ODSC-47682: Adding unit/int tests for statistics

Author: harsh97

ads/feature_store/statistics/charts/abstract_feature_stat.py renamed to ads/feature_store/statistics/abs_feature_value.py

@@ -16,40 +16,23 @@
     )
 
 
-class AbsFeatureStat:
-    class ValidationFailedException(Exception):
-        def __init__(self):
-            pass
-
+class AbsFeatureValue:
     def __init__(self):
         self.__validate__()
 
     @abstractmethod
     def __validate__(self):
         pass
 
-    @abstractmethod
-    def add_to_figure(self, fig: Figure, xaxis: int, yaxis: int):
-        pass
-
     @classmethod
     @abstractmethod
     def __from_json__(cls, json_dict: dict):
         pass
 
-    @staticmethod
-    def get_x_y_str_axes(xaxis: int, yaxis: int) -> ():
-        return (
-            ("xaxis" + str(xaxis + 1)),
-            ("yaxis" + str(yaxis + 1)),
-            ("x" + str(xaxis + 1)),
-            ("y" + str(yaxis + 1)),
-        )
-
     @classmethod
     def from_json(
         cls, json_dict: dict, ignore_errors: bool = False
-    ) -> Union["AbsFeatureStat", None]:
+    ) -> Union["AbsFeatureValue", None]:
         try:
             return cls.__from_json__(json_dict=json_dict)
         except Exception as e:

ads/feature_store/statistics/charts/abstract_feature_plot.py

@@ -0,0 +1,37 @@
+#!/usr/bin/env python
+# -*- coding: utf-8; -*-
+# Copyright (c) 2023 Oracle and/or its affiliates.
+# Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
+import abc
+
+from abc import abstractmethod
+from ads.feature_store.statistics.abs_feature_value import AbsFeatureValue
+from ads.common.decorator.runtime_dependency import OptionalDependency
+
+try:
+    from plotly.graph_objs import Figure
+except ModuleNotFoundError:
+    raise ModuleNotFoundError(
+        f"The `plotly` module was not found. Please run `pip install "
+        f"{OptionalDependency.FEATURE_STORE}`."
+    )
+
+
+class AbsFeaturePlot(abc.ABC, AbsFeatureValue):
+    @abstractmethod
+    def add_to_figure(self, fig: Figure, xaxis: int, yaxis: int):
+        pass
+
+    @classmethod
+    @abstractmethod
+    def __from_json__(cls, json_dict: dict):
+        pass
+
+    @staticmethod
+    def get_x_y_str_axes(xaxis: int, yaxis: int) -> ():
+        return (
+            ("xaxis" + str(xaxis + 1)),
+            ("yaxis" + str(yaxis + 1)),
+            ("x" + str(xaxis + 1)),
+            ("y" + str(yaxis + 1)),
+        )

ads/feature_store/statistics/charts/box_plot.py

@@ -2,10 +2,12 @@
 # -*- coding: utf-8; -*-
 # Copyright (c) 2023 Oracle and/or its affiliates.
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
-from typing import List
+from typing import List, Union
+
+from ads.feature_store.statistics.abs_feature_value import AbsFeatureValue
 
 from ads.common.decorator.runtime_dependency import OptionalDependency
-from ads.feature_store.statistics.charts.abstract_feature_stat import AbsFeatureStat
+from ads.feature_store.statistics.charts.abstract_feature_plot import AbsFeaturePlot
 from ads.feature_store.statistics.charts.frequency_distribution import (
     FrequencyDistribution,
 )
@@ -20,7 +22,7 @@
     )
 
 
-class BoxPlot(AbsFeatureStat):
+class BoxPlot(AbsFeaturePlot):
     CONST_MIN = "Min"
     CONST_MAX = "Max"
     CONST_QUARTILES = "Quartiles"
@@ -30,7 +32,7 @@ class BoxPlot(AbsFeatureStat):
     CONST_IQR = "IQR"
     CONST_BOX_POINTS = "box_points"
 
-    class Quartiles:
+    class Quartiles(AbsFeatureValue):
         CONST_Q1 = "q1"
         CONST_Q2 = "q2"
         CONST_Q3 = "q3"
@@ -39,15 +41,20 @@ def __init__(self, q1: float, q2: float, q3: float):
             self.q1 = q1
             self.q2 = q2
             self.q3 = q3
+            super().__init__()
 
         @classmethod
-        def from_json(cls, json_dict: dict) -> "BoxPlot.Quartiles":
+        def __from_json__(cls, json_dict: dict) -> "BoxPlot.Quartiles":
             return cls(
                 json_dict.get(cls.CONST_Q1),
                 json_dict.get(cls.CONST_Q2),
                 json_dict.get(cls.CONST_Q3),
             )
 
