Chapter 4. Machine Learning
After having illustrated all the data preparation steps in a data science project, we have finally arrived at the learning phase, where learning algorithms are applied. In order to introduce you to the most effective machine learning tools that are readily available in Scikit-learn and in other Python packages, we have prepared a brief introduction to all the major families of algorithms. We completed it with examples and tips on the hyper-parameters that guarantee the best possible results.
In this chapter, we will present the following topics:
- Linear and logistic regression
- Naive Bayes
- k-Nearest Neighbors (kNN)
- Support Vector Machines (SVM)
- Ensembles such as Random Forests, GBM, and XGBoost
- Stochastic, gradient-based classification and regression for big data
- Unsupervised clustering with K-means and DBSCAN
- Deep learning with Keras
