1491974567
Data Science on the Google Cloud Platform: Implementing End-to-End Real-time Data Pipelines: from ingest to machine learning
by: Valliappa Lakshmanan
ISBN-10: 1491974567
ISBN-13: 9781491974568
Edition 版本: 1
Released: 2017-08-25
Pages: 250
Book Description
Data Science on the Google Cloud Platform: Implementing End-to-End Real-time Data Pipelines: from ingest to machine learning
Learn how easy it is to apply sophisticated statistical and machine learning methods to real-world problems when you build on top of the Google Cloud Platform (GCP). With this practical guide,author and GCP Program Manager Valliappa Lakshmanan shows you how to gain insight into a sample business decision by applying different statistical and machine learning methods and tools.
Along the way,you’ll get an extensive tour of the big data and machine learning parts of GCP. You’ll start with statistical methods,move into straightforward classification,and then explore windowing and real-time prediction.
Move from basic to increasingly sophisticated methods
Understand interactive querying of very large datasets with BigQuery
Learn about probabilistic decision making with SparkSQL and Spark
Train a TensorFlow model in Python and call it from Java
Create a data processing pipeline with Dataflow
Compute time-windowed aggregates in real-time
Contents
Chapter 1 Making better decisions with data
Chapter 2 Ingesting data into the cloud (Cloud Storage,Compute Engine,AppEngine)
Chapter 3 Creating compelling dashboards (Cloud SQL,Data Studio)
Chapter 4 IStreaming data: publication and ingest (Cloud Pub/Sub,Dataflow,BigQuery,Data Studio)
Chapter 5 Interactive data exploration (BigQuery,Datalab)
Chapter 6 Bayes Classifier using Spark SQL/Pig (Dataproc)
Chapter 7 Machine Learning: Logistic Regression on Spark (Dataproc)
Chapter 8 Time-windowed aggregate features (Dataflow)
Chapter 9 Machine Learning Classifier Using Cloud MLE
Chapter 10 Real-Time Machine Learning Using Dataflow and Cloud MLE
