Summary

In this chapter, we introduced machine learning and its main components, such as datasets, algorithms, and models, as well as training and testing a model. This introduction was followed by a discussion of popular machine learning frameworks and libraries available for Python. These include scikit-learn, TensorFlow, PyTorch, and BGBoost. We also discussed the best practices of refining and managing the data for training ML models. To get familiar with the scikit-learn library, we built a sample ML model using the SVC algorithm. We trained the model and evaluated it using techniques such as k-fold cross-validation and fine-tuning hyperparameters. We also learned how to store a trained model in a file and then load that model into any program for prediction purposes. In the end, we demonstrated how we can deploy our ML model and predict results using the Google AI Platform with a few GCP Cloud SDK commands.

The concepts and the hands-on exercises included in this chapter...