data-designer 0.1.4__tar.gz → 0.2.0__tar.gz

data_designer-0.2.0/.github/workflows/build-docs.yml

@@ -0,0 +1,68 @@
+name: Build docs
+on:
+  workflow_dispatch:
+  release:
+    types:
+      - published
+
+jobs:
+  build-notebooks:
+    uses: ./.github/workflows/build-notebooks.yml
+    secrets: inherit
+  deploy:
+    needs: build-notebooks
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v2
+      - name: Install uv
+        uses: astral-sh/setup-uv@v6
+        with:
+          version: "0.9.5"
+      - name: Set up Python
+        run: uv python install
+      - name: Install dependencies for docs
+        run: uv sync --group docs
+      - name: Download artifact from previous step
+        uses: actions/download-artifact@v5
+        with:
+          name: notebooks
+          path: docs/notebooks
+      - name: Find the latest existing release tag
+        id: get_release
+        run: |
+          if [ "${{ github.event_name }}" == "release" ]; then
+            LATEST_TAG="${{ github.event.release.tag_name }}"
+          else
+            echo "::notice::Running manually via workflow_dispatch. Fetching latest release tag..."
+
+            gh auth status || echo "GitHub CLI is not authenticated, relying on GITHUB_TOKEN."
+
+            # We use tr -d '\n' to remove the trailing newline for a clean tag string
+            LATEST_TAG=$(gh release view --json tagName -q .tagName 2>/dev/null)
+
+            if [ -z "$LATEST_TAG" ]; then
+              echo "::error::Could not find the latest published release tag. Ensure a release exists."
+              exit 1
+            fi
+          fi
+
+          echo "Latest release tag found: $LATEST_TAG"
+          echo "LATEST_TAG=$LATEST_TAG" >> $GITHUB_ENV
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+      - name: Extract version from release tag
+        run: |
+          # Remove the 'v' prefix and any suffix after a space
+          VERSION=$(echo ${{ env.LATEST_TAG }} | sed 's/^v//' | sed 's/ .*$//')
+          echo "::notice::Extracted version: $VERSION"
+          echo "VERSION=$VERSION" >> $GITHUB_ENV
+      - name: Setup doc deploy
+        run: |
+          git fetch origin gh-pages --depth=1
+          git config --global user.name "github-actions[bot]"
+          git config --global user.email "41898282+github-actions[bot]@users.noreply.github.com"
+      - name: Build and deploy docs
+        run: uv run mike deploy --push --update-aliases ${{ env.VERSION }} latest

data_designer-0.2.0/.github/workflows/check-colab-notebooks.yml

@@ -0,0 +1,55 @@
+name: Check Colab notebooks
+
+on:
+  push:
+    branches: [ main ]
+    paths:
+      - 'docs/notebook_source/*.py'
+  pull_request:
+    branches: [ main ]
+    paths:
+      - 'docs/notebook_source/*.py'
+  workflow_dispatch:
+
+jobs:
+  check-colab-notebooks:
+    name: Check Colab Notebooks
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+        with:
+          version: "latest"
+          python-version: "3.11"
+          enable-cache: true
+
+      - name: Install dependencies
+        run: |
+          uv sync --group notebooks --group docs
+
+      - name: Generate Colab notebooks
+        run: |
+          make generate-colab-notebooks
+
+      - name: Check for differences
+        run: |
+          # Get the diff, filtering out cell ID changes (which are randomly generated)
+          # Filter out: file markers (--- and +++), and "id" lines
+          MEANINGFUL_DIFF=$(git diff docs/colab_notebooks/ | grep -E '^[+-]' | grep -v '^---' | grep -v '^+++' | grep -vE '^[+-]\s*"id": "[0-9a-fA-F]+",?$' || true)
+
+          if [ -z "$MEANINGFUL_DIFF" ]; then
+            echo "✅ Colab notebooks are up-to-date (ignoring cell ID changes)"
+          else
+            echo "❌ Colab notebooks are out of sync with source files"
+            echo ""
+            echo "The generated notebooks differ from the committed ones."
+            echo "Please run 'make generate-colab-notebooks' locally and commit the changes."
+            echo ""
+            echo "Differences found:"
+            echo "$MEANINGFUL_DIFF"
+            exit 1
+          fi

{data_designer-0.1.4 → data_designer-0.2.0}/.gitignore

@@ -90,4 +90,4 @@ src/data_designer/_version.py
 docs/notebooks/
 docs/notebook_source/*.ipynb
 docs/notebook_source/*.csv
-docs/notebook_source/artifacts/
+docs/**/artifacts/

