Merge branch 'master' into wrong-mocks

HISTORY.md

@@ -1,13 +1,39 @@
 # History
 
+## 1.7.0 - 2023-08-22
+
+This release adds 3 new transformers:
+
+1. `UniformEncoder` - A categorical and boolean transformer that converts the column into a uniform distribution.
+2. `OrderedUniformEncoder` - The same as above, but the order for the categories can be specified, changing which range in the uniform distribution each category belongs to.
+3. `IDGenerator`- A text transformer that drops the input column during transform and returns IDs during reverse transform. The IDs all take the form \<prefix>\<number>\<suffix> and can be configured with a custom prefix, suffix and starting point.
+
+Additionally, the `AnonymizedFaker` is enhanced to support the text sdtype. 
+
+### Deprecations
+
+* The `get_input_sdtype` method is being deprecated in favor of `get_supported_sdtypes`.
+
+### New Features
+
+* Create IDGenerator transformer - Issue [#675](https://github.com/sdv-dev/RDT/issues/675) by @R-Palazzo
+* Add UniformEncoder (and its ordered version) - Issue [#678](https://github.com/sdv-dev/RDT/issues/678) by @R-Palazzo
+* Allow me to use AnonymizedFaker with sdtype text columns - Issue [#688](https://github.com/sdv-dev/RDT/issues/688) by @amontanez24
+
+### Maintenance
+
+* Deprecate get_input_sdtype - Issue [#682](https://github.com/sdv-dev/RDT/issues/682) by @R-Palazzo
+
 ## 1.6.1 - 2023-08-02
 
 This release updates the default transformers used for certain sdtypes. It also enables the `AnonymizedFaker` and `PseudoAnonymizedFaker` to work with any sdtype besides boolean, categorical, datetime, numerical or text.
 
 ### Bugs
+
 * [Enterprise Usage] Unable to assign generic PII transformers (eg. AnonymizedFaker) - Issue [#674](https://github.com/sdv-dev/RDT/issues/674) by @amontanez24
 
 ### New Features
+
 * Update the default transformers that HyperTransformer assigns to each sdtype - Issue [#664](https://github.com/sdv-dev/RDT/issues/664) by @amontanez24
 
 ## 1.6.0 - 2023-07-12

rdt/__init__.py

@@ -5,7 +5,7 @@
 
 __author__ = 'DataCebo, Inc.'
 __email__ = 'info@sdv.dev'
-__version__ = '1.7.0.dev1'
+__version__ = '1.7.1.dev0'
 
 
 import sys

rdt/transformers/__init__.py

@@ -145,8 +145,8 @@ def get_transformers_by_type():
     sdtype_transformers = defaultdict(list)
     transformer_classes = BaseTransformer.get_subclasses()
     for transformer in transformer_classes:
-        input_sdtype = transformer.get_input_sdtype()
-        sdtype_transformers[input_sdtype].append(transformer)
+        for sdtype in transformer.get_supported_sdtypes():
+            sdtype_transformers[sdtype].append(transformer)
 
     return sdtype_transformers
 

rdt/transformers/base.py

@@ -184,7 +184,11 @@ def get_input_sdtype(cls):
             string:
                 Accepted input sdtype of the transformer.
         """
-        return cls.INPUT_SDTYPE
+        warnings.warn(
+            '`get_input_sdtype` is deprecated. Please use `get_supported_sdtypes` instead.',
+            FutureWarning
+        )
+        return cls.get_supported_sdtypes()[0]
 
     @classmethod
     def get_supported_sdtypes(cls):

rdt/transformers/pii/anonymizer.py

@@ -133,7 +133,7 @@ def get_supported_sdtypes(cls):
                 Accepted input sdtypes of the transformer.
         """
         unsupported_sdtypes = {
-            'numerical', 'datetime', 'categorical', 'boolean', 'text', None
+            'numerical', 'datetime', 'categorical', 'boolean', None
         }
         all_sdtypes = {cls.INPUT_SDTYPE}
         for transformer in BaseTransformer.get_subclasses():

setup.cfg

@@ -1,5 +1,5 @@
 [bumpversion]
-current_version = 1.7.0.dev1
+current_version = 1.7.1.dev0
 commit = True
 tag = True
 parse = (?P<major>\d+)\.(?P<minor>\d+)\.(?P<patch>\d+)(\.(?P<release>[a-z]+)(?P<candidate>\d+))?

setup.py

@@ -139,6 +139,6 @@
     test_suite='tests',
     tests_require=tests_require,
     url='https://github.com/sdv-dev/RDT',
-    version='1.7.0.dev1',
+    version='1.7.1.dev0',
     zip_safe=False,
 )

tests/contributing.py

@@ -365,7 +365,7 @@ def validate_transformer_performance(transformer):
 
     print(f'Validating Performance for transformer {transformer.get_name()}\n')
 
-    sdtype = transformer.get_input_sdtype()
+    sdtype = transformer.get_supported_sdtypes()[0]
     transformers = get_transformers_by_type().get(sdtype, [])
     dataset_generators = get_dataset_generators_by_type().get(sdtype, [])