data-designer 0.1.2__py3-none-any.whl → 0.1.3__py3-none-any.whl

data_designer/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.1.2'
-__version_tuple__ = version_tuple = (0, 1, 2)
+__version__ = version = '0.1.3'
+__version_tuple__ = version_tuple = (0, 1, 3)
 
 __commit_id__ = commit_id = None

data_designer/config/sampler_params.py

@@ -430,9 +430,6 @@ class PersonSamplerParams(ConfigBase):
         age_range: Two-element list [min_age, max_age] specifying the age range to sample from
             (inclusive). Defaults to a standard age range. Both values must be between minimum and
             maximum allowed ages.
-        state: Only supported for "en_US" locale. Filters to sample people from specified US state(s).
-            Must be provided as two-letter state abbreviations (e.g., "CA", "NY", "TX"). Can be a
-            single state or a list of states.
         with_synthetic_personas: If True, appends additional synthetic persona columns including
             personality traits, interests, and background descriptions. Only supported for certain
             locales with managed datasets.

data_designer/engine/dataset_builders/artifact_storage.py

@@ -1,6 +1,8 @@
 # SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
+from datetime import datetime
+from functools import cached_property
 import json
 import logging
 from pathlib import Path
@@ -36,9 +38,21 @@ class ArtifactStorage(BaseModel):
     def artifact_path_exists(self) -> bool:
         return self.artifact_path.exists()
 
+    @cached_property
+    def resolved_dataset_name(self) -> str:
+        dataset_path = self.artifact_path / self.dataset_name
+        if dataset_path.exists() and len(list(dataset_path.iterdir())) > 0:
+            new_dataset_name = f"{self.dataset_name}_{datetime.now().strftime('%m-%d-%Y_%H%M%S')}"
+            logger.info(
+                f"📂 Dataset path {str(dataset_path)!r} already exists. Dataset from this session"
+                f"\n\t\t     will be saved to {str(self.artifact_path / new_dataset_name)!r} instead."
+            )
+            return new_dataset_name
+        return self.dataset_name
+
     @property
     def base_dataset_path(self) -> Path:
-        return self.artifact_path / self.dataset_name
+        return self.artifact_path / self.resolved_dataset_name
 
     @property
     def dropped_columns_dataset_path(self) -> Path:

data_designer/engine/dataset_builders/column_wise_builder.py

@@ -88,8 +88,8 @@ class ColumnWiseDatasetBuilder:
         start_time = time.perf_counter()
 
         self.batch_manager.start(num_records=num_records, buffer_size=buffer_size)
-        for batch_idx in range(1, self.batch_manager.num_batches + 1):
-            logger.info(f"⏳ Processing batch {batch_idx} of {self.batch_manager.num_batches}")
+        for batch_idx in range(self.batch_manager.num_batches):
+            logger.info(f"⏳ Processing batch {batch_idx + 1} of {self.batch_manager.num_batches}")
             self._run_batch(generators)
             df_batch = self._run_processors(
                 stage=BuildStage.POST_BATCH,

data_designer/engine/sampling_gen/entities/dataset_based_person_fields.py

@@ -14,6 +14,7 @@ REQUIRED_FIELDS = {"first_name", "last_name", "age", "locale"}
 
 
 PII_FIELDS = [
+    # Core demographic fields
     "uuid",
     "first_name",
     "middle_name",
@@ -22,25 +23,38 @@ PII_FIELDS = [
     "age",
     "birth_date",
     "marital_status",
-    "street_name",
-    "street_number",
-    "unit",
     "postcode",
-    "region",
     "city",
-    "district",
+    "region",
     "country",
-    "area",
-    "zone",
+    "locale",
     "bachelors_field",
-    "education_degree",
     "education_level",
     "occupation",
-    "locale",
+    "national_id",
+    # US-specific fields
+    "street_name",
+    "street_number",
+    "unit",
+    "state",
+    "email_address",
+    "phone_number",
+    # Japan-specific fields
+    "area",
+    "prefecture",
+    "zone",
+    # India-specific fields
+    "district",
+    "religion",
+    "education_degree",
+    "first_language",
+    "second_language",
+    "third_language",
 ]
 
 
 PERSONA_FIELDS = [
+    # Core persona fields
     "persona",
     "career_goals_and_ambitions",
     "arts_persona",
@@ -61,4 +75,12 @@ PERSONA_FIELDS = [
     "extraversion",
     "agreeableness",
     "neuroticism",
+    # Japan-specific persona fields
+    "aspects",
+    "digital_skills",
+    # India-specific persona fields
+    "linguistic_persona",
+    "religious_persona",
+    "linguistic_background",
+    "religious_background",
 ]

data_designer/interface/data_designer.py

@@ -173,7 +173,11 @@ class DataDesigner(DataDesignerInterface[DatasetCreationResults]):
                 configuration (columns, constraints, seed data, etc.).
             num_records: Number of records to generate.
             dataset_name: Name of the dataset. This name will be used as the dataset
-                folder name in the artifact path directory.
+                folder name in the artifact path directory. If a non-empty directory with the
+                same name already exists, dataset will be saved to a new directory with
+                a datetime stamp. For example, if the dataset name is "awesome_dataset" and a directory
+                with the same name already exists, the dataset will be saved to a new directory
+                with the name "awesome_dataset_2025-01-01_12-00-00".
 
