Add kscomplement fix

sdmetrics/single_column/statistical/kscomplement.py

@@ -1,5 +1,7 @@
 """Kolmogorov-Smirnov test based Metric."""
 
+import sys
+
 import numpy as np
 import pandas as pd
 from scipy.stats import ks_2samp
@@ -58,6 +60,9 @@ def compute(real_data, synthetic_data):
             synthetic_data = pd.to_numeric(synthetic_data)
 
         try:
+            max_decimals = sys.float_info.dig - 1
+            real_data = real_data.round(max_decimals)
+            synthetic_data = synthetic_data.round(max_decimals)
             statistic, _ = ks_2samp(real_data, synthetic_data)
         except ValueError as e:
             if str(e) == 'Data passed to ks_2samp must not be empty':

tests/integration/reports/multi_table/test_quality_report.py

@@ -334,11 +334,11 @@ def test_quality_report_with_errors():
         'Error': [
             None,
             None,
-            "TypeError: '<' not supported between instances of 'int' and 'str'",
+            "TypeError: can't multiply sequence by non-int of type 'float'",
             np.nan,
             np.nan,
-            "TypeError: '<' not supported between instances of 'Timestamp' and 'str'",
-            "TypeError: '<' not supported between instances of 'float' and 'str'",
+            "TypeError: can't multiply sequence by non-int of type 'float'",
+            "TypeError: can't multiply sequence by non-int of type 'float'",
             None,
         ],
     })

tests/integration/reports/single_table/_properties/test_column_shapes.py

@@ -85,10 +85,8 @@ def test_get_score_errors(self):
         # Run
         column_shape_property = ColumnShapes()
 
-        expected_message_1 = (
-            "TypeError: '<' not supported between instances of 'Timestamp' and 'int'"
-        )
-        expected_message_2 = "TypeError: '<' not supported between instances of 'str' and 'float'"
+        expected_message_1 = "TypeError: unsupported operand type(s) for *: 'Timestamp' and 'float'"
+        expected_message_2 = "TypeError: can't multiply sequence by non-int of type 'float'"
 
         score = column_shape_property.get_score(real_data, synthetic_data, metadata)
 

tests/integration/single_column/statistical/test_kscomplement.py

@@ -46,3 +46,10 @@ def test_bad(array_like):
 
     assert 0.0 <= output < 0.5
     assert 0.0 <= normalized < 0.5
+
+
+def test_one_float_value():
+    real = pd.Series([0.3 - 0.2])
+    synth = pd.Series([0.2 - 0.1])
+    output = KSComplement.compute(real, synth)
+    assert output == 1

tests/unit/reports/single_table/_properties/test_column_shapes.py

@@ -108,7 +108,7 @@ def test__generate_details_error(self):
         result = column_shape_property._generate_details(real_data, synthetic_data, metadata)
 
         # Assert
-        expected_message = "TypeError: '<' not supported between instances of 'str' and 'int'"
+        expected_message = "TypeError: can't multiply sequence by non-int of type 'float'"
         result_nan = result.loc[pd.isna(result['Score'])]
         column_names_nan = result_nan['Column'].tolist()
         error_message = result_nan['Error'].tolist()