Load, clean, and summarize tabular datasets with descriptive statistics.
npx skills add https://github.com/Yeachan-Heo/My-Jogyo --skill data-analysis-yeachan-heo
Please help me install this Agent Skill. Skill: data-analysis Source: https://github.com/Yeachan-Heo/My-Jogyo/tree/main/skills/data-analysis Command: npx skills add https://github.com/Yeachan-Heo/My-Jogyo --skill data-analysis-yeachan-heo
This Skill provides reusable patterns for loading data, cleaning pipelines, and performing exploratory analysis to quickly derive insights from datasets.
Run the data-analysis skill on a sample dataset by loading data.csv, performing basic cleaning, and generating a quick report with summary statistics and plots.
High-intent search queries and answers about installing and using this skill.
To perform exploratory data analysis on a CSV, use Python with pandas to load the file, clean the data, and compute descriptive statistics. This process generates summary reports and visualizations to reveal key data relationships.
Yes, you can generate summary statistics and visualizations from Excel datasets. The workflow reads Excel formats using pandas, computes distributions and correlations, and uses optional seaborn to produce visual summaries for insights.
Yes, you need Python with pandas, numpy, and scipy installed to compute descriptive statistics. These libraries provide the required computational backend for loading, cleaning, and analyzing tabular datasets.
The best way to clean tabular data before generating a report is applying reusable cleaning pipelines. This approach handles missing values and formats across CSV or database exports, preparing datasets for accurate statistical analysis.
Yes, this data analysis workflow supports database exports. It applies reusable patterns to tabular datasets from database exports, performing data loading, cleaning, and exploratory analysis to produce insightful reports.
Use pandas for EDA because it provides repeatable patterns for loading and cleaning tabular datasets. Combined with numpy and scipy, it efficiently computes descriptive statistics and distributions directly within notebook or script-based workflows.
Sir-chawakornClean, transform, and reshape CSV, Parquet, and DataFrame tabular data.
jesseotremblayAnalyze CSV, JSON, and Excel datasets with statistics and visualizations.
jaechang-hitsGenerate statistical visualizations from pandas DataFrames using Seaborn.
LuizEduPPClean, analyze, and summarize datasets with reproducible documentation.
