Packt+ | Advance your knowledge in tech

You're reading from Apache Spark Deep Learning Cookbook Over 80 best practice recipes for the distributed training and deployment of neural networks using Keras and TensorFlow

Product type Paperback

Published in Jul 2018

Publisher Packt

ISBN-13 9781788474221

Length 474 pages

Edition 1st Edition

Languages

Scala

Tools

Apache Spark

Concepts

Deep Learning

Authors (2):

Ahmed Sherif

Amrith Ravindra

Preface

1. Setting Up Spark for Deep Learning Development

2. Creating a Neural Network in Spark FREE CHAPTER

3. Pain Points of Convolutional Neural Networks

4. Pain Points of Recurrent Neural Networks

5. Predicting Fire Department Calls with Spark ML

6. Using LSTMs in Generative Networks

7. Natural Language Processing with TF-IDF

8. Real Estate Value Prediction Using XGBoost

9. Predicting Apple Stock Market Cost with LSTM

10. Face Recognition Using Deep Convolutional Networks

11. Creating and Visualizing Word Vectors Using Word2Vec

12. Creating a Movie Recommendation Engine with Keras

13. Image Classification with TensorFlow on Spark

14. Other Books You May Enjoy

In this recipe, we will go the steps that we need to download the novels/books which we will use as input text for the execution of this recipe.

Place the input data in the form of a .txt file in the working directory.
The input may be any kind of text, such as song lyrics, novels, magazine articles, and source code.
Most of the classical texts are no longer protected by copyright and may be downloaded for free and used in experiments. The best place to get access to free books is Project Gutenberg.
In this chapter, we will be using The Jungle book by Rudyard Kipling as the input to train our model and generate statistically similar text as output. The following screenshot shows you how to download the necessary file in .txt format:

After visiting the website and searching for the required book, click on Plain Text UTF-8 and download it. UTF-8 basically specifies the type of encoding. The text may be copied and pasted or saved...