         Returns:
             DatasetCreationResults object with methods for loading the generated dataset,

{data_designer-0.1.2.dist-info → data_designer-0.1.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-designer
-Version: 0.1.2
+Version: 0.1.3
 Summary: General framework for synthetic data generation
 License-Expression: Apache-2.0
 License-File: LICENSE

{data_designer-0.1.2.dist-info → data_designer-0.1.3.dist-info}/RECORD

@@ -1,5 +1,5 @@
 data_designer/__init__.py,sha256=iCeqRnb640RrL2QpA630GY5Ng7JiDt83Vq0DwLnNugU,461
-data_designer/_version.py,sha256=Ok5oAXdWgR9aghaFXTafTeDW6sYO3uVe6d2Nket57R4,704
+data_designer/_version.py,sha256=q5nF98G8SoVeJqaknL0xdyxtv0egsqb0fK06_84Izu8,704
 data_designer/errors.py,sha256=Z4eN9XwzZvGRdBluSNoSqQYkPPzNQIDf0ET_OqWRZh8,179
 data_designer/logging.py,sha256=O6LlQRj4IdkvEEYiMkKfMb_ZDgN1YpkGQUCqcp7nY6w,5354
 data_designer/plugin_manager.py,sha256=jWoo80x0oCiOIJMA43t-vK-_hVv9_xt4WhBcurYoDqw,3098
@@ -44,7 +44,7 @@ data_designer/config/models.py,sha256=5Cy55BnKYyr-I1UHLUTqZxe6Ca9uVQWpUiwt9X0Zlr
 data_designer/config/preview_results.py,sha256=H6ETFI6L1TW8MEC9KYsJ1tXGIC5cloCggBCCZd6jiEE,1087
 data_designer/config/processors.py,sha256=qOF_plBoh6UEFNwUpyDgkqIuSDUaSM2S7k-kSAEB5p8,1328
 data_designer/config/sampler_constraints.py,sha256=4JxP-nge5KstqtctJnVg5RLM1w9mA7qFi_BjgTJl9CE,1167
-data_designer/config/sampler_params.py,sha256=NCm2uWEzFHjz8ZzSmiKcVp5jI5okp53tq9l-bWBm4FQ,26821
+data_designer/config/sampler_params.py,sha256=W2GGRwzWZ4RlJAjDpyqSoF6bjpYjT7WHIhS3D0GfupE,26574
 data_designer/config/seed.py,sha256=g-iUToYSIFuTv3sbwSG_dF-9RwC8r8AvCD-vS8c_jDg,5487
 data_designer/config/validator_params.py,sha256=sNxFIF2bk_N4jJD-aMH1N5MQynDip08AoMI1ajxtRdc,3909
 data_designer/config/analysis/column_profilers.py,sha256=Qss9gr7oHNcjijW_MMIX9JkFX-V9v5vPwYWCnxLjMDY,2749
@@ -87,8 +87,8 @@ data_designer/engine/column_generators/generators/validation.py,sha256=MbDFXzief
 data_designer/engine/column_generators/utils/errors.py,sha256=ugNwaqnPdrPZI7YnKLbYwFjYUSm0WAzgaVu_u6i5Rc8,365
 data_designer/engine/column_generators/utils/judge_score_factory.py,sha256=JRoaZgRGK24dH0zx7MNGSccK196tQK_l0sbwNkurg7c,2132
 data_designer/engine/column_generators/utils/prompt_renderer.py,sha256=d4tbyPsgmFDikW3nxL5is9RNaajMkoPDCrfkQkxw7rc,4760
-data_designer/engine/dataset_builders/artifact_storage.py,sha256=NlO8H4g4ZaI5iDwI-xnhyyKGTdLX5JunqQuiQNXW-yI,7303
-data_designer/engine/dataset_builders/column_wise_builder.py,sha256=pu7mJIc5Ld4TLeTDsh9sCzKHgCbe7cC5PDF4RmxXw8o,13077
+data_designer/engine/dataset_builders/artifact_storage.py,sha256=0hpjJ4s3kQ3h-cEpgtIcDpx3UIEMH1FNX5Sp_8yRU9s,7995
+data_designer/engine/dataset_builders/column_wise_builder.py,sha256=bXaFhFD0GsY-9b_GLXY345N0BH5z2YjiWrs_yFDqYgA,13074
 data_designer/engine/dataset_builders/errors.py,sha256=1kChleChG4rASWIiL4Bel6Ox6aFZjQUrh5ogPt1CDWo,359
 data_designer/engine/dataset_builders/multi_column_configs.py,sha256=t28fhI-WRIBohFnAJ80l5EAETEDB5rJ5RSWInMiRfyE,1619
 data_designer/engine/dataset_builders/utils/__init__.py,sha256=9eG4WHKyrJcNoK4GEz6BCw_E0Ewo9elQoDN4TLMbAog,137
@@ -148,7 +148,7 @@ data_designer/engine/sampling_gen/data_sources/base.py,sha256=BRU9pzDvgB5B1Mgtj8