{data_designer-0.1.4 → data_designer-0.2.0}/.pre-commit-config.yaml

@@ -6,6 +6,7 @@ repos:
       - id: trailing-whitespace
       - id: end-of-file-fixer
       - id: check-yaml
+        exclude: ^mkdocs\.yml$
       - id: check-added-large-files
       - id: check-json
       - id: check-toml

{data_designer-0.1.4 → data_designer-0.2.0}/Makefile

@@ -36,6 +36,7 @@ help:
 	@echo "🛠️  Utilities:"
 	@echo "  clean                     - Remove coverage reports and cache files"
 	@echo "  convert-execute-notebooks - Convert notebooks from .py to .ipynb using jupytext"
+	@echo "  generate-colab-notebooks  - Generate Colab-compatible notebooks"
 	@echo "  serve-docs-locally        - Serve documentation locally"
 	@echo "  check-license-headers     - Check if all files have license headers"
 	@echo "  update-license-headers    - Add license headers to all files"
@@ -95,6 +96,11 @@ convert-execute-notebooks:
 	rm docs/notebook_source/*.csv
 	@echo "✅ Notebooks created in docs/notebooks/"
 
+generate-colab-notebooks:
+	@echo "📓 Generating Colab-compatible notebooks..."
+	uv run --group notebooks python docs/scripts/generate_colab_notebooks.py
+	@echo "✅ Colab notebooks created in docs/colab_notebooks/"
+
 serve-docs-locally:
 	@echo "📝 Building and serving docs..."
 	uv sync --group docs
@@ -125,4 +131,4 @@ install-dev-notebooks:
 	$(call install-pre-commit-hooks)
 	@echo "✅ Dev + notebooks installation complete!"
 
-.PHONY: clean coverage format format-check lint lint-fix test check-license-headers update-license-headers check-all check-all-fix install install-dev install-dev-notebooks
+.PHONY: clean coverage format format-check lint lint-fix test check-license-headers update-license-headers check-all check-all-fix install install-dev install-dev-notebooks generate-colab-notebooks

{data_designer-0.1.4 → data_designer-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: data-designer
-Version: 0.1.4
+Version: 0.2.0
 Summary: General framework for synthetic data generation
 License-Expression: Apache-2.0
 License-File: LICENSE
@@ -144,12 +144,12 @@ 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/)** – 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/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
+- **[Quick Start Guide](https://nvidia-nemo.github.io/DataDesigner/latest/quick-start/)** – Detailed walkthrough with more examples
+- **[Tutorial Notebooks](https://nvidia-nemo.github.io/DataDesigner/latest/notebooks/)** – Step-by-step interactive tutorials
+- **[Column Types](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/columns/)** – Explore samplers, LLM columns, validators, and more
+- **[Validators](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/validators/)** – Learn how to validate generated data with Python, SQL, and remote validators
+- **[Model Configuration](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/models/model-configs/)** – Configure custom models and providers
+- **[Person Sampling](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/person_sampling/)** – Learn how to sample realistic person data with demographic attributes
 
 ### 🔧 Configure models via CLI
 
@@ -161,7 +161,7 @@ data-designer config list      # View current settings
 
 ### 🤝 Get involved
 
-- **[Contributing Guide](https://nvidia-nemo.github.io/DataDesigner/CONTRIBUTING)** – Help improve Data Designer
+- **[Contributing Guide](https://nvidia-nemo.github.io/DataDesigner/latest/CONTRIBUTING)** – Help improve Data Designer
 - **[GitHub Issues](https://github.com/NVIDIA-NeMo/DataDesigner/issues)** – Report bugs or make a feature request
 
