rdt 1.15.0.dev0__tar.gz → 1.15.1.dev0__tar.gz

{rdt-1.15.0.dev0/rdt.egg-info → rdt-1.15.1.dev0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: rdt
-Version: 1.15.0.dev0
+Version: 1.15.1.dev0
 Summary: Reversible Data Transforms
 Author-email: "DataCebo, Inc." <info@sdv.dev>
 License: BSL-1.1
@@ -70,6 +70,7 @@ Requires-Dist: coverage<8,>=4.5.12; extra == "dev"
 Requires-Dist: tox<5,>=2.9.1; extra == "dev"
 Requires-Dist: tabulate<1,>=0.8.9; extra == "dev"
 Requires-Dist: invoke; extra == "dev"
+Dynamic: license-file
 
 <div align="center">
 <br/>

{rdt-1.15.0.dev0 → rdt-1.15.1.dev0}/pyproject.toml

@@ -144,7 +144,7 @@ collect_ignore = ['pyproject.toml']
 exclude_lines = ['NotImplementedError()']
 
 [tool.bumpversion]
-current_version = "1.15.0.dev0"
+current_version = "1.15.1.dev0"
 parse = '(?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\.(?P<release>[a-z]+)(?P<candidate>\d+))?'
 serialize = [
     '{major}.{minor}.{patch}.{release}{candidate}',

{rdt-1.15.0.dev0 → rdt-1.15.1.dev0}/rdt/__init__.py

@@ -4,7 +4,7 @@
 
 __author__ = 'DataCebo, Inc.'
 __email__ = 'info@sdv.dev'
-__version__ = '1.15.0.dev0'
+__version__ = '1.15.1.dev0'
 
 
 import sys

{rdt-1.15.0.dev0 → rdt-1.15.1.dev0}/rdt/transformers/base.py

@@ -327,19 +327,19 @@ class BaseTransformer:
         custom_args = []
         args = inspect.getfullargspec(self.__init__)
         keys = args.args[1:]
-        defaults = args.defaults or []
-        defaults = dict(zip(keys, defaults))
         instanced = {
             key: getattr(self, key)
             for key in keys
             if key != 'model_missing_values' and hasattr(self, key)  # Remove after deprecation
         }
 
+        defaults = args.defaults or []
+        defaults = dict(zip(keys, defaults))
         if defaults == instanced:
             return f'{class_name}()'
 
         for arg, value in instanced.items():
-            if defaults[arg] != value:
+            if arg not in defaults or defaults[arg] != value:
                 custom_args.append(f'{arg}={repr(value)}')
 
         args_string = ', '.join(custom_args)

{rdt-1.15.0.dev0 → rdt-1.15.1.dev0}/rdt/transformers/pii/anonymizer.py

@@ -155,6 +155,7 @@ class AnonymizedFaker(BaseTransformer):
 
         self.missing_value_generation = missing_value_generation
         self._nan_frequency = 0.0
+        self._unique_categories = None
 
     @classmethod
     def get_supported_sdtypes(cls):
@@ -192,11 +193,11 @@ class AnonymizedFaker(BaseTransformer):
                 faker_attr = self.faker.unique
             else:
                 faker_attr = self.faker
+
         except AttributeError:
             faker_attr = self.faker.unique if self.enforce_uniqueness else self.faker
 
         result = getattr(faker_attr, self.function_name)(**self.function_kwargs)
-
         if isinstance(result, Iterable) and not isinstance(result, str):
             result = ', '.join(map(str, result))
 
@@ -236,39 +237,47 @@ class AnonymizedFaker(BaseTransformer):
 
     def _reverse_transform_cardinality_rule_match(self, sample_size):
         """Reverse transform the data when the cardinality rule is 'match'."""
-        reverse_transformed = np.array([], dtype=object)
-        if self.missing_value_generation == 'random':
-            num_nans = int(self._nan_frequency * sample_size)
-            reverse_transformed = np.concatenate([
-                reverse_transformed,
-                np.full(num_nans, np.nan),
-            ])
-        else:
-            num_nans = 0
+        num_nans = self._calculate_num_nans(sample_size)
+        reverse_transformed = self._generate_nans(num_nans)
 
         if sample_size <= num_nans:
             return reverse_transformed
 
-        if sample_size < num_nans + self._data_cardinality:
-            unique_categories = self._get_unique_categories(sample_size - num_nans)
-            reverse_transformed = np.concatenate([
-                reverse_transformed,
-                unique_categories,
-            ])
-        else:
-            unique_categories = self._get_unique_categories(self._data_cardinality)
-            num_copies = sample_size - self._data_cardinality - num_nans
-            copies = np.random.choice(unique_categories, num_copies)
-            reverse_transformed = np.concatenate([
-                reverse_transformed,
-                unique_categories,
-                copies,
-            ])
+        remaining_samples = sample_size - num_nans
+        sampled_values = self._generate_cardinality_match_values(remaining_samples)
 
