This is the second of two Quests of hands-on labs derived from the exercises from the book Data Science on Google Cloud Platform by Valliappa Lakshmanan, published by O'Reilly Media, Inc. In this second Quest, covering chapter 9 through the end of the book, you extend the skills practiced in the first Quest, and run full-fledged machine learning jobs with state-of-the-art tools and real-world data sets, all using Google Cloud tools and services.
Overview
Syllabus
- Machine Learning with Spark on Google Cloud Dataproc
- In this lab you will learn how to implement logistic regression using a machine learning library for Apache Spark running on a Google Cloud Dataproc cluster to develop a model for data from a multivariable dataset.
- Processing Time Windowed Data with Apache Beam and Cloud Dataflow (Java)
- Deploy a Java application using Maven to process data with Cloud Dataflow. The Java application implements time-windowed aggregation to augment the raw data in order to produce consistent training and test datasets.
- warning Machine Learning with TensorFlow
- In this lab you will learn how to use Google Cloud Machine Learning and Tensorflow to develop and evaluate prediction models using machine learning.
- Distributed Machine Learning with Google Cloud ML
- Learn the process for partitioning a data set into two separate parts: a training set to develop a model, and a test set to evaluate the accuracy of the model and then independently evaluate predictive models in a repeatable manner.
