Project import generated by Copybara. (#90)

GitOrigin-RevId: c12bb2459ddbff1633abda8352a2f126ee767eba

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

.bazelrc

@@ -25,6 +25,7 @@ build:_extended_gpu_oss --platforms //bazel/platforms:extended_conda_gpu_env --h
 build:py3.8 --repo_env=BAZEL_CONDA_PYTHON_VERSION=3.8
 build:py3.9 --repo_env=BAZEL_CONDA_PYTHON_VERSION=3.9
 build:py3.10 --repo_env=BAZEL_CONDA_PYTHON_VERSION=3.10
+build:py3.11 --repo_env=BAZEL_CONDA_PYTHON_VERSION=3.11
 
 # Default
 

CHANGELOG.md

@@ -1,5 +1,28 @@
 # Release History
 
+## 1.2.3
+
+### Bug Fixes
+
+- Registry: Now when providing Decimal Type column to a DOUBLE or FLOAT feature will not error out but auto cast with
+  warnings.
+- Registry: Improve the error message when specifying currently unsupported `pip_requirements` argument.
+- Model Development: Fix precision_recall_fscore_support incorrect results when `average="samples"`.
+- Model Registry: Fix an issue that leads to description, metrics or tags are not correctly returned in newly created
+  Model Registry (PrPr) due to Snowflake BCR [2024_01](
+  https://docs.snowflake.com/en/release-notes/bcr-bundles/2024_01/bcr-1483)
+
+### Behavior Changes
+
+- Feature Store: `FeatureStore.suspend_feature_view` and `FeatureStore.resume_feature_view` doesn't mutate input feature
+  view argument any more. The updated status only reflected in the returned feature view object.
+
+### New Features
+
+- Model Development: support `score_samples` method for all the classes, including Pipeline,
+  GridSearchCV, RandomizedSearchCV, PCA, IsolationForest, ...
+- Registry: Support deleting a version of a model.
+
 ## 1.2.2
 
 ### Bug Fixes

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, 3.9 & 3.10 are supported. You can use [miniconda](https://docs.conda.io/en/latest/miniconda.html) or
+Python versions 3.8 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.
 

WORKSPACE

@@ -4,9 +4,9 @@ load("@bazel_tools//tools/build_defs/repo:http.bzl", "http_archive", "http_jar")
 
 http_jar(
     name = "bazel_diff",
-    sha256 = "9c4546623a8b9444c06370165ea79a897fcb9881573b18fa5c9ee5c8ba0867e2",
+    sha256 = "eca2d221f5c3ec9545c841ed62d319bbb59e447a1ceade563bc8f8e1b9186a34",
     urls = [
-        "https://github.com/Tinder/bazel-diff/releases/download/4.3.0/bazel-diff_deploy.jar",
+        "https://github.com/Tinder/bazel-diff/releases/download/5.0.1/bazel-diff_deploy.jar",
     ],
 )
 

bazel/get_affected_targets.sh

@@ -69,38 +69,34 @@ trap 'rm -rf "${working_dir}"' EXIT
 starting_hashes_json="${working_dir}/starting_hashes.json"
 final_hashes_json="${working_dir}/final_hashes.json"
 impacted_targets_path="${working_dir}/impacted_targets.txt"
-bazel_diff="${working_dir}/bazel_diff"
-seed_file="${working_dir}/bazel_diff_seed"
-ci_hash_file="${working_dir}/ci_scripts_hash"
-
-cat <<SeedFileContent >"${seed_file}"
-${ci_hash_file}
-${workspace_path}/requirements.yml
-SeedFileContent
-
-"${bazel}" run --config=pre_build :bazel-diff --script_path="${bazel_diff}"
+ci_hash_file_pr="${working_dir}/ci_hash_file_pr"
+ci_hash_file_base="${working_dir}/ci_hash_file_base"
 
 git -C "${workspace_path}" checkout "${pr_revision}" --quiet
 trap 'git -C "${workspace_path}" checkout "${current_revision}" --quiet' EXIT
 
 echo "Generating Hashes for Revision '${pr_revision}'"
 
