black formatting

Author: najiyacl

ads/feature_store/dataset.py

@@ -1101,9 +1101,7 @@ def get_statistics(self, job_id: str = None) -> "Statistics":
         feature_statistics = (
             output_details.get("featureStatistics") if output_details else None
         )
-        stat_version = (
-            output_details.get("version") if output_details else None
-        )
+        stat_version = output_details.get("version") if output_details else None
         version = stat_version if stat_version is not None else 1
 
         return Statistics(feature_statistics, version)

ads/feature_store/execution_strategy/spark/spark_execution.py

@@ -77,10 +77,10 @@ def __init__(self, metastore_id: str = None):
         self._jvm = self._spark_context._jvm
 
     def ingest_feature_definition(
-            self,
-            feature_group: "FeatureGroup",
-            feature_group_job: FeatureGroupJob,
-            dataframe,
+        self,
+        feature_group: "FeatureGroup",
+        feature_group_job: FeatureGroupJob,
+        dataframe,
     ):
         try:
             self._save_offline_dataframe(dataframe, feature_group, feature_group_job)
@@ -94,7 +94,7 @@ def ingest_dataset(self, dataset, dataset_job: DatasetJob):
             raise SparkExecutionException(e).with_traceback(e.__traceback__)
 
     def delete_feature_definition(
-            self, feature_group: "FeatureGroup", feature_group_job: FeatureGroupJob
+        self, feature_group: "FeatureGroup", feature_group_job: FeatureGroupJob
     ):
         """
         Deletes a feature definition from the system.
@@ -188,7 +188,7 @@ def _validate_expectation(expectation_type, validation_output: dict):
             raise Exception(error_message)
 
     def _save_offline_dataframe(
-            self, data_frame, feature_group, feature_group_job: FeatureGroupJob
+        self, data_frame, feature_group, feature_group_job: FeatureGroupJob
     ):
         """Ingest dataframe to the feature store system. as now this handles both spark dataframe and pandas
         dataframe. in case of pandas after transformation we convert it to spark and write to the delta.
@@ -313,7 +313,7 @@ def _save_offline_dataframe(
             "validation_output": str(validation_output) if validation_output else None,
             "commit_id": "commit_id",
             "feature_statistics": feature_statistics,
-            "version": version
+            "version": version,
         }
 
         self._update_job_and_parent_details(
@@ -452,7 +452,7 @@ def _save_dataset_input(self, dataset, dataset_job: DatasetJob):
             "validation_output": str(validation_output) if validation_output else None,
             "commit_id": "commit_id",
             "feature_statistics": feature_statistics,
-            "version": version
+            "version": version,
         }
 
         self._update_job_and_parent_details(
@@ -464,7 +464,7 @@ def _save_dataset_input(self, dataset, dataset_job: DatasetJob):
 
     @staticmethod
     def _update_job_and_parent_details(
-            parent_entity, job_entity, output_features=None, output_details=None
+        parent_entity, job_entity, output_features=None, output_details=None
     ):
         """
         Updates the parent and job entities with relevant details.

ads/feature_store/feature_group.py

@@ -1348,9 +1348,7 @@ def get_statistics(self, job_id: str = None) -> "Statistics":
         feature_statistics = (
             output_details.get("featureStatistics") if output_details else None
         )
-        stat_version = (
-            output_details.get("version") if output_details else None
-        )
+        stat_version = output_details.get("version") if output_details else None
         version = stat_version if stat_version is not None else 1
 
         return Statistics(feature_statistics, version)

ads/feature_store/statistics/charts/box_plot.py

@@ -44,7 +44,9 @@ def __init__(self, q1: float, q2: float, q3: float):
             super().__init__()
 
