Chevron Left
Вернуться к Проектирование признаков

Отзывы учащихся о курсе Проектирование признаков от партнера Google Cloud

4.5
Оценки: 1,012
Рецензии: 98

О курсе

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: https://qwiklabs.com/terms_of_service <<<...

Лучшие рецензии

OA

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.

P

Mar 07, 2019

The content is great, not just from a technical point of view but for all the know-how that the different instructors share during in the videos and labs.

Фильтр по:

76–98 из 98 отзывов о курсе Проектирование признаков

автор: 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.

автор: 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".

автор: Terry L

May 01, 2019

개요를 알게 되서 좋음

автор: 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...

автор: Rahul K

May 05, 2019

Lovely Course. Thanks Google

автор: 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

автор: borja v

Jun 21, 2019

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

автор: Emily T

Jul 05, 2019

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

автор: 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.

автор: Carlos B

Dec 20, 2018

The work needed was waaaaay below a one week

автор: 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. :)

автор: 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.

автор: Matthew S

Aug 05, 2018

Some missing steps in lab descriptions

автор: 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.

автор: 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).

автор: Arturo M

Nov 20, 2018

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

автор: Xinyue Z

Sep 14, 2018

Some labs don't work

автор: 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.

автор: Marko H

Apr 06, 2019

Basically this course would receive four stars, but repeated problems with qwiklabs had a severe impact on my overall experience. I got thrown out three times in a row (and my account locked) during dataflow lab.

Every time I had to request unlockin of my account, which took half a day every time. When requesting advice to avoid this error, I got offered the general and vague explanation that I "should only use the resources required by the lab". I am 100% sure that I didn't use any extra resources, including zones and regions.

The Coursera's helpdesk went behind the excuse that Qwiklabs is a third-party service. That may be the case, but since Qwiklabs has been integrated into the Courseras' course, the ultimate responsibility lies with Coursera.

I hope that Coursera will co-operate with Qwiklabs to sort out this very annoying problem.

автор: Arman A

Apr 11, 2019

Pros: Tensorflow is an excellent framework for deep learning

Cons :

1- The way this material is designed is 10 X SHIT

2- Either teach properly or don't teach at all.

автор: yannick t

Jun 11, 2018

Not very clear + lack of real student practice

автор: john f d

Jul 18, 2018

Labs vms are to slow. Speaker is difficult to understand. Mic varies and speech pattern is not clear. The presentations need some graphics rather than a guy talking. Sketch out the ideas on a white board rather than talking 5 minutes to a single slide.

автор: Nathan K

Oct 29, 2018

Ultimately I found this course to be disappointing, because the Google APIs for DataFlow, BigQuery, etc. are unusable with the provided QuickLabs account. When you try to activate any API during the labs, it asks you for a location. It is a required field that says: "You must select a parent organization or folder." Clicking this option reveals a single organization called "no organization," which is not a legitimate choice. APIs cannot be activated and then cannot be used in the lab.

Because of this I was unable to actually do many of the labs that required the use of the Google APIs including the keystone lab "Improve ML model with Feature Engineering" where the taxi-fare prediction model is refined into a perfected state.

I'm upset that I paid money for this.