Merge branch 'fix/anonymization_support' of https://github.com/ydataa…

…i/ydata-sdk into fix/anonymization_support

# Conflicts:
#	src/ydata/sdk/synthesizers/anonymizer.py
#	src/ydata/sdk/synthesizers/synthesizer.py

examples/synthesizers/anonymize_example.py

@@ -1,12 +1,12 @@
 import os
-import os
 
 from ydata.sdk.dataset import get_dataset
 from ydata.sdk.synthesizers import RegularSynthesizer
 
 # Do not forget to add your token as env variables
 os.environ["YDATA_TOKEN"] = '<TOKEN>'  # Remove if already defined
 
+
 def main():
     """In this example, we demonstrate how to train a synthesizer from a pandas
     DataFrame.

src/ydata/sdk/synthesizers/anonymizer.py

@@ -4,12 +4,14 @@
 
 from ydata.datascience.common import AnonymizerType
 
-def build_and_validate_anonimization(anonimyze:dict, cols: list) -> dict:
-    isnested = any(isinstance(i,dict) for i in anonimyze.values())
+
+def built_and_validate_anonimization(anonimyze: dict, cols: list) -> dict:
+    isnested = any(isinstance(i, dict) for i in anonimyze.values())
 
     if not all([True if k in cols else False for k in list(anonimyze.keys())]):
-        #AnonymizationConfigurationError
-        raise Exception('The keys in your configuration must exactly match the column names in the provided dataset. Please check and update your inputs to ensure they align.')
+        # AnonymizationConfigurationError
+        raise Exception(
+            'The keys in your configuration must exactly match the column names in the provided dataset. Please check and update your inputs to ensure they align.')
 
     if isnested:
         # Validate the format here.
@@ -32,8 +34,8 @@ def build_and_validate_anonimization(anonimyze:dict, cols: list) -> dict:
         config = anonimyze
     else:
         config = {}
-        for k,v in anonimyze.items():
-            print(k,v)
+        for k, v in anonimyze.items():
+            print(k, v)
             if AnonymizerType.get_anonymizer_type(v) is None:
                 col_config = {'type': AnonymizerType.REGEX.value, 'regex': v}
             else:

src/ydata/sdk/synthesizers/synthesizer.py

@@ -26,10 +26,9 @@
 from ydata.sdk.synthesizers._models.status import PrepareState, Status, TrainingState
 from ydata.sdk.synthesizers._models.synthesizer import Synthesizer as mSynthesizer
 from ydata.sdk.synthesizers._models.synthesizers_list import SynthesizersList
+from ydata.sdk.synthesizers.anonymizer import built_and_validate_anonimization
 from ydata.sdk.utils.model_mixin import ModelFactoryMixin
 
-from ydata.sdk.synthesizers.anonymizer import build_and_validate_anonimization
-
 
 @typechecked
 class BaseSynthesizer(ABC, ModelFactoryMixin):
@@ -248,8 +247,9 @@ def _fit_from_datasource(
         payload['type'] = str(datatype.value)
 
         if anonymize is not None:
-            #process and validated the anonymization config shared by the end user
-            anonymize = build_and_validate_anonimization(anonimyze=anonymize, cols=[col.name for col in X.metadata.columns])
+            # process and validated the anonymization config shared by the end user
+            anonymize = built_and_validate_anonimization(
+                anonimyze=anonymize, cols=[col.name for col in X.metadata.columns])
             payload["extraData"]["anonymize"] = anonymize
         if condition_on is not None:
             payload["extraData"]["condition_on"] = condition_on