data-designer-config 0.4.0__py3-none-any.whl

data_designer/config/__init__.py

@@ -0,0 +1,149 @@
+# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+
+from __future__ import annotations
+
+from data_designer.config.analysis.column_profilers import JudgeScoreProfilerConfig
+from data_designer.config.column_configs import (
+    EmbeddingColumnConfig,
+    ExpressionColumnConfig,
+    LLMCodeColumnConfig,
+    LLMJudgeColumnConfig,
+    LLMStructuredColumnConfig,
+    LLMTextColumnConfig,
+    SamplerColumnConfig,
+    Score,
+    SeedDatasetColumnConfig,
+    ValidationColumnConfig,
+)
+from data_designer.config.column_types import DataDesignerColumnType
+from data_designer.config.config_builder import DataDesignerConfigBuilder
+from data_designer.config.data_designer_config import DataDesignerConfig
+from data_designer.config.dataset_builders import BuildStage
+from data_designer.config.models import (
+    ChatCompletionInferenceParams,
+    EmbeddingInferenceParams,
+    GenerationType,
+    ImageContext,
+    ImageFormat,
+    ManualDistribution,
+    ManualDistributionParams,
+    Modality,
+    ModalityContext,
+    ModalityDataType,
+    ModelConfig,
+    ModelProvider,
+    UniformDistribution,
+    UniformDistributionParams,
+)
+from data_designer.config.processors import (
+    DropColumnsProcessorConfig,
+    ProcessorType,
+    SchemaTransformProcessorConfig,
+)
+from data_designer.config.run_config import RunConfig
+from data_designer.config.sampler_constraints import ColumnInequalityConstraint, ScalarInequalityConstraint
+from data_designer.config.sampler_params import (
+    BernoulliMixtureSamplerParams,
+    BernoulliSamplerParams,
+    BinomialSamplerParams,
+    CategorySamplerParams,
+    DatetimeSamplerParams,
+    GaussianSamplerParams,
+    PersonFromFakerSamplerParams,
+    PersonSamplerParams,
+    PoissonSamplerParams,
+    SamplerType,
+    ScipySamplerParams,
+    SubcategorySamplerParams,
+    TimeDeltaSamplerParams,
+    UniformSamplerParams,
+    UUIDSamplerParams,
+)
+from data_designer.config.seed import (
+    IndexRange,
+    PartitionBlock,
+    SamplingStrategy,
+    SeedConfig,
+)
+from data_designer.config.seed_source import (
+    DataFrameSeedSource,
+    HuggingFaceSeedSource,
+    LocalFileSeedSource,
+)
+from data_designer.config.utils.code_lang import CodeLang
+from data_designer.config.utils.info import InfoType
+from data_designer.config.validator_params import (
+    CodeValidatorParams,
+    LocalCallableValidatorParams,
+    RemoteValidatorParams,
+    ValidatorType,
+)
+
+
+def get_config_exports() -> list[str]:
+    return [
+        SchemaTransformProcessorConfig.__name__,
+        BernoulliMixtureSamplerParams.__name__,
+        BernoulliSamplerParams.__name__,
+        BinomialSamplerParams.__name__,
+        CategorySamplerParams.__name__,
+        CodeLang.__name__,
+        CodeValidatorParams.__name__,
+        ColumnInequalityConstraint.__name__,
+        ChatCompletionInferenceParams.__name__,
+        DataDesignerColumnType.__name__,
+        DataDesignerConfig.__name__,
+        DataDesignerConfigBuilder.__name__,
+        DataFrameSeedSource.__name__,
+        BuildStage.__name__,
+        DatetimeSamplerParams.__name__,
+        DropColumnsProcessorConfig.__name__,
+        EmbeddingColumnConfig.__name__,
+        EmbeddingInferenceParams.__name__,
+        ExpressionColumnConfig.__name__,
+        GaussianSamplerParams.__name__,
+        GenerationType.__name__,
+        HuggingFaceSeedSource.__name__,
+        IndexRange.__name__,
+        InfoType.__name__,
+        ImageContext.__name__,
+        ImageFormat.__name__,
+        JudgeScoreProfilerConfig.__name__,
+        LLMCodeColumnConfig.__name__,
+        LLMJudgeColumnConfig.__name__,
+        LLMStructuredColumnConfig.__name__,
+        LLMTextColumnConfig.__name__,
+        LocalCallableValidatorParams.__name__,
+        LocalFileSeedSource.__name__,
+        ManualDistribution.__name__,
+        ManualDistributionParams.__name__,
+        Modality.__name__,
+        ModalityContext.__name__,
+        ModalityDataType.__name__,
+        ModelConfig.__name__,
+        ModelProvider.__name__,
+        PartitionBlock.__name__,
+        PersonSamplerParams.__name__,
+        PersonFromFakerSamplerParams.__name__,
+        PoissonSamplerParams.__name__,
+        ProcessorType.__name__,
+        RemoteValidatorParams.__name__,
+        RunConfig.__name__,
+        SamplerColumnConfig.__name__,
+        SamplerType.__name__,
+        SamplingStrategy.__name__,
+        ScalarInequalityConstraint.__name__,
+        ScipySamplerParams.__name__,
+        Score.__name__,
+        SeedConfig.__name__,
+        SeedDatasetColumnConfig.__name__,
+        SubcategorySamplerParams.__name__,
+        TimeDeltaSamplerParams.__name__,
+        UniformDistribution.__name__,
+        UniformDistributionParams.__name__,
+        UniformSamplerParams.__name__,
+        UUIDSamplerParams.__name__,
+        ValidationColumnConfig.__name__,
+        ValidatorType.__name__,
+    ]

