Can this handle large datasets without crashing?

Yes, it includes a --sample-size parameter for large files and a 'minimal' mode that focuses on essential statistics to reduce memory usage and processing time.

What kind of statistical insights are provided?

The report includes central tendency measures, dispersion, skewness, kurtosity, Pearson/Spearman correlation matrices, and missing value heatmaps.

Does it require manual steps to view the analysis?

No, the skill is designed to automatically detect your operating system (macOS, Linux, or Windows) and open the generated HTML report in your default browser immediately after completion.

What data formats does the Profiling skill support?

The skill supports a wide range of common data formats including CSV, Excel, Parquet, and JSON.

Data Profiling & EDA

Name: Data Profiling & EDA
Author: dandacompany

bydandacompany

•

Data Science & ML

Generates comprehensive data profiling reports and automated exploratory data analysis (EDA) for various datasets.

The Profiling skill automates the critical first steps of any data science project by performing deep statistical analysis and data quality validation. Using ydata-profiling, it automatically detects missing values, correlations, outliers, and distribution patterns across multiple file formats like CSV, Excel, and Parquet. It streamlines the workflow by generating interactive HTML reports and automatically opening them in your browser, providing immediate visual insights into data characteristics and potential issues like class imbalance or high cardinality.

Key Features

016 GitHub stars

02Interactive visualizations including histograms, scatter plots, and correlation heatmaps

03Deep statistical analysis including distribution, correlation, skewness, and kurtosis

04Cross-platform HTML report generation with automatic browser execution

05Automated data quality validation for missing values, duplicates, and outliers

06Support for large datasets through smart sampling and optimized 'minimal' analysis modes

Use Cases

01Generating detailed statistical documentation for data governance and stakeholders

02Performing rapid Exploratory Data Analysis (EDA) on new or unknown datasets

03Auditing data quality and identifying cleaning requirements before model training

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add dandacompany/dantelabs-agentic-school profiling

For use in Claude.ai and ChatGPT

Download Skill