snowpark-checkpoints-validators 0.1.0rc1__tar.gz → 0.1.0rc3__tar.gz

{snowpark_checkpoints_validators-0.1.0rc1 → snowpark_checkpoints_validators-0.1.0rc3}/.gitignore

@@ -4,10 +4,13 @@
 
 # demos
 snowpark-checkpoints-output/
+Demos/Demos/
+Demos/snowpark-checkpoints-output/
 
 # env
 wheelvenv/
 
+
 # version
 !__version__.py
 

snowpark_checkpoints_validators-0.1.0rc3/PKG-INFO

@@ -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-0.1.0rc1 → snowpark_checkpoints_validators-0.1.0rc3}/README.md

@@ -1,4 +1,4 @@
-# Snowpark Checkpoints Validators
+# snowpark-checkpoints-validators
 
 ---
 **NOTE**
@@ -24,9 +24,16 @@ This package is on Private Preview.
 The `validate_dataframe_checkpoint` function validates a Snowpark DataFrame against a checkpoint schema file or dataframe.
 
 ```python
-from snowflake.snowpark_checkpoints.checkpoint import validate_dataframe_checkpoint
+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
 
-validate_dataframe_checkpoint(
+# Signature of the function
+def validate_dataframe_checkpoint(
     df: SnowparkDataFrame,
     checkpoint_name: str,
     job_context: Optional[SnowparkJobContext] = None,
@@ -37,16 +44,17 @@ validate_dataframe_checkpoint(
     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.
+- `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_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.
@@ -55,16 +63,24 @@ validate_dataframe_checkpoint(
 
 ```python
 from snowflake.snowpark import Session
-from snowflake.snowpark import DataFrame as SnowparkDataFrame
+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=session,
+    job_context=job_context,
     mode=CheckpointMode.SCHEMA,
     sample_frac=0.1,
     sampling_strategy=SamplingStrategy.RANDOM_SAMPLE
@@ -73,22 +89,24 @@ validate_dataframe_checkpoint(
 
 ### Check with Spark Decorator
 
-The `check_with_spark` decorator converts any Snowpark DataFrame arguments to a function, samples them, and converts them to PySpark DataFrames. It then executes a provided Spark function and compares the outputs between the two implementations.
+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.spark_migration import check_with_spark
+from snowflake.snowpark_checkpoints.job_context import SnowparkJobContext
+from snowflake.snowpark_checkpoints.spark_migration import SamplingStrategy
+from typing import Callable, Optional, TypeVar
 
-@check_with_spark(
+fn = TypeVar("F", bound=Callable)
+
+# Signature of the decorator
+def check_with_spark(
     job_context: Optional[SnowparkJobContext],
-    spark_function: Callable,
+    spark_function: fn,
     checkpoint_name: str,
     sample_number: Optional[int] = 100,
     sampling_strategy: Optional[SamplingStrategy] = SamplingStrategy.RANDOM_SAMPLE,
-    check_dtypes: Optional[bool] = False,
-    check_with_precision: Optional[bool] = False,
     output_path: Optional[str] = None,
-)
-def snowpark_fn(df: SnowparkDataFrame):
+) -> Callable[[fn], fn]:
     ...
 ```
 
@@ -97,8 +115,6 @@ def snowpark_fn(df: SnowparkDataFrame):
 - `checkpoint_name`: Name of the check.
 - `sample_number`: Number of rows to sample.
 - `sampling_strategy`: Sampling strategy to use.
-- `check_dtypes`: Check data types.
-- `check_with_precision`: Check with precision.
 - `output_path`: Output path for the checkpoint report.
 
 ### Usage Example
@@ -107,52 +123,63 @@ def snowpark_fn(df: SnowparkDataFrame):
 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()
-df = session.read.format("csv").load("data.csv")
+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=session,
-    spark_function=lambda df: df.withColumn("COLUMN1", df["COLUMN1"] + 1),
-    checkpoint_name="Check_Column1_Increment",
-    sample_number=100,
-    sampling_strategy=SamplingStrategy.RANDOM_SAMPLE,
+    job_context=job_context,
+    spark_function=my_spark_scalar_fn,
+    checkpoint_name="count_checkpoint",
 )
-def increment_column1(df: SnowparkDataFrame):
-    return df.with_column("COLUMN1", df["COLUMN1"] + 1)
+def my_snowpark_scalar_fn(df: SnowparkDataFrame):
+    return df.count()
 
-increment_column1(df)
+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.
+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.checkpoint import check_input_schema, check_output_schema
+from snowflake.snowpark_checkpoints.spark_migration import SamplingStrategy
+from snowflake.snowpark_checkpoints.job_context import SnowparkJobContext
+from pandera import DataFrameSchema
+from typing import Optional
 
-@check_input_schema(
+# 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],
+    job_context: Optional[SnowparkJobContext] = None,
     output_path: Optional[str] = None,
-)
-def snowpark_fn(df: SnowparkDataFrame):
+):
     ...
 
-@check_output_schema(
+# 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],
+    job_context: Optional[SnowparkJobContext] = None,
     output_path: Optional[str] = None,
-)
-def snowpark_fn(df: SnowparkDataFrame):
+):
     ...
 ```
 
