snowpark-checkpoints-validators 0.1.0rc2__py3-none-any.whl → 0.1.0rc3__py3-none-any.whl

snowpark_checkpoints_validators-0.1.0rc3.dist-info/METADATA

@@ -0,0 +1,313 @@
+Metadata-Version: 2.4
+Name: snowpark-checkpoints-validators
+Version: 0.1.0rc3
+Summary: Migration tools for Snowpark
+Project-URL: Bug Tracker, https://github.com/snowflakedb/snowpark-checkpoints/issues
+Project-URL: Source code, https://github.com/snowflakedb/snowpark-checkpoints/
+Author-email: "Snowflake, Inc." <snowflake-python-libraries-dl@snowflake.com>
+License: Apache License, Version 2.0
+License-File: LICENSE
+Keywords: Snowflake,Snowpark,analytics,cloud,database,db
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: Console
+Classifier: Environment :: Other Environment
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Education
+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 :: Only
+Classifier: Programming Language :: SQL
+Classifier: Topic :: Database
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Software Development
+Classifier: Topic :: Software Development :: Libraries
+Classifier: Topic :: Software Development :: Libraries :: Application Frameworks
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: <3.12,>=3.9
+Requires-Dist: pandera-report==0.1.2
+Requires-Dist: pandera[io]==0.20.4
+Requires-Dist: pyspark
+Requires-Dist: snowflake-connector-python
+Requires-Dist: snowflake-snowpark-python
+Provides-Extra: development
+Requires-Dist: coverage>=7.6.7; extra == 'development'
+Requires-Dist: deepdiff>=8.0.0; extra == 'development'
+Requires-Dist: hatchling==1.25.0; extra == 'development'
+Requires-Dist: pre-commit>=4.0.1; extra == 'development'
+Requires-Dist: pyarrow>=18.0.0; extra == 'development'
+Requires-Dist: pytest-cov>=6.0.0; extra == 'development'
+Requires-Dist: pytest>=8.3.3; extra == 'development'
+Requires-Dist: setuptools>=70.0.0; extra == 'development'
+Requires-Dist: twine==5.1.1; extra == 'development'
+Description-Content-Type: text/markdown
+
+# snowpark-checkpoints-validators
+
+---
+**NOTE**
+
+This package is on Private Preview.
+
+---
+
+**snowpark-checkpoints-validators** is a package designed to validate Snowpark DataFrames against predefined schemas and checkpoints. This package ensures data integrity and consistency by performing schema and data validation checks at various stages of a Snowpark pipeline.
+
+## Features
+
+- Validate Snowpark DataFrames against predefined Pandera schemas.
+- Perform custom checks and skip specific checks as needed.
+- Generate validation results and log them for further analysis.
+- Support for sampling strategies to validate large datasets efficiently.
+- Integration with PySpark for cross-validation between Snowpark and PySpark DataFrames.
+
+## Functionalities
+
+### Validate DataFrame Schema from File
+
+The `validate_dataframe_checkpoint` function validates a Snowpark DataFrame against a checkpoint schema file or dataframe.
+
+```python
+from snowflake.snowpark import DataFrame as SnowparkDataFrame
+from snowflake.snowpark_checkpoints.job_context import SnowparkJobContext
+from snowflake.snowpark_checkpoints.utils.constant import (
+    CheckpointMode,
+)
+from snowflake.snowpark_checkpoints.spark_migration import SamplingStrategy
+from typing import Any, Optional
+
+# Signature of the function
+def validate_dataframe_checkpoint(
+    df: SnowparkDataFrame,
+    checkpoint_name: str,
+    job_context: Optional[SnowparkJobContext] = None,
+    mode: Optional[CheckpointMode] = CheckpointMode.SCHEMA,
+    custom_checks: Optional[dict[Any, Any]] = None,
+    skip_checks: Optional[dict[Any, Any]] = None,
+    sample_frac: Optional[float] = 1.0,
+    sample_number: Optional[int] = None,
+    sampling_strategy: Optional[SamplingStrategy] = SamplingStrategy.RANDOM_SAMPLE,
+    output_path: Optional[str] = None,
+):
+...
+```
+
+- `df`: Snowpark dataframe to validate.
+- `checkpoint_name`: Name of the checkpoint schema file or dataframe.
+- `job_context`: Snowpark job context.
+- `mode`: Checkpoint mode (schema or data).
+- `custom_checks`: Custom checks to perform.
+- `skip_checks`: Checks to skip.
