Search

PythonReactSEOPDF
GitHub Skill

ydata-eda-profiling

Generate and compare ydata-profiling EDA reports with sampling, consistent random seeds, and HTML outputs; often follows duckdb-parquet-lab-workflow when data is queried from Parquet.

crossxwill☆ 5 Repository stars0 Repository forks

Installation

Follow the repository instructions for this skill and your agent. Review the files and dependencies before adding it to your workflow.

View source ↗Guides

Skill instructions

YData Profiling EDA

Purpose

Create consistent EDA reports for train and test or accepted and rejected datasets using ProfileReport, including comparisons and saved HTML outputs.

Usage

  • "generate ydata-profiling report"
  • "compare train and test EDA"
  • "create HTML EDA report"

Instructions

  1. Set a sampling fraction for large datasets and a fixed random seed.
  2. Create ProfileReport objects with progress_bar=False, and disable duplicates and interactions when speed matters.
  3. Compare reports using .compare() and save to HTML with .to_file().
  4. Use ./scripts/generate_eda_report.py for consistent report creation.
  5. Use ./templates/eda_compare_block.md to document inputs, sample fractions, and output paths.

Examples

Read the usage examples in the source repository.

View source ↗

Source history

Indexed on
2026-01-20
Index updated
2026-01-26
Branch
main

Index and sync dates describe this directory. View the source repository for code history.

GitHub ↗

chat Comments (0)

chat_bubble_outline

No comments yet. Be the first to share your thoughts!