stats representation via plotly in to_viz interface (#335)

Author: KshitizLohia

THIRD_PARTY_LICENSES.txt

@@ -229,6 +229,12 @@ pandavro
 * Source code: https://github.com/ynqa/pandavro
 * Project home: https://github.com/ynqa/pandavro
 
+plotly
+* Copyright (c) 2016-2018 Plotly, Inc
+* License: MIT License
+* Source code: https://github.com/plotly/plotly.py
+* Project home: https://plotly.com/
+
 protobuf
 * Copyright 2008 Google Inc.  All rights reserved.
 * License: Google Protobuf License

ads/feature_store/dataset.py

@@ -38,7 +38,7 @@
 from ads.feature_store.feature_group_expectation import Expectation
 from ads.feature_store.feature_option_details import FeatureOptionDetails
 from ads.feature_store.service.oci_dataset import OCIDataset
-from ads.feature_store.statistics import Statistics
+from ads.feature_store.statistics.statistics import Statistics
 from ads.feature_store.statistics_config import StatisticsConfig
 from ads.feature_store.service.oci_lineage import OCILineage
 from ads.feature_store.model_details import ModelDetails
@@ -164,7 +164,7 @@ def __init__(self, spec: Dict = None, **kwargs) -> None:
         self.oci_dataset = self._to_oci_dataset(**kwargs)
         self.lineage = OCILineage(**kwargs)
 
-    def _to_oci_dataset(self, **kwargs):
+    def _to_oci_dataset(self, **kwargs) -> OCIDataset:
         """Creates an `OCIDataset` instance from the  `Dataset`.
 
         kwargs
@@ -235,8 +235,8 @@ def name(self) -> str:
         return self.get_spec(self.CONST_NAME)
 
     @name.setter
-    def name(self, name: str) -> "Dataset":
-        return self.with_name(name)
+    def name(self, name: str):
+        self.with_name(name)
 
     def with_name(self, name: str) -> "Dataset":
         """Sets the name.
@@ -1207,12 +1207,14 @@ def to_dict(self) -> Dict:
         for key, value in spec.items():
             if hasattr(value, "to_dict"):
                 value = value.to_dict()
-            if hasattr(value, "attribute_map"):
-                value = self.oci_dataset.client.base_client.sanitize_for_serialization(
+            if key == self.CONST_FEATURE_GROUP:
+                spec[
+                    key
+                ] = self.oci_dataset.client.base_client.sanitize_for_serialization(
                     value
                 )
-            spec[key] = value
-
+            else:
+                spec[key] = value
         return {
             "kind": self.kind,
             "type": self.type,

ads/feature_store/docs/Makefile

@@ -18,7 +18,7 @@ help:
 .PHONY: help Makefile
 
 # Catch-all target: route all unknown targets to Sphinx using the new
-# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+# "make mode" option.  $(O) is me`ant as a shortcut for $(SPHINXOPTS).
 %: Makefile
 	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
 

ads/feature_store/docs/source/dataset.rst

@@ -220,6 +220,14 @@ The ``get_statistics()`` method takes the following optional parameter:
 
 .. image:: figures/dataset_statistics.png
 
+.. code-block:: python3
+
+  # Fetch and visualize stats for a dataset job
+  df = dataset.get_statistics(job_id).to_viz()
+
+.. image:: figures/dataset_statistics_viz.png
+
+
 .. seealso::
 
     :ref:`Statistics`

ads/feature_store/docs/source/feature_group.rst

@@ -254,6 +254,13 @@ The ``get_statistics()`` method takes the following optional parameter:
 
 .. image:: figures/stats_1.png
 
+.. code-block:: python3
+
+  # Fetch and visualize stats for a dataset job
+  df = feature_group.get_statistics(job_id).to_viz()
+
+.. image:: figures/feature_group_statistics_viz.png
+
 .. seealso::
 
     :ref:`Statistics`

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

@@ -44,7 +44,7 @@
 from ads.feature_store.service.oci_feature_group import OCIFeatureGroup
 from ads.feature_store.service.oci_feature_group_job import OCIFeatureGroupJob
 from ads.feature_store.service.oci_lineage import OCILineage
-from ads.feature_store.statistics import Statistics
+from ads.feature_store.statistics.statistics import Statistics
 from ads.feature_store.statistics_config import StatisticsConfig
 from ads.feature_store.validation_output import ValidationOutput
 
@@ -244,8 +244,8 @@ def name(self) -> str:
         return self.get_spec(self.CONST_NAME)
 
     @name.setter
-    def name(self, name: str) -> "FeatureGroup":
-        return self.with_name(name)
+    def name(self, name: str):
+        self.with_name(name)
 
     def with_name(self, name: str) -> "FeatureGroup":
         """Sets the name.
@@ -338,7 +338,7 @@ def transformation_kwargs(self, value: Dict):
         self.with_transformation_kwargs(value)
 
     def with_transformation_kwargs(
-        self, transformation_kwargs: Dict = {}
+        self, transformation_kwargs: Dict = ()
     ) -> "FeatureGroup":
         """Sets the primary keys of the feature group.
 
@@ -604,7 +604,6 @@ def with_statistics_config(
         FeatureGroup
             The FeatureGroup instance (self).
         """
-        statistics_config_in = None
         if isinstance(statistics_config, StatisticsConfig):
             statistics_config_in = statistics_config
         elif isinstance(statistics_config, bool):
@@ -1108,7 +1107,6 @@ def restore(self, version_number: int = None, timestamp: datetime = None):
                 f"RESTORE TABLE {target_table} TO VERSION AS OF {version_number}"
             )
         else:
-            iso_timestamp = timestamp.isoformat(" ", "seconds").__str__()
             sql_query = f"RESTORE TABLE {target_table} TO TIMESTAMP AS OF {timestamp}"
 
         restore_output = self.spark_engine.sql(sql_query)