validation output changes (#255)

Author: KshitizLohia

ads/feature_store/dataset.py

@@ -887,11 +887,7 @@ def get_validation_output(self, job_id: str = None) -> "ValidationOutput":
         validation_output = (
             output_details.get("validationOutput") if output_details else None
         )
-        validation_output_json = (
-            json.loads(validation_output) if validation_output else None
-        )
-
-        return ValidationOutput(validation_output_json)
+        return ValidationOutput(validation_output)
 
     @classmethod
     def list_df(cls, compartment_id: str = None, **kwargs) -> "pandas.DataFrame":

ads/feature_store/docs/source/dataset.rst

@@ -119,28 +119,60 @@ With a Dataset instance, we can get the last dataset job details using ``get_las
 
 .. code-block:: python3
 
-  # Fetch validation results for a dataset
   dataset_job = dataset.get_last_job()
-  df = dataset_job.get_validation_output().to_dataframe()
-  df.show()
 
 Save expectation entity
 =======================
-Feature store allows you to define expectations on data being materialized into feature group instance. With a ``FeatureGroup`` instance, we can save the expectation entity using ``save_expectation()``
-
-
-.. image:: figures/validation.png
+Feature store allows you to define expectations on data being materialized into dataset instance.With a ``Dataset`` instance, You can save the expectation details using ``with_expectation_suite()`` with parameters
 
-The ``.save_expectation()`` method takes the following optional parameter:
-
-- ``expectation: Expectation``. Expectation of great expectation
+- ``expectation_suite: ExpectationSuite``. ExpectationSuit of great expectation
 - ``expectation_type: ExpectationType``. Type of expectation
         - ``ExpectationType.STRICT``: Fail the job if expectation not met
         - ``ExpectationType.LENIENT``: Pass the job even if expectation not met
 
+.. note::
+
+  Great Expectations is a Python-based open-source library for validating, documenting, and profiling your data. It helps you to maintain data quality and improve communication about data between teams. Software developers have long known that automated testing is essential for managing complex codebases.
+
+.. image:: figures/validation.png
+
 .. code-block:: python3
 
-  feature_group.save_expectation(expectation_suite, expectation_type="STRICT")
+    expectation_suite = ExpectationSuite(
+        expectation_suite_name="expectation_suite_name"
+    )
+    expectation_suite.add_expectation(
+        ExpectationConfiguration(
+            expectation_type="expect_column_values_to_not_be_null",
+            kwargs={"column": "<column>"},
+        )
+
+    dataset_resource = (
+            Dataset()
+            .with_description("dataset description")
+            .with_compartment_id(<compartment_id>)
+            .with_name(<name>)
+            .with_entity_id(entity_id)
+            .with_feature_store_id(feature_store_id)
+            .with_query(f"SELECT * FROM `{entity_id}`.{feature_group_name}")
+            .with_expectation_suite(
+                expectation_suite=expectation_suite,
+                expectation_type=ExpectationType.STRICT,
+            )
+        )
+
+You can call the ``get_validation_output()`` method of the Dataset instance to fetch validation results for a specific ingestion job.
+The ``get_validation_output()`` method takes the following optional parameter:
+
+- ``job_id: string``. Id of dataset job
+
+``get_validation_output().to_pandas()`` will output  the validation results for each expectation as pandas dataframe
+
+.. image:: figures/dataset_validation_results.png
+
+``get_validation_output().to_summary()`` will output the overall summary of validation as pandas dataframe.
+
+.. image:: figures/dataset_validation_summary.png
 
 .. seealso::
 
@@ -186,7 +218,7 @@ The ``get_statistics()`` method takes the following optional parameter:
   # Fetch stats results for a dataset job
   df = dataset.get_statistics(job_id).to_pandas()
 
-.. image:: figures/stats_1.png
+.. image:: figures/dataset_statistics.png
 
 .. seealso::
 

ads/feature_store/docs/source/feature_group.rst

@@ -152,22 +152,55 @@ Feature store provides an API similar to Pandas to join feature groups together
 
 Save expectation entity
 =======================
-Feature store allows you to define expectations on data being materialized into feature group instance. With a ``FeatureGroup`` instance, we can save the expectation entity using ``save_expectation()``
+With a ``FeatureGroup`` instance, You can save the expectation details using ``with_expectation_suite()`` with parameters
 
