Project import generated by Copybara. (#105)

GitOrigin-RevId: 799da6cf0e5020abb73dcf1be9906fc318c1b2b9 Co-authored-by: Snowflake Authors <[email protected]>
snowflakedb · Jun 18, 2024 · f0ff796 · f0ff796
1 parent 0634c4f
commit f0ff796
Show file tree

Hide file tree

Showing 72 changed files with 1,397 additions and 504 deletions.
diff --git a/.gitignore b/.gitignore
@@ -394,4 +394,4 @@ user.bazelrc
 html_coverage_report/
 
 # VSCode configuration
-.vscode/
+.vscode
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,6 +1,22 @@
 # Release History
 
-## 1.5.2
+## 1.5.3
+
+### Bug Fixes
+
+- Modeling: Fix an issue causing lineage information to be missing for
+  `Pipeline`, `GridSearchCV` , `SimpleImputer`, and `RandomizedSearchCV`
+- Registry: Fix an issue that leads to incorrect result when using pandas Dataframe with over 100, 000 rows as the input
+  of `ModelVersion.run` method in Stored Procedure.
+
+### Behavior Changes
+
+### New Features
+
+- Registry: Add support for TIMESTAMP_NTZ model signature data type, allowing timestamp input and output.
+- Dataset: Add `DatasetVersion.label_cols` and `DatasetVersion.exclude_cols` properties.
+
+## 1.5.2 (06-10-2024)
 
 ### Bug Fixes
 
@@ -12,7 +28,7 @@
 
 ### New Features
 
-## 1.5.1
+## 1.5.1 (05-22-2024)
 
 ### Bug Fixes
 
@@ -37,7 +53,7 @@
   permissions to operate on schema. Please call
   `import snowflake.ml.modeling.parameters.enable_anonymous_sproc  # noqa: F401`
 
-## 1.5.0
+## 1.5.0 (05-01-2024)
 
 ### Bug Fixes
 

diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
@@ -139,7 +139,7 @@ bazel build --config=typecheck <your target>
 Or you could run
 
 ```sh
-./ci/type_check.sh -b <path_to_bazel>
+./ci/type_check/type_check.sh -b <path_to_bazel>
 ```
 
 You only need to specify `-b <path_to_bazel>` if your `bazel` is not in `$PATH` or is an alias.

diff --git a/bazel/environments/conda-env-snowflake.yml b/bazel/environments/conda-env-snowflake.yml
@@ -50,8 +50,8 @@ dependencies:
   - sentence-transformers==2.2.2
   - sentencepiece==0.1.99
   - shap==0.42.1
-  - snowflake-connector-python==3.5.0
-  - snowflake-snowpark-python==1.11.1
+  - snowflake-connector-python==3.10.0
+  - snowflake-snowpark-python==1.15.0
   - sphinx==5.0.2
   - sqlparse==0.4.4
   - tensorflow==2.12.0

diff --git a/bazel/environments/conda-env.yml b/bazel/environments/conda-env.yml
@@ -55,8 +55,8 @@ dependencies:
   - sentence-transformers==2.2.2
   - sentencepiece==0.1.99
   - shap==0.42.1
-  - snowflake-connector-python==3.5.0
-  - snowflake-snowpark-python==1.11.1
+  - snowflake-connector-python==3.10.0
+  - snowflake-snowpark-python==1.15.0
   - sphinx==5.0.2
   - sqlparse==0.4.4
   - tensorflow==2.12.0

diff --git a/bazel/environments/conda-gpu-env.yml b/bazel/environments/conda-gpu-env.yml
@@ -57,8 +57,8 @@ dependencies:
   - sentence-transformers==2.2.2
   - sentencepiece==0.1.99
   - shap==0.42.1
-  - snowflake-connector-python==3.5.0
-  - snowflake-snowpark-python==1.11.1
+  - snowflake-connector-python==3.10.0
+  - snowflake-snowpark-python==1.15.0
   - sphinx==5.0.2
   - sqlparse==0.4.4
   - tensorflow==2.12.0