data_designer/config/_version.py

@@ -0,0 +1,34 @@
+# file generated by setuptools-scm
+# don't change, don't track in version control
+
+__all__ = [
+    "__version__",
+    "__version_tuple__",
+    "version",
+    "version_tuple",
+    "__commit_id__",
+    "commit_id",
+]
+
+TYPE_CHECKING = False
+if TYPE_CHECKING:
+    from typing import Tuple
+    from typing import Union
+
+    VERSION_TUPLE = Tuple[Union[int, str], ...]
+    COMMIT_ID = Union[str, None]
+else:
+    VERSION_TUPLE = object
+    COMMIT_ID = object
+
+version: str
+__version__: str
+__version_tuple__: VERSION_TUPLE
+version_tuple: VERSION_TUPLE
+commit_id: COMMIT_ID
+__commit_id__: COMMIT_ID
+
+__version__ = version = '0.4.0'
+__version_tuple__ = version_tuple = (0, 4, 0)
+
+__commit_id__ = commit_id = None

data_designer/config/analysis/__init__.py

@@ -0,0 +1,2 @@
+# SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0

data_designer/config/analysis/column_profilers.py

@@ -0,0 +1,159 @@
+# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+# SPDX-License-Identifier: Apache-2.0
+
+from __future__ import annotations
+
+from abc import ABC
+from enum import Enum
+
+from pydantic import BaseModel, Field
+from rich.panel import Panel
+from rich.table import Column, Table
+from typing_extensions import TypeAlias
+
+from data_designer.config.analysis.column_statistics import (
+    CategoricalDistribution,
+    CategoricalHistogramData,
+    ColumnDistributionType,
+    MissingValue,
+    NumericalDistribution,
+)
+from data_designer.config.analysis.utils.reporting import TITLE_STYLE, create_judge_score_summary_table
+from data_designer.config.base import ConfigBase
+from data_designer.config.utils.visualization import ColorPalette
+
+
+class ColumnProfilerType(str, Enum):
+    JUDGE_SCORE = "judge-score"
+
+
+class ColumnProfilerResults(BaseModel, ABC):
+    """Abstract base class for column profiler results.
+
+    Stores results from column profiling operations. Subclasses hold profiler-specific
+    analysis results and provide methods for generating formatted report sections for display.
+    """
+
+    def create_report_section(self) -> Panel:
+        """Creates a Rich Panel containing the formatted profiler results for display.
+
+        Returns:
+            A Rich Panel containing the formatted profiler results. Default implementation
+            returns a "Not Implemented" message; subclasses should override to provide
+            specific formatting.
+        """
+        return Panel(
+            f"Report section generation not implemented for '{self.__class__.__name__}'.",
+            title="Not Implemented",
+            border_style=f"bold {ColorPalette.YELLOW.value}",
+            padding=(1, 2),
+        )
+
+
+class JudgeScoreProfilerConfig(ConfigBase):
+    """Configuration for the LLM-as-a-judge score profiler.
+
+    Attributes:
+        model_alias: Alias of the LLM model to use for generating score distribution summaries.
+            Must match a model alias defined in the Data Designer configuration.
+        summary_score_sample_size: Number of score samples to include when prompting the LLM
+            to generate summaries. Larger sample sizes provide more context but increase
+            token usage. Must be at least 1. Defaults to 20.
+    """
+
+    model_alias: str
+    summary_score_sample_size: int | None = Field(default=20, ge=1)
+
+
+class JudgeScoreSample(BaseModel):
+    """Container for a single judge score and its associated reasoning.
+
+    Stores a paired score-reasoning sample extracted from an LLM-as-a-judge column.
+    Used when generating summaries to provide the LLM with examples of scoring patterns.
