Machine Learning · Chapter 7 of 40

scikit-learn Introduction

scikit-learn is the standard Python ML library. It provides a consistent API: `fit`, `predict`, `score` — the same three methods for every model.

Install: `pip install scikit-learn`.

Example 1 (python)
from sklearn.linear_model import LogisticRegression
model = LogisticRegression()
model.fit(X_train, y_train)
print(model.score(X_test, y_test))
Output
0.85

Same API across all models.

Example 2 (python)
from sklearn.tree import DecisionTreeClassifier
model = DecisionTreeClassifier(max_depth=3)
model.fit(X, y)

Different algorithm, same interface.

Key points

  • Consistent fit/predict/score API.
  • Ships many algorithms + utilities.
  • Great docs and examples.
  • The industry standard for classical ML.
💡 Note: scikit-learn works best on structured/tabular data. For deep learning use PyTorch or TensorFlow.

📝 Quick Quiz

1. Which method trains a scikit-learn model?

2. predict() returns:

3. scikit-learn's API is: