Applied Machine Learning Tutorials

Author: Alejandro Monroy

Welcome! This repository includes tutorials to learn the basics of machine learning using Python and scikit-learn, as part of the Applied Machine Learning course of the BSc Information Science at the University of Amsterdam.

Note

This repository just contains the first half of the course for now. The second half will be added at a later date.

Contents

Introduction

• Setting up your Python environment
• Tutorial 0: Python warm-up
  • 1. Python basics
  • 2. Handling multi-dimensional data with Numpy
  • 3. Handling multi-dimensional data (with more options) with Pandas
  • 4. Making awesome plots with Matplotlib
• Tutorial 1: Introduction to ML and Sklearn
  • 1. Loading the data
  • 2. Data exploration
  • 3. Data preprocessing
  • 4. Our first ML model

Regression

• Tutorial 2: Regression with kNN and Linear Regression
  • 1. Loading and preparing the data
  • 2. K-Nearest Neighbors
  • 3. Evaluating regression models
  • 4. Linear Regression
• Tutorial 3: Linear regression with polynomial features
  • 1. Polynomial features to learn non-linear dependencies
  • 2. A more complex dataset: How to deal with overfitting

Classification

• Tutorial 4: Classification with kNN
  • 1. Loading and preparing the data
  • 2. K-Nearest Neighbors for classification
  • 3. Evaluating classification models
• Tutorial 5: Logistic regression + Grid search for hyperparameter tuning
  • 1. Loading and preparing the data
  • 2. Logistic regression (binary case)
  • 2. Cross validation and Grid Search for hyperparameter tuning

Clustering

• Tutorial 6: Clustering with K-Means
  • 1. Loading and preparing the data
  • 2. K‑Means clustering
  • 3. Evaluating the clustering
  • 4. When K-Means Fails and DBSCAN Succeeds