Update logic

sdv-dev · Jan 11, 2024 · d7f7302 · d7f7302
1 parent de011e2
commit d7f7302
Showing 1 changed file with 16 additions and 37 deletions.
diff --git a/rdt/transformers/text.py b/rdt/transformers/text.py
@@ -154,47 +154,26 @@ def _reverse_transform(self, data):
         else:
             sample_size = self.data_length
 
-        if sample_size > self.generator_size:
-            if self.enforce_uniqueness:
-                raise TransformerProcessingError(
-                    f'The regex is not able to generate {sample_size} unique values. '
-                    f"Please use a different regex for column ('{self.get_input_column()}')."
-                )
-
-            warnings.warn(
-                f"The data has {sample_size} rows but the regex for '{self.get_input_column()}' "
-                f'can only create {self.generator_size} unique values. Some values in '
-                f"'{self.get_input_column()}' may be repeated."
-            )
-
-        remaining = self.generator_size - self.generated
         if sample_size > self.generator_size - self.generated:
             if self.enforce_uniqueness:
-                raise TransformerProcessingError(
-                    f'The regex generator is not able to generate {sample_size} new unique '
-                    f'values (only {remaining} unique value left). Please use '
-                    "'reset_randomization' in order to restart the generator."
+                warnings.warn(
+                    f"The regex for '{self.get_input_column()}' can only generate {sample_size} "
+                    "unique values. Additional values may not exactly follow the provided regex."
+                )
+            else:
+                warnings.warn(
+                    f"The data has {sample_size} rows but the regex for '{self.get_input_column()}' "
+                    f'can only create {self.generator_size} unique values. Some values in '
+                    f"'{self.get_input_column()}' may be repeated."
                 )
 
-            self.reset_randomization()
-            remaining = self.generator_size
-
-        if remaining >= sample_size:
-            reverse_transformed = np.array([
-                next(self.generator)
-                for _ in range(sample_size)
-            ], dtype=object)
-
-            self.generated += sample_size
+        generated_values = list(self.generator)
+        reverse_transformed = []
+        while len(reverse_transformed) < sample_size:
+            remaining_samples = sample_size - len(reverse_transformed)
+            reverse_transformed.extend(generated_values[:remaining_samples])
+            self.generated += remaining_samples
 
-        else:
-            self.generated = self.generator_size
-            generated_values = list(self.generator)
-            reverse_transformed = []
-            while len(reverse_transformed) < sample_size:
-                remaining_samples = sample_size - len(reverse_transformed)
-                reverse_transformed.extend(generated_values[:remaining_samples])
-
-            reverse_transformed = np.array(reverse_transformed, dtype=object)
+        reverse_transformed = np.array(reverse_transformed, dtype=object)
 
         return reverse_transformed