.

-

.

.

g

T

e

G

e

E

R

O

G

g

g

I

I

I'm doing this training for the second time, now as a beta-tester. Particular comments about lecture content, problems, etc. have been put in every lecture.

General comments, in short:

1) Related to the new platform and UI design:

_ It is cleaner and simpler than the previous one. I like it, BUT...

_ It lacks of some useful features: saving intermediate results in quizzes before submit them; calendar; limited number of subforums.

_ The most relevant flaw: there are not downloadable versions of lecture slides. Unacceptable! No way to check most of the links we saw in slides (URLs not visible).

_ Description and steps in course project appear "too packed" together. I prefer the former design.

2) Related to content:

_ The course is mainly for preparing students for the rest of data science specialization program. When you said "toolbox" you mean the concrete toolbox you will need to do the program. Some people expect to have a general introduction to data science but that is only a half of the content. I think this is clear enough in the presentation but for some reasons there are people in forums who protest the content, so maybe you should insist more in this fact.

_ I would like to suggest some kind of reorder of material: week 2 is all about installing a running tools and week 3 about key aspects of data analysis. Maybe you can split both types of content between wk2 and wk3 to make wk2 more appealing for not technical oriented students.

_ Git is a source of problems for a good portion of people. See my comments in lectures about how Git is explained.

So why not 5 *'s - because I could not give 4.93 *'s

What I found excellent and thus 5 *'s - *****

a) material

b) even the automaton of a voice - was not a deterrent but rather soothing - oh well tells you something about me!!!

c) Material is deceptively easy in the front end and gets progressively more difficult later

d) the references are well thought out even of the entry into Data science

e) The build up is very logical

f) Lots of thought has been put into the design by the team

What I found lacking and thus dinged a couple of points (perhaps too harshly)

1) The mini quizzes do not sufficiently force you to think about the material and thus easy to breeze thru to the next week - perhaps I am being too judgmental and it may improve in the next course of the specialization

2) I could not see an easy way to get the material to review when taking the test - most of the time I forced myself to not look at the material to test myself but the onus is on you

3) It should not be about getting some questions wrong but learn the material so that every question can be right (imparting knowledge vs getting a certificate with 80% pass - think how would we feel if this was a training for a neurosurgeon ;) ) - a suggestion would be to force the student to read the section that pertains to the incorrect answer and not allow the test to be taken again until that is accomplished - like in a class room setting.

This course is a great intro to the potentials of R and the world of Data Science and Big Data as well as the approaches and mindset needed for it. It's fairly straightforward, my only suggestion is to maybe include some tips on troubleshooting some installations for some parts of the lectures. For example, I already had R and Rstudio installed from my college days, but the versions were outdated (R 3.2.3) and weren't compatible with some packages and they weren't working but I wasn't understanding why until I had to google it. Similarly, I had some issues with linking my GitHub account to my Rstudio because the route it was using wasn't working and the correct one was highly similar, I was only able to fix it thanks to forums. These details can be frustrating for someone who's trying to follow along with the lecture but is stuck, so thank god for forums. It would be nice if the instructor could write a couple of tips on how to fix some common issues like those for novices.

I understand the decision to use synthetic voice, but at some point it gets boring and uninteresting because of the lack of variety in the tone and loudness. I still get reminded from time to time that the voice I'm hearing is AI generated. But besides this, the course content is a good way of introducing a beginner in the environments of GitHub, R, and RStudio, although personally I still don't fully master how I to connect these different platforms or languages or interfaces. Particularly, the lesson on commit, push, and pull and how to these tasks are supposed to be done in and across the different platforms (including GitHub) still confuse me. The programming per se does not worry me as much as getting the file paths and directories right and making sure that I am where I am supposed to be whenever I do a task. Lastly, I believe there are some typos in the transcript so please review and make the necessary corrections.

Excellent Course for learning Basics. I had no previous experience with software, computers aside from surfing web, checking e-mails and some Microsoft Office. I'd recommend this course to anyone Interested in data-science or coding in general. The course is easy but not too easy the frustration of dealing with computers exists and I feel it was important for myself to struggle a little bit. I followed the advice of the instructors and sought out solutions to issues. I spent twenty hours a week but if you are tech savvy, take good notes, follow directions and everything goes as planned you could possibly get through the course in a lot less time. There are also a lot of people willing to help. The course shows you how to seek out help efficiently. I didn't request any help this time around had I done so I would have spent half as much time on the course.

I think this is an excellent course. If I could I would give four and a half stars. The only reason I wouldn't give it 5 stars is because I would prefer to have my work graded by an expert rather than my coursemates. I tried to mark as fairly as possible but didn't know whether I'd done one of the questions properly. So I marked other people down on where I thought I'd made an error (but wasn't sure whether I had or not). I think this could be potentially unfair to people as they may have got it right. If an expert had marked all the work then we would all be sure that the assessments were correct. This is quite a big deal when it comes to confidence in one's own progress moving forward. However, I thought the content was great and easily accessible and I am looking forward to continuing the course.

A good introduction to some of the tools used in data science. However, it felt like the lectures for git were a bit rushed. Also, while it is easy to do so by following the provided instructions for Mac, I have noticed there is no lecture/tutorial for installing RStudio on a Windows System. Overall, I think the course was a good introduction to the 10-course specialisation. Although, as a course in itself, it is somewhat lacking. The provided reference text by Professor Jeff Leek (The Elements of Data Analytic Style) is a concise summation of the course with extra information on best practices. I would recommend all students enrolled to download and read the book twice to get a better understanding of the concepts introduced. Personally, this helped me quite a bit.

I think there could be more lectures on programming related to R. After this course, I am now able to just link any R file(project, script, markdown files) to Github. I also got to learn various features of world's largest repository holder like steps involved in pushing any document to Github repository. Since I am little more interested in leaning the programming languages, so this course did not meet my expectations. Instead it turned out to be some course with greater emphasis on theory and working of the RStudio.

Rest overall, it provided me with the base knowledge of data science. I am sure that this course will cater greatly to my foundation of career as a data scientist. Thank you.