data-designer 0.1.2__py3-none-any.whl → 0.1.4__py3-none-any.whl

data_designer/engine/models/parsers/parser.py

@@ -4,12 +4,12 @@
 from functools import reduce
 from typing import Optional
 
+import marko
 from lxml import etree
 from lxml.etree import _Element
-import marko
 
-from data_designer.engine.models.parsers.postprocessors import merge_text_blocks
 import data_designer.engine.models.parsers.tag_parsers as tp
+from data_designer.engine.models.parsers.postprocessors import merge_text_blocks
 from data_designer.engine.models.parsers.types import (
     LLMStructuredResponse,
     PostProcessor,

data_designer/engine/models/recipes/response_recipes.py

@@ -1,8 +1,8 @@
 # SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
-from collections.abc import Callable
 import json
+from collections.abc import Callable
 
 from pydantic import BaseModel
 

data_designer/engine/processing/ginja/environment.py

@@ -1,9 +1,9 @@
 # SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
+import re
 from collections.abc import Callable
 from functools import partial, wraps
-import re
 from typing import Any
 
 from jinja2 import meta

data_designer/engine/processing/gsonschema/validators.py

@@ -1,8 +1,8 @@
 # SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
-from copy import deepcopy
 import logging
+from copy import deepcopy
 from typing import Any, overload
 
 from jsonschema import Draft202012Validator, ValidationError, validators

data_designer/engine/resources/managed_dataset_repository.py

@@ -1,14 +1,14 @@
 # SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
-from abc import ABC, abstractmethod
-from dataclasses import dataclass
-from functools import cached_property
 import logging
-from pathlib import Path
 import tempfile
 import threading
 import time
+from abc import ABC, abstractmethod
+from dataclasses import dataclass
+from functools import cached_property
+from pathlib import Path
 from typing import Any
 
 import duckdb

data_designer/engine/resources/managed_storage.py

@@ -1,10 +1,10 @@
 # SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
+import logging
 from abc import ABC, abstractmethod
 from collections.abc import Iterator
 from contextlib import contextmanager
-import logging
 from pathlib import Path
 from typing import IO
 

data_designer/engine/sampling_gen/constraints.py

@@ -5,8 +5,8 @@ from abc import ABC, abstractmethod
 from typing import Type
 
 import numpy as np
-from numpy.typing import NDArray
 import pandas as pd
+from numpy.typing import NDArray
 
 from data_designer.config.base import ConfigBase
 from data_designer.config.sampler_constraints import (

data_designer/engine/sampling_gen/data_sources/base.py

@@ -5,8 +5,8 @@ from abc import ABC, abstractmethod
 from typing import Any, Generic, Optional, Type, TypeVar, Union
 
 import numpy as np
-from numpy.typing import NDArray
 import pandas as pd
+from numpy.typing import NDArray
 from scipy import stats
 
 from data_designer.config.sampler_params import SamplerParamsT

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/engine/sampling_gen/entities/email_address_utils.py

@@ -1,9 +1,9 @@
 # SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
-from datetime import date
 import random
 import re
+from datetime import date
 
 import anyascii
 

data_designer/engine/sampling_gen/entities/national_id_utils.py

@@ -1,8 +1,8 @@
 # SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
-from datetime import date
 import random
+from datetime import date
 
 SSN_RANDOMIZATION_DATE = date(2011, 6, 25)
 

data_designer/engine/sampling_gen/entities/person.py

@@ -1,8 +1,8 @@
 # SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
-from datetime import date, timedelta
 import random
+from datetime import date, timedelta
 from typing import Any, Literal, TypeAlias
 
 from data_designer.config.utils.constants import LOCALES_WITH_MANAGED_DATASETS

data_designer/engine/sampling_gen/entities/phone_number.py

@@ -1,8 +1,8 @@
 # SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
-from pathlib import Path
 import random
+from pathlib import Path
 from typing import Optional
 
 import pandas as pd

data_designer/engine/sampling_gen/people_gen.py

@@ -3,15 +3,15 @@
 
 from __future__ import annotations
 
+import random
+import uuid
 from abc import ABC, abstractmethod
 from collections.abc import Callable
 from copy import deepcopy
-import random
 from typing import TYPE_CHECKING, Any, Union
-import uuid
 