 data_designer/engine/sampling_gen/data_sources/errors.py,sha256=5pq42e5yvUqaH-g09jWvJolYCO2I2Rdrqo1O0gwet8Y,326
 data_designer/engine/sampling_gen/data_sources/sources.py,sha256=63YaRau37NIc2TDn8JvTOsd0zfnY4_aaF9UOU5ryKSo,13387
 data_designer/engine/sampling_gen/entities/__init__.py,sha256=9eG4WHKyrJcNoK4GEz6BCw_E0Ewo9elQoDN4TLMbAog,137
-data_designer/engine/sampling_gen/entities/dataset_based_person_fields.py,sha256=-_ebkhKeRYtlGpY8ZKGuc40aJfeWQahW2L-BBRxRnO0,1316
+data_designer/engine/sampling_gen/entities/dataset_based_person_fields.py,sha256=W_QSYNO2ynsXGJ71y_M9uRpYjjcbcAFhp1MpDFdl9YM,1844
 data_designer/engine/sampling_gen/entities/email_address_utils.py,sha256=-V4zuuFq1t3nzzO_FqzCWApPcWNKAh-ZQYFMmCiu5RE,5231
 data_designer/engine/sampling_gen/entities/errors.py,sha256=QEq-6Ld9OlModEYbse0pvY21OC5CyO-OalrL03-iLME,311
 data_designer/engine/sampling_gen/entities/national_id_utils.py,sha256=vxxHnrfQP98W8dWGysCjvfIT-h1xEGdfxn5xF_-UeXw,2611
@@ -163,15 +163,15 @@ data_designer/engine/validators/remote.py,sha256=jtDIvWzfHh17m2ac_Fp93p49Th8RlkB
 data_designer/engine/validators/sql.py,sha256=bxbyxPxDT9yuwjhABVEY40iR1pzWRFi65WU4tPgG2bE,2250
 data_designer/essentials/__init__.py,sha256=zrDZ7hahOmOhCPdfoj0z9ALN10lXIesfwd2qXRqTcdY,4125
 data_designer/interface/__init__.py,sha256=9eG4WHKyrJcNoK4GEz6BCw_E0Ewo9elQoDN4TLMbAog,137
-data_designer/interface/data_designer.py,sha256=EzOT_kkWXm9-1Zgbj4RvBfV6_r5ABR7mOuNwbgvKKLQ,16273
+data_designer/interface/data_designer.py,sha256=USPTruC5axBJNEWEnYBJ4ol2d3mXGubHELBmWeahFe8,16664
 data_designer/interface/errors.py,sha256=jagKT3tPUnYq4e3e6AkTnBkcayHyEfxjPMBzx-GEKe4,565
 data_designer/interface/results.py,sha256=qFxa8SuCXeADiRpaCMBwJcExkJBCfUPeGCdcJSTjoTc,2111
 data_designer/plugins/__init__.py,sha256=c_V7q4QhfVoNf_uc9UwmXCsWqwtyWogI7YoN_0PzzE4,234
 data_designer/plugins/errors.py,sha256=yPIHpSddEr-o9ZcNVibb2hI-73O15Kg_Od8SlmQlnRs,297
 data_designer/plugins/plugin.py,sha256=7ErdUyrTdOb5PCBE3msdhTOrvQpldjOQw90-Bu4Bosc,2522
 data_designer/plugins/registry.py,sha256=iPDTh4duV1cKt7H1fXkj1bKLG6SyUKmzQ9xh-vjEoaM,3018
-data_designer-0.1.2.dist-info/METADATA,sha256=PjPyL9UQ0Ys4XPqRuruAjuUJ6XPMDf1n1bz17wwoct4,6644
-data_designer-0.1.2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-data_designer-0.1.2.dist-info/entry_points.txt,sha256=NWWWidyDxN6CYX6y664PhBYMhbaYTQTyprqfYAgkyCg,57
-data_designer-0.1.2.dist-info/licenses/LICENSE,sha256=cSWJDwVqHyQgly8Zmt3pqXJ2eQbZVYwN9qd0NMssxXY,11336
-data_designer-0.1.2.dist-info/RECORD,,
+data_designer-0.1.3.dist-info/METADATA,sha256=fCI36BVPIOC7FVxQviBmzWMX8HRnc69afkJ82xPYXbY,6644
+data_designer-0.1.3.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+data_designer-0.1.3.dist-info/entry_points.txt,sha256=NWWWidyDxN6CYX6y664PhBYMhbaYTQTyprqfYAgkyCg,57
+data_designer-0.1.3.dist-info/licenses/LICENSE,sha256=cSWJDwVqHyQgly8Zmt3pqXJ2eQbZVYwN9qd0NMssxXY,11336
+data_designer-0.1.3.dist-info/RECORD,,

{data_designer-0.1.2.dist-info → data_designer-0.1.3.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: hatchling 1.27.0
+Generator: hatchling 1.28.0
 Root-Is-Purelib: true
 Tag: py3-none-any