diff --git a/ci/conda_recipe/meta.yaml b/ci/conda_recipe/meta.yaml
@@ -17,7 +17,7 @@ build:
   noarch: python
 package:
   name: snowflake-ml-python
-  version: 1.5.2
+  version: 1.5.3
 requirements:
   build:
     - python
@@ -42,7 +42,7 @@ requirements:
     - scikit-learn>=1.2.1,<1.4
     - scipy>=1.9,<2
     - snowflake-connector-python>=3.5.0,<4
-    - snowflake-snowpark-python>=1.11.1,<2,!=1.12.0
+    - snowflake-snowpark-python>=1.15.0,<2
     - sqlparse>=0.4,<1
     - typing-extensions>=4.1.0,<5
     - xgboost>=1.7.3,<2

diff --git a/codegen/sklearn_wrapper_template.py_template b/codegen/sklearn_wrapper_template.py_template
@@ -142,7 +142,7 @@ class {transform.original_class_name}(BaseTransformer):
                         inspect.currentframe(), {transform.original_class_name}.__class__.__name__
                     ),
                     api_calls=[Session.call],
-                    custom_tags=dict([("autogen", True)]) if self._autogenerated else None,
+                    custom_tags={{"autogen": True}} if self._autogenerated else None,
                 )
                 pd_df: pd.DataFrame = dataset.to_pandas(statement_params=statement_params)
                 pd_df.columns = dataset.columns

diff --git a/docs/source/cortex.rst b/docs/source/cortex.rst
@@ -0,0 +1,23 @@
+===================
+snowflake.ml.cortex
+===================
+
+.. automodule:: snowflake.cortex
+    :noindex:
+
+.. currentmodule:: snowflake.cortex
+
+.. rubric:: Classes
+
+.. autosummary::
+    :toctree: api/model
+
+    Complete
+    ExtractAnswer
+    Sentiment
+    Summarize
+    Translate
+
+.. .. rubric:: Attributes
+
+.. None
diff --git a/docs/source/dataset.rst b/docs/source/dataset.rst
@@ -0,0 +1,27 @@
+:orphan:
+
+===========================
+snowflake.ml.dataset
+===========================
+
+.. automodule:: snowflake.ml.dataset
+    :noindex:
+
+.. currentmodule:: snowflake.ml.dataset
+
+.. rubric:: Classes
+
+.. autosummary::
+    :toctree: api/dataset
+
+    Dataset
+    DatasetReader
+    DatasetVersion
+
+.. rubric:: Functions
+
+.. autosummary::
+    :toctree: api/dataset
+
+    create_from_dataframe
+    load_dataset
diff --git a/docs/source/feature_store.rst b/docs/source/feature_store.rst
@@ -0,0 +1,26 @@
+:orphan:
+
+===========================
+snowflake.ml.feature_store
+===========================
+
+.. automodule:: snowflake.ml.feature_store
+    :noindex:
+
+.. currentmodule:: snowflake.ml.feature_store
+
+.. rubric:: Classes
+
+.. autosummary::
+    :toctree: api/feature_store
+
+    Entity
+    FeatureStore
+    FeatureView
+
+.. rubric:: Functions
+
+.. autosummary::
+    :toctree: api/feature_store
+
+    setup_feature_store
diff --git a/docs/source/index.rst b/docs/source/index.rst
@@ -15,14 +15,20 @@ Portions of the Snowpark ML API Reference are derived from
 | **scikit-learn** Copyright © 2007-2023 The scikit-learn developers. All rights reserved.
 | **xgboost** Copyright © 2019 by xgboost contributors.
 | **lightgbm** Copyright © Microsoft Corporation.
+|
+
+----
 
 Table of Contents
 =================
 
 .. toctree::
    :maxdepth: 3
 
-   modeling
+   cortex
+   dataset
+   feature_store
    fileset
    model
+   modeling
    registry
diff --git a/docs/source/model.rst b/docs/source/model.rst
@@ -1,13 +1,10 @@
-===========================
+==================
 snowflake.ml.model
-===========================
+==================
 
 .. automodule:: snowflake.ml.model
     :noindex:
 
-snowflake.ml.model
----------------------------------
-
 .. currentmodule:: snowflake.ml.model
 
 .. rubric:: Classes

diff --git a/docs/source/modeling.rst b/docs/source/modeling.rst
@@ -384,11 +384,11 @@ snowflake.ml.modeling.naive_bayes
 .. autosummary::
     :toctree: api/modeling
 
