Automate exploratory data analysis and generate narrative and HTML reports.
npx skills add https://github.com/vathymut/copilot-skills --skill explore-ml-data
Please help me install this Agent Skill. Skill: explore-ml-data Source: https://github.com/vathymut/copilot-skills/tree/main/.github/skills/explore-ml-data Command: npx skills add https://github.com/vathymut/copilot-skills --skill explore-ml-data
This Skill helps users gain a comprehensive understanding of their datasets before building machine learning models, enabling informed decisions based on real dataset insights.
Run the 'explore-ml-data' skill to perform EDA on your dataset.
High-intent search queries and answers about installing and using this skill.
Automated exploratory data analysis identifies dataset characteristics like class balance, missingness, and cardinality. This generates narrative and interactive HTML reports to inform machine learning model design decisions.
Understanding dataset characteristics requires exploratory data analysis to evaluate class balance, datetime columns, missingness, and cardinality. This yields a narrative report and interactive HTML summary for each table.
Automated EDA works with polars dataframes and requires either pandas or polars alongside skrub for data analysis. It processes dataset tables to produce comprehensive EDA reports for machine learning preparation.
You can generate an interactive HTML report and narrative documentation for each table in your dataset. The EDA output also includes a JOURNAL section summarizing findings for subsequent model design.
Exploratory data analysis is needed before building machine learning models to ensure informed decisions based on real dataset insights. It automates understanding of key dataset characteristics to prepare for model design.
Automating dataset analysis with skrub requires pandas or polars dependencies for data processing. The generated EDA reports focus on structural dataset characteristics like class balance and missingness rather than model performance evaluation.
Ritabrata-ChakrabortyProcess large datasets with Polars DataFrame operations and lazy evaluation.
agiprolabsGenerate predictive features from time-series market data for trading models.
dieu-donneePerform advanced pandas DataFrame operations for analysis, cleaning, and transformation.
niranjannavAnalyze Excel spreadsheets to extract summaries, formulas, and data quality issues.