+        def __validate__(self):
+            assert type(self.q1) == type(self.q2) == type(self.q3) == int or float
+            assert self.q3 >= self.q2 >= self.q1
+
     def __init__(
         self,
         mean: float,
@@ -67,14 +74,14 @@ def __init__(
         super().__init__()
 
     def __validate__(self):
-        if (
-            self.q1 is None
-            or self.q3 is None
-            or self.iqr is None
-            or type(self.box_points) is not list
-            or len(self.box_points) == 0
-        ):
-            return self.ValidationFailedException()
+        assert self.q1 is not None
+        assert self.q3 is not None
+        assert self.iqr is not None
+        assert self.q3 is not None
+        assert self.median is not None
+        assert self.mean is not None
+        assert type(self.box_points) is list
+        assert len(self.box_points) > 0
 
     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)

ads/feature_store/statistics/charts/frequency_distribution.py

@@ -5,7 +5,7 @@
 
 from typing import List
 from ads.common.decorator.runtime_dependency import OptionalDependency
-from ads.feature_store.statistics.charts.abstract_feature_stat import AbsFeatureStat
+from ads.feature_store.statistics.charts.abstract_feature_plot import AbsFeaturePlot
 
 try:
     from plotly.graph_objs import Figure
@@ -16,24 +16,21 @@
     )
 
 
-class FrequencyDistribution(AbsFeatureStat):
+class FrequencyDistribution(AbsFeaturePlot):
     CONST_FREQUENCY = "frequency"
     CONST_BINS = "bins"
     CONST_FREQUENCY_DISTRIBUTION_TITLE = "Frequency Distribution"
 
-    def __validate__(self):
-        if not (
-            type(self.frequency) == list
-            and type(self.bins) == list
-            and 0 < len(self.frequency) == len(self.bins) > 0
-        ):
-            raise self.ValidationFailedException()
-
     def __init__(self, frequency: List, bins: List):
         self.frequency = frequency
         self.bins = bins
         super().__init__()
 
+    def __validate__(self):
+        assert type(self.frequency) == list
+        assert type(self.bins) == list
+        assert 0 < len(self.frequency) == len(self.bins) > 0
+
     @classmethod
     def __from_json__(cls, json_dict: dict) -> "FrequencyDistribution":
         return FrequencyDistribution(

ads/feature_store/statistics/charts/probability_distribution.py

@@ -5,7 +5,7 @@
 from typing import List
 
 from ads.common.decorator.runtime_dependency import OptionalDependency
-from ads.feature_store.statistics.charts.abstract_feature_stat import AbsFeatureStat
+from ads.feature_store.statistics.charts.abstract_feature_plot import AbsFeaturePlot
 
 try:
     from plotly.graph_objs import Figure
@@ -16,15 +16,7 @@
     )
 
 
-class ProbabilityDistribution(AbsFeatureStat):
-    def __validate__(self):
-        if not (
-            type(self.density) == list
-            and type(self.bins) == list
-            and 0 < len(self.density) == len(self.bins) > 0
-        ):
-            raise self.ValidationFailedException()
-
+class ProbabilityDistribution(AbsFeaturePlot):
     CONST_DENSITY = "density"
     CONST_BINS = "bins"
     CONST_PROBABILITY_DISTRIBUTION_TITLE = "Probability Distribution"
@@ -34,6 +26,11 @@ def __init__(self, density: List, bins: List):
         self.bins = bins
         super().__init__()
 
+    def __validate__(self):
+        assert type(self.density) == list
+        assert type(self.bins) == list
+        assert 0 < len(self.density) == len(self.bins) > 0
+
     @classmethod
     def __from_json__(cls, json_dict: dict) -> "ProbabilityDistribution":
         return cls(

ads/feature_store/statistics/charts/top_k_frequent_elements.py

@@ -3,9 +3,12 @@
 # Copyright (c) 2023 Oracle and/or its affiliates.
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
 from typing import List
+
+from ads.feature_store.statistics.abs_feature_value import AbsFeatureValue
+
 from ads.common.decorator.runtime_dependency import OptionalDependency
 
-from ads.feature_store.statistics.charts.abstract_feature_stat import AbsFeatureStat
+from ads.feature_store.statistics.charts.abstract_feature_plot import AbsFeaturePlot
 
 try:
     from plotly.graph_objs import Figure
@@ -16,15 +19,11 @@
     )
 
 
-class TopKFrequentElements(AbsFeatureStat):
-    def __validate__(self):
-        if not (type(self.elements) == list and len(self.elements) > 0):
-            raise self.ValidationFailedException
-
+class TopKFrequentElements(AbsFeaturePlot):
     CONST_VALUE = "value"
     CONST_TOP_K_FREQUENT_TITLE = "Top K Frequent Elements"
 