+- `sample_frac`: Fraction of the dataframe to sample.
+- `sample_number`: Number of rows to sample.
+- `sampling_strategy`: Sampling strategy to use.
+- `output_path`: Output path for the checkpoint report.
+
+### Usage Example
+
+```python
+from snowflake.snowpark import Session
+from snowflake.snowpark_checkpoints.utils.constant import (
+    CheckpointMode,
+)
+from snowflake.snowpark_checkpoints.checkpoint import validate_dataframe_checkpoint
+from snowflake.snowpark_checkpoints.spark_migration import SamplingStrategy
+from snowflake.snowpark_checkpoints.job_context import SnowparkJobContext
+from pyspark.sql import SparkSession
+
+session = Session.builder.getOrCreate()
+job_context = SnowparkJobContext(
+    session, SparkSession.builder.getOrCreate(), "job_context", True
+)
+df = session.read.format("csv").load("data.csv")
+
+validate_dataframe_checkpoint(
+    df,
+    "schema_checkpoint",
+    job_context=job_context,
+    mode=CheckpointMode.SCHEMA,
+    sample_frac=0.1,
+    sampling_strategy=SamplingStrategy.RANDOM_SAMPLE
+)
+```
+
+### Check with Spark Decorator
+
+The `check_with_spark` decorator converts any Snowpark dataframe arguments to a function, samples them, and converts them to PySpark dataframe. It then executes a provided Spark function and compares the outputs between the two implementations.
+
+```python
+from snowflake.snowpark_checkpoints.job_context import SnowparkJobContext
+from snowflake.snowpark_checkpoints.spark_migration import SamplingStrategy
+from typing import Callable, Optional, TypeVar
+
+fn = TypeVar("F", bound=Callable)
+
+# Signature of the decorator
+def check_with_spark(
+    job_context: Optional[SnowparkJobContext],
+    spark_function: fn,
+    checkpoint_name: str,
+    sample_number: Optional[int] = 100,
+    sampling_strategy: Optional[SamplingStrategy] = SamplingStrategy.RANDOM_SAMPLE,
+    output_path: Optional[str] = None,
+) -> Callable[[fn], fn]:
+    ...
+```
+
+- `job_context`: Snowpark job context.
+- `spark_function`: PySpark function to execute.
+- `checkpoint_name`: Name of the check.
+- `sample_number`: Number of rows to sample.
+- `sampling_strategy`: Sampling strategy to use.
+- `output_path`: Output path for the checkpoint report.
+
+### Usage Example
+
+```python
+from snowflake.snowpark import Session
+from snowflake.snowpark import DataFrame as SnowparkDataFrame
+from snowflake.snowpark_checkpoints.spark_migration import check_with_spark
+from snowflake.snowpark_checkpoints.job_context import SnowparkJobContext
+from pyspark.sql import DataFrame as SparkDataFrame, SparkSession
+
+session = Session.builder.getOrCreate()
+job_context = SnowparkJobContext(
+    session, SparkSession.builder.getOrCreate(), "job_context", True
+)
+
+def my_spark_scalar_fn(df: SparkDataFrame):
+    return df.count()
+
+@check_with_spark(
+    job_context=job_context,
+    spark_function=my_spark_scalar_fn,
+    checkpoint_name="count_checkpoint",
+)
+def my_snowpark_scalar_fn(df: SnowparkDataFrame):
+    return df.count()
+
+df = job_context.snowpark_session.create_dataframe(
+    [[1, 2], [3, 4]], schema=["a", "b"]
+)
+count = my_snowpark_scalar_fn(df)
+```
+
+### Pandera Snowpark Decorators
+
+The decorators `@check_input_schema` and `@check_output_schema` allow for sampled schema validation of Snowpark dataframes in the input arguments or in the return value.
+
+```python
+from snowflake.snowpark_checkpoints.spark_migration import SamplingStrategy
+from snowflake.snowpark_checkpoints.job_context import SnowparkJobContext
+from pandera import DataFrameSchema
+from typing import Optional
+
+# Signature of the decorator
+def check_input_schema(
+    pandera_schema: DataFrameSchema,
+    checkpoint_name: str,
+    sample_frac: Optional[float] = 1.0,
+    sample_number: Optional[int] = None,
+    sampling_strategy: Optional[SamplingStrategy] = SamplingStrategy.RANDOM_SAMPLE,
+    job_context: Optional[SnowparkJobContext] = None,
+    output_path: Optional[str] = None,
+):
+    ...
