skills.rest
hung-phan
hung-phanCOMMUNITY
Explore all skills by this author →
GitHub

eda

Perform exploratory data analysis with statistical summaries, correlation, and outlier detection.

1|Updated Jun 4, 2026
Search Tags:#data quality#data analysis#exploratory data analysis#statistical analysis#eda
One-click install
npx skills add https://github.com/hung-phan/ml-skills --skill eda-hung-phan
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: eda
Source: https://github.com/hung-phan/ml-skills/tree/main/skills/ml-review/references/data-prep/eda
Command: npx skills add https://github.com/hung-phan/ml-skills --skill eda-hung-phan

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pandas, numpy, scipy, matplotlib, ydata-profiling, sweetviz, statsmodels, missingno, phik, sklearn, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill aids in understanding your dataset before modeling, by performing comprehensive exploratory data analysis (EDA) and identifying key insights or issues in your data.

Core Features & Use Cases

  • Statistical Summaries: Provide a detailed overview of numerical and categorical features, including measures of central tendency, spread, and missing values.
  • Distribution Analysis: Check for normality, and visualize data distributions.
  • Correlation Analysis: Determine relationships between features.
  • Outlier Detection: Identify and analyze outliers in your data.
  • Missing Data Analysis: Assess and understand missing data patterns.
  • Automated Profiling: Generate detailed EDA reports with ydata-profiling.
  • Hypothesis Testing with Effect Sizes: Perform statistical tests to understand the significance of relationships.
  • Time Series EDA: Decompose and analyze time series data.
  • Multivariate Analysis: Perform principal component analysis (PCA) and t-SNE for dimensionality reduction and visualization.
  • Use Case: Before training a model, you can use this Skill to analyze a dataset and uncover insights that may affect your model's performance.

Quick Start

Perform exploratory data analysis on the 'customer_data.csv' dataset using the eda skill.

Frequently Asked Questions about eda

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I perform exploratory data analysis on a CSV dataset before modeling?▼

Exploratory data analysis on a CSV dataset involves generating statistical summaries, analyzing distributions, and identifying missing values to uncover insights affecting model performance. This Skill provides comprehensive EDA functionalities to understand data quality and relationships before training.

What is the best way to analyze missing data patterns and detect outliers in pandas?▼

Analyzing missing data patterns and detecting outliers in pandas requires dedicated visualization and statistical methods. This Skill utilizes the missingno library to assess missing data structures and applies statistical techniques to identify and analyze outliers within your dataset.

Can I generate automated EDA profiling reports using ydata-profiling and sweetviz?▼

Yes, you can generate automated EDA profiling reports using ydata-profiling and sweetviz. This Skill integrates both libraries to automatically produce detailed data summaries, highlight feature relationships, and export comprehensive exploratory reports.

Does this EDA workflow support time series decomposition and hypothesis testing?▼

This EDA workflow supports time series decomposition and hypothesis testing. It utilizes statsmodels to decompose and analyze time series data, while also performing statistical hypothesis tests with effect sizes to determine the significance of feature relationships.

How do I use PCA and t-SNE for multivariate analysis in Python?▼

Using PCA and t-SNE for multivariate analysis in Python involves applying dimensionality reduction techniques to visualize complex relationships. This Skill leverages scikit-learn to perform principal component analysis and t-SNE, reducing dimensions for effective multivariate data visualization.

When should I use phik correlation instead of standard correlation analysis?▼

You should use phik correlation when analyzing relationships between categorical and numerical features where standard linear correlation falls short. This Skill includes the phik library to determine non-linear relationships and dependencies between mixed feature types accurately.

Related Skills

Explore More Data & Analytics Skills→
Sir-chawakornSir-chawakorn
9

wrangle-tabular-data

Clean, transform, and reshape CSV, Parquet, and DataFrame tabular data.

Community
Advanced
robotlearning123robotlearning123

scikit-learn

Build, evaluate, and refine machine learning models with scikit-learn.

Community
Advanced
nahisahonahisaho
3

scientific-advanced-visualization

Build interactive 3D Plotly plots and Altair visuals from scientific data.

Community
Advanced
nimadorostkarnimadorostkar
25

data-quality

Implement data validation gates for automated pipelines using Pandera or Great Expectations.

Community
Advanced