 ---
@@ -178,7 +178,7 @@ If you use NeMo Data Designer in your research, please cite it using the followi
 
 ```bibtex
 @misc{nemo-data-designer,
-  author = {The NeMo Data Designer Team},
+  author = {The NeMo Data Designer Team, NVIDIA},
   title = {NeMo Data Designer: A framework for generating synthetic data from scratch or based on your own seed data},
   howpublished = {\url{https://github.com/NVIDIA-NeMo/DataDesigner}},
   year = {2025},

{data_designer-0.1.4 → data_designer-0.2.0}/README.md

@@ -95,12 +95,12 @@ 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/)** – 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/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
+- **[Quick Start Guide](https://nvidia-nemo.github.io/DataDesigner/latest/quick-start/)** – Detailed walkthrough with more examples
+- **[Tutorial Notebooks](https://nvidia-nemo.github.io/DataDesigner/latest/notebooks/)** – Step-by-step interactive tutorials
+- **[Column Types](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/columns/)** – Explore samplers, LLM columns, validators, and more
+- **[Validators](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/validators/)** – Learn how to validate generated data with Python, SQL, and remote validators
+- **[Model Configuration](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/models/model-configs/)** – Configure custom models and providers
+- **[Person Sampling](https://nvidia-nemo.github.io/DataDesigner/latest/concepts/person_sampling/)** – Learn how to sample realistic person data with demographic attributes
 
 ### 🔧 Configure models via CLI
 
@@ -112,7 +112,7 @@ data-designer config list      # View current settings
 
 ### 🤝 Get involved
 
-- **[Contributing Guide](https://nvidia-nemo.github.io/DataDesigner/CONTRIBUTING)** – Help improve Data Designer
+- **[Contributing Guide](https://nvidia-nemo.github.io/DataDesigner/latest/CONTRIBUTING)** – Help improve Data Designer
 - **[GitHub Issues](https://github.com/NVIDIA-NeMo/DataDesigner/issues)** – Report bugs or make a feature request
 
 ---
@@ -129,7 +129,7 @@ If you use NeMo Data Designer in your research, please cite it using the followi
 
 ```bibtex
 @misc{nemo-data-designer,
-  author = {The NeMo Data Designer Team},
+  author = {The NeMo Data Designer Team, NVIDIA},
   title = {NeMo Data Designer: A framework for generating synthetic data from scratch or based on your own seed data},
   howpublished = {\url{https://github.com/NVIDIA-NeMo/DataDesigner}},
   year = {2025},

