data-designer 0.3.8__tar.gz → 0.3.8rc2__tar.gz

{data_designer-0.3.8 → data_designer-0.3.8rc2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-designer
-Version: 0.3.8
+Version: 0.3.8rc2
 Summary: General framework for synthetic data generation
 License-Expression: Apache-2.0
 License-File: LICENSE

{data_designer-0.3.8/packages/data-designer-engine/src/data_designer/engine → data_designer-0.3.8rc2/packages/data-designer/src/data_designer/interface}/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.3.8rc3.dev39+gb6e375d29.d20260126'
-__version_tuple__ = version_tuple = (0, 3, 8, 'rc3', 'dev39', 'gb6e375d29.d20260126')
+__version__ = version = '0.3.8rc2.dev38+ga53f0df07.d20260126'
+__version_tuple__ = version_tuple = (0, 3, 8, 'rc2', 'dev38', 'ga53f0df07.d20260126')
 
 __commit_id__ = commit_id = None

{data_designer-0.3.8/packages/data-designer/src/data_designer/interface → data_designer-0.3.8rc2/packages/data-designer-config/src/data_designer/config}/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.3.8rc3.dev39+gb6e375d29.d20260126'
-__version_tuple__ = version_tuple = (0, 3, 8, 'rc3', 'dev39', 'gb6e375d29.d20260126')
+__version__ = version = '0.3.8rc2.dev38+ga53f0df07.d20260126'
+__version_tuple__ = version_tuple = (0, 3, 8, 'rc2', 'dev38', 'ga53f0df07.d20260126')
 
 __commit_id__ = commit_id = None

{data_designer-0.3.8/packages/data-designer-config/src/data_designer/config → data_designer-0.3.8rc2/packages/data-designer-engine/src/data_designer/engine}/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.3.8rc3.dev39+gb6e375d29.d20260126'
-__version_tuple__ = version_tuple = (0, 3, 8, 'rc3', 'dev39', 'gb6e375d29.d20260126')
+__version__ = version = '0.3.8rc2.dev38+ga53f0df07.d20260126'
+__version_tuple__ = version_tuple = (0, 3, 8, 'rc2', 'dev38', 'ga53f0df07.d20260126')
 
 __commit_id__ = commit_id = None

{data_designer-0.3.8 → data_designer-0.3.8rc2}/src/data_designer/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.3.8'
-__version_tuple__ = version_tuple = (0, 3, 8)
+__version__ = version = '0.3.8rc2'
+__version_tuple__ = version_tuple = (0, 3, 8, 'rc2')
 
 __commit_id__ = commit_id = None

{data_designer-0.3.8 → data_designer-0.3.8rc2}/src/data_designer/config/utils/constants.py

@@ -353,11 +353,9 @@ PREDEFINED_PROVIDERS_MODEL_MAP = {
 NEMOTRON_PERSONAS_DATASET_SIZES = {
     "en_US": "1.24 GB",
     "en_IN": "2.39 GB",
-    "en_SG": "0.30 GB",
     "hi_Deva_IN": "4.14 GB",
     "hi_Latn_IN": "2.7 GB",
     "ja_JP": "1.69 GB",
-    "pt_BR": "2.33 GB",
 }
 
 LOCALES_WITH_MANAGED_DATASETS = list[str](NEMOTRON_PERSONAS_DATASET_SIZES.keys())

{data_designer-0.3.8 → data_designer-0.3.8rc2}/src/data_designer/engine/sampling_gen/entities/dataset_based_person_fields.py

@@ -40,16 +40,13 @@ PII_FIELDS = [
     "state",
     "email_address",
     "phone_number",
-    # Brazil-specific fields
-    "race",
     # Japan-specific fields
     "area",
     "prefecture",
     "zone",
-    # Brazil and India shared fields
-    "religion",
     # India-specific fields
     "district",
+    "religion",
     "education_degree",
     "first_language",
     "second_language",
@@ -81,10 +78,9 @@ PERSONA_FIELDS = [
     # Japan-specific persona fields
     "aspects",
     "digital_skills",
-    # Brazil and India shared persona fields
-    "religious_persona",
-    "religious_background",
     # India-specific persona fields
     "linguistic_persona",
+    "religious_persona",
     "linguistic_background",
+    "religious_background",
 ]