+
+    Attributes:
+        score: The score value assigned by the judge. Can be numeric (int) or categorical (str).
+        reasoning: The reasoning or explanation provided by the judge for this score.
+    """
+
+    score: int | str
+    reasoning: str
+
+
+class JudgeScoreDistributions(BaseModel):
+    """Container for computed distributions across all judge score dimensions.
+
+    Stores the complete distribution analysis for all score dimensions in an LLM-as-a-judge
+    column. Each score dimension (e.g., "relevance", "fluency") has its own distribution
+    computed from the generated data.
+
+    Attributes:
+        scores: Mapping of each score dimension name to its list of score values.
+        reasoning: Mapping of each score dimension name to its list of reasoning texts.
+        distribution_types: Mapping of each score dimension name to its classification.
+        distributions: Mapping of each score dimension name to its computed distribution statistics.
+        histograms: Mapping of each score dimension name to its histogram data.
+    """
+
+    scores: dict[str, list[int | str]]
+    reasoning: dict[str, list[str]]
+    distribution_types: dict[str, ColumnDistributionType]
+    distributions: dict[str, CategoricalDistribution | NumericalDistribution | MissingValue]
+    histograms: dict[str, CategoricalHistogramData | MissingValue]
+
+
+class JudgeScoreSummary(BaseModel):
+    """Container for an LLM-generated summary of a judge score dimension.
+
+    Stores the natural language summary and sample data for a single score dimension
+    generated by the judge score profiler. The summary is created by an LLM analyzing
+    the distribution and patterns in the score-reasoning pairs.
+
+    Attributes:
+        score_name: Name of the score dimension being summarized (e.g., "relevance", "fluency").
+        summary: LLM-generated natural language summary describing the scoring patterns,
+            distribution characteristics, and notable trends for this score dimension.
+        score_samples: List of score-reasoning pairs that were used to generate the summary.
+            These are the examples of the scoring behavior that were used to generate the summary.
+    """
+
+    score_name: str
+    summary: str
+    score_samples: list[JudgeScoreSample]
+
+
+class JudgeScoreProfilerResults(ColumnProfilerResults):
+    """Container for complete judge score profiler analysis results.
+
+    Attributes:
+        column_name: Name of the judge column that was profiled.
+        summaries: Mapping of each score dimension name to its LLM-generated summary.
+        score_distributions: Complete distribution analysis across all score dimensions.
+    """
+
+    column_name: str
+    summaries: dict[str, JudgeScoreSummary]
+    score_distributions: JudgeScoreDistributions | MissingValue
+
+    def create_report_section(self) -> Panel:
+        layout = Table.grid(Column(), expand=True, padding=(2, 0))
+
+        for score_name in self.summaries.keys():
+            layout.add_row(
+                create_judge_score_summary_table(
+                    score_name=score_name,
+                    histogram=self.score_distributions.histograms[score_name],
+                    summary=self.summaries[score_name].summary,
+                )
+            )
+
+        return Panel(
+            layout,
+            title=f"[{TITLE_STYLE}]LLM-as-a-Judge Score Profile: '{self.column_name}'[/{TITLE_STYLE}]",
+            padding=(1, 2),
+        )
+
+
+ColumnProfilerConfigT: TypeAlias = JudgeScoreProfilerConfig
+
+ColumnProfilerResultsT: TypeAlias = JudgeScoreProfilerResults