data_designer-0.2.0/docs/assets/recipes/code_generation/text_to_python.py

@@ -0,0 +1,318 @@
+from pathlib import Path
+
+from data_designer.essentials import (
+    CategorySamplerParams,
+    CodeLang,
+    CodeValidatorParams,
+    DataDesigner,
+    DataDesignerConfigBuilder,
+    LLMCodeColumnConfig,
+    LLMJudgeColumnConfig,
+    LLMTextColumnConfig,
+    SamplerColumnConfig,
+    SamplerType,
+    Score,
+    SubcategorySamplerParams,
+    ValidationColumnConfig,
+    ValidatorType,
+)
+from data_designer.interface.results import DatasetCreationResults
+
+
+def build_config(model_alias: str) -> DataDesignerConfigBuilder:
+    config_builder = DataDesignerConfigBuilder()
+
+    config_builder.add_column(
+        SamplerColumnConfig(
+            name="industry_sector",
+            sampler_type=SamplerType.CATEGORY,
+            params=CategorySamplerParams(
+                values=[
+                    "Healthcare",
+                    "Finance",
+                    "Technology",
+                ],
+            ),
+        ),
+    )
+
+    config_builder.add_column(
+        SamplerColumnConfig(
+            name="topic",
+            sampler_type=SamplerType.SUBCATEGORY,
+            params=SubcategorySamplerParams(
+                category="industry_sector",
+                values={
+                    "Healthcare": [
+                        "Electronic Health Records (EHR) Systems",
+                        "Telemedicine Platforms",
+                        "AI-Powered Diagnostic Tools",
+                    ],
+                    "Finance": [
+                        "Fraud Detection Software",
+                        "Automated Trading Systems",
+                        "Personal Finance Apps",
+                    ],
+                    "Technology": [
+                        "Cloud Computing Platforms",
+                        "Artificial Intelligence and Machine Learning Platforms",
+                        "DevOps and CI/CD Tools",
+                    ],
+                },
+            ),
+        ),
+    )
+
+    config_builder.add_column(
+        SamplerColumnConfig(
+            name="code_complexity",
+            sampler_type=SamplerType.CATEGORY,
+            params=CategorySamplerParams(
+                values=[
+                    "Beginner",
+                    "Intermediate",
+                    "Advanced",
+                ],
+            ),
+        ),
+    )
+
+    config_builder.add_column(
+        SamplerColumnConfig(
+            name="code_concept",
+            sampler_type=SamplerType.SUBCATEGORY,
+            params=SubcategorySamplerParams(
+                category="code_complexity",
+                values={
+                    "Beginner": [
+                        "Variables",
+                        "Data Types",
+                        "Functions",
+                        "Loops",
+                        "Classes",
+                    ],
+                    "Intermediate": [
+                        "List Comprehensions",
+                        "Object-oriented programming",
+                        "Lambda Functions",
+                        "Web frameworks",
+                        "Pandas",
+                    ],
+                    "Advanced": [
+                        "Multithreading",
+                        "Context Managers",
+                        "Generators",
+                    ],
+                },
+            ),
+        ),
+    )
+
+    config_builder.add_column(
+        SamplerColumnConfig(
+            name="instruction_phrase",
+            sampler_type=SamplerType.CATEGORY,
+            params=CategorySamplerParams(
+                values=[
+                    "Write a function that",
+                    "Create a class that",
+                    "Implement a script",
+                    "Can you create a function",
+                    "Develop a module that",
+                ],
+            ),
+        ),
+    )
+
+    config_builder.add_column(
+        LLMTextColumnConfig(
+            name="instruction",
+            model_alias=model_alias,
+            system_prompt=("You are an expert at generating clear and specific programming tasks."),
+            prompt=(
+                "Generate an instruction to create Python code that solves a specific problem.\n"
+                "Each instruction should begin with one of the following phrases: {{ instruction_phrase }}.\n\n"
+                "Important Guidelines:\n"
+                "* Industry Relevance: Ensure the instruction pertains to the {{ industry_sector }} sector and {{ topic }} topic.\n"
+                "* Code Complexity: Tailor the instruction to the {{ code_complexity }} level. Utilize relevant {{ code_concept }} where appropriate to match the complexity level.\n"
+                "* Clarity and Specificity: Make the problem statement clear and unambiguous. Provide sufficient context to understand the requirements without being overly verbose.\n"
+                "* Response Formatting: Do not include any markers such as ### Response ### in the instruction.\n"
+            ),
+        )
+    )
+
+    config_builder.add_column(
+        LLMCodeColumnConfig(
+            name="code_implementation",
+            model_alias=model_alias,
+            code_lang=CodeLang.PYTHON,
+            system_prompt=(
+                "You are an expert Python programmer who writes clean, efficient, and well-documented code."
+            ),
+            prompt=(
+                "Write Python code for the following instruction:\n"
+                "Instruction: {{ instruction }}\n\n"
+                "Important Guidelines:\n"
+                "* Code Quality: Your code should be clean, complete, self-contained, and accurate.\n"
+                "* Code Validity: Please ensure that your Python code is executable and does not contain any errors.\n"
+                "* Packages: Remember to import any necessary libraries, and to use all libraries you import.\n"
+                "* Complexity & Concepts: The code should be written at a {{ code_complexity }} level, making use of concepts such as {{code_concept}}.\n"
+            ),
+        )
+    )
+
+    config_builder.add_column(
+        LLMTextColumnConfig(
+            name="instruction",
+            model_alias=model_alias,
+            system_prompt=("You are an expert at generating clear and specific programming tasks."),
+            prompt=(
+                "Generate an instruction to create Python code that solves a specific problem.\n"
+                "Each instruction should begin with one of the following phrases: {{ instruction_phrase }}.\n\n"
+                "Important Guidelines:\n"
+                "* Industry Relevance: Ensure the instruction pertains to the {{ industry_sector }} sector and {{ topic }} topic.\n"
+                "* Code Complexity: Tailor the instruction to the {{ code_complexity }} level. Utilize relevant {{ code_concept }} where appropriate to match the complexity level.\n"