+        reverse_transformed = np.concatenate([reverse_transformed, sampled_values])
         np.random.shuffle(reverse_transformed)
 
         return reverse_transformed
 
+    def _calculate_num_nans(self, sample_size):
+        """Calculate the number of NaN values to generate."""
+        if self.missing_value_generation == 'random':
+            return int(self._nan_frequency * sample_size)
+
+        return 0
+
+    def _generate_nans(self, num_nans):
+        """Generate an array of NaN values."""
+        return np.full(num_nans, np.nan, dtype=object)
+
+    def _generate_cardinality_match_values(self, remaining_samples):
+        """Generate sampled values while ensuring each unique category appears at least once."""
+        # Backwards compatibility requires us to generate the values at this point
+        if self._unique_categories is None:
+            self._unique_categories = self._get_unique_categories(self._data_cardinality)
+
+        unique_categories = np.array(self._unique_categories)
+        if remaining_samples <= len(unique_categories):
+            return np.random.choice(unique_categories, remaining_samples, replace=False)
+
+        # Ensure all unique categories appear at least once
+        extra_samples_needed = remaining_samples - len(unique_categories)
+        extra_samples = np.random.choice(unique_categories, extra_samples_needed, replace=True)
+
+        return np.concatenate((unique_categories, extra_samples))
+
     def _reverse_transform(self, data):
         """Generate new anonymized data using a ``faker.provider.function``.
 
@@ -328,6 +337,7 @@ class AnonymizedFaker(BaseTransformer):
                 raise TransformerInputError(
                     'Cardinality "match" rule must specify a cardinality value.'
                 )
+
         self._data_cardinality = cardinality
         self._nan_frequency = nan_frequency
 

{rdt-1.15.0.dev0 → rdt-1.15.1.dev0}/rdt/transformers/utils.py

@@ -15,7 +15,7 @@ import sre_parse  # isort:skip
 
 LOGGER = logging.getLogger(__name__)
 
-MAX_DECIMALS = sys.float_info.dig - 1
+MAX_DECIMALS = sys.float_info.dig
 DEPRECATED_SDTYPES_MAPPING = {'text': 'id'}
 
 
@@ -270,17 +270,19 @@ def learn_rounding_digits(data):
         data = data.to_numpy()
     roundable_data = data[~(np.isinf(data.astype(float)) | pd.isna(data))]
 
-    # Doesn't contain numbers
+    # Empty dataset
     if len(roundable_data) == 0:
         return None
 
-    # Doesn't contain decimal digits
-    if (roundable_data == roundable_data.astype(int)).all():
-        return 0
+    if roundable_data.dtype == 'object':
+        roundable_data = roundable_data.astype(float)
 
     # Try to round to fewer digits
-    if (roundable_data == roundable_data.round(MAX_DECIMALS)).all():
-        for decimal in range(MAX_DECIMALS + 1):
+    highest_int = int(np.max(np.abs(roundable_data)))
+    most_digits = len(str(highest_int)) if highest_int != 0 else 0
+    max_decimals = max(0, MAX_DECIMALS - most_digits)
+    if (roundable_data == roundable_data.round(max_decimals)).all():
+        for decimal in range(max_decimals + 1):
             if (roundable_data == roundable_data.round(decimal)).all():
                 return decimal
 

{rdt-1.15.0.dev0 → rdt-1.15.1.dev0/rdt.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.2
+Metadata-Version: 2.4
 Name: rdt
-Version: 1.15.0.dev0
+Version: 1.15.1.dev0
 Summary: Reversible Data Transforms
 Author-email: "DataCebo, Inc." <info@sdv.dev>
 License: BSL-1.1
@@ -70,6 +70,7 @@ Requires-Dist: coverage<8,>=4.5.12; extra == "dev"
 Requires-Dist: tox<5,>=2.9.1; extra == "dev"
 Requires-Dist: tabulate<1,>=0.8.9; extra == "dev"
 Requires-Dist: invoke; extra == "dev"
+Dynamic: license-file
 
 <div align="center">
 <br/>