Book Image

Machine Learning Using TensorFlow Cookbook

By : Luca Massaron, Alexia Audevart, Konrad Banachewicz
Book Image

Machine Learning Using TensorFlow Cookbook

By: Luca Massaron, Alexia Audevart, Konrad Banachewicz

Overview of this book

The independent recipes in Machine Learning Using TensorFlow Cookbook will teach you how to perform complex data computations and gain valuable insights into your data. Dive into recipes on training models, model evaluation, sentiment analysis, regression analysis, artificial neural networks, and deep learning - each using Google’s machine learning library, TensorFlow. This cookbook covers the fundamentals of the TensorFlow library, including variables, matrices, and various data sources. You’ll discover real-world implementations of Keras and TensorFlow and learn how to use estimators to train linear models and boosted trees, both for classification and regression. Explore the practical applications of a variety of deep learning architectures, such as recurrent neural networks and Transformers, and see how they can be used to solve computer vision and natural language processing (NLP) problems. With the help of this book, you will be proficient in using TensorFlow, understand deep learning from the basics, and be able to implement machine learning algorithms in real-world scenarios.
Table of Contents (15 chapters)
5
Boosted Trees
11
Reinforcement Learning with TensorFlow and TF-Agents
13
Other Books You May Enjoy
14
Index

Processing ordinal data

Ordinal data (for instance, rankings or star values in a review) is certainly more similar to numerical data than it is to categorical data, yet we have to first consider certain differences before dealing with it plainly as a number. The problem with categorical data is that you can process it as numerical data, but probably the distance between one point and the following one in the scale is different than the distance between the following one and the next (technically the steps could be different). This is because ordinal data doesn't represent quantities, but just ordering. On the other hand, we also treat it as categorical data, because categories are independent and we will lose the information implied in the ordering. The solution for ordinal data is simply to treat it as both a numerical and a categorical variable.

Getting ready

First, we need to import the OrdinalEncoder function from scikit-learn, which will help us in numerically recoding...