-  BernoulliNB
-  CategoricalNB
-  ComplementNB
-  GaussianNB
-  MultinomialNB
+    BernoulliNB
+    CategoricalNB
+    ComplementNB
+    GaussianNB
+    MultinomialNB
 
 
 snowflake.ml.modeling.neighbors
@@ -401,15 +401,15 @@ snowflake.ml.modeling.neighbors
 .. autosummary::
     :toctree: api/modeling
 
-  KernelDensity
-  KNeighborsClassifier
-  KNeighborsRegressor
-  LocalOutlierFactor
-  NearestCentroid
-  NearestNeighbors
-  NeighborhoodComponentsAnalysis
-  RadiusNeighborsClassifier
-  RadiusNeighborsRegressor
+    KernelDensity
+    KNeighborsClassifier
+    KNeighborsRegressor
+    LocalOutlierFactor
+    NearestCentroid
+    NearestNeighbors
+    NeighborhoodComponentsAnalysis
+    RadiusNeighborsClassifier
+    RadiusNeighborsRegressor
 
 
 snowflake.ml.modeling.neural_network
@@ -422,9 +422,9 @@ snowflake.ml.modeling.neural_network
 .. autosummary::
     :toctree: api/modeling
 
-  BernoulliRBM
-  MLPClassifier
-  MLPRegressor
+    BernoulliRBM
+    MLPClassifier
+    MLPRegressor
 
 snowflake.ml.modeling.pipeline
 -------------------------------------------
@@ -436,7 +436,7 @@ snowflake.ml.modeling.pipeline
 .. autosummary::
     :toctree: api/modeling
 
-  Pipeline
+    Pipeline
 
 snowflake.ml.modeling.preprocessing
 -----------------------------------------------
@@ -469,8 +469,8 @@ snowflake.ml.modeling.semi_supervised
 .. autosummary::
     :toctree: api/modeling
 
-  LabelPropagation
-  LabelSpreading
+    LabelPropagation
+    LabelSpreading
 
 
 snowflake.ml.modeling.svm
@@ -483,12 +483,12 @@ snowflake.ml.modeling.svm
 .. autosummary::
     :toctree: api/modeling
 
-  LinearSVC
-  LinearSVR
-  NuSVC
-  NuSVR
-  SVC
-  SVR
+    LinearSVC
+    LinearSVR
+    NuSVC
+    NuSVR
+    SVC
+    SVR
 
 
 
@@ -502,10 +502,10 @@ snowflake.ml.modeling.tree
 .. autosummary::
     :toctree: api/modeling
 
-  DecisionTreeClassifier
-  DecisionTreeRegressor
-  ExtraTreeClassifier
-  ExtraTreeRegressor
+    DecisionTreeClassifier
+    DecisionTreeRegressor
+    ExtraTreeClassifier
+    ExtraTreeRegressor
 
 
 snowflake.ml.modeling.xgboost
@@ -518,7 +518,7 @@ snowflake.ml.modeling.xgboost
 .. autosummary::
     :toctree: api/modeling
 
-  XGBClassifier
-  XGBRegressor
-  XGBRFClassifier
-  XGBRFRegressor
+    XGBClassifier
+    XGBRegressor
+    XGBRFClassifier
+    XGBRFRegressor
diff --git a/requirements.txt b/requirements.txt
@@ -45,8 +45,8 @@ scipy==1.9.3
 sentence-transformers==2.2.2
 sentencepiece==0.1.99
 shap==0.42.1
-snowflake-connector-python[pandas]==3.5.0
-snowflake-snowpark-python==1.11.1
+snowflake-connector-python[pandas]==3.10.0
+snowflake-snowpark-python==1.15.0
 sphinx==5.0.2
 sqlparse==0.4.4
 starlette==0.27.0

diff --git a/requirements.yml b/requirements.yml
@@ -252,11 +252,11 @@
     - transformers
 - name_conda: snowflake-connector-python
   name_pypi: snowflake-connector-python[pandas]
-  dev_version: 3.5.0
+  dev_version: 3.10.0
   version_requirements: '>=3.5.0,<4'
 - name: snowflake-snowpark-python
-  dev_version: 1.11.1
-  version_requirements: '>=1.11.1,<2,!=1.12.0'
+  dev_version: 1.15.0
+  version_requirements: '>=1.15.0,<2'
   tags:
     - deployment_core
     - snowml_inference_alternative