Automate data cleaning for CRISP-DM 3.2 workflows with notebooks and summaries.
npx skills add https://github.com/thbraet/claude-template --skill clean-data-thbraet
Please help me install this Agent Skill. Skill: clean-data Source: https://github.com/thbraet/claude-template/tree/main/skills/clean-data Command: npx skills add https://github.com/thbraet/claude-template --skill clean-data-thbraet
This skill raises data quality to the level required by the selected analysis techniques. It addresses missing values, outliers, noise, encoding errors, and type corrections, while documenting every cleaning decision with rationale and impact. It produces a structured data cleaning report and organizes outputs to CRISP-DM 3.2 standards.
Run the clean-data workflow to produce notebooks/3.2-clean-data.ipynb and docs/crisp-dm/3-data-preparation/3.2-clean-data.md.
High-intent search queries and answers about installing and using this skill.
Automating end-to-end data cleaning handles missing values, outliers, encoding errors, and duplicates while producing a Jupyter notebook and a structured markdown summary documenting every operation for auditability.
Preparing datasets for CRISP-DM 3.2 involves executing a complete cleaning workflow that generates a reproducible notebook and a concise summary document stored at docs/crisp-dm/3-data-preparation/3.2-clean-data.md.
Imputation prevents data leakage by fitting imputation models exclusively on training data, ensuring that all missing value treatments are learned before being applied to validation or test sets.
Yes, data cleaning preserves raw data by logging all operations and storing cleaned outputs separately as artifacts, ensuring the original dataset remains unmodified throughout the preparation process.
Handling encoding errors and type corrections requires fitting imputation models on training data only, limiting transformations to learned parameters to maintain reproducibility and prevent data leakage across workflow stages.
thbraetTranslate business objectives into data mining goals with success criteria.
ActiveInferenceInstituteExtracts GNN features and trains/evaluates ML models across multiple frameworks.
teradata-labsImpute missing values using TD_SimpleImputeFit in Teradata Vantage.
thbraetDerive and transform features from cleaned datasets for CRISP-DM workflows.