-from faker import Faker
 import pandas as pd
+from faker import Faker
 
 from data_designer.config.utils.constants import AVAILABLE_LOCALES, DEFAULT_AGE_RANGE
 from data_designer.engine.resources.managed_dataset_generator import ManagedDatasetGenerator

data_designer/engine/secret_resolver.py

@@ -1,10 +1,10 @@
 # SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
-from collections.abc import Sequence
 import json
 import logging
 import os
+from collections.abc import Sequence
 from pathlib import Path
 from typing import Protocol
 

data_designer/engine/validators/python.py

@@ -2,12 +2,12 @@
 # SPDX-License-Identifier: Apache-2.0
 
 import ast
-from collections import defaultdict
 import logging
-from pathlib import Path
 import re
 import subprocess
 import tempfile
+from collections import defaultdict
+from pathlib import Path
 from uuid import uuid4
 
 import pandas as pd

data_designer/essentials/__init__.py

@@ -1,137 +1,29 @@
 # SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
-from ..logging import LoggingConfig, configure_logging
+
+from data_designer.config.default_model_settings import resolve_seed_default_model_settings
+from data_designer.config.exports import *  # noqa: F403
+from data_designer.config.validator_params import LocalCallableValidatorParams
+from data_designer.interface.data_designer import DataDesigner
+from data_designer.logging import LoggingConfig, configure_logging
 
 configure_logging(LoggingConfig.default())
 
-from ..config.analysis.column_profilers import JudgeScoreProfilerConfig
-from ..config.column_configs import (
-    ExpressionColumnConfig,
-    LLMCodeColumnConfig,
-    LLMJudgeColumnConfig,
-    LLMStructuredColumnConfig,
-    LLMTextColumnConfig,
-    SamplerColumnConfig,
-    Score,
-    SeedDatasetColumnConfig,
-    ValidationColumnConfig,
-)
-from ..config.column_types import DataDesignerColumnType
-from ..config.config_builder import DataDesignerConfigBuilder
-from ..config.data_designer_config import DataDesignerConfig
-from ..config.dataset_builders import BuildStage
-from ..config.datastore import DatastoreSettings
-from ..config.models import (
-    ImageContext,
-    ImageFormat,
-    InferenceParameters,
-    ManualDistribution,
-    ManualDistributionParams,
-    Modality,
-    ModalityContext,
-    ModalityDataType,
-    ModelConfig,
-    UniformDistribution,
-    UniformDistributionParams,
-)
-from ..config.processors import DropColumnsProcessorConfig, ProcessorType
-from ..config.sampler_constraints import ColumnInequalityConstraint, ScalarInequalityConstraint
-from ..config.sampler_params import (
-    BernoulliMixtureSamplerParams,
-    BernoulliSamplerParams,
-    BinomialSamplerParams,
-    CategorySamplerParams,
-    DatetimeSamplerParams,
-    GaussianSamplerParams,
-    PersonFromFakerSamplerParams,
-    PersonSamplerParams,
-    PoissonSamplerParams,
-    SamplerType,
-    ScipySamplerParams,
-    SubcategorySamplerParams,
-    TimeDeltaSamplerParams,
-    UniformSamplerParams,
-    UUIDSamplerParams,
-)
-from ..config.seed import DatastoreSeedDatasetReference, IndexRange, PartitionBlock, SamplingStrategy, SeedConfig
-from ..config.utils.code_lang import CodeLang
-from ..config.utils.info import InfoType
-from ..config.utils.misc import can_run_data_designer_locally
-from ..config.validator_params import (
-    CodeValidatorParams,
-    RemoteValidatorParams,
-    ValidatorType,
-)
+# Resolve default model settings on import to ensure they are available when the library is used.
+resolve_seed_default_model_settings()
+
 
