Explore
For Enterprise
Join for Free
Log In

Arts et humanités
Business
Informatique
Science des données
Technologies de l'information
santé
Mathématiques et logique
Développement personnel
Sciences physiques et ingénierie
Sciences sociales
Apprentissage des langues
Diplômes
Certificats

Explorez l'intégralité de Coursera

Parcourir
Rechercher
For Enterprise
Connexion
Inscrivez-vous gratuitement

Activity: Explore real customer solution architectures

Loading...

Google Cloud Platform Big Data and Machine Learning Fundamentals

4.6 (6,592 notes) | 69K étudiants inscrits

Cours 1 de 5 dans Data Engineering, Big Data, and Machine Learning on GCP Spécialisation

This 1-week accelerated on-demand course introduces participants to the Big Data and Machine Learning capabilities of Google Cloud Platform (GCP). It provides a quick overview of the Google Cloud Platform and a deeper dive of the data processing capabilities. At the end of this course, participants will be able to: • Identify the purpose and value of the key Big Data and Machine Learning products in the Google Cloud Platform • Use CloudSQL and Cloud Dataproc to migrate existing MySQL and Hadoop/Pig/Spark/Hive workloads to Google Cloud Platform • Employ BigQuery and Cloud Datalab to carry out interactive data analysis • Choose between Cloud SQL, BigTable and Datastore • Train and use a neural network using TensorFlow • Choose between different data processing products on the Google Cloud Platform Before enrolling in this course, participants should have roughly one (1) year of experience with one or more of the following: • A common query language such as SQL • Extract, transform, load activities • Data modeling • Machine learning and/or statistics • Programming in Python Google Account Notes: • Google services are currently unavailable in China.

Visualiser le programme de cours

Compétences que vous apprendrez

Tensorflow, Bigquery, Google Cloud Platform, Cloud Computing

Avis

4.6 (6,592 notes)

5 stars
4,582 ratings
4 stars
1,662 ratings
3 stars
263 ratings
2 stars
43 ratings
1 star
42 ratings

DK

Apr 08, 2019

This course provides the basics of Google Cloud Platform and makes us understand Google Products and services on Cloud. I would love to explore GCP more and will opt for the remaining GCP courses.

AR

May 27, 2019

This course gives you a pretty good fundamental idea on what you are diving into. Google cloud platform has bucket of data engineering features. This course sets you on the starting line for them.

À partir de la leçon

Introduction to the Data and Machine Learning on Google Cloud Platform Specialization

Welcome to the Big Data and Machine Learning fundamentals on GCP course. Here you will learn the basics of how the course is structured and the four main big data challenges you will solve for.

Choosing the right approach5:52

What you can do with Google Cloud Platform3:41

Activity: Explore real customer solution architectures7:17

Key roles in a data-driven organization6:54

Enseigné par

Google Cloud Training

Transcription

Now, it's your turn.

One of the best ways to inspire and

drive your team and projects to the cloud,

is to show your stakeholders examples from your industry,

examples where someone has already

succeeded with building a solution.

For this activity, navigate to

cloud.google.com/customers and scroll down.

For Products and Solutions,

filter on big data analytics

and also on machine learning.

Select a customer use case that interests you,

then answer these three questions.

Number one, what were

the barriers or challenges the customer faced?

The challenges are important,

you want to understand what they were.

Second, how were these challenges

solved with a cloud solution?

What products did they use?

Three, what was the business impact?

Take a moment to complete

the activity and then return to the video.

For our example we chose GO-JEK,

because they use a data engineering solution that maps

nicely to the topics

that we're going to cover as part of this course.

GO-JEK is an Indonesia-based company

that gives shared motorcycle rides,

brings goods, and provides

a wide variety of other services for

over two million families across 50 cities in Indonesia.

Their App has over 77 million downloads,

and they're connected with over a

150,000 merchants who sell

through their delivery platform.

