Apache Spark deep learning cookbook: over 80 recipes that streamline deep learning in a distributed environment with Apache Spark

Cover --
Title Page --
Copyright and Credits --
Packt Upsell --
Foreword --
Contributors --
Table of Contents --
Preface --
Chapter 1: Setting Up Spark for Deep Learning Development --
Introduction --
Downloading an Ubuntu Desktop image --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Installing and configuring Ubuntu with VMWare Fusion on macOS --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Installing and configuring Ubuntu with Oracle VirtualBox on Windows --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Installing and configuring Ubuntu Desktop for Google Cloud Platform --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Installing and configuring Spark and prerequisites on Ubuntu Desktop --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Integrating Jupyter notebooks with Spark --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Starting and configuring a Spark cluster --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Stopping a Spark cluster --
How to do it ... --
How it works ... --
There's more ... --
Chapter 2: Creating a Neural Network in Spark --
Introduction --
Creating a dataframe in PySpark --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Manipulating columns in a PySpark dataframe --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
Converting a PySpark dataframe to an array --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Visualizing an array in a scatterplot --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also. Setting up weights and biases for input into the neural network --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Normalizing the input data for the neural network --
Getting ready --
How to do it ... --
How it works ... --
See also --
Validating array for optimal neural network performance --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Setting up the activation function with sigmoid --
Getting ready --
How to do it ... --
How it works ... --
See also --
Creating the sigmoid derivative function --
Getting ready --
How to do it ... --
How it works ... --
See also --
Calculating the cost function in a neural network --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Predicting gender based on height and weight --
Getting ready --
How to do it ... --
How it works ... --
See also --
Visualizing prediction scores --
Getting ready --
How to do it ... --
How it works ... --
Pain Points of Convolutional Neural Chapter 3: Networks --
Introduction --
Pain Point #1: Importing MNIST images --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Pain Point #2: Visualizing MNIST images --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Pain Point #3: Exporting MNIST images as files --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Pain Point #4: Augmenting MNIST images --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Pain Point #5: Utilizing alternate sources for trained images --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Pain Point #6: Prioritizing high-level libraries for CNNs --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also. Chapter 4: Pain Points of Recurrent Neural Networks --
Introduction --
Introduction to feedforward networks --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Sequential workings of RNNs --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Pain point #1 --
The vanishing gradient problem --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Pain point #2 --
The exploding gradient problem --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Sequential working of LSTMs --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Chapter 5: Predicting Fire Department Calls with Spark ML --
Introduction --
Downloading the San Francisco fire department calls dataset --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Identifying the target variable of the logistic regression model --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Preparing feature variables for the logistic regression model --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Applying the logistic regression model --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Evaluating the accuracy of the logistic regression model --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Chapter 6: Using LSTMs in Generative Networks --
Introduction --
Downloading novels/books that will be used as input text --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Preparing and cleansing data --
Getting ready --
How to do it ... --
How it works ... --
See also --
Tokenizing sentences --
Getting ready --
How to do it ... How it works ... --
There's more ... --
Training and saving the LSTM model --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Generating similar text using the model --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Chapter 7: Natural Language Processing with TF-IDF --
Introduction --
Downloading the therapy bot session text dataset --
Getting ready --
How it works ... --
How to do it ... --
There's more ... --
Analyzing the therapy bot session dataset --
Getting ready --
How to do it ... --
How it works ... --
Visualizing word counts in the dataset --
Getting ready --
How to do it ... --
How it works ... --
See also --
Calculating sentiment analysis of text --
Getting ready --
How to do it ... --
How it works ... --
See also --
Removing stop words from the text --
Getting ready --
How to do it ... --
How it works ... --
See also --
Training the TF-IDF model --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Evaluating TF-IDF model performance --
Getting ready --
How to do it ... --
How it works ... --
See also --
Comparing model performance to a baseline score --
How to do it ... --
How it works ... --
See also --
Chapter 8: Real Estate Value Prediction Using XGBoost --
Downloading the King County House sales dataset --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Performing exploratory analysis and visualization --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Plotting correlation between price and other features --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Predicting the price of a house --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also. Chapter 9: Predicting Apple Stock Market Cost with LSTM --
Downloading stock market data for Apple --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Exploring and visualizing stock market data for Apple --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Preparing stock data for model performance --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Building the LSTM model --
Getting ready --
How to do it ... --
How it works ... --
See also --
Evaluating the model --
Getting ready --
How to do it ... --
How it works ... --
See also --
Chapter 10: Face Recognition Using Deep Convolutional Networks --
Introduction --
Downloading and loading the MIT-CBCL dataset into the memory --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Plotting and visualizing images from the directory --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Preprocessing images --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Model building, training, and analysis --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Chapter 11: Creating and Visualizing Word Vectors Using Word2Vec --
Introduction --
Acquiring data --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Importing the necessary libraries --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Preparing the data --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Building and training the model --
Getting ready --
How to do it ... --
How it works ... --
There's more ... --
See also --
Visualizing further --
Getting ready --
How to do it ... --
How it works ...