-local_library_imports = []
-try:
-    if can_run_data_designer_locally():
-        from ..config.validator_params import LocalCallableValidatorParams  # noqa: F401
-        from ..engine.model_provider import ModelProvider  # noqa: F401
-        from ..interface.data_designer import DataDesigner  # noqa: F401
+def get_essentials_exports() -> list[str]:
+    logging = [
+        configure_logging.__name__,
+        LoggingConfig.__name__,
+    ]
+    local = [
+        DataDesigner.__name__,
+        LocalCallableValidatorParams.__name__,
+    ]
 
-        local_library_imports = ["DataDesigner", "LocalCallableValidatorParams", "ModelProvider"]
-except ModuleNotFoundError:
-    pass
+    return logging + local + get_config_exports()  # noqa: F405
 
-__all__ = [
-    "BernoulliMixtureSamplerParams",
-    "BernoulliSamplerParams",
-    "BinomialSamplerParams",
-    "CategorySamplerParams",
-    "CodeLang",
-    "CodeValidatorParams",
-    "ColumnInequalityConstraint",
-    "configure_logging",
-    "DataDesignerColumnType",
-    "DataDesignerConfig",
-    "DataDesignerConfigBuilder",
-    "BuildStage",
-    "DatastoreSeedDatasetReference",
-    "DatastoreSettings",
-    "DatetimeSamplerParams",
-    "DropColumnsProcessorConfig",
-    "ExpressionColumnConfig",
-    "GaussianSamplerParams",
-    "IndexRange",
-    "InfoType",
-    "ImageContext",
-    "ImageFormat",
-    "InferenceParameters",
-    "JudgeScoreProfilerConfig",
-    "LLMCodeColumnConfig",
-    "LLMJudgeColumnConfig",
-    "LLMStructuredColumnConfig",
-    "LLMTextColumnConfig",
-    "LoggingConfig",
-    "ManualDistribution",
-    "ManualDistributionParams",
-    "Modality",
-    "ModalityContext",
-    "ModalityDataType",
-    "ModelConfig",
-    "PartitionBlock",
-    "PersonSamplerParams",
-    "PersonFromFakerSamplerParams",
-    "PoissonSamplerParams",
-    "ProcessorType",
-    "RemoteValidatorParams",
-    "SamplerColumnConfig",
-    "SamplerType",
-    "SamplingStrategy",
-    "ScalarInequalityConstraint",
-    "ScipySamplerParams",
-    "Score",
-    "SeedConfig",
-    "SeedDatasetColumnConfig",
-    "SubcategorySamplerParams",
-    "TimeDeltaSamplerParams",
-    "UniformDistribution",
-    "UniformDistributionParams",
-    "UniformSamplerParams",
-    "UUIDSamplerParams",
-    "ValidationColumnConfig",
-    "ValidatorType",
-]
 
-__all__.extend(local_library_imports)
+__all__ = get_essentials_exports()

data_designer/interface/data_designer.py

@@ -13,7 +13,6 @@ from data_designer.config.default_model_settings import (
     get_default_model_providers_missing_api_keys,
     get_default_provider_name,
     get_default_providers,
-    resolve_seed_default_model_settings,
 )
 from data_designer.config.interface import DataDesignerInterface
 from data_designer.config.models import (
@@ -31,7 +30,6 @@ from data_designer.config.utils.constants import (
 )
 from data_designer.config.utils.info import InfoType, InterfaceInfo
 from data_designer.config.utils.io_helpers import write_seed_dataset
-from data_designer.config.utils.misc import can_run_data_designer_locally
 from data_designer.engine.analysis.dataset_profiler import (
     DataDesignerDatasetProfiler,
     DatasetProfilerConfig,
@@ -66,11 +64,6 @@ DEFAULT_BUFFER_SIZE = 1000
 logger = logging.getLogger(__name__)
 
 
-# Resolve default model settings on import to ensure they are available when the library is used.
-if can_run_data_designer_locally():
-    resolve_seed_default_model_settings()
-
-
 class DataDesigner(DataDesignerInterface[DatasetCreationResults]):
     """Main interface for creating datasets with Data Designer.
 