-
-.. image:: figures/validation.png
-
-The ``.save_expectation()`` method takes the following optional parameter:
-
-- ``expectation: Expectation``. Expectation of great expectation
+- ``expectation_suite: ExpectationSuite``. ExpectationSuit of great expectation
 - ``expectation_type: ExpectationType``. Type of expectation
         - ``ExpectationType.STRICT``: Fail the job if expectation not met
         - ``ExpectationType.LENIENT``: Pass the job even if expectation not met
 
+.. note::
+
+  Great Expectations is a Python-based open-source library for validating, documenting, and profiling your data. It helps you to maintain data quality and improve communication about data between teams. Software developers have long known that automated testing is essential for managing complex codebases.
+
+.. image:: figures/validation.png
+
 .. code-block:: python3
 
-  feature_group.save_expectation(expectation_suite, expectation_type="STRICT")
+    expectation_suite = ExpectationSuite(
+        expectation_suite_name="expectation_suite_name"
+    )
+    expectation_suite.add_expectation(
+        ExpectationConfiguration(
+            expectation_type="expect_column_values_to_not_be_null",
+            kwargs={"column": "<column>"},
+        )
+
+    feature_group_resource = (
+        FeatureGroup()
+        .with_feature_store_id(feature_store.id)
+        .with_primary_keys(["<key>"])
+        .with_name("<name>")
+        .with_entity_id(entity.id)
+        .with_compartment_id(<compartment_id>)
+        .with_schema_details_from_dataframe(<datframe>)
+        .with_expectation_suite(
+            expectation_suite=expectation_suite,
+            expectation_type=ExpectationType.STRICT,
+         )
+    )
+
+You can call the ``get_validation_output()`` method of the FeatureGroup instance to fetch validation results for a specific ingestion job.
+The ``get_validation_output()`` method takes the following optional parameter:
+
+- ``job_id: string``. Id of feature group job
+``get_validation_output().to_pandas()`` will output  the validation results for each expectation as pandas dataframe
+
+.. image:: figures/validation_results.png
+
+``get_validation_output().to_summary()`` will output the overall summary of validation as pandas dataframe.
 
+.. image:: figures/validation_summary.png
 .. seealso::
 
    :ref:`Feature Validation`

ads/feature_store/docs/source/feature_validation.rst

@@ -7,7 +7,7 @@ Feature validation is the process of checking the quality and accuracy of the fe
 Feature store allows you to define expectation on the data which is being materialized into feature group and dataset. This is achieved using open source library Great Expectations.
 
 .. note::
-  `Great Expectations <https://docs.greatexpectations.io/docs/>`_ is a Python-based open-source library for validating, documenting, and profiling your data. It helps you to maintain data quality and improve communication about data between teams. Software developers have long known that automated testing is essential for managing complex codebases.
+  `Great Expectations <https://docs.greatexpectations.io/docs/0.15.50/>`_ is a Python-based open-source library for validating, documenting, and profiling your data. It helps you to maintain data quality and improve communication about data between teams. Software developers have long known that automated testing is essential for managing complex codebases.
 
 
 Expectations
@@ -50,5 +50,7 @@ Expectation Suite is a collection of verifiable assertions i.e. expectations abo
 .. code-block:: python3
 
     # Create an Expectation Suite
-    suite = context.add_expectation_suite(expectation_suite_name="example_suite")
-    suite.add_expectation(expect_config)
+    expectation_suite = ExpectationSuite(
+        expectation_suite_name=<expectation_suite_name>
+    )
+    expectation_suite.add_expectation(expect_config)

ads/feature_store/docs/source/figures/dataset_statistics.png

@@ -1288,11 +1288,7 @@ def get_validation_output(self, job_id: str = None) -> "ValidationOutput":
             output_details.get("validationOutput") if output_details else None
         )
 
-        validation_output_json = (
-            json.loads(validation_output) if validation_output else None
-        )
-
-        return ValidationOutput(validation_output_json)
+        return ValidationOutput(validation_output)
 
     def __getattr__(self, name):
         try: