This is the worst of the Data Science courses so far (they've all been pretty good up to this point).

It's called Exploratory Data Analysis, but is actually all about the graphics systems in R. And it does a botched job on those as well.

All quizzes and assignments are about the graphics systems. The only portion of the course that deviates from that is Week 3 (for which there is no quiz or project) where we "learn" about clustering and dimension reduction. However, that material is presented really poorly: not enough depth for someone who is already familiar with the subject matter; and not nearly well enough explained for newbies.

On the graphics side, none of the systems is explored in great depth. The lattice system is essentially just mentioned in passing.

To cap it all off, the brief for the last assignment is really ambiguous, which often causes perfectly valid work to be graded poorly by peers. (Just look at the forums, if you need proof.)

Provides a solid overview of the base plotting system and a discussion (better elsewhere) of others. Introduces some higher level exploratory methods, without much information on either the theory or application (simply walks through the recipe). Assessments do not match the lecture material, so the credential is essentially meaningless. Read the associated book, watch the video lectures if you'd like. Don't bother with paying for the certificate.

Cons:

# Too much focus on hopelessly outdated R functions.

# Lectures are mostly powerpoint karaoke along the lines of "You can do that thing. And you can also do that other thing. And also you do this third thing" without much real-world application.

# ggplot2 is the only modern viz package that gets mentioned

Pros:

# The swirl exercises are great (but very buggy on Mac)

When it comes down to it, there's simply not the support to assist a student that has a really hard problem, "hacker mentality" seems to equate to "figure it out on your own cuz nobody's going to help you". If things do not work perfectly for you then you are likely never to be able to finish because your "peers" don't know any better either. The way this class is set up makes me angry every time I have to deal with it. I would probably be just as well served doing just the swirl() exercises. I would quit if I hadn't paid all the way through in advance. I can't believe this is the type of school John Hopkins is to produce a course of this quality, but I guess I have to.

This has been a challenging course for me, for whatever reasons. I have devoted a great deal of time in reading Dr. Peng's books as well as reviewing work product of other students to get a better grasp of the logic and methodology. I have enjoyed this course more than any of the preceding courses. And, the struggle I believe will be worth the effort and facilitate my completion of the data science specialization program.

This lesson could have been significantly improved if there was at least one assignment on clustering/dimensional reduction. Those are probably the hardest concepts thought thus far, so it would have been extremely useful to have at least one challenge to work through.

This course covers plotting (base, lattice, ggplot) then takes a confusing tour into heavy topics of clustering and dimension reduction, then flips back to coloring in charts. The order of the lectures is confusing and PCA/SVD needs more background, clearer explanation and treatment (gets covered a bit more later under regression). Assignments are good and swirl courses helped solidify the lectures.

This course is basically plotting with R and clustering/dimensionality reduction. There's is not enough emphasis on the later in my opinion. The final assignment focuses only on plotting, which is a shame.

Once it got to the clustering section the lessons were inscrutable. Extremely difficult to understand and not explained well.

Alas, after only 10 minutes of the first video, I am reminded that this instructor does not gear his lectures to the true Beginners among us. He speaks much more for an audience of grad students. I do want to complete this Specialization, so I will try again perhaps after learning more - about statistics and R and who knows what else. I fought my way through the first three courses, but now I'm going to work smarter by finding other ways to acquire this knowledge. Then return to him; maybe. This course should be labelled Intermediate and Statistics should be listed as a prerequisite. (I think; since I don't know what it is that I don't know, I am making a guess as to the missing piece of the puzzle.)

The videos were merely repeating the content from swirl, with absolutely no added values.

This course mostly about how to use plotting libraries in R.

Very insightful course!!!

The swirl packages and course projects in "Exploratory Data Analysis" course have really helped me to understand the power of R in performing introductory graphical analyses towards initial inferences. It has good hands-on exercises to really put to action various sophisticated graphs and plots for boardroom conversations on how to go deeper into the data analysis in order to find meaningful business insights or build powerful predictive models. As I advance through the specialization, I am getting to realize how powerful Statistical Learning through R is for quick business action and automation.

