Deep Learning with Apache Spark Solutions

Course Curriculum

Chapter 1: Apache Spark Deep Learning Recipes

Lecture 1: The Course overview

Lecture 2: Creating a Dataframes in Pyspark

Lecture 3: Manipulating Columns in a Pyspark Dataframes

Lecture 4: Converting a PySparkdataframe to an array

Lecture 5: Visualizing an Array in a Scatterplot

Lecture 6: Setting up Weights and Biases for Input into the Neural Network

Lecture 7: Normalizing the Input Data for the Neural Network

Lecture 8: Validating Array for Optimal Neural Network Performance

Lecture 9: Setting up the Activation Function with Sigmoid

Lecture 10: Creating the Sigmoid Derivative Function

Lecture 11: Calculating the Cost Function in a Neural Network

Lecture 12: Predicting Gender based on Height and Weight

Lecture 13: Visualizing Prediction Scores

Lecture 14: Pain Point #1: Importing MNIST Images

Lecture 15: Pain Point #2: Visualizing MNIST Images

Lecture 16: Pain Point #3: Exporting MNIST Images as Files

Lecture 17: Pain Point #4: Augmenting MNIST Images

Lecture 18: Pain Point #5: Utilizing Alternate Sources for Trained Images

Lecture 19: Pain Point #6: Prioritizing High-Level Libraries for CNNs

Lecture 20: Downloading the San Francisco Fire Department Calls Dataset

Lecture 21: Identifying the Target Variable of the Logistic Regression Model

Lecture 22: Preparing Feature Variables for the Logistic Regression Model

Lecture 23: Applying the Logistic Regression Model

Lecture 24: Evaluating the Accuracy of the Logistic Regression Model

Lecture 25: Downloading and Analyzing the Therapy Bot Session Dataset

Lecture 26: Visualizing Word Counts in the Dataset

Lecture 27: Calculating Sentiment Analysis of Text

Lecture 28: Removing Stop Words from the Text

Lecture 29: Training and Evaluating TF-IDF Model Performance

Lecture 30: Comparing Model Performance to a Baseline Score

Lecture 31: Downloading Stock Market Data for Apple

Lecture 32: Exploring and Visualizing Stock Market Data for Apple

Lecture 33: Preparing Stock Data for Model Performance

Lecture 34: Building the LSTM Model

Lecture 35: Evaluating the Model

Chapter 2: Apache Spark Deep Learning Advanced Recipes

Lecture 1: The Course overview

Lecture 2: Downloading Novels/Books that will be used as Input Text

Lecture 3: Preparing and Cleansing Data

Lecture 4: Tokenizing Sentences

Lecture 5: Generating Similar Text using the Model

Lecture 6: Downloading the King County House Sales Dataset

Lecture 7: Performing Exploratory Analysis and Visualization

Lecture 8: Plotting Correlation Between Price and Other Features

Lecture 9: Predicting the Price of a House

Lecture 10: Downloading and Loading the MIT-CBCL Dataset into the Memory

Lecture 11: Plotting and Visualizing Images from the Directory

Lecture 12: Preprocessing Images

Lecture 13: Acquiring Data

Lecture 14: Importing the Necessary Libraries

Lecture 15: Preparing the Data

Lecture 16: Building and Training the Model

Lecture 17: Visualizing Further

Lecture 18: Analyzing Further

Lecture 19: Downloading MovieLens Datasets

Lecture 20: Manipulating and Merging the MovieLens Datasets

Lecture 21: Exploring the MovieLens Datasets

Lecture 22: Preparing Dataset for the Deep Learning Pipeline

Lecture 23: Applying the Deep Learning Model with Keras

Lecture 24: Evaluating the recommendation engine's accuracy