data-designer 0.1.1__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 = '0.1.1'
-__version_tuple__ = version_tuple = (0, 1, 1)
+__version__ = version = '0.1.3'
+__version_tuple__ = version_tuple = (0, 1, 3)
 
 __commit_id__ = commit_id = None

data_designer/config/column_configs.py

@@ -2,9 +2,9 @@
 # SPDX-License-Identifier: Apache-2.0
 
 from abc import ABC
-from typing import Literal, Optional, Type, Union
+from typing import Annotated, Literal, Optional, Type, Union
 
-from pydantic import BaseModel, Field, model_validator
+from pydantic import BaseModel, Discriminator, Field, model_validator
 from typing_extensions import Self
 
 from .base import ConfigBase
@@ -89,11 +89,36 @@ class SamplerColumnConfig(SingleColumnConfig):
     """
 
     sampler_type: SamplerType
-    params: SamplerParamsT
-    conditional_params: dict[str, SamplerParamsT] = {}
+    params: Annotated[SamplerParamsT, Discriminator("sampler_type")]
+    conditional_params: dict[str, Annotated[SamplerParamsT, Discriminator("sampler_type")]] = {}
     convert_to: Optional[str] = None
     column_type: Literal["sampler"] = "sampler"
 
+    @model_validator(mode="before")
+    @classmethod
+    def inject_sampler_type_into_params(cls, data: dict) -> dict:
+        """Inject sampler_type into params dict to enable discriminated union resolution.
+
+        This allows users to pass params as a simple dict without the sampler_type field,
+        which will be automatically added based on the outer sampler_type field.
+        """
+        if isinstance(data, dict):
+            sampler_type = data.get("sampler_type")
+            params = data.get("params")
+
+            # If params is a dict and doesn't have sampler_type, inject it
+            if sampler_type and isinstance(params, dict) and "sampler_type" not in params:
+                data["params"] = {"sampler_type": sampler_type, **params}
+
+            # Handle conditional_params similarly
+            conditional_params = data.get("conditional_params")
+            if conditional_params and isinstance(conditional_params, dict):
+                for condition, cond_params in conditional_params.items():
+                    if isinstance(cond_params, dict) and "sampler_type" not in cond_params:
+                        data["conditional_params"][condition] = {"sampler_type": sampler_type, **cond_params}
+
+        return data
+
 
 class LLMTextColumnConfig(SingleColumnConfig):
     """Configuration for text generation columns using Large Language Models.

data_designer/config/datastore.py

@@ -31,34 +31,37 @@ class DatastoreSettings(BaseModel):
     token: Optional[str] = Field(default=None, description="If needed, token to use for authentication.")
 
 
-def get_file_column_names(file_path: Union[str, Path], file_type: str) -> list[str]:
-    """Extract column names based on file type. Supports glob patterns like '../path/*.parquet'."""
-    file_path = Path(file_path)
-    if "*" in str(file_path):
-        matching_files = sorted(file_path.parent.glob(file_path.name))
-        if not matching_files:
-            raise InvalidFilePathError(f"🛑 No files found matching pattern: {str(file_path)!r}")
-        logger.debug(f"0️⃣ Using the first matching file in {str(file_path)!r} to determine column names in seed dataset")
-        file_path = matching_files[0]
+def get_file_column_names(file_reference: Union[str, Path, HfFileSystem], file_type: str) -> list[str]:
+    """Get column names from a dataset file.
+
+    Args:
+        file_reference: Path to the dataset file, or an HfFileSystem object.
+        file_type: Type of the dataset file. Must be one of: 'parquet', 'json', 'jsonl', 'csv'.
 
