Book Image

TensorFlow Machine Learning Cookbook

By : Nick McClure
Book Image

TensorFlow Machine Learning Cookbook

By: Nick McClure

Overview of this book

TensorFlow is an open source software library for Machine Intelligence. The independent recipes in this book will teach you how to use TensorFlow for complex data computations and will let you dig deeper and gain more insights into your data than ever before. You’ll work through recipes on training models, model evaluation, sentiment analysis, regression analysis, clustering analysis, artificial neural networks, and deep learning – each using Google’s machine learning library TensorFlow. This guide starts with the fundamentals of the TensorFlow library which includes variables, matrices, and various data sources. Moving ahead, you will get hands-on experience with Linear Regression techniques with TensorFlow. The next chapters cover important high-level concepts such as neural networks, CNN, RNN, and NLP. Once you are familiar and comfortable with the TensorFlow ecosystem, the last chapter will show you how to take it to production.
Table of Contents (19 chapters)
TensorFlow Machine Learning Cookbook
About the Author
About the Reviewer
Customer Feedback

Clustering Using K-Means

TensorFlow can also be used to implement iterative clustering algorithms such as k-means. In this recipe, we show an example of using k-means on the iris dataset.

Getting ready

Almost all of the machine learning models we have explored in this book have been supervised models. TensorFlow is ideal for these types of problems. But we can also implement unsupervised models if we wish. As an example, this recipe will implement k-means clustering.

The dataset we will implement clustering on is the iris dataset. One of the reasons this is a good dataset is because we already know there are three different targets (three types of iris flowers). This gives us a leg up on knowing that we are looking for three different clusters in the data.

We will cluster the iris dataset into three groups, and then compare the accuracy of these clusters against the real labels.

How to do it…

  1. To start, we load the necessary libraries. We are also loading some PCA tools from sklearn so that we...