-git ls-files -s "${workspace_path}/ci" | git hash-object --stdin >"${ci_hash_file}"
+git ls-files -s "${workspace_path}/ci" "${workspace_path}/bazel" | git hash-object --stdin >"${ci_hash_file_pr}"
 
-"${bazel_diff}" generate-hashes -w "${workspace_path}" -b "${bazel}" -s "${seed_file}" "${final_hashes_json}"
+"${bazel}" run --config=pre_build :bazel-diff -- generate-hashes -w "${workspace_path}" -b "${bazel}"  "${final_hashes_json}"
 
 MERGE_BASE_MAIN=$(git merge-base "${pr_revision}" main)
 git -C "${workspace_path}" checkout "${MERGE_BASE_MAIN}" --quiet
 
 echo "Generating Hashes for merge base ${MERGE_BASE_MAIN}"
 
-git ls-files -s "${workspace_path}/ci" | git hash-object --stdin >"${ci_hash_file}"
+git ls-files -s "${workspace_path}/ci" "${workspace_path}/bazel" | git hash-object --stdin >"${ci_hash_file_base}"
 
-$"${bazel_diff}" generate-hashes -w "${workspace_path}" -b "${bazel}" -s "${seed_file}" "${starting_hashes_json}"
+"${bazel}" run --config=pre_build :bazel-diff -- generate-hashes -w "${workspace_path}" -b "${bazel}" "${starting_hashes_json}"
 
 git -C "${workspace_path}" checkout "${pr_revision}" --quiet
 echo "Determining Impacted Targets and output to ${output_path}"
-$"${bazel_diff}" get-impacted-targets -sh "${starting_hashes_json}" -fh "${final_hashes_json}" -o "${impacted_targets_path}"
+"${bazel}" run --config=pre_build :bazel-diff -- get-impacted-targets -sh "${starting_hashes_json}" -fh "${final_hashes_json}" -o "${impacted_targets_path}"
+
+if ! cmp -s "$ci_hash_file_pr" "$ci_hash_file_base"; then
+    echo '//...' >> "${impacted_targets_path}"
+fi
 
 filter_query_rules_file="${working_dir}/filter_query_rules"
 

bazel/requirements/templates/meta.tpl.yaml

@@ -13,7 +13,7 @@ requirements:
     - python
     - bazel >=6.0.0
   run:
-    - python>=3.8,<3.11
+    - python>=3.8,<3.12
   run_constrained:
     - pytorch<2.1.0  # [win]
 

bazel/requirements/templates/pyproject.toml

@@ -22,14 +22,15 @@ classifiers = [
   "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, <4"
+requires-python = ">=3.8, <3.12"
 dynamic = ["version", "readme"]
 
 [project.urls]

ci/build_and_run_tests.sh

@@ -40,6 +40,7 @@ WITH_SNOWPARK=false
 MODE="continuous_run"
 PYTHON_VERSION=3.8
 PYTHON_JENKINS_ENABLE="/opt/rh/rh-python38/enable"
+PYTHON_ENABLE_SCRIPT="bin/activate"
 SNOWML_DIR="snowml"
 SNOWPARK_DIR="snowpark-python"
 IS_NT=false
@@ -96,21 +97,6 @@ while (($#)); do
     shift
 done
 
-case ${PYTHON_VERSION} in
-  3.8)
-    PYTHON_EXECUTABLE="python3.8"
-    PYTHON_JENKINS_ENABLE="/opt/rh/rh-python38/enable"
-    ;;
-  3.9)
-    PYTHON_EXECUTABLE="python3.9"
-    PYTHON_JENKINS_ENABLE="/opt/rh/rh-python39/enable"
-    ;;
-  3.10)
-    PYTHON_EXECUTABLE="python3.10"
-    PYTHON_JENKINS_ENABLE="/opt/rh/rh-python310/enable"
-    ;;
-esac
-
 echo "Running build_and_run_tests with PYTHON_VERSION ${PYTHON_VERSION}"
 