-    class TopKFrequentElement:
+    class TopKFrequentElement(AbsFeatureValue):
         CONST_VALUE = "value"
         CONST_ESTIMATE = "estimate"
         CONST_LOWER_BOUND = "lower_bound"
@@ -37,9 +36,14 @@ def __init__(
             self.estimate = estimate
             self.lower_bound = lower_bound
             self.upper_bound = upper_bound
+            super().__init__()
+
+        def __validate__(self):
+            assert type(self.value) == str and len(self.value) > 0
+            assert type(self.estimate) == int and self.estimate >= 0
 
         @classmethod
-        def from_json(
+        def __from_json__(
             cls, json_dict: dict
         ) -> "TopKFrequentElements.TopKFrequentElement":
             return cls(
@@ -53,6 +57,12 @@ def __init__(self, elements: List[TopKFrequentElement]):
         self.elements = elements
         super().__init__()
 
+    def __validate__(self):
+        assert type(self.elements) == list
+        assert len(self.elements) > 0
+        for element in self.elements:
+            assert element is not None
+
     @classmethod
     def __from_json__(cls, json_dict: dict) -> "TopKFrequentElements":
         elements = json_dict.get(cls.CONST_VALUE)

ads/feature_store/statistics/feature_stat.py

@@ -5,7 +5,7 @@
 
 from ads.common.decorator.runtime_dependency import OptionalDependency
 from typing import List
-from ads.feature_store.statistics.charts.abstract_feature_stat import AbsFeatureStat
+from ads.feature_store.statistics.charts.abstract_feature_plot import AbsFeaturePlot
 from ads.feature_store.statistics.charts.box_plot import BoxPlot
 from ads.feature_store.statistics.charts.frequency_distribution import (
     FrequencyDistribution,
@@ -79,7 +79,7 @@ def from_json(cls, feature_name: str, json_dict: dict) -> "FeatureStatistics":
             return cls(feature_name)
 
     @property
-    def __feature_stat_objects__(self) -> List[AbsFeatureStat]:
+    def __feature_stat_objects__(self) -> List[AbsFeaturePlot]:
         return [
             stat
             for stat in [
@@ -101,14 +101,15 @@ def next_graph_position_generator():
         if len(self.__feature_stat_objects__) > 0:
             fig = make_subplots(cols=3, column_titles=[" "] * 3)
             for idx, stat in zip(
-                next_graph_position_generator(),
-                [stat for stat in self.__feature_stat_objects__ if stat is not None],
+                next_graph_position_generator(), self.__feature_stat_objects__
             ):
                 stat.add_to_figure(fig, idx, idx)
 
             fig.layout.title = self.CONST_TITLE_FORMAT.format(self.feature_name)
             fig.update_layout(title_font_size=20)
+            # Center align the title
             fig.update_layout(title_x=0.5)
+            # Disable legend for unrelated plots
             fig.update_layout(showlegend=False)
             plotly.offline.iplot(
                 fig,

ads/feature_store/statistics/generic_feature_value.py

@@ -1,17 +1,24 @@
 #!/usr/bin/env python
 # -*- coding: utf-8; -*-
+from ads.feature_store.statistics.abs_feature_value import AbsFeatureValue
 
 
 # Copyright (c) 2023 Oracle and/or its affiliates.
 # Licensed under the Universal Permissive License v 1.0 as shown at https://oss.oracle.com/licenses/upl/
-class GenericFeatureValue:
+class GenericFeatureValue(AbsFeatureValue):
     CONST_VALUE = "value"
 
     def __init__(self, val: any):
         self.val = val
+        super().__init__()
+
+    def __validate__(self):
+        pass
 
     @classmethod
-    def from_json(cls, json_dict: dict) -> "GenericFeatureValue":
-        return GenericFeatureValue(
-            val=json_dict.get(cls.CONST_VALUE),
-        )
+    def __from_json__(cls, json_dict: dict) -> "GenericFeatureValue":
+        val = None
+        if type(json_dict) == dict:
+            val = json_dict.get(cls.CONST_VALUE)
+
+        return GenericFeatureValue(val=val)

tests/integration/feature_store/test_dataset_statistics.py

@@ -67,7 +67,8 @@ def test_dataset_statistics_with_default_config(self):
         stat_obj = dataset.get_statistics()
         assert stat_obj is not None
         assert len(stat_obj.to_pandas().columns) == 6
-
+        # Validate visualisation is possible
+        dataset.get_statistics().to_viz()
         self.clean_up_dataset(dataset)
         self.clean_up_feature_group(fg)
         self.clean_up_entity(entity)

tests/integration/feature_store/test_feature_group_statistics.py

@@ -61,7 +61,8 @@ def test_feature_group_statistics_with_default_config(self):
         stat_obj = fg.get_statistics()
         assert stat_obj.content is not None
         assert len(stat_obj.to_pandas().columns) == 6
-
+        # Validate visualisation is possible
+        fg.get_statistics().to_viz()
         self.clean_up_feature_group(fg)
         self.clean_up_entity(entity)
         self.clean_up_feature_store(fs)