+    Raises:
+        InvalidFilePathError: If the file type is not supported.
+
+    Returns:
+        List of column names.
+    """
     if file_type == "parquet":
         try:
-            schema = pq.read_schema(file_path)
+            schema = pq.read_schema(file_reference)
             if hasattr(schema, "names"):
                 return schema.names
             else:
                 return [field.name for field in schema]
         except Exception as e:
-            logger.warning(f"Failed to process parquet file {file_path}: {e}")
+            logger.warning(f"Failed to process parquet file {file_reference}: {e}")
             return []
     elif file_type in ["json", "jsonl"]:
-        return pd.read_json(file_path, orient="records", lines=True, nrows=1).columns.tolist()
+        return pd.read_json(file_reference, orient="records", lines=True, nrows=1).columns.tolist()
     elif file_type == "csv":
         try:
-            df = pd.read_csv(file_path, nrows=1)
+            df = pd.read_csv(file_reference, nrows=1)
             return df.columns.tolist()
         except (pd.errors.EmptyDataError, pd.errors.ParserError) as e:
-            logger.warning(f"Failed to process CSV file {file_path}: {e}")
+            logger.warning(f"Failed to process CSV file {file_reference}: {e}")
             return []
     else:
         raise InvalidFilePathError(f"🛑 Unsupported file type: {file_type!r}")
@@ -66,12 +69,36 @@ def get_file_column_names(file_path: Union[str, Path], file_type: str) -> list[s
 
 def fetch_seed_dataset_column_names(seed_dataset_reference: SeedDatasetReference) -> list[str]:
     if hasattr(seed_dataset_reference, "datastore_settings"):
-        return _fetch_seed_dataset_column_names_from_datastore(
+        return fetch_seed_dataset_column_names_from_datastore(
             seed_dataset_reference.repo_id,
             seed_dataset_reference.filename,
             seed_dataset_reference.datastore_settings,
         )
-    return _fetch_seed_dataset_column_names_from_local_file(seed_dataset_reference.dataset)
+    return fetch_seed_dataset_column_names_from_local_file(seed_dataset_reference.dataset)
+
+
+def fetch_seed_dataset_column_names_from_datastore(
+    repo_id: str,
+    filename: str,
+    datastore_settings: Optional[Union[DatastoreSettings, dict]] = None,
+) -> list[str]:
+    file_type = filename.split(".")[-1]
+    if f".{file_type}" not in VALID_DATASET_FILE_EXTENSIONS:
+        raise InvalidFileFormatError(f"🛑 Unsupported file type: {filename!r}")
+
+    datastore_settings = resolve_datastore_settings(datastore_settings)
+    fs = HfFileSystem(endpoint=datastore_settings.endpoint, token=datastore_settings.token, skip_instance_cache=True)
+
+    file_path = _extract_single_file_path_from_glob_pattern_if_present(f"datasets/{repo_id}/{filename}", fs=fs)
+
+    with fs.open(file_path) as f:
+        return get_file_column_names(f, file_type)
+
+
+def fetch_seed_dataset_column_names_from_local_file(dataset_path: str | Path) -> list[str]:
+    dataset_path = _validate_dataset_path(dataset_path, allow_glob_pattern=True)
+    dataset_path = _extract_single_file_path_from_glob_pattern_if_present(dataset_path)
+    return get_file_column_names(dataset_path, str(dataset_path).split(".")[-1])
 
 
 def resolve_datastore_settings(datastore_settings: DatastoreSettings | dict | None) -> DatastoreSettings:
@@ -114,25 +141,34 @@ def upload_to_hf_hub(
     return f"{repo_id}/{filename}"
 
 
-def _fetch_seed_dataset_column_names_from_datastore(
-    repo_id: str,
-    filename: str,
-    datastore_settings: Optional[Union[DatastoreSettings, dict]] = None,
-) -> list[str]:
-    file_type = filename.split(".")[-1]
-    if f".{file_type}" not in VALID_DATASET_FILE_EXTENSIONS:
-        raise InvalidFileFormatError(f"🛑 Unsupported file type: {filename!r}")
-
-    datastore_settings = resolve_datastore_settings(datastore_settings)
-    fs = HfFileSystem(endpoint=datastore_settings.endpoint, token=datastore_settings.token, skip_instance_cache=True)
-
-    with fs.open(f"datasets/{repo_id}/{filename}") as f:
-        return get_file_column_names(f, file_type)
-
+def _extract_single_file_path_from_glob_pattern_if_present(
+    file_path: str | Path,
+    fs: HfFileSystem | None = None,
+) -> Path:
+    file_path = Path(file_path)
 