+
+# Signature of the decorator
+def check_output_schema(
+    pandera_schema: DataFrameSchema,
+    checkpoint_name: str,
+    sample_frac: Optional[float] = 1.0,
+    sample_number: Optional[int] = None,
+    sampling_strategy: Optional[SamplingStrategy] = SamplingStrategy.RANDOM_SAMPLE,
+    job_context: Optional[SnowparkJobContext] = None,
+    output_path: Optional[str] = None,
+):
+    ...
+```
+
+- `pandera_schema`: Pandera schema to validate.
+- `checkpoint_name`: Name of the checkpoint schema file or DataFrame.
+- `sample_frac`: Fraction of the DataFrame to sample.
+- `sample_number`: Number of rows to sample.
+- `sampling_strategy`: Sampling strategy to use.
+- `job_context`: Snowpark job context.
+- `output_path`: Output path for the checkpoint report.
+
+### Usage Example
+
+#### Check Input Schema Example
+```python
+from pandas import DataFrame as PandasDataFrame
+from pandera import DataFrameSchema, Column, Check
+from snowflake.snowpark import Session
+from snowflake.snowpark import DataFrame as SnowparkDataFrame
+from snowflake.snowpark_checkpoints.checkpoint import check_input_schema
+from numpy import int8
+
+df = PandasDataFrame(
+    {
+        "COLUMN1": [1, 4, 0, 10, 9],
+        "COLUMN2": [-1.3, -1.4, -2.9, -10.1, -20.4],
+    }
+)
+
+in_schema = DataFrameSchema(
+    {
+        "COLUMN1": Column(int8, Check(lambda x: 0 <= x <= 10, element_wise=True)),
+        "COLUMN2": Column(float, Check(lambda x: x < -1.2, element_wise=True)),
+    }
+)
+
+@check_input_schema(in_schema, "input_schema_checkpoint")
+def preprocessor(dataframe: SnowparkDataFrame):
+    dataframe = dataframe.withColumn(
+        "COLUMN3", dataframe["COLUMN1"] + dataframe["COLUMN2"]
+    )
+    return dataframe
+
+session = Session.builder.getOrCreate()
+sp_dataframe = session.create_dataframe(df)
+
+preprocessed_dataframe = preprocessor(sp_dataframe)
+```
+
+#### Check Input Schema Example
+```python
+from pandas import DataFrame as PandasDataFrame
+from pandera import DataFrameSchema, Column, Check
+from snowflake.snowpark import Session
+from snowflake.snowpark import DataFrame as SnowparkDataFrame
+from snowflake.snowpark_checkpoints.checkpoint import check_output_schema
+from numpy import int8
+
+df = PandasDataFrame(
+    {
+        "COLUMN1": [1, 4, 0, 10, 9],
+        "COLUMN2": [-1.3, -1.4, -2.9, -10.1, -20.4],
+    }
+)
+
+out_schema = DataFrameSchema(
+    {
+        "COLUMN1": Column(int8, Check.between(0, 10, include_max=True, include_min=True)),
+        "COLUMN2": Column(float, Check.less_than_or_equal_to(-1.2)),
+        "COLUMN3": Column(float, Check.less_than(10)),
+    }
+)
+
+@check_output_schema(out_schema, "output_schema_checkpoint")
+def preprocessor(dataframe: SnowparkDataFrame):
+    return dataframe.with_column(
+        "COLUMN3", dataframe["COLUMN1"] + dataframe["COLUMN2"]
+    )
+
+session = Session.builder.getOrCreate()
+sp_dataframe = session.create_dataframe(df)
+
+preprocessed_dataframe = preprocessor(sp_dataframe)
+```
+
+------

snowpark_checkpoints_validators-0.1.0rc3.dist-info/RECORD

@@ -0,0 +1,4 @@
+snowpark_checkpoints_validators-0.1.0rc3.dist-info/METADATA,sha256=tjA56AFxmFIDPB3jx0ySyf2sHNAdEFYUu9RuqwySQ4M,11002
+snowpark_checkpoints_validators-0.1.0rc3.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+snowpark_checkpoints_validators-0.1.0rc3.dist-info/licenses/LICENSE,sha256=pmjhbh6uVhV5MBXOlou_UZgFP7CYVQITkCCdvfcS5lY,11340
+snowpark_checkpoints_validators-0.1.0rc3.dist-info/RECORD,,

snowpark_checkpoints_validators-0.1.0rc2.dist-info/METADATA

@@ -1,514 +0,0 @@
-Metadata-Version: 2.4
-Name: snowpark-checkpoints-validators
-Version: 0.1.0rc2
-Summary: Migration tools for Snowpark
-Project-URL: Bug Tracker, https://github.com/snowflakedb/snowpark-checkpoints/issues
-Project-URL: Source code, https://github.com/snowflakedb/snowpark-checkpoints/
-Author: Snowflake Inc.