@@ -166,28 +193,71 @@ def snowpark_fn(df: SnowparkDataFrame):
 
 ### Usage Example
 
-The following will result in a Pandera `SchemaError`:
+#### 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],
-})
+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(lambda x: 0 <= x <= 10, element_wise=True)),
-    "COLUMN2": Column(float, Check(lambda x: x < -1.2)),
-})
+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("COLUMN1", lit('Some bad data yo'))
+    return dataframe.with_column(
+        "COLUMN3", dataframe["COLUMN1"] + dataframe["COLUMN2"]
+    )
 
 session = Session.builder.getOrCreate()
 sp_dataframe = session.create_dataframe(df)
@@ -195,6 +265,4 @@ sp_dataframe = session.create_dataframe(df)
 preprocessed_dataframe = preprocessor(sp_dataframe)
 ```
 
-## License
-
-This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for more details.
+------

{snowpark_checkpoints_validators-0.1.0rc1 → snowpark_checkpoints_validators-0.1.0rc3}/pyproject.toml

@@ -3,7 +3,9 @@ build-backend = "hatchling.build"
 requires = ["hatchling"]
 
 [project]
-authors = [{name = "Snowflake Inc."}]
+authors = [
+  {name = "Snowflake, Inc.", email = "snowflake-python-libraries-dl@snowflake.com"},
+]
 classifiers = [
   "Development Status :: 4 - Beta",
   "Environment :: Console",
@@ -31,6 +33,7 @@ dependencies = [
   "pandera-report==0.1.2",
 ]
 description = "Migration tools for Snowpark"
+dynamic = ['version']
 keywords = [
   'Snowflake',
   'analytics',
@@ -39,11 +42,10 @@ keywords = [
   'db',
   'Snowpark',
 ]
-license = {file = "LICENSE"}
+license = {text = "Apache License, Version 2.0"}
 name = "snowpark-checkpoints-validators"
 readme = "README.md"
 requires-python = '>=3.9,<3.12'
-dynamic = ['version']
 
 [project.optional-dependencies]
 development = [
@@ -118,7 +120,7 @@ check = [
 
 [tool.hatch.envs.test.scripts]
 check = [
-  "pip install -e ../snowpark-checkpoints-configuration" ,
+  "pip install -e ../snowpark-checkpoints-configuration",
   'pytest -v --junitxml=test/outcome/test-results.xml --cov=. --cov-config=test/.coveragerc --cov-report=xml:test/outcome/coverage-{matrix:python:{env:PYTHON_VERSION:unset}}.xml {args:test} --cov-report=term --cov-report=json:test/outcome/coverage-{matrix:python:{env:PYTHON_VERSION:unset}}.json',
 ]
 

{snowpark_checkpoints_validators-0.1.0rc1 → snowpark_checkpoints_validators-0.1.0rc3}/src/snowflake/snowpark_checkpoints/__init__.py

@@ -10,6 +10,7 @@ from snowflake.snowpark_checkpoints.checkpoint import (
 )
 from snowflake.snowpark_checkpoints.job_context import SnowparkJobContext
 from snowflake.snowpark_checkpoints.spark_migration import check_with_spark
+from snowflake.snowpark_checkpoints.utils.constants import CheckpointMode
 
 __all__ = [
     "check_with_spark",
@@ -18,4 +19,5 @@ __all__ = [
     "check_output_schema",
     "check_input_schema",
     "validate_dataframe_checkpoint",
+    "CheckpointMode",
 ]