-def _fetch_seed_dataset_column_names_from_local_file(dataset_path: str | Path) -> list[str]:
-    dataset_path = _validate_dataset_path(dataset_path, allow_glob_pattern=True)
-    return get_file_column_names(dataset_path, str(dataset_path).split(".")[-1])
+    # no glob pattern
+    if "*" not in str(file_path):
+        return file_path
+
+    # glob pattern with HfFileSystem
+    if fs is not None:
+        file_to_check = None
+        file_extension = file_path.name.split(".")[-1]
+        for file in fs.ls(str(file_path.parent)):
+            filename = file["name"]
+            if filename.endswith(f".{file_extension}"):
+                file_to_check = filename
+        if file_to_check is None:
+            raise InvalidFilePathError(f"🛑 No files found matching pattern: {str(file_path)!r}")
+        logger.debug(f"Using the first matching file in {str(file_path)!r} to determine column names in seed dataset")
+        return Path(file_to_check)
+
+    # glob pattern with local file system
+    if not (matching_files := sorted(file_path.parent.glob(file_path.name))):
+        raise InvalidFilePathError(f"🛑 No files found matching pattern: {str(file_path)!r}")
+    logger.debug(f"Using the first matching file in {str(file_path)!r} to determine column names in seed dataset")
+    return matching_files[0]
 
 
 def _validate_dataset_path(dataset_path: Union[str, Path], allow_glob_pattern: bool = False) -> Path:

data_designer/config/default_model_settings.py

@@ -78,7 +78,7 @@ def get_default_model_configs() -> list[ModelConfig]:
     return []
 
 
-def get_defaul_model_providers_missing_api_keys() -> list[str]:
+def get_default_model_providers_missing_api_keys() -> list[str]:
     missing_api_keys = []
     for predefined_provider in PREDEFINED_PROVIDERS:
         if os.environ.get(predefined_provider["api_key"]) is None:

data_designer/config/sampler_params.py

@@ -66,6 +66,7 @@ class CategorySamplerParams(ConfigBase):
             "Larger values will be sampled with higher probability."
         ),
     )
+    sampler_type: Literal[SamplerType.CATEGORY] = SamplerType.CATEGORY
 
     @model_validator(mode="after")
     def _normalize_weights_if_needed(self) -> Self:
@@ -106,6 +107,7 @@ class DatetimeSamplerParams(ConfigBase):
         default="D",
         description="Sampling units, e.g. the smallest possible time interval between samples.",
     )
+    sampler_type: Literal[SamplerType.DATETIME] = SamplerType.DATETIME
 
     @field_validator("start", "end")
     @classmethod
@@ -136,6 +138,7 @@ class SubcategorySamplerParams(ConfigBase):
         ...,
         description="Mapping from each value of parent category to a list of subcategory values.",
     )
+    sampler_type: Literal[SamplerType.SUBCATEGORY] = SamplerType.SUBCATEGORY
 
 
 class TimeDeltaSamplerParams(ConfigBase):
@@ -187,6 +190,7 @@ class TimeDeltaSamplerParams(ConfigBase):
         default="D",
         description="Sampling units, e.g. the smallest possible time interval between samples.",
     )
+    sampler_type: Literal[SamplerType.TIMEDELTA] = SamplerType.TIMEDELTA
 
     @model_validator(mode="after")
     def _validate_min_less_than_max(self) -> Self:
@@ -219,6 +223,7 @@ class UUIDSamplerParams(ConfigBase):
         default=False,
         description="If true, all letters in the UUID will be capitalized.",
     )
+    sampler_type: Literal[SamplerType.UUID] = SamplerType.UUID
 
     @property
     def last_index(self) -> int:
@@ -257,6 +262,7 @@ class ScipySamplerParams(ConfigBase):
     decimal_places: Optional[int] = Field(
         default=None, description="Number of decimal places to round the sampled values to."
     )
+    sampler_type: Literal[SamplerType.SCIPY] = SamplerType.SCIPY
 
 
 class BinomialSamplerParams(ConfigBase):
@@ -273,6 +279,7 @@ class BinomialSamplerParams(ConfigBase):
 
     n: int = Field(..., description="Number of trials.")
     p: float = Field(..., description="Probability of success on each trial.", ge=0.0, le=1.0)
+    sampler_type: Literal[SamplerType.BINOMIAL] = SamplerType.BINOMIAL
 
 
 class BernoulliSamplerParams(ConfigBase):
@@ -288,6 +295,7 @@ class BernoulliSamplerParams(ConfigBase):
     """
 
     p: float = Field(..., description="Probability of success.", ge=0.0, le=1.0)
+    sampler_type: Literal[SamplerType.BERNOULLI] = SamplerType.BERNOULLI
 