-License: 
-                                         Apache License
-                                   Version 2.0, January 2004
-                                http://www.apache.org/licenses/
-        
-           TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
-        
-           1. Definitions.
-        
-              "License" shall mean the terms and conditions for use, reproduction,
-              and distribution as defined by Sections 1 through 9 of this document.
-        
-              "Licensor" shall mean the copyright owner or entity authorized by
-              the copyright owner that is granting the License.
-        
-              "Legal Entity" shall mean the union of the acting entity and all
-              other entities that control, are controlled by, or are under common
-              control with that entity. For the purposes of this definition,
-              "control" means (i) the power, direct or indirect, to cause the
-              direction or management of such entity, whether by contract or
-              otherwise, or (ii) ownership of fifty percent (50%) or more of the
-              outstanding shares, or (iii) beneficial ownership of such entity.
-        
-              "You" (or "Your") shall mean an individual or Legal Entity
-              exercising permissions granted by this License.
-        
-              "Source" form shall mean the preferred form for making modifications,
-              including but not limited to software source code, documentation
-              source, and configuration files.
-        
-              "Object" form shall mean any form resulting from mechanical
-              transformation or translation of a Source form, including but
-              not limited to compiled object code, generated documentation,
-              and conversions to other media types.
-        
-              "Work" shall mean the work of authorship, whether in Source or
-              Object form, made available under the License, as indicated by a
-              copyright notice that is included in or attached to the work
-              (an example is provided in the Appendix below).
-        
-              "Derivative Works" shall mean any work, whether in Source or Object
-              form, that is based on (or derived from) the Work and for which the
-              editorial revisions, annotations, elaborations, or other modifications
-              represent, as a whole, an original work of authorship. For the purposes
-              of this License, Derivative Works shall not include works that remain
-              separable from, or merely link (or bind by name) to the interfaces of,
-              the Work and Derivative Works thereof.
-        
-              "Contribution" shall mean any work of authorship, including
-              the original version of the Work and any modifications or additions
-              to that Work or Derivative Works thereof, that is intentionally
-              submitted to Licensor for inclusion in the Work by the copyright owner
-              or by an individual or Legal Entity authorized to submit on behalf of
-              the copyright owner. For the purposes of this definition, "submitted"
-              means any form of electronic, verbal, or written communication sent
-              to the Licensor or its representatives, including but not limited to
-              communication on electronic mailing lists, source code control systems,
-              and issue tracking systems that are managed by, or on behalf of, the
-              Licensor for the purpose of discussing and improving the Work, but
-              excluding communication that is conspicuously marked or otherwise
-              designated in writing by the copyright owner as "Not a Contribution."
-        
-              "Contributor" shall mean Licensor and any individual or Legal Entity
-              on behalf of whom a Contribution has been received by Licensor and
-              subsequently incorporated within the Work.
-        
-           2. Grant of Copyright License. Subject to the terms and conditions of
-              this License, each Contributor hereby grants to You a perpetual,
-              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-              copyright license to reproduce, prepare Derivative Works of,
-              publicly display, publicly perform, sublicense, and distribute the
-              Work and such Derivative Works in Source or Object form.
-        
-           3. Grant of Patent License. Subject to the terms and conditions of
-              this License, each Contributor hereby grants to You a perpetual,
-              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-              (except as stated in this section) patent license to make, have made,
-              use, offer to sell, sell, import, and otherwise transfer the Work,
-              where such license applies only to those patent claims licensable
-              by such Contributor that are necessarily infringed by their
-              Contribution(s) alone or by combination of their Contribution(s)
-              with the Work to which such Contribution(s) was submitted. If You
-              institute patent litigation against any entity (including a
-              cross-claim or counterclaim in a lawsuit) alleging that the Work
-              or a Contribution incorporated within the Work constitutes direct
-              or contributory patent infringement, then any patent licenses
-              granted to You under this License for that Work shall terminate
-              as of the date such litigation is filed.
