Model Explainability: Handle explanations for multiclass XGBoost classification models
+- Model Explainability: Workarounds and better error handling for XGB>2.1.0 not working with SHAP==0.42.1
+
+### New Features
+
+- Data: Add top-level exports for `DataConnector` and `DataSource` to `snowflake.ml.data`.
+- Data: Add native batching support via `batch_size` and `drop_last_batch` arguments to `DataConnector.to_torch_dataset()`
+- Feature Store: update_feature_view() supports taking feature view object as argument.
+
+### Behavior Changes
+
+## 1.6.1 (2024-08-12)
 
 ### Bug Fixes
 
@@ -17,7 +37,6 @@
 ### New Features
 
 - Enable `set_params` to set the parameters of the underlying sklearn estimator, if the snowflake-ml model has been fit.
-- Data: Add top-level exports for `DataConnector` and `DataSource` to `snowflake.ml.data`.
 - Data: Add `snowflake.ml.data.ingestor_utils` module with utility functions helpful for `DataIngestor` implementations.
 - Data: Add new `to_torch_dataset()` connector to `DataConnector` to replace deprecated DataPipe.
 - Registry: Option to `enable_explainability` set to True by default for XGBoost, LightGBM and CatBoost as PuPr feature.

CONTRIBUTING.md

@@ -304,7 +304,7 @@ Example:
 
 ## Unit Testing
 
-Write `pytest` or Python `unittest` style unit tests.
+Write Python `unittest` style unit tests. Pytest is allowed, but not recommended.
 