 EXT=""
@@ -148,9 +134,53 @@ case "${PLATFORM}_${ARCH}" in
     ;;
 esac
 
-# Verify that the requested python version exists
-# TODO(SNOW-845592): ideally we should download python from conda if it's not present. Currently we just fail.
-if [ "${ENV}" = "pip" ]; then
+if [ ${IS_NT} = true ]; then
+    EXT=".exe"
+    PYTHON_ENABLE_SCRIPT="Scripts/activate"
+    BAZEL_ADDITIONAL_BUILD_FLAGS+=(--nobuild_python_zip)
+    BAZEL_ADDITIONAL_BUILD_FLAGS+=(--enable_runfiles)
+    BAZEL_ADDITIONAL_BUILD_FLAGS+=(--action_env="USERPROFILE=${USERPROFILE}")
+    BAZEL_ADDITIONAL_BUILD_FLAGS+=(--host_action_env="USERPROFILE=${USERPROFILE}")
+    BAZEL_ADDITIONAL_STARTUP_FLAGS+=(--output_user_root=C:/broot)
+fi
+
+case ${PYTHON_VERSION} in
+  3.8)
+    if [ ${IS_NT} = true ]; then
+        PYTHON_EXECUTABLE="py -3.8"
+    else
+        PYTHON_EXECUTABLE="python3.8"
+    fi
+    PYTHON_JENKINS_ENABLE="/opt/rh/rh-python38/enable"
+    ;;
+  3.9)
+    if [ ${IS_NT} = true ]; then
+        PYTHON_EXECUTABLE="py -3.9"
+    else
+        PYTHON_EXECUTABLE="python3.9"
+    fi
+    PYTHON_JENKINS_ENABLE="/opt/rh/rh-python39/enable"
+    ;;
+  3.10)
+    if [ ${IS_NT} = true ]; then
+        PYTHON_EXECUTABLE="py -3.10"
+    else
+        PYTHON_EXECUTABLE="python3.10"
+    fi
+    PYTHON_JENKINS_ENABLE="/opt/rh/rh-python310/enable"
+    ;;
+  3.11)
+    if [ ${IS_NT} = true ]; then
+        PYTHON_EXECUTABLE="py -3.11"
+    else
+        PYTHON_EXECUTABLE="python3.11"
+    fi
+    PYTHON_JENKINS_ENABLE="/opt/rh/rh-python311/enable"
+    ;;
+esac
+
+# TODO(SNOW-901629): Use native python provided in the node once SNOW-1046060 resolved
+if [[ "${ENV}" = "pip" && ${IS_NT} = false ]]; then
     set +eu
     # shellcheck source=/dev/null
     source ${PYTHON_JENKINS_ENABLE}
@@ -163,13 +193,6 @@ if [ "${ENV}" = "pip" ]; then
     set -eu
 fi
 
-if [ ${IS_NT} = true ]; then
-    EXT=".exe"
-    BAZEL_ADDITIONAL_BUILD_FLAGS+=(--nobuild_python_zip)
-    BAZEL_ADDITIONAL_BUILD_FLAGS+=(--enable_runfiles)
-    BAZEL_ADDITIONAL_STARTUP_FLAGS+=(--output_user_root=D:/broot)
-fi
-
 cd "${WORKSPACE}"
 
 # Check and download yq if not presented.
@@ -210,12 +233,7 @@ pushd "${TEMP_TEST_DIR}"
 rsync -av --exclude-from "${EXCLUDE_TESTS}" "../${SNOWML_DIR}/tests" .
 popd
 
