rdt 1.11.1.dev0__tar.gz → 1.12.0.dev0__tar.gz

{rdt-1.11.1.dev0/rdt.egg-info → rdt-1.12.0.dev0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: rdt
-Version: 1.11.1.dev0
+Version: 1.12.0.dev0
 Summary: Reversible Data Transforms
 Author-email: "DataCebo, Inc." <info@sdv.dev>
 License: BSL-1.1
@@ -71,12 +71,12 @@ Requires-Dist: flake8-multiline-containers<0.1,>=0.0.18; extra == "dev"
 Requires-Dist: flake8-mutable<1.3,>=1.2.0; extra == "dev"
 Requires-Dist: flake8-expression-complexity<0.1,>=0.0.9; extra == "dev"
 Requires-Dist: flake8-print<4.1,>=4.0.0; extra == "dev"
-Requires-Dist: flake8-pytest-style<3,>=1.5.0; extra == "dev"
+Requires-Dist: flake8-pytest-style<3,>=2.0.0; extra == "dev"
 Requires-Dist: flake8-quotes<4,>=3.3.0; extra == "dev"
 Requires-Dist: flake8-sfs<2,>=0.0.3; extra == "dev"
 Requires-Dist: flake8-variables-names<0.1,>=0.0.4; extra == "dev"
 Requires-Dist: dlint<1,>=0.11.0; extra == "dev"
-Requires-Dist: isort<6,>=4.3.4; extra == "dev"
+Requires-Dist: isort<6,>=5.13.2; extra == "dev"
 Requires-Dist: pandas-vet<2024,>=0.2.3; extra == "dev"
 Requires-Dist: pep8-naming<1,>=0.12.1; extra == "dev"
 Requires-Dist: pydocstyle<7,>=6.1.1; extra == "dev"

{rdt-1.11.1.dev0 → rdt-1.12.0.dev0}/pyproject.toml

@@ -86,12 +86,12 @@ dev = [
     'flake8-mutable>=1.2.0,<1.3',
     'flake8-expression-complexity>=0.0.9,<0.1',
     'flake8-print>=4.0.0,<4.1',
-    'flake8-pytest-style>=1.5.0,<3',
+    'flake8-pytest-style>=2.0.0,<3',
     'flake8-quotes>=3.3.0,<4',
     'flake8-sfs>=0.0.3,<2',
     'flake8-variables-names>=0.0.4,<0.1',
     'dlint>=0.11.0,<1',
-    'isort>=4.3.4,<6',
+    'isort>=5.13.2,<6',
     'pandas-vet>=0.2.3,<2024',
     'pep8-naming>=0.12.1,<1',
     'pydocstyle>=6.1.1,<7',
@@ -166,7 +166,7 @@ collect_ignore = ['pyproject.toml']
 exclude_lines = ['NotImplementedError()']
 
 [tool.bumpversion]
-current_version = "1.11.1.dev0"
+current_version = "1.12.0.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-1.11.1.dev0 → rdt-1.12.0.dev0}/rdt/__init__.py

@@ -5,7 +5,7 @@
 
 __author__ = 'DataCebo, Inc.'
 __email__ = 'info@sdv.dev'
-__version__ = '1.11.1.dev0'
+__version__ = '1.12.0.dev0'
 
 
 import sys
@@ -159,7 +159,7 @@ def _find_addons():
         try:
             addon = entry_point.load()
         except Exception:  # pylint: disable=broad-exception-caught
-            msg = f'Failed to load "{entry_point.name}" from "{entry_point.module_name}".'
+            msg = f'Failed to load "{entry_point.name}" from "{entry_point.version}".'
             warnings.warn(msg)
             continue
 

{rdt-1.11.1.dev0 → rdt-1.12.0.dev0}/rdt/transformers/categorical.py

@@ -351,7 +351,7 @@ class FrequencyEncoder(BaseTransformer):
             dict:
                 intervals for each categorical value (start, end).
         """
-        data = data.fillna(np.nan)
+        data = data.infer_objects().fillna(np.nan)
         frequencies = data.value_counts(dropna=False)
         augmented_frequencies = frequencies.to_frame()
         sortable_column_name = f'sortable_{frequencies.name}'
@@ -460,7 +460,9 @@ class FrequencyEncoder(BaseTransformer):
 
     def _transform_by_row(self, data):
         """Transform the data row by row."""
-        return data.fillna(np.nan).apply(self._get_value).to_numpy()
+        data = data.infer_objects().fillna(np.nan).apply(self._get_value).to_numpy()
+
+        return data
 
     def _transform(self, data):
         """Transform the categorical values to float representatives.
@@ -756,7 +758,7 @@ class LabelEncoder(BaseTransformer):
                 Data to fit the transformer to.
         """
         self.dtype = data.dtype
-        unique_data = pd.unique(data.fillna(np.nan))
+        unique_data = pd.unique(data.infer_objects().fillna(np.nan))
         unique_data = self._order_categories(unique_data)
         self.values_to_categories = dict(enumerate(unique_data))
         self.categories_to_values = {
@@ -779,7 +781,7 @@ class LabelEncoder(BaseTransformer):
         Returns:
             pd.Series
         """
-        mapped = data.fillna(np.nan).map(self.categories_to_values)
+        mapped = data.infer_objects().fillna(np.nan).map(self.categories_to_values)
         is_null = mapped.isna()
         if is_null.any():
             # Select only the first 5 unseen categories to avoid flooding the console.
@@ -879,7 +881,8 @@ class OrderedLabelEncoder(LabelEncoder):
                 Data to fit the transformer to.
         """
         self.dtype = data.dtype
-        data = data.fillna(np.nan)
+        data = data.infer_objects().fillna(np.nan)
+
         missing = list(data[~data.isin(self.order)].unique())
         if len(missing) > 0:
             raise TransformerInputError(