 ### `unittest`
 
@@ -320,6 +320,10 @@ from absl.testing import absltest
 # instead of
 # from unittest import TestCase, main
 from absl.testing.absltest import TestCase, main
+
+# Call main.
+if __name__ == '__main__':
+  absltest.main()
 ```
 
 `absltest` provides better `bazel` integration which produces a more detailed XML

bazel/environments/conda-env-snowflake.yml

@@ -28,6 +28,7 @@ dependencies:
   - lightgbm==3.3.5
   - mlflow==2.3.1
   - moto==4.0.11
+  - mypy==1.10.0
   - networkx==2.8.4
   - numpy==1.23.5
   - packaging==23.0
@@ -54,14 +55,16 @@ dependencies:
   - snowflake-snowpark-python==1.17.0
   - sphinx==5.0.2
   - sqlparse==0.4.4
+  - starlette==0.27.0
   - tensorflow==2.12.0
   - tokenizers==0.13.2
   - toml==0.10.2
   - torchdata==0.6.1
   - transformers==4.32.1
+  - types-PyYAML==6.0.12.12
   - types-protobuf==4.23.0.1
   - types-requests==2.30.0.0
   - types-toml==0.10.8.6
-  - typing-extensions==4.5.0
+  - typing-extensions==4.6.3
   - werkzeug==2.2.2
   - xgboost==1.7.3

bazel/environments/conda-env.yml

@@ -14,11 +14,6 @@ dependencies:
   - cachetools==4.2.2
   - catboost==1.2.0
   - cloudpickle==2.2.1
-  - conda-forge::accelerate==0.22.0
-  - conda-forge::mypy==1.5.1
-  - conda-forge::starlette==0.27.0
-  - conda-forge::types-PyYAML==6.0.12
-  - conda-forge::types-cachetools==4.2.2
   - conda-libmamba-solver==23.7.0
   - coverage==6.3.2
   - cryptography==39.0.1
@@ -33,6 +28,7 @@ dependencies:
   - lightgbm==3.3.5
   - mlflow==2.3.1
   - moto==4.0.11
+  - mypy==1.10.0
   - networkx==2.8.4
   - numpy==1.23.5
   - packaging==23.0
@@ -59,18 +55,22 @@ dependencies:
   - snowflake-snowpark-python==1.17.0
   - sphinx==5.0.2
   - sqlparse==0.4.4
+  - starlette==0.27.0
   - tensorflow==2.12.0
   - tokenizers==0.13.2
   - toml==0.10.2
   - torchdata==0.6.1
   - transformers==4.32.1
+  - types-PyYAML==6.0.12.12
   - types-protobuf==4.23.0.1
   - types-requests==2.30.0.0
   - types-toml==0.10.8.6
-  - typing-extensions==4.5.0
+  - typing-extensions==4.6.3
   - werkzeug==2.2.2
   - xgboost==1.7.3
   - pip
   - pip:
       - --extra-index-url https://pypi.org/simple
+      - accelerate==0.22.0
+      - types-cachetools==4.2.2
       - peft==0.5.0

bazel/environments/conda-gpu-env.yml

@@ -14,11 +14,6 @@ dependencies:
   - cachetools==4.2.2
   - catboost==1.2.0
   - cloudpickle==2.2.1
-  - conda-forge::accelerate==0.22.0
-  - conda-forge::mypy==1.5.1
-  - conda-forge::starlette==0.27.0
-  - conda-forge::types-PyYAML==6.0.12
-  - conda-forge::types-cachetools==4.2.2
   - conda-libmamba-solver==23.7.0
   - coverage==6.3.2
   - cryptography==39.0.1
@@ -33,6 +28,7 @@ dependencies:
   - lightgbm==3.3.5
   - mlflow==2.3.1
   - moto==4.0.11
+  - mypy==1.10.0
   - networkx==2.8.4
   - numpy==1.23.5
   - nvidia::cuda==11.7.*
@@ -61,19 +57,23 @@ dependencies:
   - snowflake-snowpark-python==1.17.0
   - sphinx==5.0.2
   - sqlparse==0.4.4
+  - starlette==0.27.0
   - tensorflow==2.12.0
   - tokenizers==0.13.2
   - toml==0.10.2
   - torchdata==0.6.1
   - transformers==4.32.1
+  - types-PyYAML==6.0.12.12
   - types-protobuf==4.23.0.1
   - types-requests==2.30.0.0
   - types-toml==0.10.8.6
-  - typing-extensions==4.5.0
+  - typing-extensions==4.6.3
   - werkzeug==2.2.2
   - xgboost==1.7.3
   - pip
   - pip:
       - --extra-index-url https://pypi.org/simple
+      - accelerate==0.22.0
+      - types-cachetools==4.2.2
       - peft==0.5.0
       - vllm==0.2.1.post1

bazel/requirements/requirements.schema.json

@@ -59,11 +59,6 @@
           "pattern": "^$|^([1-9][0-9]*!)?(0|[1-9][0-9]*)(\\.(0|[1-9][0-9]*))*((a|b|rc|alpha|beta)(0|[1-9][0-9]*))?(\\.post(0|[1-9][0-9]*))?(\\.dev(0|[1-9][0-9]*))?$",
           "type": "string"
         },
-        "from_channel": {
-          "default": "https://repo.anaconda.com/pkgs/snowflake",
-          "description": "The channel where the package come from, set if not from Snowflake Anaconda Channel.",
-          "type": "string"
-        },
         "gpu_only": {
           "default": false,
           "description": "The package is required when running in an environment where GPU is available.",

ci/conda_recipe/meta.yaml

@@ -17,7 +17,7 @@ build:
   noarch: python
 package:
   name: snowflake-ml-python
-  version: 1.6.1
+  version: 1.6.2
 requirements:
   build:
     - python
@@ -45,7 +45,7 @@ requirements:
     - snowflake-snowpark-python>=1.17.0,<2
     - sqlparse>=0.4,<1
     - typing-extensions>=4.1.0,<5
-    - xgboost>=1.7.3,<2
+    - xgboost>=1.7.3,<2.1
     - python>=3.8,<3.12
   run_constrained:
     - catboost>=1.2.0, <2

codegen/codegen_rules.bzl

@@ -90,7 +90,6 @@ def autogen_estimators(module, estimator_info_list):
                 "//snowflake/ml/_internal/exceptions:exceptions",
                 "//snowflake/ml/_internal/utils:temp_file_utils",
                 "//snowflake/ml/_internal/utils:query_result_checker",
-                "//snowflake/ml/_internal/utils:pkg_version_utils",
                 "//snowflake/ml/_internal/utils:identifier",
                 "//snowflake/ml/model:model_signature",
                 "//snowflake/ml/model/_signatures:utils",
@@ -181,7 +180,6 @@ def autogen_snowpark_pandas_tests(module, module_root_dir, snowpark_pandas_estim
                 "//snowflake/ml/_internal/snowpark_pandas:snowpark_pandas_lib",
                 "//snowflake/ml/utils:connection_params",
             ],
-            compatible_with_snowpark = False,
             timeout = "long",
             legacy_create_init = 0,
             shard_count = 5,

codegen/sklearn_wrapper_generator.py

@@ -1153,15 +1153,18 @@ def generate(self) -> "XGBoostWrapperGenerator":
         super().generate()
 
         # Populate XGBoost specific values
-        self.estimator_imports_list.append("import xgboost")
+        self.estimator_imports_list.extend(["import sklearn", "import xgboost"])
         self.test_estimator_input_args_list.extend(
             ["random_state=0", "subsample=1.0", "colsample_bynode=1.0", "n_jobs=1"]
         )
-        self.score_sproc_imports = ["xgboost"]
+        self.score_sproc_imports = ["xgboost", "sklearn"]
         # TODO(snandamuri): Replace cloudpickle with joblib after latest version of joblib is added to snowflake conda.
         self.supported_export_method = "to_xgboost"
         self.unsupported_export_methods = ["to_sklearn", "to_lightgbm"]
-        self.deps = "f'numpy=={np.__version__}', f'xgboost=={xgboost.__version__}', f'cloudpickle=={cp.__version__}'"
+        self.deps = (
+            "f'numpy=={np.__version__}', f'scikit-learn=={sklearn.__version__}', "
+            + "f'xgboost=={xgboost.__version__}', f'cloudpickle=={cp.__version__}'"
+        )
         self._construct_string_from_lists()
         return self