Merge 37c250f into 73abc56

.bumpversion.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 0.3.3-dev1
+current_version = 0.3.3-dev2
 commit = True
 tag = False
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\-(?P<release>[a-z]+)(?P<build>\d+))?

docs/conf.py

@@ -119,7 +119,7 @@ def setup(app):
 # built documents.
 #
 # The short X.Y version.
-version = "0.3.3-dev1"
+version = "0.3.3-dev2"
 # The full version, including alpha/beta/rc tags.
 release = ""  # Is set by calling `setup.py docs`
 

setup.cfg

@@ -4,7 +4,7 @@
 
 [metadata]
 name = whylogs
-version = 0.3.3-dev1
+version = 0.3.3-dev2
 description = Profile and monitor your ML data pipeline end-to-end
 author = WhyLabs.ai
 author-email = support@whylabs.ai

src/whylogs/_version.py

@@ -1,3 +1,3 @@
 """WhyLabs version number."""
 
-__version__ = "0.3.3-dev1"
+__version__ = "0.3.3-dev2"

src/whylogs/core/columnprofile.py

@@ -6,10 +6,9 @@
 from whylogs.core.statistics.hllsketch import HllSketch
 from whylogs.core.statistics.constraints import ValueConstraints, SummaryConstraints, SummaryConstraint
 from whylogs.core.types import TypedDataConverter
-from whylogs.proto import ColumnMessage, ColumnSummary, InferredType, Op
+from whylogs.proto import ColumnMessage, ColumnSummary, InferredType, Op, UniqueCountSummary
 from whylogs.util.dsketch import FrequentItemsSketch
 
-
 import pandas as pd
 
 _TYPES = InferredType.Type
@@ -48,15 +47,15 @@ class ColumnProfile:
     """
 
     def __init__(
-        self,
-        name: str,
-        number_tracker: NumberTracker = None,
-        string_tracker: StringTracker = None,
-        schema_tracker: SchemaTracker = None,
-        counters: CountersTracker = None,
-        frequent_items: FrequentItemsSketch = None,
-        cardinality_tracker: HllSketch = None,
-        constraints: ValueConstraints = None,
+            self,
+            name: str,
+            number_tracker: NumberTracker = None,
+            string_tracker: StringTracker = None,
+            schema_tracker: SchemaTracker = None,
+            counters: CountersTracker = None,
+            frequent_items: FrequentItemsSketch = None,
+            cardinality_tracker: HllSketch = None,
+            constraints: ValueConstraints = None,
     ):
         # Handle default values
         if counters is None:
@@ -113,6 +112,19 @@ def track(self, value):
 
         self.constraints.update(typed_data)
 
+    def _unique_count_summary(self) -> UniqueCountSummary:
+        cardinality_summary = self.cardinality_tracker.to_summary(_UNIQUE_COUNT_BOUNDS_STD)
+        if cardinality_summary:
+            return cardinality_summary
+
+        inferred_type = self.schema_tracker.infer_type()
+        if inferred_type.type == _TYPES.STRING:
+            cardinality_summary = self.string_tracker.theta_sketch.to_summary()
+        else:  # default is number summary
+            print("Inferred type: ", inferred_type)
+            cardinality_summary = self.number_tracker.theta_sketch.to_summary()
+        return cardinality_summary
+
     def to_summary(self):
         """
         Generate a summary of the statistics
@@ -129,8 +141,7 @@ def to_summary(self):
         opts = dict(
             counters=self.counters.to_protobuf(),
             frequent_items=self.frequent_items.to_summary(),
-            unique_count=self.cardinality_tracker.to_summary(
-                _UNIQUE_COUNT_BOUNDS_STD),
+            unique_count=self._unique_count_summary(),
         )
         if self.string_tracker is not None and self.string_tracker.count > 0:
             opts["string_summary"] = self.string_tracker.to_summary()

tests/unit/core/test_columnprofile.py

@@ -4,13 +4,13 @@
 from testutil import compare_frequent_items
 
 from whylogs.core import ColumnProfile
+from whylogs.core.statistics.hllsketch import HllSketch
 from whylogs.util.protobuf import message_to_dict
 import numpy as np
 import pandas as pd
 
 
 def test_all_numeric_types_get_tracked_by_number_tracker():
-
     all_values = [
         [1.0, 2.0, 3.0],
         [1, 2, 3],
@@ -118,8 +118,10 @@ def test_summary():
             "mean": 2.0,
             "stddev": 1.0,
             "isDiscrete": False,
-            "histogram": {"start": 1.0, "end": 3.0000003, "counts": ["3"], "max": 3.0, "min": 1.0, "bins": [1.0, 3.0000003], "n": "3", "width": 0.0, },
-            "quantiles": {"quantiles": [0.0, 0.01, 0.05, 0.25, 0.5, 0.75, 0.95, 0.99, 1.0], "quantileValues": [1.0, 1.0, 1.0, 1.0, 2.0, 3.0, 3.0, 3.0, 3.0], },
+            "histogram": {"start": 1.0, "end": 3.0000003, "counts": ["3"], "max": 3.0, "min": 1.0,
+                          "bins": [1.0, 3.0000003], "n": "3", "width": 0.0, },
+            "quantiles": {"quantiles": [0.0, 0.01, 0.05, 0.25, 0.5, 0.75, 0.95, 0.99, 1.0],
+                          "quantileValues": [1.0, 1.0, 1.0, 1.0, 2.0, 3.0, 3.0, 3.0, 3.0], },
             "uniqueCount": {"estimate": 3.0, "upper": 3.0, "lower": 3.0},
         },
     }
@@ -179,3 +181,36 @@ def test_merge():
     assert merged.number_tracker.ints.count == 0
     assert merged.number_tracker.floats.count == 4
     assert merged.string_tracker.count == 2
+
+
+def test_fallback_number_counter():
+    col = ColumnProfile("test")
+    vals = [1, 1.0, 2, 3, 4, 5, 6, 6.0, "text"]
+    for v in vals:
+        col.track(v)
+    col.cardinality_tracker = HllSketch()
+
+    summary = col.to_summary()
+    assert summary.unique_count.estimate == summary.number_summary.unique_count.estimate
+
+
+def test_fallback_string_counter():
+    col = ColumnProfile("test")
+    vals = ["a", "b", "c", "d", "e", "f", 1.0, 2.0]
+    for v in vals:
+        col.track(v)
+    col.cardinality_tracker = HllSketch()
+
+    summary = col.to_summary()
+    assert summary.unique_count.estimate == summary.string_summary.unique_count.estimate
+
+
+def test_fallback_fallbacks_to_number_counter():
+    col = ColumnProfile("test")
+    vals = ["a", "b", 1.0, 2.0]
+    for v in vals:
+        col.track(v)
+    col.cardinality_tracker = HllSketch()
+
+    summary = col.to_summary()
+    assert summary.unique_count.estimate == summary.number_summary.unique_count.estimate