Profile numeric and categorical data to identify quality issues and relationships.
npx skills add https://github.com/tim-krausz/mlstack --skill eda-tim-krausz
Please help me install this Agent Skill. Skill: eda Source: https://github.com/tim-krausz/mlstack/tree/main/eda Command: npx skills add https://github.com/tim-krausz/mlstack --skill eda-tim-krausz
Provides a structured, repeatable approach to understand datasets by profiling variables, identifying data quality issues, and revealing relationships to inform modeling decisions.
Analyze a dataset path and run the EDA skill to produce a structured notebook (e.g., notebooks/eda.ipynb) and a data-profile report.
High-intent search queries and answers about installing and using this skill.
Exploratory data analysis profiles variables, identifies data quality issues, and reveals relationships to inform modeling decisions. You can run full, quick, or targeted profiling across numeric and categorical data to generate a structured Jupyter notebook and data-profile report.
To identify data quality issues before modeling, run systematic exploratory data analysis to surface missingness patterns, distributions, correlations, and potential anomalies. This process quantifies variable relationships and guides your modeling strategies.
Yes, you can generate a reproducible notebook for data profiling automatically. The skill produces a structured Jupyter notebook, such as eda.ipynb, ensuring compatibility with common Python data libraries and supporting collaboration in standard data-analytic workflows.
Exploratory data analysis works with both numeric and categorical data. It accommodates different time and depth requirements through full, quick, and targeted profiling modes, enabling comprehensive variable profiling and relationship identification across mixed data types.
Use quick profiling instead of full data analysis when time is limited and you need rapid insights. Quick profiling accommodates different depth requirements, while full profiling provides comprehensive distributions, missingness patterns, and correlations for deeper modeling preparation.
Structured outputs for reproducible data profiling ensure your variable analysis and data quality insights are documented and repeatable. Generating a Jupyter notebook captures the full exploratory data analysis workflow, enabling collaboration and consistent results across common Python data libraries.
AreteDriverConvert raw datasets into publication-quality visuals with reproducible Python code.
zhangzhang-111-iDesign A/B tests, engineer features, and evaluate models with MLflow.
legoutConvert Jupyter .ipynb files into reactive marimo Python scripts.
nimadorostkarImplement data validation gates for automated pipelines using Pandera or Great Expectations.
