scikit-learn

1. Supervised learning

   Linear models, SVMs, trees, ensembles, and neighbors for classification and regression.

2. Unsupervised learning

   Clustering, decomposition, and density estimation.

3. Model selection and evaluation

   Cross-validation, hyperparameter search, and metrics.

4. Cross-validation

   K-fold, stratified and group splitters, and avoiding leakage.

5. Hyperparameter tuning

   GridSearchCV, RandomizedSearchCV, and successive halving.

6. Metrics and scoring

   Scoring parameters, classification, regression, and clustering metrics.

7. Preprocessing data

   Scaling, encoding categorical features, imputation, and transformers.

8. Pipelines and composite estimators

   Pipeline, ColumnTransformer, and FeatureUnion.

9. Feature selection

   Univariate, recursive, and model-based feature selection.

10. Ensemble methods

    Random forests, gradient boosting, bagging, and stacking.

11. Dimensionality reduction

    PCA, NMF, and related decompositions.

12. Common pitfalls and recommended practices

    Data leakage, inconsistent preprocessing, and randomness control.

13. Model persistence

    Saving models with pickle, joblib, and ONNX and security concerns.

14. Inspection

    Partial dependence and permutation importance for interpretation.

Each section links to the official page. Titles and summaries by Extra Credit; the docs belong to their authors.