-        
-           4. Redistribution. You may reproduce and distribute copies of the
-              Work or Derivative Works thereof in any medium, with or without
-              modifications, and in Source or Object form, provided that You
-              meet the following conditions:
-        
-              (a) You must give any other recipients of the Work or
-                  Derivative Works a copy of this License; and
-        
-              (b) You must cause any modified files to carry prominent notices
-                  stating that You changed the files; and
-        
-              (c) You must retain, in the Source form of any Derivative Works
-                  that You distribute, all copyright, patent, trademark, and
-                  attribution notices from the Source form of the Work,
-                  excluding those notices that do not pertain to any part of
-                  the Derivative Works; and
-        
-              (d) If the Work includes a "NOTICE" text file as part of its
-                  distribution, then any Derivative Works that You distribute must
-                  include a readable copy of the attribution notices contained
-                  within such NOTICE file, excluding those notices that do not
-                  pertain to any part of the Derivative Works, in at least one
-                  of the following places: within a NOTICE text file distributed
-                  as part of the Derivative Works; within the Source form or
-                  documentation, if provided along with the Derivative Works; or,
-                  within a display generated by the Derivative Works, if and
-                  wherever such third-party notices normally appear. The contents
-                  of the NOTICE file are for informational purposes only and
-                  do not modify the License. You may add Your own attribution
-                  notices within Derivative Works that You distribute, alongside
-                  or as an addendum to the NOTICE text from the Work, provided
-                  that such additional attribution notices cannot be construed
-                  as modifying the License.
-        
-              You may add Your own copyright statement to Your modifications and
-              may provide additional or different license terms and conditions
-              for use, reproduction, or distribution of Your modifications, or
-              for any such Derivative Works as a whole, provided Your use,
-              reproduction, and distribution of the Work otherwise complies with
-              the conditions stated in this License.
-        
-           5. Submission of Contributions. Unless You explicitly state otherwise,
-              any Contribution intentionally submitted for inclusion in the Work
-              by You to the Licensor shall be under the terms and conditions of
-              this License, without any additional terms or conditions.
-              Notwithstanding the above, nothing herein shall supersede or modify
-              the terms of any separate license agreement you may have executed
-              with Licensor regarding such Contributions.
-        
-           6. Trademarks. This License does not grant permission to use the trade
-              names, trademarks, service marks, or product names of the Licensor,
-              except as required for reasonable and customary use in describing the
-              origin of the Work and reproducing the content of the NOTICE file.
-        
-           7. Disclaimer of Warranty. Unless required by applicable law or
-              agreed to in writing, Licensor provides the Work (and each
-              Contributor provides its Contributions) on an "AS IS" BASIS,
-              WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-              implied, including, without limitation, any warranties or conditions
-              of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
-              PARTICULAR PURPOSE. You are solely responsible for determining the
-              appropriateness of using or redistributing the Work and assume any
-              risks associated with Your exercise of permissions under this License.
-        
-           8. Limitation of Liability. In no event and under no legal theory,
-              whether in tort (including negligence), contract, or otherwise,
-              unless required by applicable law (such as deliberate and grossly
-              negligent acts) or agreed to in writing, shall any Contributor be
-              liable to You for damages, including any direct, indirect, special,
-              incidental, or consequential damages of any character arising as a
-              result of this License or out of the use or inability to use the
-              Work (including but not limited to damages for loss of goodwill,
-              work stoppage, computer failure or malfunction, or any and all
-              other commercial damages or losses), even if such Contributor
-              has been advised of the possibility of such damages.
-        
-           9. Accepting Warranty or Additional Liability. While redistributing
-              the Work or Derivative Works thereof, You may choose to offer,
-              and charge a fee for, acceptance of support, warranty, indemnity,
-              or other liability obligations and/or rights consistent with this
-              License. However, in accepting such obligations, You may act only
-              on Your own behalf and on Your sole responsibility, not on behalf
-              of any other Contributor, and only if You agree to indemnify,
-              defend, and hold each Contributor harmless for any liability
-              incurred by, or claims asserted against, such Contributor by reason
-              of your accepting any such warranty or additional liability.
-        
-           END OF TERMS AND CONDITIONS
-        
-           APPENDIX: How to apply the Apache License to your work.
-        
-              To apply the Apache License to your work, attach the following
-              boilerplate notice, with the fields enclosed by brackets "[]"
-              replaced with your own identifying information. (Don't include
-              the brackets!)  The text should be enclosed in the appropriate
-              comment syntax for the file format. We also recommend that a
-              file or class name and description of purpose be included on the
-              same "printed page" as the copyright notice for easier
-              identification within third-party archives.