{data_designer-0.3.8 → data_designer-0.3.8rc2}/tests/cli/controllers/test_download_controller.py

@@ -85,18 +85,16 @@ def test_run_personas_with_all_flag(
     # Verify NGC check was called
     mock_check_ngc.assert_called_once()
 
-    # Verify all 7 locales were downloaded
-    assert mock_download.call_count == 7
+    # Verify all 5 locales were downloaded
+    assert mock_download.call_count == 5
 
     # Verify each locale was downloaded
     downloaded_locales = [call[0][0] for call in mock_download.call_args_list]
     assert "en_US" in downloaded_locales
     assert "en_IN" in downloaded_locales
-    assert "en_SG" in downloaded_locales
     assert "hi_Deva_IN" in downloaded_locales
     assert "hi_Latn_IN" in downloaded_locales
     assert "ja_JP" in downloaded_locales
-    assert "pt_BR" in downloaded_locales
 
 
 @patch.object(DownloadController, "_download_locale", return_value=True)
@@ -219,14 +217,12 @@ def test_determine_locales_with_all_flag(controller: DownloadController) -> None
     """Test _determine_locales returns all locales when all_locales=True."""
     result = controller._determine_locales(locales=None, all_locales=True)
 
-    assert len(result) == 7
+    assert len(result) == 5
     assert "en_US" in result
     assert "en_IN" in result
-    assert "en_SG" in result
     assert "hi_Deva_IN" in result
     assert "hi_Latn_IN" in result
     assert "ja_JP" in result
-    assert "pt_BR" in result
 
 
 def test_determine_locales_with_valid_locale_flags(controller: DownloadController) -> None:

{data_designer-0.3.8 → data_designer-0.3.8rc2}/tests/cli/repositories/test_persona_repository.py

@@ -15,7 +15,7 @@ def repository() -> PersonaRepository:
 def test_init(repository: PersonaRepository) -> None:
     """Test repository initialization creates registry."""
     assert repository._registry is not None
-    assert len(repository._registry.locales) == 7
+    assert len(repository._registry.locales) == 5
     assert repository._registry.dataset_prefix == "nemotron-personas-dataset-"
 
 
@@ -24,11 +24,11 @@ def test_list_all(repository: PersonaRepository) -> None:
     locales = repository.list_all()
 
     assert isinstance(locales, list)
-    assert len(locales) == 7
+    assert len(locales) == 5
 
     # Verify all expected locales are present
     locale_codes = {locale.code for locale in locales}
-    assert locale_codes == {"en_US", "en_IN", "en_SG", "hi_Deva_IN", "hi_Latn_IN", "ja_JP", "pt_BR"}
+    assert locale_codes == {"en_US", "en_IN", "hi_Deva_IN", "hi_Latn_IN", "ja_JP"}
 
     # Verify each locale has required fields
     for locale in locales:

{data_designer-0.3.8 → data_designer-0.3.8rc2}/tests/cli/services/test_download_service.py

@@ -51,14 +51,12 @@ def test_get_available_locales(service: DownloadService) -> None:
     locales = service.get_available_locales()
 
     assert isinstance(locales, dict)
-    assert len(locales) == 7
+    assert len(locales) == 5
     assert "en_US" in locales
     assert "en_IN" in locales
-    assert "en_SG" in locales
     assert "hi_Deva_IN" in locales
     assert "hi_Latn_IN" in locales
     assert "ja_JP" in locales
-    assert "pt_BR" in locales
 
     # Verify values are locale codes (not descriptions)
     assert locales["en_US"] == "en_US"