on Google Cloud Platform
This four-day instructor-led class provides participants a hands-on introduction to designing and building on Google Cloud Platform. Through a combination of presentations, demos, and hand-on labs, participants will how to , build end-to-end pipelines, analyze and carry out . The course covers structured, unstructured, and streaming . A laptop is required for all workshops and will not be provided.
This course teaches participants the following skills:
- and build on Google Cloud Platform
- and streaming by implementing autoscaling pipelines on Cloud Dataflow
- Derive business from extremely large datasets using Google BigQuery
- Train, evaluate and predict using models using and Cloud
- Leverage unstructured using and APIs on Cloud Dataproc
- Enable instant from streaming
This class is intended for experienced developers who are responsible for managing transformations including:
- Extracting, Loading, Transforming, cleaning, and validating
- Designing pipelines and architectures for
- Creating and maintaining and models
- Querying datasets, visualizing query results and creating reports
To get the most of out of this course, participants should have:
- Completed Google Cloud Fundamentals- and course OR have equivalent experience
- Basic proficiency with common such as SQL
- Experience with modeling, extract, transform, load activities Developing applications using a common such
- Familiarity with and/or
Module 1: Google Cloud Dataproc Overview
- Creating and managing clusters.
- Leveraging custom types and preemptible worker nodes.
- Scaling and deleting Clusters.
- Lab: Creating Hadoop Clusters with Google Cloud Dataproc.
Module 2: Running Dataproc Jobs
- Running Pig and Hive jobs.
- of storage and compute.
- Lab: Running Hadoop and Jobs with Dataproc.
- Lab: Submit and monitor jobs.
Module 3: Integrating Dataproc with Google Cloud Platform
- Customize with initialization actions.
- BigQuery .
- Lab: Leveraging Google Cloud Platform Services.
Module 4: Making of Unstructured with Googles APIs
- Googles APIs.
- Common Use Cases.
- Invoking APIs.
- Lab: Adding Capabilities to .
Module 5: Serverless with BigQuery
- What is BigQuery.
- Queries and Functions.
- Lab: Writing queries in BigQuery.
- Loading into BigQuery.
- Exporting from BigQuery.
- Lab: Loading and exporting .
- Nested and repeated fields.
- Querying multiple tables.
- Lab: Complex queries.
- Performance and pricing.
Module 6: Serverless, autoscaling pipelines with Dataflow
- The Beam .
- pipelines in Beam .
- pipelines in Beam Java.
- Lab: Writing a Dataflow pipeline.
- Scalable using Beam.
- Lab: MapReduce in Dataflow.
- Incorporating additional data.
- Lab: Side inputs.
- Handling stream data.
- GCP Reference .
Module 7: Getting started with
- What is ().
- Effective : concepts, types.
- datasets: generalization.
- Lab: Explore and create datasets.
Module 8: Building models with
- Getting started with .
- Lab: Using tf..
- graphs and loops + lab.
- Lab: Using low-level + early stopping.
- Monitoring training.
- Lab: Charts and graphs of training.
Module 9: Scaling models with CloudML
- Why Cloud ML?
- Packaging up a .
- End-to-end training.
- Lab: Run a locally and on cloud.
- Creating good features.
- Transforming inputs.
- Preprocessing with Cloud .
- Lab: .
Module 11: of streaming pipelines
- Stream : Challenges.
- Handling variable volumes.
- Dealing with unordered/late .
- Lab: Designing streaming pipeline.
Module 12: Ingesting Variable Volumes
- What is Cloud Pub/Sub?
- How it works: Topics and Subscriptions.
- Lab: Simulator.
Module 13: Implementing streaming pipelines
- Challenges in stream .
- Handle late : watermarks, triggers, accumulation.
- Lab: Stream pipeline for live traffic .
Module 14: Streaming and dashboards
- Streaming : from to decisions.
- Querying streaming with BigQuery.
- What is Google ?
- Lab: build a real-time dashboard to visualize processed .
Module 15: High throughput and low-latency with Bigtable
- What is Cloud Spanner?
- Designing Bigtable schema.
- Ingesting into Bigtable.
- Lab: streaming into Bigtable.