-        
-           Copyright 2025 Snowflake
-        
-           Licensed under the Apache License, Version 2.0 (the "License");
-           you may not use this file except in compliance with the License.
-           You may obtain a copy of the License at
-        
-               http://www.apache.org/licenses/LICENSE-2.0
-        
-           Unless required by applicable law or agreed to in writing, software
-           distributed under the License is distributed on an "AS IS" BASIS,
-           WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-           See the License for the specific language governing permissions and
-           limitations under the License.
-License-File: LICENSE
-Keywords: Snowflake,Snowpark,analytics,cloud,database,db
-Classifier: Development Status :: 4 - Beta
-Classifier: Environment :: Console
-Classifier: Environment :: Other Environment
-Classifier: Intended Audience :: Developers
-Classifier: Intended Audience :: Education
-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 :: Only
-Classifier: Programming Language :: SQL
-Classifier: Topic :: Database
-Classifier: Topic :: Scientific/Engineering :: Information Analysis
-Classifier: Topic :: Software Development
-Classifier: Topic :: Software Development :: Libraries
-Classifier: Topic :: Software Development :: Libraries :: Application Frameworks
-Classifier: Topic :: Software Development :: Libraries :: Python Modules
-Requires-Python: <3.12,>=3.9
-Requires-Dist: pandera-report==0.1.2
-Requires-Dist: pandera[io]==0.20.4
-Requires-Dist: pyspark
-Requires-Dist: snowflake-connector-python
-Requires-Dist: snowflake-snowpark-python
-Provides-Extra: development
-Requires-Dist: coverage>=7.6.7; extra == 'development'
-Requires-Dist: deepdiff>=8.0.0; extra == 'development'
-Requires-Dist: hatchling==1.25.0; extra == 'development'
-Requires-Dist: pre-commit>=4.0.1; extra == 'development'
-Requires-Dist: pyarrow>=18.0.0; extra == 'development'
-Requires-Dist: pytest-cov>=6.0.0; extra == 'development'
-Requires-Dist: pytest>=8.3.3; extra == 'development'
-Requires-Dist: setuptools>=70.0.0; extra == 'development'
-Requires-Dist: twine==5.1.1; extra == 'development'
-Description-Content-Type: text/markdown
-
-# snowpark-checkpoints-validators
-
----
-**NOTE**
-
-This package is on Private Preview.
-
----
-
-**snowpark-checkpoints-validators** is a package designed to validate Snowpark DataFrames against predefined schemas and checkpoints. This package ensures data integrity and consistency by performing schema and data validation checks at various stages of a Snowpark pipeline.
-
-## Features
-
-- Validate Snowpark DataFrames against predefined Pandera schemas.
-- Perform custom checks and skip specific checks as needed.
-- Generate validation results and log them for further analysis.
-- Support for sampling strategies to validate large datasets efficiently.
-- Integration with PySpark for cross-validation between Snowpark and PySpark DataFrames.
-
-## Functionalities
-
-### Validate DataFrame Schema from File
-
-The `validate_dataframe_checkpoint` function validates a Snowpark DataFrame against a checkpoint schema file or dataframe.
-
-```python
-from snowflake.snowpark import DataFrame as SnowparkDataFrame
-from snowflake.snowpark_checkpoints.job_context import SnowparkJobContext
-from snowflake.snowpark_checkpoints.utils.constant import (
-    CheckpointMode,
-)
-from snowflake.snowpark_checkpoints.spark_migration import SamplingStrategy
-from typing import Any, Optional
-
-# Signature of the function
-def validate_dataframe_checkpoint(
-    df: SnowparkDataFrame,
-    checkpoint_name: str,
-    job_context: Optional[SnowparkJobContext] = None,
-    mode: Optional[CheckpointMode] = CheckpointMode.SCHEMA,
-    custom_checks: Optional[dict[Any, Any]] = None,
-    skip_checks: Optional[dict[Any, Any]] = None,
-    sample_frac: Optional[float] = 1.0,
-    sample_number: Optional[int] = None,
-    sampling_strategy: Optional[SamplingStrategy] = SamplingStrategy.RANDOM_SAMPLE,
-    output_path: Optional[str] = None,
-):
-...
-```
-
-- `df`: Snowpark dataframe to validate.
-- `checkpoint_name`: Name of the checkpoint schema file or dataframe.
-- `job_context`: Snowpark job context.
-- `mode`: Checkpoint mode (schema or data).
