Fix floating point

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/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/timeseries/test_inter_row_msas.py

@@ -71,6 +71,24 @@ def test_compute_with_log(self):
         # Assert
         assert score == 1
 
+    def test_compute_with_log_distinct_data(self):
+        """Test it with logarithmic transformation distinct data."""
+        # Setup
+        real_keys = pd.Series(['id1', 'id1', 'id1', 'id2', 'id2', 'id2'])
+        real_values = pd.Series([1, 2, 4, 12, 24, 48])
+        synthetic_keys = pd.Series(['id1', 'id1', 'id1', 'id2', 'id2', 'id2'])
+        synthetic_values = pd.Series([3, 6, 12, 5, 10, 20])
+
+        # Run
+        score = InterRowMSAS.compute(
+            real_data=(real_keys, real_values),
+            synthetic_data=(synthetic_keys, synthetic_values),
+            apply_log=True,
+        )
+
+        # Assert
+        assert score == 1
+
     def test_compute_different_n_rows_diff(self):
         """Test it with different n_rows_diff."""
         # Setup