DataLearn Supervised ML Intro 2019

The repository of the hands-on introduction to machine learning workshop of the DataLearn 2019 track at DataHack 2019.

Outline

• Data exploration
• Preprocessing
  • Scaling and normalization
  • Handling outliers
  • Feature engineering
  • Feature selection
  • Dimensionality reduction
• Classification
  • Model fit
    • Loss function
    • Gradient descent
    • Overfitting
    • Hyperparameter Optimization
  • Evaluation
    • Model selection
    • Cross validation
• Regression
  • Modeling
  • Evaluation