@@ -173,7 +166,11 @@ 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,
@@ -311,18 +308,17 @@ class DataDesigner(DataDesignerInterface[DatasetCreationResults]):
 
     def _resolve_model_providers(self, model_providers: list[ModelProvider] | None) -> list[ModelProvider]:
         if model_providers is None:
-            if can_run_data_designer_locally():
-                model_providers = get_default_providers()
-                missing_api_keys = get_default_model_providers_missing_api_keys()
-                if len(missing_api_keys) == len(PREDEFINED_PROVIDERS):
-                    logger.warning(
-                        "🚨 You are trying to use a default model provider but your API keys are missing."
-                        "\n\t\t\tSet the API key for the default providers you intend to use and re-initialize the Data Designer object."
-                        "\n\t\t\tAlternatively, you can provide your own model providers during Data Designer object initialization."
-                        "\n\t\t\tSee https://nvidia-nemo.github.io/DataDesigner/models/model-providers/ for more information."
-                    )
-                    self._get_interface_info(model_providers).display(InfoType.MODEL_PROVIDERS)
-                return model_providers
+            model_providers = get_default_providers()
+            missing_api_keys = get_default_model_providers_missing_api_keys()
+            if len(missing_api_keys) == len(PREDEFINED_PROVIDERS):
+                logger.warning(
+                    "🚨 You are trying to use a default model provider but your API keys are missing."
+                    "\n\t\t\tSet the API key for the default providers you intend to use and re-initialize the Data Designer object."
+                    "\n\t\t\tAlternatively, you can provide your own model providers during Data Designer object initialization."
+                    "\n\t\t\tSee https://nvidia-nemo.github.io/DataDesigner/concepts/models/model-providers/ for more information."
+                )
+                self._get_interface_info(model_providers).display(InfoType.MODEL_PROVIDERS)
+            return model_providers
         return model_providers or []
 
     def _create_dataset_builder(

data_designer/logging.py

@@ -1,11 +1,11 @@
 # SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
-from dataclasses import dataclass, field
 import logging
-from pathlib import Path
 import random
 import sys
+from dataclasses import dataclass, field
+from pathlib import Path
 from typing import TextIO, Union
 
 from pythonjsonlogger import jsonlogger

data_designer/plugin_manager.py

@@ -6,25 +6,16 @@ from __future__ import annotations
 from enum import Enum
 from typing import TYPE_CHECKING, Type, TypeAlias
 
-from .config.utils.misc import can_run_data_designer_locally
+from data_designer.plugins.plugin import PluginType
+from data_designer.plugins.registry import PluginRegistry
 
 if TYPE_CHECKING:
     from data_designer.plugins.plugin import Plugin
 
 
-if can_run_data_designer_locally():
-    from data_designer.plugins.plugin import PluginType
-    from data_designer.plugins.registry import PluginRegistry
-
-
 class PluginManager:
     def __init__(self):
-        if can_run_data_designer_locally():
-            self._plugins_supported = True
-            self._plugin_registry = PluginRegistry()
-        else:
-            self._plugins_supported = False
-            self._plugin_registry = None
+        self._plugin_registry = PluginRegistry()
 
     def get_column_generator_plugins(self) -> list[Plugin]:
         """Get all column generator plugins.
@@ -32,7 +23,7 @@ class PluginManager:
         Returns:
             A list of all column generator plugins.
         """
-        return self._plugin_registry.get_plugins(PluginType.COLUMN_GENERATOR) if self._plugins_supported else []
+        return self._plugin_registry.get_plugins(PluginType.COLUMN_GENERATOR)
 