If you're interested in GIS data,

they have over one million drivers

delivering goods and giving rides

across 50 cities and

GO-JEK gets censored data from all of these drivers.

So GO-JEK manages more than five terabytes

per day of data for analysis.

The Chief Technology Officer, the CTO,

Ajey Gore, gives this meaningful statistic.

For example, we ping

everyone of our drivers every 10 seconds.

Which means, six million pings per

minute and eight billion pings per day,

that's Gore who's saying this.

If you look at the scale

and number of our customer interactions as well,

we generate about four terabytes

to five terabytes of data every day.

We need to leverage this data to tell our drivers where

demand from customers is strongest and how to get there.

With the success of

their on-demand motorcycle ride service,

GO-JEK faced the challenges when

looking to scale their existing big data platform.

What challenges? Their management team stated,

"Most of the reports are produced one day later so we

couldn't identify the problems

that were happening as soon as possible."

GO-JEK chose Google Cloud Platform

and migrated the data pipelines to GCP,

so that they could get high performance

with minimal day-to-day maintenance.

Their data engineering team

uses Cloud Dataflow for streaming

data processing and Google Big Query

for real-time business insights.

Their end to architecture looks like this.

First, they ingest data from

their mobile App online and

IoT devices on vehicles

like the GPS tracking for deliveries.

They ingest this data into Cloud PubSub.

Then, the data is brought into Cloud Dataflow for

processing and a variety of

other data sources are used to enrich this event data.

Finally, after Dataflow has done the processing,

Dataflow streams that data into BigQuery and

BigQuery in this case is used

as a data warehouse to store the data.

What's the business impact?

So here's an example of one of

the problems that the GO-JEK team solved.

The question was, how could they quickly know

which locations had too many drivers or too few drivers?

Too few drivers to meet the demand for that area.

To solve this problem,

what does the team need to do?

Number one, they needed to check

the demand of bookings by

customer against the supply of

drivers and do this thing in real-time.

Then, the team needed to identify who these drivers

are and notify them to reroute to higher demand areas.

How they achieved this,

was by building a streaming event data pipeline

using Cloud Dataflow.

Driver locations would ping out to Pub/Sub

every 30 seconds and

these locations would go into Dataflow for processing.

The data for pipeline aggregates the supply pings

from the drivers against the requests for bookings,

and then connects to GO-JEK's

notification system to alert drivers.

From a technology standpoint,

the system needs to handle

an arbitrarily high throughput of

messages and scale up and down to process.

Cloud Dataflow automatically manages a number of workers,

processing the pipeline to meet demand.

The GO-JEK team is then able to visualize and

highlight supply-demand mismatch areas

for management reporting,

as you see in this example here.

The green dots, the small green dots,

represent riders and new booking requests,

and the red dots,

the small red dots,

those are the drivers,

so you have riders in

the green dots and the drivers in the small red dots.

Then you see the areas that the system has

identified as a highest mismatch of supply and demand,

those areas are highlighted in red like

the train station which has many booking requests,

but not enough drivers.

The team can now actively monitor and ensure that

they're sending drivers to the areas in highest demand,

which means faster booking times for

riders and more fairs for the drivers.

Explorer notre catalogue

Rejoignez-nous gratuitement et obtenez des recommendations, des mises à jour et des offres personnalisées.

Coursera propose un accès universel à la meilleure formation au monde, en partenariat avec des universités et des organisations du plus haut niveau, pour proposer des cours en ligne.

© 2019 Coursera Inc. Tous droits réservés.

Télécharger dans l'App Store

Disponible sur Google Play

Coursera
À propos
Direction
Carrières
Catalogue
Certificats
Certificats MasterTrack™
Diplômes
For Enterprise
For Government

Communauté
Learners
Partners
Developers
Beta Testers
Translators

Se connecter
Blog
Facebook
LinkedIn
Twitter
Instagram
YouTube
Blog Tech

Plus
Conditions
Confidentialité
Aide
Accessibilité
Presse
Contact
Répertoire
Filiales