         @classmethod
-        def __from_json__(cls, json_dict: dict, version: int = 1) -> "BoxPlot.Quartiles":
+        def __from_json__(
+            cls, json_dict: dict, version: int = 1
+        ) -> "BoxPlot.Quartiles":
             if version == 2:
                 return cls.__from_json_v2__(json_dict)
             return cls(
@@ -56,11 +58,7 @@ def __from_json__(cls, json_dict: dict, version: int = 1) -> "BoxPlot.Quartiles"
         @classmethod
         def __from_json_v2__(cls, json_dict: dict) -> "BoxPlot.Quartiles":
             metric_data = json_dict.get(AbsFeatureValue.CONST_METRIC_DATA)
-            return cls(
-                metric_data[0],
-                metric_data[1],
-                metric_data[2]
-            )
+            return cls(metric_data[0], metric_data[1], metric_data[2])
 
         def __validate__(self):
             assert type(self.q1) == type(self.q2) == type(self.q3) == int or float
@@ -139,9 +137,11 @@ def get_box_points_from_frequency_distribution(
     def __from_json__(cls, json_dict: dict, version: int = 1) -> "BoxPlot":
         quartiles = cls.Quartiles.from_json(json_dict.get(cls.CONST_QUARTILES), version)
         return cls(
-            mean=GenericFeatureValue.from_json(json_dict.get(cls.CONST_MEAN),version).val,
+            mean=GenericFeatureValue.from_json(
+                json_dict.get(cls.CONST_MEAN), version
+            ).val,
             median=quartiles.q2,
-            sd=GenericFeatureValue.from_json(json_dict.get(cls.CONST_SD),version).val,
+            sd=GenericFeatureValue.from_json(json_dict.get(cls.CONST_SD), version).val,
             q1=quartiles.q1,
             q3=quartiles.q3,
             box_points=json_dict.get(cls.CONST_BOX_POINTS),

ads/feature_store/statistics/charts/frequency_distribution.py

@@ -34,7 +34,9 @@ def __validate__(self):
         assert len(self.bins) > 0
 
     @classmethod
-    def __from_json__(cls, json_dict: dict, version: int = 1) -> "FrequencyDistribution":
+    def __from_json__(
+        cls, json_dict: dict, version: int = 1
+    ) -> "FrequencyDistribution":
         if version == 2:
             return cls.__from_json_v2__(json_dict)
         return FrequencyDistribution(
@@ -45,17 +47,15 @@ def __from_json__(cls, json_dict: dict, version: int = 1) -> "FrequencyDistribut
     @classmethod
     def __from_json_v2__(cls, json_dict: dict) -> "FrequencyDistribution":
         metric_data = json_dict.get(AbsFeatureValue.CONST_METRIC_DATA)
-        return FrequencyDistribution(
-            bins=metric_data[0],
-            frequency=metric_data[1]
-        )
+        return FrequencyDistribution(bins=metric_data[0], frequency=metric_data[1])
 
     def add_to_figure(self, fig: Figure, xaxis: int, yaxis: int):
         xaxis_str, yaxis_str, x_str, y_str = self.get_x_y_str_axes(xaxis, yaxis)
         if (
-                type(self.frequency) == list
-                and type(self.bins) == list
-                and 0 < len(self.frequency) and 0 < len(self.bins)
+            type(self.frequency) == list
+            and type(self.bins) == list
+            and 0 < len(self.frequency)
+            and 0 < len(self.bins)
         ):
             fig.add_bar(
                 x=self.bins, y=self.frequency, xaxis=x_str, yaxis=y_str, name=""

ads/feature_store/statistics/charts/probability_distribution.py

@@ -33,7 +33,9 @@ def __validate__(self):
         # assert 0 < len(self.density) == len(self.bins) > 0
 
     @classmethod
-    def __from_json__(cls, json_dict: dict, version: int = 1) -> "ProbabilityDistribution":
+    def __from_json__(
+        cls, json_dict: dict, version: int = 1
+    ) -> "ProbabilityDistribution":
         if version == 2:
             return cls.__from_json_v2__(json_dict)
         return cls(
@@ -44,17 +46,15 @@ def __from_json__(cls, json_dict: dict, version: int = 1) -> "ProbabilityDistrib
     @classmethod
     def __from_json_v2__(cls, json_dict: dict) -> "ProbabilityDistribution":
         metric_data = json_dict.get(AbsFeatureValue.CONST_METRIC_DATA)
-        return cls(
-            bins=metric_data[0],
-            density=metric_data[1]
-        )
+        return cls(bins=metric_data[0], density=metric_data[1])
 