     def get_column_generator_plugin_if_exists(self, plugin_name: str) -> Plugin | None:
         """Get a column generator plugin by name if it exists.
@@ -43,9 +34,8 @@ class PluginManager:
         Returns:
             The plugin if found, otherwise None.
         """
-        if self._plugins_supported and self._plugin_registry.plugin_exists(plugin_name):
+        if self._plugin_registry.plugin_exists(plugin_name):
             return self._plugin_registry.get_plugin(plugin_name)
-        return None
 
     def get_plugin_column_types(self, enum_type: Type[Enum], required_resources: list[str] | None = None) -> list[Enum]:
         """Get a list of plugin column types.
@@ -58,13 +48,12 @@ class PluginManager:
             A list of plugin column types.
         """
         type_list = []
-        if self._plugins_supported:
-            for plugin in self._plugin_registry.get_plugins(PluginType.COLUMN_GENERATOR):
-                if required_resources:
-                    task_required_resources = plugin.task_cls.metadata().required_resources or []
-                    if not all(resource in task_required_resources for resource in required_resources):
-                        continue
-                type_list.append(enum_type(plugin.name))
+        for plugin in self._plugin_registry.get_plugins(PluginType.COLUMN_GENERATOR):
+            if required_resources:
+                task_required_resources = plugin.task_cls.metadata().required_resources or []
+                if not all(resource in task_required_resources for resource in required_resources):
+                    continue
+            type_list.append(enum_type(plugin.name))
         return type_list
 
     def inject_into_column_config_type_union(self, column_config_type: Type[TypeAlias]) -> Type[TypeAlias]:
@@ -76,8 +65,7 @@ class PluginManager:
         Returns:
             The column config type with plugins injected.
         """
-        if self._plugins_supported:
-            column_config_type = self._plugin_registry.add_plugin_types_to_union(
-                column_config_type, PluginType.COLUMN_GENERATOR
-            )
+        column_config_type = self._plugin_registry.add_plugin_types_to_union(
+            column_config_type, PluginType.COLUMN_GENERATOR
+        )
         return column_config_type

data_designer/plugins/registry.py

@@ -1,10 +1,10 @@
 # SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 # SPDX-License-Identifier: Apache-2.0
 
-from importlib.metadata import entry_points
 import logging
 import os
 import threading
+from importlib.metadata import entry_points
 from typing import Type, TypeAlias
 
 from typing_extensions import Self

{data_designer-0.1.2.dist-info → data_designer-0.1.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-designer
-Version: 0.1.2
+Version: 0.1.4
 Summary: General framework for synthetic data generation
 License-Expression: Apache-2.0
 License-File: LICENSE
@@ -148,7 +148,7 @@ preview.display_sample_record()
 - **[Tutorial Notebooks](https://nvidia-nemo.github.io/DataDesigner/notebooks/)** – Step-by-step interactive tutorials
 - **[Column Types](https://nvidia-nemo.github.io/DataDesigner/concepts/columns/)** – Explore samplers, LLM columns, validators, and more
 - **[Validators](https://nvidia-nemo.github.io/DataDesigner/concepts/validators/)** – Learn how to validate generated data with Python, SQL, and remote validators
-- **[Model Configuration](https://nvidia-nemo.github.io/DataDesigner/models/model-configs/)** – Configure custom models and providers
+- **[Model Configuration](https://nvidia-nemo.github.io/DataDesigner/concepts/models/model-configs/)** – Configure custom models and providers
 - **[Person Sampling](https://nvidia-nemo.github.io/DataDesigner/concepts/person_sampling/)** – Learn how to sample realistic person data with demographic attributes
 
 ### 🔧 Configure models via CLI