Not bad, but certainly not good. I cannot believe there is a style of teaching where you never get to see the best way to do something. I can slog thru the programming, but I doubt it's the best way to do something, but I never get to see how something should have been done. It's odd we have no feedback from prof and just 'grading' from other students who also are slogging thru without ever seeing the best or even some good ways to have done something.

The instructor cares very little about the ability of his students to keep up with his explanations. The pace at which the material is presented is horrible, the amount of details is just the bare minimum. I do not think it would be too much work for the instructor to double or maybe even triple the length of the course videos. But he just does not seem to care.

Instructor reads lectures in monotonic voice. The lectures themselves are just a series of cases of some R functions usage with no basics of Why you need to clean the data or real cases with complete examples how and where to get your data and what steps you can do to make it useful.

The course has a lot of links for tutorials in R. That's a plus.

The project at the end requires actions that data scientists should know but does not actually talk about the items. For example the project "book". You hear about it but are not actually taught the right way to make one. At best case you are taking a guess and at worst you are learning bad habits or missing out on what should be in it.

Didn't really cover how to deal with messy data, e.g. if you need to join to datasets and have orphans, or you have no foreign keys between two datasets and you need to use fuzzy matching.

Basic validation was also not covered (i.e. making sure that your data covers all that you expect).

I saw two main issues with this course: 1) dated lecture videos, oftentimes with R code that can't be replicated using up-to-date packages, and 2) lack of thoughtful design: example after example after example after example doesn't really teach you anything.

The class is getting stale. The instructors didn't respond to questions on the discussion forums about quiz items, the majority of assessment items seem to be available on Google and 50% of the peer reviewed assessment I checked used plagiarized solutions.

The code for the final assignment is peer reviewed which doesn't make sense. It should be reviewed by either a TA or some kind of application than can verify what you've done. Also, the assignments were a bit of a leap from the video tutorials at times.

The videos did not teach anything that was going to be on the quiz so it was like answering 5 questions at random using google. The lesson plans and project were very vague and too much time was spent trying to figure out what was even being asked.

This is a very crucial part of the data science specialisation and I feel more hands-on exercises and quizzes should have been there. Small practice quizzes for testing incremental learning within a week should be there.

In my opinion the structure of the course is not the best. I mainly dislike the fact that some libraries, packages, etc. (e.g. MySQL) are not trivial to install.

Still I learnt quite a lot, so I wouldn't say it's bad.

Mediocre presentation of tidy data, which is probably the most critical topic. Otherwise, its mostly just walking through what commands to use in R to load in various file formats.

This class needs more content, more explanation. It is clearly a very important aspect of Data Science, but the assignments were more complex than the given course content.

I learned a lot but my usually happy & grateful attitude was sorely challenged by the fact that so many facts in the videos and obvious course material was, well, wrong.

Out of date material. Many links broken. Some of the functions taught are sunset. Week 2 was too surface level to do anything useful. Weeks 3 and 4 better than week 2.

This course has a very interesting subject and a concise syllabus, but is very poorly prepared. I hope coursera will pass on the message to Johns Hopkins University!

Too difficult practical exercises with the theorical background given. I know that hackers skill should be used but it is too much assumption in the projects!!

It is somehow just an extension on R Programming course, with many unnecessary details that will be forgotten in a few days after the course.

The video is simple and good.

But the final project and some test are too hard based on material presented.

Also staff's support are not good.

The only interesting part was dplyr. The rest was too confusing, with lots of lists and no explanations.

The information in the lectures is very stale, which makes it extremely frustrating to learn from.

The course material needs update. There are code snippets that do not work.

This course could have been better. It was all textual and it got boring.

Final assignment is not well detailed, and may cause confusion.

This course lacks projects to implement the skills we learn.