 
 class BernoulliMixtureSamplerParams(ConfigBase):
@@ -327,6 +335,7 @@ class BernoulliMixtureSamplerParams(ConfigBase):
         ...,
         description="Parameters of the scipy.stats distribution given in `dist_name`.",
     )
+    sampler_type: Literal[SamplerType.BERNOULLI_MIXTURE] = SamplerType.BERNOULLI_MIXTURE
 
 
 class GaussianSamplerParams(ConfigBase):
@@ -350,6 +359,7 @@ class GaussianSamplerParams(ConfigBase):
     decimal_places: Optional[int] = Field(
         default=None, description="Number of decimal places to round the sampled values to."
     )
+    sampler_type: Literal[SamplerType.GAUSSIAN] = SamplerType.GAUSSIAN
 
 
 class PoissonSamplerParams(ConfigBase):
@@ -369,6 +379,7 @@ class PoissonSamplerParams(ConfigBase):
     """
 
     mean: float = Field(..., description="Mean number of events in a fixed interval.")
+    sampler_type: Literal[SamplerType.POISSON] = SamplerType.POISSON
 
 
 class UniformSamplerParams(ConfigBase):
@@ -390,6 +401,7 @@ class UniformSamplerParams(ConfigBase):
     decimal_places: Optional[int] = Field(
         default=None, description="Number of decimal places to round the sampled values to."
     )
+    sampler_type: Literal[SamplerType.UNIFORM] = SamplerType.UNIFORM
 
 
 #########################################
@@ -418,9 +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.
@@ -470,11 +479,12 @@ class PersonSamplerParams(ConfigBase):
         default=False,
         description="If True, then append synthetic persona columns to each generated person.",
     )
+    sampler_type: Literal[SamplerType.PERSON] = SamplerType.PERSON
 
     @property
     def generator_kwargs(self) -> list[str]:
         """Keyword arguments to pass to the person generator."""
-        return [f for f in list(PersonSamplerParams.model_fields) if f != "locale"]
+        return [f for f in list(PersonSamplerParams.model_fields) if f not in ("locale", "sampler_type")]
 
     @property
     def people_gen_key(self) -> str:
@@ -533,11 +543,12 @@ class PersonFromFakerSamplerParams(ConfigBase):
         min_length=2,
         max_length=2,
     )
+    sampler_type: Literal[SamplerType.PERSON_FROM_FAKER] = SamplerType.PERSON_FROM_FAKER
 
     @property
     def generator_kwargs(self) -> list[str]:
         """Keyword arguments to pass to the person generator."""
-        return [f for f in list(PersonFromFakerSamplerParams.model_fields) if f != "locale"]
+        return [f for f in list(PersonFromFakerSamplerParams.model_fields) if f not in ("locale", "sampler_type")]
 
     @property
     def people_gen_key(self) -> str:

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

@@ -9,8 +9,8 @@ import pandas as pd
 from data_designer.config.analysis.dataset_profiler import DatasetProfilerResults
 from data_designer.config.config_builder import DataDesignerConfigBuilder
 from data_designer.config.default_model_settings import (
-    get_defaul_model_providers_missing_api_keys,
     get_default_model_configs,
+    get_default_model_providers_missing_api_keys,
     get_default_provider_name,
     get_default_providers,
     resolve_seed_default_model_settings,
@@ -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,
@@ -313,7 +317,7 @@ class DataDesigner(DataDesignerInterface[DatasetCreationResults]):
         if model_providers is None:
             if can_run_data_designer_locally():
                 model_providers = get_default_providers()
-                missing_api_keys = get_defaul_model_providers_missing_api_keys()
+                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."

