MediStat EDA
Exploratory Data Analysis
Explore distributions, missing data and potential outliers with Exploratory Data Analysis (EDA). The tool produces a Korean HTML report highlighting issues to review before analysis.
What to prepare
An Excel or CSV dataset and the study design
What you get
An HTML report covering distributions, missing data and correlations
Requirements
Python 3.9+ · pandas, numpy, matplotlib, scipy, openpyxl
Python setup guide ↗Interpreting the results
Flagged outliers are candidates for review. The report does not automatically clean your data or finalize an analysis method.
Install in Claude Code
Enter these commands in the Code view of the Claude app or the Claude Code panel in VS Code. These are installation commands, not prompts for a regular Claude chat.
Run the first line, then the second. Restart Claude Code after installation to load the skill.
/plugin marketplace add JeonKH81/MediStat-EDA /plugin install medistat-eda@medistat-eda
These commands register the skill. Python, R and analysis packages must be prepared separately; check the requirements above and the original documentation.
Installation instructions on GitHub ↗Try this prompt after installation
Replace the bracketed fields with your own information, then paste the prompt into Claude Code.
[Goal] Create an exploratory data analysis report for my study. [Inputs] File: [data filename] Study design: [study design] Comparison groups: [group variable] [Task] Use MediStat EDA to examine distributions, missing data and potential outliers, and generate an HTML report. The tool defaults to Korean; please report whether an English version can also be produced. [Checks] Ask about missing information before analysis. Do not modify the data without asking.
This page provides usage and installation guidance. Analyses and file processing take place in your installed Claude Code environment.