Chevron Left
Retour à Ingénierie des fonctionnalités

Avis et commentaires pour l'étudiant pour Ingénierie des fonctionnalités par Google Cloud

1,156 notes
110 avis

À propos du cours

Want to know how you can improve the accuracy of your machine learning models? What about how to find which data columns make the most useful features? Welcome to Feature Engineering on Google Cloud Platform where we will discuss the elements of good vs bad features and how you can preprocess and transform them for optimal use in your machine learning models. In this course you will get hands-on practice choosing features and preprocessing them inside of Google Cloud Platform with interactive labs. Our instructors will walk you through the code solutions which will also be made public for your reference as you work on your own future data science projects. >>> By enrolling in this course you agree to the Qwiklabs Terms of Service as set out in the FAQ and located at: <<< COMPLETION CHALLENGE Complete any GCP specialization from November 5 - November 30, 2019 for an opportunity to receive a GCP t-shirt (while supplies last). Check Discussion Forums for details....

Meilleurs avis


Nov 26, 2018

It's a pretty interesting course, specially that's the only one that teaches featuring engineering with a focus on production issues, but it assumes some knowledge with apache beam, and dataflow.


Sep 23, 2019

Feature engineering is important but less discussed compared to general ML or DNN. Feature cross is a new concept and yet very useful for dealing with large datasets.

Filtrer par :

76 - 100 sur 110 Examens pour Ingénierie des fonctionnalités

par Timothy L

Aug 21, 2018

Some of the labs had big query errors, and some of the google cloud interfaces changed, so careful when doing the labs, the options and the buttons may have been shifted or renamed

par Kevin C

Aug 26, 2018

In contrast to other courses in this specialization, this course had some meat in it and was more than just a thinly disguised ad for Google Services.

par Michal K

Aug 19, 2018

In general, this course is very well prepared, covers a good piece of material and I'm leaving it with a lot of new things to try. One thing I would correct in the future: more coding. Don't get me wrong, labs are quite good in terms of examples quality, but since everything is already there, it is difficult to "learn by doing".

par Wang Y

Oct 07, 2018

Nicely explained concepts with real world examples! Could have explain more about the code and the meaning behind some of the qwiklabs.

par Evren G

Nov 03, 2018

As ever excellent course content, the major let down and loss of star is because of the labs. There are no graded lab exercises where you have to think about and apply your theoretical learnings. Instead you get python notebooks that have completely prepopulated code. So the only thing you need to do is run the cells. A missed opportunity for excellent learning.

par Francois R

Apr 17, 2019

Very interesting theory, shows the power of Tensorflow in the field. I had trouble with the last lab though, which when I ran it step by step, would block my qwiklab account because of resource limitations...

par Terry L

May 01, 2019

개요를 알게 되서 좋음

par Maheboob P

Apr 21, 2019

faced multiple issues

a)Qwiklab wasnt allowing to login with error that said "account is locked"

b) labs were not as interesting as others

par Rahul K

May 05, 2019

Lovely Course. Thanks Google

par borja v

Jun 21, 2019

the course needs some code upgrades because of ML engine is close to be depecreated

par Emily T

Jul 05, 2019

This course really needs more hands on work with code, but it was still good and I learned lots.

par Anupam P

Aug 26, 2019

Comprehensive yet precise and clear.

par Ahmad T

Aug 27, 2019


par Keith H

Sep 01, 2019

Love the course but this specialization is fairly complex and is new type of thinking as such take a bit of understanding.

par Frederik C

Nov 18, 2019

Very well explained, lost time during tutorials because of apache beam version conficts with google cloud dataflow

par Carlos B

Dec 20, 2018

The work needed was waaaaay below a one week

par Arturo M

Nov 20, 2018

Too long for one week. I would suggest to split it in two or even three weeks

par Alejandro O

Jan 15, 2019

More hands on activities is the common theme on all classes, its a lot of talking and not a lot of putting things together, follow the University of Michigan Python curriculum, that one is great for hands on learning.

par Matthew S

Aug 05, 2018

Some missing steps in lab descriptions

par Fabrizio F

Aug 06, 2018

The subject is very interesting and I was alwyas curious about how Feature Engineering should be done with Tensorflow. I come from Pandas, where feature engineering is not that difficult, but with Tensorflow it is different and not that intuitive. Here in the course three different ways are presented. I guess I'll have to study more Apache Beam.

par Leszek Ś

Aug 13, 2018

Please update instructions. UI has been changed.

Some code doesn't execute. Last lab. Should be updated. This can be just one sentence (simply, versions of packages don't fit).

par Jonathan A

Aug 27, 2018

The concepts were taught well. However, a lot of code and cloud interaction was involved, making the labs a key piece of the material. Two of the labs didn't work because the Google lectures aren't up-to-date with the Google APIs. Although Coursera response to the bad labs was prompt, the Google team did not respond.

par Xinyue Z

Sep 14, 2018

Some labs don't work

par Alouini M Y

Sep 16, 2018

A good course overall. However, the last two labs didn't run since packages couldn't be installed. Please update these labs. :)

par Yingchuan H

Sep 17, 2018

The content of this course might be a bit too much for one week compared to previous courses in the specialization. Also, it would be great if some of the labs are more clarified and introduce more opportunities for students to participate in writing code for the lab session rather than just going through it and running existing code. I did experience some issues installing the tf transform package for the last lab, which might not be a common issue, but was kind of frustrating as it prevents me from more exploration of the learned skills. Thanks for providing the course anyway. I learned a lot from it.