Yimeng-Zhang/feature-engineering-and-feature-selection

Covers the complete feature engineering pipeline from data exploration through selection, including univariate/bivariate analysis, missing value imputation, outlier detection, encoding, and dimensionality reduction techniques. Implementations leverage scikit-learn and pandas with Jupyter notebook demos that explain the rationale and trade-offs for each method. The guide emphasizes practical decision-making—when and why to apply specific techniques—rather than just algorithmic implementations.

1,639 stars. No commits in the last 6 months.