rdt 1.12.2.dev0__tar.gz → 1.12.3.dev0__tar.gz

{rdt-1.12.2.dev0/rdt.egg-info → rdt-1.12.3.dev0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: rdt
-Version: 1.12.2.dev0
+Version: 1.12.3.dev0
 Summary: Reversible Data Transforms
 Author-email: "DataCebo, Inc." <info@sdv.dev>
 License: BSL-1.1

{rdt-1.12.2.dev0 → rdt-1.12.3.dev0}/pyproject.toml

@@ -137,7 +137,7 @@ collect_ignore = ['pyproject.toml']
 exclude_lines = ['NotImplementedError()']
 
 [tool.bumpversion]
-current_version = "1.12.2.dev0"
+current_version = "1.12.3.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-1.12.2.dev0 → rdt-1.12.3.dev0}/rdt/__init__.py

@@ -4,7 +4,7 @@
 
 __author__ = 'DataCebo, Inc.'
 __email__ = 'info@sdv.dev'
-__version__ = '1.12.2.dev0'
+__version__ = '1.12.3.dev0'
 
 
 import sys

{rdt-1.12.2.dev0 → rdt-1.12.3.dev0}/rdt/hyper_transformer.py

@@ -62,6 +62,7 @@ class HyperTransformer:
     # pylint: disable=too-many-instance-attributes
 
     _DTYPES_TO_SDTYPES = {
+        'u': 'numerical',
         'i': 'numerical',
         'f': 'numerical',
         'O': 'categorical',

{rdt-1.12.2.dev0 → rdt-1.12.3.dev0}/rdt/transformers/numerical.py

@@ -2,11 +2,11 @@
 
 import copy
 import warnings
+from importlib import import_module
 
 import numpy as np
 import pandas as pd
 import scipy
-from sklearn.mixture import BayesianGaussianMixture
 
 from rdt.errors import TransformerInputError
 from rdt.transformers.base import BaseTransformer
@@ -103,7 +103,7 @@ class FloatFormatter(BaseTransformer):
         )
 
     def _validate_values_within_bounds(self, data):
-        if self.computer_representation != 'Float':
+        if not self.computer_representation.startswith('Float'):
             fractions = data[~data.isna() & data % 1 != 0]
             if not fractions.empty:
                 raise ValueError(
@@ -184,20 +184,22 @@ class FloatFormatter(BaseTransformer):
         data = self.null_transformer.reverse_transform(data)
         if self.enforce_min_max_values:
             data = data.clip(self._min_value, self._max_value)
-        elif self.computer_representation != 'Float':
+        elif not self.computer_representation.startswith('Float'):
             min_bound, max_bound = INTEGER_BOUNDS[self.computer_representation]
             data = data.clip(min_bound, max_bound)
 
-        is_integer = np.dtype(self._dtype).kind == 'i'
+        is_integer = pd.api.types.is_integer_dtype(self._dtype)
+        np_integer_with_nans = (
+            not pd.api.types.is_extension_array_dtype(self._dtype)
+            and is_integer
+            and pd.isna(data).any()
+        )
         if self.learn_rounding_scheme and self._rounding_digits is not None:
             data = data.round(self._rounding_digits)
         elif is_integer:
             data = data.round(0)
 
-        if pd.isna(data).any() and is_integer:
-            return data
-
-        return data.astype(self._dtype)
+        return data.astype(self._dtype if not np_integer_with_nans else 'float64')
 
     def _set_fitted_parameters(
         self,
@@ -523,7 +525,9 @@ class ClusterBasedNormalizer(FloatFormatter):
             data (pandas.Series):
                 Data to fit to.
         """
-        self._bgm_transformer = BayesianGaussianMixture(
+        sm = import_module('sklearn.mixture')
+
+        self._bgm_transformer = sm.BayesianGaussianMixture(
             n_components=self.max_clusters,
             weight_concentration_prior_type='dirichlet_process',
             weight_concentration_prior=0.001,

{rdt-1.12.2.dev0 → rdt-1.12.3.dev0}/rdt/transformers/pii/utils.py

@@ -5,24 +5,6 @@ import inspect
 from faker import Faker
 
 
-def is_faker_function(function_name):
-    """Return whether or not the function name is a valid Faker function.
-
-    Args:
-        function_name (str):
-            String representing a ``faker`` function.
-
-    Returns:
-        True if the ``function_name`` is know to ``Faker``, otherwise False.
-    """
-    try:
-        getattr(Faker(), function_name)
-    except AttributeError:
-        return False
-
-    return True
-
-
 def get_provider_name(function_name):
     """Return the ``faker`` provider name for a given ``function_name``.
 

{rdt-1.12.2.dev0 → rdt-1.12.3.dev0}/rdt/transformers/utils.py

@@ -252,8 +252,7 @@ def learn_rounding_digits(data):
     """
     # check if data has any decimals
     name = data.name
-    data = np.array(data)
-    roundable_data = data[~(np.isinf(data) | pd.isna(data))]
+    roundable_data = data[~(np.isinf(data.astype(float)) | pd.isna(data))]
 
     # Doesn't contain numbers
     if len(roundable_data) == 0:

{rdt-1.12.2.dev0 → rdt-1.12.3.dev0/rdt.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: rdt
-Version: 1.12.2.dev0
+Version: 1.12.3.dev0
 Summary: Reversible Data Transforms
 Author-email: "DataCebo, Inc." <info@sdv.dev>
 License: BSL-1.1