-# Bazel on windows is consuming a lot of memory, let's clean it before proceed to avoid OOM.
-if [ ${IS_NT} = true ]; then
-    "${BAZEL}" "${BAZEL_ADDITIONAL_STARTUP_FLAGS[@]+"${BAZEL_ADDITIONAL_STARTUP_FLAGS[@]}"}" clean --expunge
-    "${BAZEL}" "${BAZEL_ADDITIONAL_STARTUP_FLAGS[@]+"${BAZEL_ADDITIONAL_STARTUP_FLAGS[@]}"}" shutdown
-fi
-
+"${BAZEL}" "${BAZEL_ADDITIONAL_STARTUP_FLAGS[@]+"${BAZEL_ADDITIONAL_STARTUP_FLAGS[@]}"}" clean --expunge
 popd
 
 # Build snowml package
@@ -228,10 +246,12 @@ if [ "${ENV}" = "pip" ]; then
         pushd ${SNOWPARK_DIR}
         rm -rf venv
         ${PYTHON_EXECUTABLE} -m venv venv
-        source venv/bin/activate
-        ${PYTHON_EXECUTABLE} -m pip install -U pip setuptools wheel
+        # shellcheck disable=SC1090
+        source "venv/${PYTHON_ENABLE_SCRIPT}"
+        python --version
+        python -m pip install -U pip setuptools wheel
         echo "Building snowpark wheel from main:$(git rev-parse HEAD)."
-        pip wheel . --no-deps
+        python -m pip wheel . --no-deps
         cp "$(find . -maxdepth 1 -iname 'snowflake_snowpark_python-*.whl')" "${WORKSPACE}"
         deactivate
         popd
@@ -240,7 +260,7 @@ if [ "${ENV}" = "pip" ]; then
     # Build SnowML
     pushd ${SNOWML_DIR}
     "${BAZEL}" "${BAZEL_ADDITIONAL_STARTUP_FLAGS[@]+"${BAZEL_ADDITIONAL_STARTUP_FLAGS[@]}"}" build "${BAZEL_ADDITIONAL_BUILD_FLAGS[@]+"${BAZEL_ADDITIONAL_BUILD_FLAGS[@]}"}" //:wheel
-    cp "$(${BAZEL} info bazel-bin)/dist/snowflake_ml_python-${VERSION}-py3-none-any.whl" "${WORKSPACE}"
+    cp "$("${BAZEL}" "${BAZEL_ADDITIONAL_STARTUP_FLAGS[@]+"${BAZEL_ADDITIONAL_STARTUP_FLAGS[@]}"}" info bazel-bin)/dist/snowflake_ml_python-${VERSION}-py3-none-any.whl" "${WORKSPACE}"
     popd
 else
     # Clean conda cache
@@ -284,21 +304,23 @@ if [ "${ENV}" = "pip" ]; then
 
     # Create testing env
     ${PYTHON_EXECUTABLE} -m venv testenv
-    source testenv/bin/activate
+    # shellcheck disable=SC1090
+    source "testenv/${PYTHON_ENABLE_SCRIPT}"
     # Install all of the packages in single line,
     # otherwise it will fail in dependency resolution.
-    ${PYTHON_EXECUTABLE} -m pip install --upgrade pip
-    ${PYTHON_EXECUTABLE} -m pip list
-    ${PYTHON_EXECUTABLE} -m pip install "snowflake_ml_python-${VERSION}-py3-none-any.whl[all]" "pytest-xdist[psutil]==2.5.0" -r "${WORKSPACE}/${SNOWML_DIR}/requirements.txt" --no-cache-dir --force-reinstall
+    python --version
+    python -m pip install --upgrade pip
+    python -m pip list
+    python -m pip install "snowflake_ml_python-${VERSION}-py3-none-any.whl[all]" "pytest-xdist[psutil]==2.5.0" -r "${WORKSPACE}/${SNOWML_DIR}/requirements.txt" --no-cache-dir --force-reinstall
     if [ "${WITH_SNOWPARK}" = true ]; then
         cp "$(find "${WORKSPACE}" -maxdepth 1 -iname 'snowflake_snowpark_python-*.whl')" "${TEMP_TEST_DIR}"
-        ${PYTHON_EXECUTABLE} -m pip install "$(find . -maxdepth 1 -iname 'snowflake_snowpark_python-*.whl')" --no-deps --force-reinstall
+        python -m pip install "$(find . -maxdepth 1 -iname 'snowflake_snowpark_python-*.whl')" --no-deps --force-reinstall
     fi
-    ${PYTHON_EXECUTABLE} -m pip list
+    python -m pip list
 
