ds-eda-process

What problem does it solve?

Guides a disciplined, reproducible approach to exploratory data analysis that helps you quickly identify data quality issues, understand distributions, and surface relationships before modeling.

Core Features & Use Cases

• CRISP-DM aligned Phases: Business Understanding → Data Understanding → Data Preparation to structure the analysis and deliver actionable insights with a clean, well-commented Python workflow.
• Comprehensive Understanding: Produce shape, types, missing value audits, descriptive statistics, and uniqueness checks to assess data readiness.
• Visual Exploration: Provide guidance on appropriate plots (histograms, box plots, heatmaps, scatter plots) and a consistent plotting setup to reveal patterns and outliers.
• Data Quality Assessment & Preparation: Outline missing-value strategies, outlier notes, type corrections, duplicate checks, and feature engineering opportunities; deliver an end-to-end preparation plan.

Quick Start

Provide an input dataset or path to a CSV and receive an end-to-end CRISP-DM guided EDA, including summaries, visualizations, and a data quality report.