-- `custom_checks`: Custom checks to perform.
-- `skip_checks`: Checks to skip.
-- `sample_frac`: Fraction of the dataframe to sample.
-- `sample_number`: Number of rows to sample.
-- `sampling_strategy`: Sampling strategy to use.
-- `output_path`: Output path for the checkpoint report.
-
-### Usage Example
-
-```python
-from snowflake.snowpark import Session
-from snowflake.snowpark_checkpoints.utils.constant import (
-    CheckpointMode,
-)
-from snowflake.snowpark_checkpoints.checkpoint import validate_dataframe_checkpoint
-from snowflake.snowpark_checkpoints.spark_migration import SamplingStrategy
-from snowflake.snowpark_checkpoints.job_context import SnowparkJobContext
-from pyspark.sql import SparkSession
-
-session = Session.builder.getOrCreate()
-job_context = SnowparkJobContext(
-    session, SparkSession.builder.getOrCreate(), "job_context", True
-)
-df = session.read.format("csv").load("data.csv")
-
-validate_dataframe_checkpoint(
-    df,
-    "schema_checkpoint",
-    job_context=job_context,
-    mode=CheckpointMode.SCHEMA,
-    sample_frac=0.1,
-    sampling_strategy=SamplingStrategy.RANDOM_SAMPLE
-)
-```
-
-### Check with Spark Decorator
-
-The `check_with_spark` decorator converts any Snowpark dataframe arguments to a function, samples them, and converts them to PySpark dataframe. It then executes a provided Spark function and compares the outputs between the two implementations.
-
-```python
-from snowflake.snowpark_checkpoints.job_context import SnowparkJobContext
-from snowflake.snowpark_checkpoints.spark_migration import SamplingStrategy
-from typing import Callable, Optional, TypeVar
-
-fn = TypeVar("F", bound=Callable)
-
-# Signature of the decorator
-def check_with_spark(
-    job_context: Optional[SnowparkJobContext],
-    spark_function: fn,
-    checkpoint_name: str,
-    sample_number: Optional[int] = 100,
-    sampling_strategy: Optional[SamplingStrategy] = SamplingStrategy.RANDOM_SAMPLE,
-    output_path: Optional[str] = None,
-) -> Callable[[fn], fn]:
-    ...
-```
-
-- `job_context`: Snowpark job context.
-- `spark_function`: PySpark function to execute.
-- `checkpoint_name`: Name of the check.
-- `sample_number`: Number of rows to sample.
-- `sampling_strategy`: Sampling strategy to use.
-- `output_path`: Output path for the checkpoint report.
-
-### Usage Example
-
-```python
-from snowflake.snowpark import Session
-from snowflake.snowpark import DataFrame as SnowparkDataFrame
-from snowflake.snowpark_checkpoints.spark_migration import check_with_spark
-from snowflake.snowpark_checkpoints.job_context import SnowparkJobContext
-from pyspark.sql import DataFrame as SparkDataFrame, SparkSession
-
-session = Session.builder.getOrCreate()
-job_context = SnowparkJobContext(
-    session, SparkSession.builder.getOrCreate(), "job_context", True
-)
-
-def my_spark_scalar_fn(df: SparkDataFrame):
-    return df.count()
-
-@check_with_spark(
-    job_context=job_context,
-    spark_function=my_spark_scalar_fn,
-    checkpoint_name="count_checkpoint",
-)
-def my_snowpark_scalar_fn(df: SnowparkDataFrame):
-    return df.count()
-
-df = job_context.snowpark_session.create_dataframe(
-    [[1, 2], [3, 4]], schema=["a", "b"]
-)
-count = my_snowpark_scalar_fn(df)
-```
-
-### Pandera Snowpark Decorators
-
-The decorators `@check_input_schema` and `@check_output_schema` allow for sampled schema validation of Snowpark dataframes in the input arguments or in the return value.
-
-```python
-from snowflake.snowpark_checkpoints.spark_migration import SamplingStrategy
-from snowflake.snowpark_checkpoints.job_context import SnowparkJobContext
-from pandera import DataFrameSchema
-from typing import Optional
-
-# Signature of the decorator
-def check_input_schema(
-    pandera_schema: DataFrameSchema,
-    checkpoint_name: str,
-    sample_frac: Optional[float] = 1.0,
-    sample_number: Optional[int] = None,
-    sampling_strategy: Optional[SamplingStrategy] = SamplingStrategy.RANDOM_SAMPLE,
-    job_context: Optional[SnowparkJobContext] = None,
-    output_path: Optional[str] = None,
-):
-    ...