{data_designer-0.1.1.dist-info → data_designer-0.1.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-designer
-Version: 0.1.1
+Version: 0.1.3
 Summary: General framework for synthetic data generation
 License-Expression: Apache-2.0
 License-File: LICENSE
@@ -97,8 +97,7 @@ export NVIDIA_API_KEY="your-api-key-here"
 export OPENAI_API_KEY="your-openai-api-key-here"
 ```
 
-### 3. Generate your first dataset
-
+### 3. Start generating data!
 ```python
 from data_designer.essentials import (
     CategorySamplerParams,
@@ -139,8 +138,6 @@ preview = data_designer.preview(config_builder=config_builder)
 preview.display_sample_record()
 ```
 
-**That's it!** You've created a dataset.
-
 ---
 
 ## What's next?
@@ -148,7 +145,7 @@ preview.display_sample_record()
 ### 📚 Learn more
 
 - **[Quick Start Guide](https://nvidia-nemo.github.io/DataDesigner/quick-start/)** – Detailed walkthrough with more examples
-- **[Tutorial Notebooks](https://nvidia-nemo.github.io/DataDesigner/notebooks/intro/)** – Step-by-step interactive tutorials
+- **[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

{data_designer-0.1.1.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=m8HxkqoKGw_wAJtc4ZokpJKNLXqp4zwnNhbnfDtro7w,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
@@ -31,20 +31,20 @@ data_designer/cli/services/model_service.py,sha256=Fn3c0qMZqFAEqzBr0haLjp-nLKAkk
 data_designer/cli/services/provider_service.py,sha256=pdD2_C4yK0YBabcuan95H86UreZJ5zWFGI3Ue99mXXo,3916
 data_designer/config/__init__.py,sha256=9eG4WHKyrJcNoK4GEz6BCw_E0Ewo9elQoDN4TLMbAog,137
 data_designer/config/base.py,sha256=xCbvwxXKRityWqeGP4zTXVuPHAOoUdpuQr8_t8vY8f8,2423
-data_designer/config/column_configs.py,sha256=QG65him__Xj4d47YX8x7jgVOZz81FrB9C8hpWTGzxLM,16640
+data_designer/config/column_configs.py,sha256=ixpanQApbn4LUyW7E4IJefXQG6c0eYbGxF-GGwV1xCg,18000
 data_designer/config/column_types.py,sha256=V0Ijwb-asYOX-GQyG9W-X_A-FIbFSajKuus58sG8CSM,6774
 data_designer/config/config_builder.py,sha256=NlAe6cwN6IAE90A8uPLsOdABmmYyUt6UnGYZwgmf_xE,27288
 data_designer/config/data_designer_config.py,sha256=cvIXMVQzYn9vC4GINPz972pDBmt-HrV5dvw1568LVmE,1719
 data_designer/config/dataset_builders.py,sha256=1pNFy_pkQ5lJ6AVZ43AeTuSbz6yC_l7Ndcyp5yaT8hQ,327
-data_designer/config/datastore.py,sha256=okuwUz-M5bSThvp_a9erKRoG4ej0bey1HUQBA7hgL98,6298
-data_designer/config/default_model_settings.py,sha256=b_oWsD350rb43009kcRxuPNgCZegB_noohURR4n1ZR0,4516
+data_designer/config/datastore.py,sha256=Ra6MsPCK6Q1Y8JbTQGRrKtyceig1s41ishyKSZoxgno,7572
+data_designer/config/default_model_settings.py,sha256=aMud_RrRStHnDSbwLxU3BnmIu08YtB1-EG6UUY9NedI,4517
 data_designer/config/errors.py,sha256=XneHH6tKHG2sZ71HzmPr7k3UBZ_psnSANknT30n-aa8,449
 data_designer/config/interface.py,sha256=2_tHvxtKAv0C5L7K4ztm-Xa1A-u9Njlwo2drdPa2qmk,1499
 data_designer/config/models.py,sha256=5Cy55BnKYyr-I1UHLUTqZxe6Ca9uVQWpUiwt9X0ZlrU,7521
 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=rrub7LPnXb032ClEZfo0eB0WhMekW8DFH8yr20xSz3s,25759
+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=MSzT9OFd3V6saZID0vfQxx0oB6Fth8GmEFcnmFNXOVo,16271
+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-0.1.1.dist-info/METADATA,sha256=MeR9kVPEkyXH8I-qiYdZpTiZ1yM2FWWi3PiPYsGsX9c,6698
-data_designer-0.1.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-data_designer-0.1.1.dist-info/entry_points.txt,sha256=NWWWidyDxN6CYX6y664PhBYMhbaYTQTyprqfYAgkyCg,57
-data_designer-0.1.1.dist-info/licenses/LICENSE,sha256=cSWJDwVqHyQgly8Zmt3pqXJ2eQbZVYwN9qd0NMssxXY,11336
-data_designer-0.1.1.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-0.1.1.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