     def add_to_figure(self, fig: Figure, xaxis: int, yaxis: int):
         xaxis_str, yaxis_str, x_str, y_str = self.get_x_y_str_axes(xaxis, yaxis)
         if (
             type(self.density) == list
             and type(self.bins) == list
-            and 0 < len(self.density) and 0 < len(self.bins)
+            and 0 < len(self.density)
+            and 0 < len(self.bins)
         ):
             fig.add_bar(
                 x=self.bins,

ads/feature_store/statistics/charts/top_k_frequent_elements.py

@@ -30,7 +30,7 @@ class TopKFrequentElement(AbsFeatureValue):
         CONST_UPPER_BOUND = "upper_bound"
 
         def __init__(
-                self, value: str, estimate: int, lower_bound: int, upper_bound: int
+            self, value: str, estimate: int, lower_bound: int, upper_bound: int
         ):
             self.value = value
             self.estimate = estimate
@@ -68,23 +68,26 @@ def __from_json__(cls, json_dict: dict, version: int = 1) -> "TopKFrequentElemen
         if version == 2:
             return cls.__from_json_v2__(json_dict)
         elements = json_dict.get(cls.CONST_VALUE)
-        top_k_frequent_elements = [cls.TopKFrequentElement.__from_json__(element) for element in elements]
+        top_k_frequent_elements = [
+            cls.TopKFrequentElement.__from_json__(element) for element in elements
+        ]
         values = [element.value for element in top_k_frequent_elements]
         estimates = [element.estimate for element in top_k_frequent_elements]
         return cls(values, estimates)
 
     @classmethod
     def __from_json_v2__(cls, json_dict: dict) -> "TopKFrequentElements":
         metric_data = json_dict.get(AbsFeatureValue.CONST_METRIC_DATA)
-        return cls(
-            values=metric_data[0],
-            estimates=metric_data[1]
-        )
+        return cls(values=metric_data[0], estimates=metric_data[1])
 
     def add_to_figure(self, fig: Figure, xaxis: int, yaxis: int):
         xaxis_str, yaxis_str, x_str, y_str = self.get_x_y_str_axes(xaxis, yaxis)
-        if type(self.values) == list and len(self.values) > 0 and \
-                type(self.estimates) == list and len(self.estimates) > 0:
+        if (
+            type(self.values) == list
+            and len(self.values) > 0
+            and type(self.estimates) == list
+            and len(self.estimates) > 0
+        ):
             y_axis = [value for value in self.values]
             x_axis = [estimate for estimate in self.estimates]
             fig.add_bar(

ads/feature_store/statistics/feature_stat.py

@@ -51,10 +51,14 @@ def __init__(
         self.box_plot = box_plot
 
     @classmethod
-    def from_json(cls, feature_name: str, json_dict: dict, version: int) -> "FeatureStatistics":
+    def from_json(
+        cls, feature_name: str, json_dict: dict, version: int
+    ) -> "FeatureStatistics":
         if json_dict is not None:
             frequency_distribution = FrequencyDistribution.from_json(
-                json_dict.get(cls.CONST_FREQUENCY_DISTRIBUTION), version, ignore_errors=True,
+                json_dict.get(cls.CONST_FREQUENCY_DISTRIBUTION),
+                version,
+                ignore_errors=True,
             )
 
             # inject box points for boxplot creation
@@ -70,7 +74,8 @@ def from_json(cls, feature_name: str, json_dict: dict, version: int) -> "Feature
                 ),
                 frequency_distribution,
                 ProbabilityDistribution.from_json(
-                    json_dict.get(cls.CONST_PROBABILITY_DISTRIBUTION), version,
+                    json_dict.get(cls.CONST_PROBABILITY_DISTRIBUTION),
+                    version,
                     ignore_errors=True,
                 ),
                 BoxPlot.from_json(json_dict, version, ignore_errors=True),