rdt 1.13.0.dev0__tar.gz → 1.13.1.dev0__tar.gz

{rdt-1.13.0.dev0/rdt.egg-info → rdt-1.13.1.dev0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: rdt
-Version: 1.13.0.dev0
+Version: 1.13.1.dev0
 Summary: Reversible Data Transforms
 Author-email: "DataCebo, Inc." <info@sdv.dev>
 License: BSL-1.1
@@ -39,8 +39,11 @@ Requires-Dist: scikit-learn>=1.1.3; python_version >= "3.11" and python_version
 Requires-Dist: scikit-learn>=1.3.1; python_version >= "3.12"
 Requires-Dist: Faker>=17
 Provides-Extra: copulas
-Requires-Dist: copulas>=0.11.0; extra == "copulas"
+Requires-Dist: copulas>=0.12.0; extra == "copulas"
+Provides-Extra: pyarrow
+Requires-Dist: pyarrow>=17.0.0; extra == "pyarrow"
 Provides-Extra: test
+Requires-Dist: rdt[pyarrow]; extra == "test"
 Requires-Dist: rdt[copulas]; extra == "test"
 Requires-Dist: pytest>=3.4.2; extra == "test"
 Requires-Dist: pytest-cov>=2.6.0; extra == "test"

{rdt-1.13.0.dev0 → rdt-1.13.1.dev0}/pyproject.toml

@@ -48,8 +48,10 @@ dependencies = [
 rdt = { main = 'rdt.cli.__main__:main' }
 
 [project.optional-dependencies]
-copulas = ['copulas>=0.11.0',]
+copulas = ['copulas>=0.12.0',]
+pyarrow = ['pyarrow>=17.0.0']
 test = [
+    'rdt[pyarrow]',
     'rdt[copulas]',
 
     'pytest>=3.4.2',
@@ -137,7 +139,7 @@ collect_ignore = ['pyproject.toml']
 exclude_lines = ['NotImplementedError()']
 
 [tool.bumpversion]
-current_version = "1.13.0.dev0"
+current_version = "1.13.1.dev0"
 parse = '(?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\.(?P<release>[a-z]+)(?P<candidate>\d+))?'
 serialize = [
     '{major}.{minor}.{patch}.{release}{candidate}',
@@ -203,10 +205,11 @@ select = [
     # print statements
     "T201",
     # pandas-vet
-    "PD"
+    "PD",
+    # numpy 2.0
+    "NPY201"
 ]
 ignore = [
-    "E501",
     # pydocstyle
     "D107",  # Missing docstring in __init__
     "D417",   # Missing argument descriptions in the docstring, this is a bug from pydocstyle: https://github.com/PyCQA/pydocstyle/issues/449

{rdt-1.13.0.dev0 → rdt-1.13.1.dev0}/rdt/__init__.py

@@ -4,7 +4,7 @@
 
 __author__ = 'DataCebo, Inc.'
 __email__ = 'info@sdv.dev'
-__version__ = '1.13.0.dev0'
+__version__ = '1.13.1.dev0'
 
 
 import sys

{rdt-1.13.0.dev0 → rdt-1.13.1.dev0}/rdt/transformers/base.py

@@ -343,7 +343,7 @@ class BaseTransformer:
         instanced = {
             key: getattr(self, key)
             for key in keys
-            if key != 'model_missing_values'  # Remove after deprecation
+            if key != 'model_missing_values' and hasattr(self, key)  # Remove after deprecation
         }
 
         if defaults == instanced:

{rdt-1.13.0.dev0 → rdt-1.13.1.dev0}/rdt/transformers/numerical.py

@@ -104,7 +104,7 @@ class FloatFormatter(BaseTransformer):
 
     def _validate_values_within_bounds(self, data):
         if not self.computer_representation.startswith('Float'):
-            fractions = data[~data.isna() & data % 1 != 0]
+            fractions = data[~data.isna() & (data != (data // 1))]
             if not fractions.empty:
                 raise ValueError(
                     f"The column '{data.name}' contains float values {fractions.tolist()}. "

{rdt-1.13.0.dev0 → rdt-1.13.1.dev0}/rdt/transformers/pii/anonymizer.py

@@ -133,8 +133,7 @@ class AnonymizedFaker(BaseTransformer):
         self.provider_name = provider_name if provider_name else 'BaseProvider'
         if self.provider_name != 'BaseProvider' and function_name is None:
             raise TransformerInputError(
-                'Please specify the function name to use from the '
-                f"'{self.provider_name}' provider."
+                f"Please specify the function name to use from the '{self.provider_name}' provider."
             )
 
         self.function_name = function_name if function_name else 'lexify'

{rdt-1.13.0.dev0 → rdt-1.13.1.dev0}/rdt/transformers/utils.py

@@ -254,6 +254,8 @@ def learn_rounding_digits(data):
     """
     # check if data has any decimals
     name = data.name
+    if str(data.dtype).endswith('[pyarrow]'):
+        data = data.to_numpy()
     roundable_data = data[~(np.isinf(data.astype(float)) | pd.isna(data))]
 
     # Doesn't contain numbers
@@ -261,7 +263,7 @@ def learn_rounding_digits(data):
         return None
 
     # Doesn't contain decimal digits
-    if ((roundable_data % 1) == 0).all():
+    if (roundable_data == roundable_data.astype(int)).all():
         return 0
 
     # Try to round to fewer digits

{rdt-1.13.0.dev0 → rdt-1.13.1.dev0/rdt.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: rdt
-Version: 1.13.0.dev0
+Version: 1.13.1.dev0
 Summary: Reversible Data Transforms
 Author-email: "DataCebo, Inc." <info@sdv.dev>
 License: BSL-1.1
@@ -39,8 +39,11 @@ Requires-Dist: scikit-learn>=1.1.3; python_version >= "3.11" and python_version
 Requires-Dist: scikit-learn>=1.3.1; python_version >= "3.12"
 Requires-Dist: Faker>=17
 Provides-Extra: copulas
-Requires-Dist: copulas>=0.11.0; extra == "copulas"
+Requires-Dist: copulas>=0.12.0; extra == "copulas"
+Provides-Extra: pyarrow
+Requires-Dist: pyarrow>=17.0.0; extra == "pyarrow"
 Provides-Extra: test
+Requires-Dist: rdt[pyarrow]; extra == "test"
 Requires-Dist: rdt[copulas]; extra == "test"
 Requires-Dist: pytest>=3.4.2; extra == "test"
 Requires-Dist: pytest-cov>=2.6.0; extra == "test"

{rdt-1.13.0.dev0 → rdt-1.13.1.dev0}/rdt.egg-info/requires.txt

@@ -26,7 +26,7 @@ scipy>=1.12.0
 scikit-learn>=1.3.1
 
 [copulas]
-copulas>=0.11.0
+copulas>=0.12.0
 
 [dev]
 rdt[test]
@@ -42,7 +42,11 @@ tox<5,>=2.9.1
 tabulate<1,>=0.8.9
 invoke
 
+[pyarrow]
+pyarrow>=17.0.0
+
 [test]
+rdt[pyarrow]
 rdt[copulas]
 pytest>=3.4.2
 pytest-cov>=2.6.0