     # Run the tests
     set +e
-    TEST_SRCDIR="${TEMP_TEST_DIR}" ${PYTHON_EXECUTABLE} -m pytest "${COMMON_PYTEST_FLAG[@]}" -m "not pip_incompatible" tests/integ/
+    TEST_SRCDIR="${TEMP_TEST_DIR}" python -m pytest "${COMMON_PYTEST_FLAG[@]}" -m "not pip_incompatible" tests/integ/
     TEST_RETCODE=$?
     set -e
 else

ci/conda_recipe/README.md

@@ -6,7 +6,7 @@ Conda's guide on building a conda package from a wheel:
 To invoke conda build:
 
 ```sh
-conda build --prefix-length=0 --python=[3.8|3.9|3.10] ci/conda_recipe
+conda build --prefix-length=0 --python=[3.8|3.9|3.10|3.11] ci/conda_recipe
 ```
 
 - `--prefix-length=0`: prevent the conda build environment from being created in

ci/conda_recipe/conda_build_config.yaml

@@ -3,3 +3,4 @@ python:
   - 3.8
   - 3.9
   - 3.10
+  - 3.11

ci/conda_recipe/meta.yaml

@@ -17,7 +17,7 @@ build:
   noarch: python
 package:
   name: snowflake-ml-python
-  version: 1.2.2
+  version: 1.2.3
 requirements:
   build:
     - python
@@ -26,7 +26,7 @@ requirements:
     - absl-py>=0.15,<2
     - aiohttp!=4.0.0a0, !=4.0.0a1
     - anyio>=3.5.0,<4
-    - cachetools>=3.1.1,<5
+    - cachetools>=3.1.1,<6
     - cloudpickle>=2.0.0
     - fsspec>=2022.11,<2024
     - importlib_resources>=5.1.4, <6
@@ -46,7 +46,7 @@ requirements:
     - sqlparse>=0.4,<1
     - typing-extensions>=4.1.0,<5
     - xgboost>=1.7.3,<2
-    - python>=3.8,<3.11
+    - python>=3.8,<3.12
   run_constrained:
     - lightgbm==3.3.5
     - mlflow>=2.1.0,<2.4

codegen/sklearn_wrapper_generator.py

@@ -583,6 +583,7 @@ def __init__(self, module_name: str, class_object: Tuple[str, type]) -> None:
         self.fit_predict_docstring = ""
         self.fit_transform_docstring = ""
         self.predict_proba_docstring = ""
+        self.score_samples_docstring = ""
         self.score_docstring = ""
         self.predict_log_proba_docstring = ""
         self.decision_function_docstring = ""
@@ -728,6 +729,7 @@ def _populate_function_doc_fields(self) -> None:
             "transform",
             "score",
             "kneighbors",
+            "score_samples",
         ]
         _CLASS_FUNC = {name: func for name, func in inspect.getmembers(self.class_object[1])}
         for _each_method in _METHODS:
@@ -757,6 +759,7 @@ def _populate_function_doc_fields(self) -> None:
         self.predict_docstring = self.estimator_function_docstring["predict"]
         self.fit_predict_docstring = self.estimator_function_docstring["fit_predict"]
         self.predict_proba_docstring = self.estimator_function_docstring["predict_proba"]
+        self.score_samples_docstring = self.estimator_function_docstring["score_samples"]
         self.predict_log_proba_docstring = self.estimator_function_docstring["predict_log_proba"]
         self.decision_function_docstring = self.estimator_function_docstring["decision_function"]
         self.score_docstring = self.estimator_function_docstring["score"]