Course Wiki

scikit-learn

The Python ML library behind Machine Learning Zoomcamp's classical models: linear models, trees, metrics, and preprocessing.

scikit-learn is the workhorse library of Machine Learning Zoomcamp’s classical modules. After the course implements linear and logistic regression by hand with NumPy, scikit-learn provides the production-grade versions — LinearRegression, LogisticRegression, Ridge — plus DictVectorizer for one-hot encoding and the metrics module for RMSE, accuracy, and F1.

The tree module uses it for DecisionTreeClassifier, RandomForestClassifier, and the validation machinery (train_test_split, cross-validation), before the course switches to XGBoost for gradient boosting. The library’s fit/predict interface is the pattern every later tool reuses.

Taught in

• Machine Learning Zoomcamp

  • Module 1: Introduction to Machine Learning
    • Setting up the Environment
    • Summary
  • Module 2: Machine Learning for Regression
    • Explore more
  • Module 3: Machine Learning for Classification
    • Setting up the validation framework
    • Feature importance: Mutual information
    • One-hot encoding
    • Training logistic regression with Scikit-Learn
    • Summary
    • Explore more
  • Module 4: Evaluation Metrics for Classification
    • Accuracy and dummy model
    • ROC Curves
    • ROC AUC
    • Cross-Validation
  • Module 5: Deploying Machine Learning Models
    • Python virtual environment: Pipenv
  • Module 6: Decision Trees and Ensemble Learning
    • Decision trees
    • Decision tree learning algorithm
    • Ensemble learning and random forest
  • Module 9: Serverless Deep Learning
    • Explore more

• LLM Zoomcamp

  • Module 1: Agentic RAG
    • Search
  • Module 7: End-to-End Project
    • End-to-End Project Example ## Related concepts

• Linear Regression

• Logistic Regression

• Decision Trees

• Gradient Boosting

• Classification Metrics