scikit-learn ML

Build classical ML pipelines with scikit-learn. Covers classification, regression, clustering, preprocessing, feature selection, model selection, and cross-validation with a consistent fit/transform/predict API.

This skill builds end-to-end ML workflows in scikit-learn. It assembles preprocessing and modeling Pipelines, handles encoding, scaling, and imputation, selects features, tunes models with grid and randomized search and cross-validation, and evaluates classification, regression, and clustering with the right metrics — all on scikit-learn's uniform API.

When to use

Use when building classical (non-deep-learning) ML models in Python — classification, regression, clustering, preprocessing pipelines, and model selection with scikit-learn.

Examples

Build a pipeline

Preprocess and model together

Build a scikit-learn Pipeline that imputes, scales, one-hot encodes, and trains a gradient-boosted classifier, tuned with cross-validation

Tune and evaluate

Grid search with CV

Help me set up GridSearchCV for a random forest and report precision, recall, and a confusion matrix on the test set