Graphs and plotting is at the heart of data analysis and data science, and without it you would have difficulty conveying ideas, and having graphs to explain numerical/statistical data is always handy. Visual representation of a data set, and using visual cues to gain an understanding of data, can save a lot of time, and can help you gain additional insights into the data. This course teaches you key techniques on how to apply some graphing and plotting methods to visually explore data, and it does so really well and in great detail, and also provides some good demos.

I was able to learn the material presented over the time of the course. It's a lot of material to cover in the time I could commit to it but I feel confident using the tools and methods presented. The projects were very valuable both from getting to practice the methods and tooling and also from seeing how other students approached the solutions. I really helped put all the options into context and highlighted the value of using the different tools and where to use them. Only knock would be sometimes the background noises in the videos were distracting.

I really appreciate the course design. Even if somebody doesn't have much background in R, she/he can comfortably learn from the videos and understand the concepts. The exercises and project assignments are challenging and actually help you practice and re-visit the lectures and explore further. Though I had already known and used Clustering, PCA and SVD in my work before, I really liked the way these concepts were explained here. I would strongly recommend this course to anybody who is keen to see R in action!

It was a wonderful experience to read the structure of data before delving into the advanced statistical levels of data analysis.The need for inclusion or exclusion of dependent variables or dimension reduction in regression analysis can be intuitively understood and visualized using Data Exploratory techniques and then we have the clue as what to do in the next level.It is like putting the whole characteristic of the data under full control.

This course is the first real step from using R for basic data manipulation/stats, to using it for advanced stats. However, the videos on PCA (principal component analysis) and SVD (singular value decomposition) were difficult to understand, and I had to view several videos on YouTube (e.g., StateQuest or Standord U) that do a far better job of explaining. Once I did that, the course videos seemed to make more sense.

My name is Jose Antonio from Brazil. I am looking for a new Data Scientist career.

Please, take a look at my LinkedIn profile: https://www.linkedin.com/in/joseantonio11

I did this course to get new knowledge about Data Science and better understand the technology and your practical applications.

The course was excellent and the classes well taught by teachers.

Congratulations to Coursera team and Instructors.

This course is nice but ggplot should have been given more emphasis probably. I really enjoyed the sections on SVD and PCA as these really require mathematical maturity. Other than that solid introduction to the plotting systems in R which is a must have. This course coupled with Applied Charting with Python will complete my skillset. Looking forward to the rest of the specialization.

Great Course. Week 3 requires a bit of mathematical savvy (google SVD/PCA), but since there is no quiz, it won't affect your ability to finish the course, just your ability to fully understand what you are doing. The last project was a bit challenging, which is always good, but most of the information to complete it and earn full marks is in the discussion forums as usual.

A great course I had to do research on the side to get some ideas and concepts that were presented in this course.... if this was my first course i would have found that not a good thing . However, every time i search i get better as a data science student and i know what to search for and how to find it and i think this is essential if you want to be a data scientist :)

A very good introduction to the exploratory analysis and the R's plotting systems. The most advanced exploratory techniques (singular values decomposition, etc.) are not explained in depth but the overall role that these kinds of statistical learning techniques plays in the exploratory analysis is firmly established.

Great work with the course!

Well organised course for Exploratory Data Analysis. After this course you will be thorough with the basics of the Exploratory Data Analysis. The peer graded assignment is one level higher than the concepts thought in the lectures is what I felt. Overall, it is worth taking this course. Thanks a lot, Coursera.

Dr R D Peng is clear, concise and teaches quite systematically so that data visualization and exploration is broken down into its constituent pieces and explained in a way I am yet to come across elsewhere in other MOOCs on the subject. I'm really impressed and happy to have taken up this course.