-
-# Signature of the decorator
-def check_output_schema(
-    pandera_schema: DataFrameSchema,
-    checkpoint_name: str,
-    sample_frac: Optional[float] = 1.0,
-    sample_number: Optional[int] = None,
-    sampling_strategy: Optional[SamplingStrategy] = SamplingStrategy.RANDOM_SAMPLE,
-    job_context: Optional[SnowparkJobContext] = None,
-    output_path: Optional[str] = None,
-):
-    ...
-```
-
-- `pandera_schema`: Pandera schema to validate.
-- `checkpoint_name`: Name of the checkpoint schema file or DataFrame.
-- `sample_frac`: Fraction of the DataFrame to sample.
-- `sample_number`: Number of rows to sample.
-- `sampling_strategy`: Sampling strategy to use.
-- `job_context`: Snowpark job context.
-- `output_path`: Output path for the checkpoint report.
-
-### Usage Example
-
-#### Check Input Schema Example
-```python
-from pandas import DataFrame as PandasDataFrame
-from pandera import DataFrameSchema, Column, Check
-from snowflake.snowpark import Session
-from snowflake.snowpark import DataFrame as SnowparkDataFrame
-from snowflake.snowpark_checkpoints.checkpoint import check_input_schema
-from numpy import int8
-
-df = PandasDataFrame(
-    {
-        "COLUMN1": [1, 4, 0, 10, 9],
-        "COLUMN2": [-1.3, -1.4, -2.9, -10.1, -20.4],
-    }
-)
-
-in_schema = DataFrameSchema(
-    {
-        "COLUMN1": Column(int8, Check(lambda x: 0 <= x <= 10, element_wise=True)),
-        "COLUMN2": Column(float, Check(lambda x: x < -1.2, element_wise=True)),
-    }
-)
-
-@check_input_schema(in_schema, "input_schema_checkpoint")
-def preprocessor(dataframe: SnowparkDataFrame):
-    dataframe = dataframe.withColumn(
-        "COLUMN3", dataframe["COLUMN1"] + dataframe["COLUMN2"]
-    )
-    return dataframe
-
-session = Session.builder.getOrCreate()
-sp_dataframe = session.create_dataframe(df)
-
-preprocessed_dataframe = preprocessor(sp_dataframe)
-```
-
-#### Check Input Schema Example
-```python
-from pandas import DataFrame as PandasDataFrame
-from pandera import DataFrameSchema, Column, Check
-from snowflake.snowpark import Session
-from snowflake.snowpark import DataFrame as SnowparkDataFrame
-from snowflake.snowpark_checkpoints.checkpoint import check_output_schema
-from numpy import int8
-
-df = PandasDataFrame(
-    {
-        "COLUMN1": [1, 4, 0, 10, 9],
-        "COLUMN2": [-1.3, -1.4, -2.9, -10.1, -20.4],
-    }
-)
-
-out_schema = DataFrameSchema(
-    {
-        "COLUMN1": Column(int8, Check.between(0, 10, include_max=True, include_min=True)),
-        "COLUMN2": Column(float, Check.less_than_or_equal_to(-1.2)),
-        "COLUMN3": Column(float, Check.less_than(10)),
-    }
-)
-
-@check_output_schema(out_schema, "output_schema_checkpoint")
-def preprocessor(dataframe: SnowparkDataFrame):
-    return dataframe.with_column(
-        "COLUMN3", dataframe["COLUMN1"] + dataframe["COLUMN2"]
-    )
-
-session = Session.builder.getOrCreate()
-sp_dataframe = session.create_dataframe(df)
-
-preprocessed_dataframe = preprocessor(sp_dataframe)
-```
-
-------

snowpark_checkpoints_validators-0.1.0rc2.dist-info/RECORD

@@ -1,4 +0,0 @@
-snowpark_checkpoints_validators-0.1.0rc2.dist-info/METADATA,sha256=IgK1FDpHJmzVAtFmrBgQxNUmGCW29DReLcXgPlsXGf8,23867
-snowpark_checkpoints_validators-0.1.0rc2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-snowpark_checkpoints_validators-0.1.0rc2.dist-info/licenses/LICENSE,sha256=pmjhbh6uVhV5MBXOlou_UZgFP7CYVQITkCCdvfcS5lY,11340
-snowpark_checkpoints_validators-0.1.0rc2.dist-info/RECORD,,