{rdt-1.11.1.dev0 → rdt-1.12.0.dev0}/rdt/transformers/null.py

@@ -143,7 +143,7 @@ class NullTransformer():
             data = data.mask(data.isna(), data_mask)
 
         elif isna.any() and self._missing_value_replacement is not None:
-            data = data.fillna(self._missing_value_replacement)
+            data = data.infer_objects().fillna(self._missing_value_replacement)
 
         if self._missing_value_generation == 'from_column':
             return pd.concat([data, isna.astype(np.float64)], axis=1).to_numpy()

{rdt-1.11.1.dev0 → rdt-1.12.0.dev0}/rdt/transformers/text.py

@@ -83,6 +83,11 @@ class RegexGenerator(BaseTransformer):
             Whether or not to ensure that the new generated data is all unique. If it isn't
             possible to create the requested number of rows, then an error will be raised.
             Defaults to ``False``.
+        generation_order (str):
+            String defining how to generate the output. If set to ``alphanumeric``, it will
+            generate the output in alphanumeric order (ie. 'aaa', 'aab' or '1', '2'...). If
+            set to ``scrambled``, the the output will be scrambled in order. Defaults to
+            ``alphanumeric``.
     """
 
     IS_GENERATOR = True
@@ -111,7 +116,8 @@ class RegexGenerator(BaseTransformer):
         state['generator'] = generator
         self.__dict__ = state
 
-    def __init__(self, regex_format='[A-Za-z]{5}', enforce_uniqueness=False):
+    def __init__(self, regex_format='[A-Za-z]{5}', enforce_uniqueness=False,
+                 generation_order='alphanumeric'):
         super().__init__()
         self.output_properties = {None: {'next_transformer': None}}
         self.enforce_uniqueness = enforce_uniqueness
@@ -120,6 +126,10 @@ class RegexGenerator(BaseTransformer):
         self.generator = None
         self.generator_size = None
         self.generated = None
+        if generation_order not in ['alphanumeric', 'scrambled']:
+            raise ValueError("generation_order must be one of 'alphanumeric' or 'scrambled'.")
+
+        self.generation_order = generation_order
 
     def reset_randomization(self):
         """Create a new generator and reset the generated values counter."""
@@ -222,4 +232,7 @@ class RegexGenerator(BaseTransformer):
                     remaining_samples = sample_size - len(reverse_transformed)
                     reverse_transformed.extend(generated_values[:remaining_samples])
 
+        if self.generation_order == 'scrambled':
+            np.random.shuffle(reverse_transformed)
+
         return np.array(reverse_transformed, dtype=object)

{rdt-1.11.1.dev0 → rdt-1.12.0.dev0}/rdt/transformers/utils.py

@@ -170,7 +170,7 @@ def fill_nan_with_none(data):
         data:
             Original data with nan values replaced by None.
     """
-    return data.fillna(np.nan).replace([np.nan], [None])
+    return data.infer_objects().fillna(np.nan).replace([np.nan], [None])
 
 
 def flatten_column_list(column_list):

{rdt-1.11.1.dev0 → rdt-1.12.0.dev0/rdt.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: rdt
-Version: 1.11.1.dev0
+Version: 1.12.0.dev0
 Summary: Reversible Data Transforms
 Author-email: "DataCebo, Inc." <info@sdv.dev>
 License: BSL-1.1
@@ -71,12 +71,12 @@ Requires-Dist: flake8-multiline-containers<0.1,>=0.0.18; extra == "dev"
 Requires-Dist: flake8-mutable<1.3,>=1.2.0; extra == "dev"
 Requires-Dist: flake8-expression-complexity<0.1,>=0.0.9; extra == "dev"
 Requires-Dist: flake8-print<4.1,>=4.0.0; extra == "dev"
-Requires-Dist: flake8-pytest-style<3,>=1.5.0; extra == "dev"
+Requires-Dist: flake8-pytest-style<3,>=2.0.0; extra == "dev"
 Requires-Dist: flake8-quotes<4,>=3.3.0; extra == "dev"
 Requires-Dist: flake8-sfs<2,>=0.0.3; extra == "dev"
 Requires-Dist: flake8-variables-names<0.1,>=0.0.4; extra == "dev"
 Requires-Dist: dlint<1,>=0.11.0; extra == "dev"
-Requires-Dist: isort<6,>=4.3.4; extra == "dev"
+Requires-Dist: isort<6,>=5.13.2; extra == "dev"
 Requires-Dist: pandas-vet<2024,>=0.2.3; extra == "dev"
 Requires-Dist: pep8-naming<1,>=0.12.1; extra == "dev"
 Requires-Dist: pydocstyle<7,>=6.1.1; extra == "dev"

{rdt-1.11.1.dev0 → rdt-1.12.0.dev0}/rdt.egg-info/requires.txt

@@ -48,12 +48,12 @@ flake8-multiline-containers<0.1,>=0.0.18
 flake8-mutable<1.3,>=1.2.0
 flake8-expression-complexity<0.1,>=0.0.9
 flake8-print<4.1,>=4.0.0
-flake8-pytest-style<3,>=1.5.0
+flake8-pytest-style<3,>=2.0.0
 flake8-quotes<4,>=3.3.0
 flake8-sfs<2,>=0.0.3
 flake8-variables-names<0.1,>=0.0.4
 dlint<1,>=0.11.0
-isort<6,>=4.3.4
+isort<6,>=5.13.2
 pandas-vet<2024,>=0.2.3
 pep8-naming<1,>=0.12.1
 pydocstyle<7,>=6.1.1