+                "* Clarity and Specificity: Make the problem statement clear and unambiguous. Provide sufficient context to understand the requirements without being overly verbose.\n"
+                "* Response Formatting: Do not include any markers such as ### Response ### in the instruction.\n"
+            ),
+        )
+    )
+
+    config_builder.add_column(
+        LLMCodeColumnConfig(
+            name="code_implementation",
+            model_alias=model_alias,
+            code_lang=CodeLang.PYTHON,
+            system_prompt=(
+                "You are an expert Python programmer who writes clean, efficient, and well-documented code."
+            ),
+            prompt=(
+                "Write Python code for the following instruction:\n"
+                "Instruction: {{ instruction }}\n\n"
+                "Important Guidelines:\n"
+                "* Code Quality: Your code should be clean, complete, self-contained, and accurate.\n"
+                "* Code Validity: Please ensure that your Python code is executable and does not contain any errors.\n"
+                "* Packages: Remember to import any necessary libraries, and to use all libraries you import.\n"
+                "* Complexity & Concepts: The code should be written at a {{ code_complexity }} level, making use of concepts such as {{ code_concept }}.\n"
+            ),
+        )
+    )
+
+    config_builder.add_column(
+        LLMJudgeColumnConfig(
+            name="code_judge_result",
+            model_alias=model_alias,
+            prompt=TEXT_TO_PYTHON_JUDGE_TEMPLATE,
+            scores=python_scoring,
+        )
+    )
+
+    config_builder.add_column(
+        ValidationColumnConfig(
+            name="code_validity_result",
+            validator_type=ValidatorType.CODE,
+            target_columns=["code_implementation"],
+            validator_params=CodeValidatorParams(
+                code_lang=CodeLang.PYTHON,
+            ),
+            batch_size=100,
+        )
+    )
+
+    return config_builder
+
+
+def create_dataset(
+    config_builder: DataDesignerConfigBuilder,
+    num_records: int,
+    artifact_path: Path | str | None = None,
+) -> DatasetCreationResults:
+    data_designer = DataDesigner(artifact_path=artifact_path)
+    results = data_designer.create(config_builder, num_records=num_records)
+    return results
+
+
+TEXT_TO_PYTHON_JUDGE_TEMPLATE = """\
+You are an expert in Python programming, with specialized knowledge in software engineering, data science, and algorithmic problem-solving.
+
+You think about potential flaws and errors in the code. You are a tough critic, but a fair one.
+
+Take a deep breath and use the Python Code Quality Rubric below to score the **Generated Python Code** based on the INSTRUCTIONS.
+
+#### INSTRUCTIONS
+The Generated Python Code should be a valid response to the Natural Language Prompt below
+
+Natural Language Prompt:
+{{ instruction }}
+
+Generated Python Code
+{{ code_implementation }}
+"""
+
+
+python_scoring = [
+    Score(
+        name="Relevance",
+        description="Adherence to INSTRUCTIONS and CONTEXT",
+        options={
+            4: "Perfectly meets all specified requirements.",
+            3: "Meets most requirements with minor deviations.",
+            2: "Moderate deviation from the instructions.",
+            1: "Significant deviations from the instructions.",
+            0: "Does not adhere to the instructions.",
+        },
+    ),
+    Score(
+        name="Pythonic",
+        description="Pythonic Code and Best Practices (Does the code follow Python conventions and best practices?)",
+        options={
+            4: "The code exemplifies Pythonic principles, making excellent use of Python-specific constructs, standard library modules and programming idioms; follows all relevant PEPs.",
+            3: "The code closely follows Python conventions and adheres to many best practices; good use of Python-specific constructs, standard library modules and programming idioms.",
+            2: "The code generally follows Python conventions but has room for better alignment with Pythonic practices.",
+            1: "The code loosely follows Python conventions, with several deviations from best practices.",
+            0: "The code does not follow Python conventions or best practices, using non-Pythonic approaches.",
+        },
+    ),
+    Score(
+        name="Readability",
+        description="Readability and Maintainability (Is the Python code easy to understand and maintain?)",
+        options={
+            4: (
+                "The code is excellently formatted, follows PEP 8 guidelines, is elegantly concise and clear, uses meaningful variable names, "
+                "ensuring high readability and ease of maintenance; organizes complex logic well. Docstrings are given in a Google Docstring format."
+            ),
+            3: "The code is well-formatted in the sense of code-as-documentation, making it relatively easy to understand and maintain; uses descriptive names and organizes logic clearly.",
+            2: "The code is somewhat readable with basic formatting and some comments, but improvements are needed; needs better use of descriptive names and organization.",
+            1: "The code has minimal formatting, making it hard to understand; lacks meaningful names and organization.",
+            0: "The code is unreadable, with no attempt at formatting or description.",
+        },
+    ),
+    Score(
+        name="Efficiency",
+        description="Efficiency and Performance (Is the code optimized for performance?)",
+        options={
+            4: "The solution is highly efficient, using appropriate data structures and algorithms; avoids unnecessary computations and optimizes for both time and space complexity.",
+            3: "The solution is efficient, with good use of Python's built-in functions and libraries; minor areas for optimization.",
+            2: "The solution is moderately efficient, but misses some opportunities for optimization; uses some inefficient patterns.",
+            1: "The solution shows poor efficiency, with notable performance issues; lacks effective optimization techniques.",
+            0: "The solution is highly inefficient; overlooks fundamental optimization practices, resulting in significant performance issues.",
+        },
+    ),
+]
+
+
+if __name__ == "__main__":
+    from argparse import ArgumentParser
+
+    parser = ArgumentParser()
+    parser.add_argument("--model-alias", type=str, default="openai-text")
+    parser.add_argument("--num-records", type=int, default=5)
+    parser.add_argument("--artifact-path", type=str, default=None)
+    args = parser.parse_args()
+
+    config_builder = build_config(model_alias=args.model_alias)
+    results = create_dataset(config_builder, num_records=args.num_records, artifact_path=args.artifact_path)
+
+    print(f"Dataset saved to: {results.artifact_storage.final_dataset_path}")
+
+    results.load_analysis().to_report()