The course had good content and lectures, and the quizes were an appropriate level for the material covered.

Some problems I had:

The lectures are quite old so many of the data sets used in the examples are unavailable now. This makes it difficult and frustrating to find new data sets that have the characteristics needed to follow along with the exercises.

The first swirl exercises has problems with some of the files that make the lesson malfunction and therefore can't be completed. Looking through past reviews and discussion threads, this has been a problem for years that still hasn't been fully addressed.

The final project was quite difficult and I felt it was a bit beyond the level of the course. It wasn't as bad as in the R Programming course, but I still think that examinations and assignments should be at an appropriate level for the material covered in the course. What's the point in testing people on skills and material that you haven't taught them? What's the point in signing up to the course and doing all the lectures and exercises if we have to teach ourselves new skills using external resources to pass the final exam?

The course is teaches you some principles of tidy data and cleaning data but it's very messy.

There is no systematic approach to plyr and dplyr libraries. The teachers peak some functions from one and some functions from other library, but without any clear principle. It looks that prof. Leek and prof. Peng are presenting their favorite functions without consulting each other. They are doing it in the right way, though very confusing. On the other hand loading data is approached very encyclopedically.

Assignments not only check what was taught in the videos but also sometimes require new skills and going through stackoverflow etc. (e.g. codes to read fortran files). This is not the way how you construct good coursers.

Additionally some instruction in the final assignment are provided in submission part! (Expected names of the files should be provided in the assignment description, not on the submission page).

Prof. Peng and prof. Leek are very skilled, they know their job, but they don't know how to teach efficiently. Nonetheless if you are motivated to learn, this course may be very helpful.

The course is great and essential to becoming a good data scientist. Provided me with valuable lessons in managing and processing raw data.

A major issue is that the course has not been updated in a while and has a lot of missing/ expired data sources. You will however be able to find and download the data if you do a bit of searching online. All the data used in the course is still available online and you just need to find it.

The course will also need you to do a bit of research and exploration on your own to use some of the methods specified in lectures. All the details are not handed to you in the video lecture. I have seen other people complain about this, but my personal view is that you will anyway need the skill to research and adapt in a practical scenario outside the course and this is the best place to learn this skill as well.

It would have been great for the course to be updated and made easier for beginners but alas. It will be good to have your basics in R, using libraries and a bit of data analysis under your belt already before jumping into this course.

This course was quite challenging in comparison with the first two. I felt that the material provided by the instructors was not enough to approach the quizes and assignments, so it's necessary to spent a lot of time researching for your own in other sources. I struggled with the Course Project Assignment because I didn't understand what I was supposed to do exactly. Fortunately, the forum threads were really helpful. Nevertheless, the course's intention is very valuable and if you are patient and go all the way through it you will improve your data science skills, learn very useful techniques and habits, specially if you're a beginner. But I strongly suggest the instructors to make the course contents more explicit and helpful.

Great class for an important piece of data analytics and data science. One issue I've been noticing with R compared to using Anaconda/Python is that a lot of the libraries required for the class aren't explicitly mentioned. That's fine if you're experienced with these environments and able to read error codes with familiarity. Minor annoyance to me when I run a script and realize I don't have a library installed.

I'd imagine though its extremely frustrating for beginners who may have written perfectly good code but haven't figured out that they simply need to install certain packages to answer quiz or homework questions. Perhaps having a full library or package list for Course 1 of this series will be helpful.

There was a lot to like about this course but there were several aspects that kept the course from being stellar. This course attempts to convey a lot of important information without connecting the dots. The videos did not align well with the Swirl exercises and the videos did not attempt to address foundational principles of the course topics. Rather, many topics were covered on a superficial level without in-depth examples that demonstrate application of the topics. I think the course needs to updated as some of the quiz questions and material seem to be out of date. The final project description had aspects that were vague and hard to interpret given the data set we had to work with.

The material that's ultimately learned from this course is very powerful and provides a major milestone in one's data science journey. However, I had to mostly teach myself. The instructor's video lectures only teach at the most basic level, and the quizzes are much more advanced - thus creating a very large gap which I needed to fill by lots of self learning and research. The course project is a great opportunity to put the course's objectives into practice, but it wasn't explained clearly - it took me many hours to understand what needed to be done. All in all, I am satisfied with the course's material, but not the way it's communicated to the students. Three stars.

Lecture content is very drab and filled with "...and here's another thing you can do...". I think it would be a lot more effective with more problems and various solutions. There should be a project every week along with the quizzes.

I also found the peer review process for the course project to be sub-par. I personally put a LOT of work into the course project, and put together what was a really thoughtful and well-written README and CODEBOOK just to have my project downgraded because someone wasn't sure the run_analysis did what it was supposed to. It's not a big deal but I think if an instructor saw it they would've found it very thoughtful, thorough and accurate.

This course was largely helpful and the instructor was clear in the lectures. However, much like many of the courses in this specialization, the quizzes and the final project were misaligned with what was taught in the lectures. For example, we sit through a whole week of lectures on the details of reading in many different data types, but never talk about fixed-width format once, it's never even mentioned. And that is what is on the quiz. The final project was challenging and fun to figure out once I was on the right track, but the directions were not sufficiently clear and I wasted a lot of time needlessly simply trying to figure out what the instructor wanted.

This is a very brief course, many of the topics deserve a much more thorough explanations. This part of the data analysis (i.e. data cleaning and acquisition) is in fact a complex subject and subjects are not covered in this course. There were also technical issues. For instance, the audio quality of lectures by prof. Jeff Leek is very poor. And the other major problem that I had with this course is the ambiguity of the requirements, although it wasn't difficult to finish. But if you are planning on taking this course, be ready to spend considerable amount of time on understanding the structure of the final submission's materials.

Like all courses in this specialization, there is an incredible lack of practice and application for a large amount of the skills taught in lecture. I would say that only about 60 percent, or maybe less, of the content in the lecture is assessed in the quizzes and assignments. Additionally, the peer review process is wildly flawed for the final project. I did not receive any constructive criticism from anyone, and I doubt they even truly looked at my code to make sure it worked. I don't blame them, they have little incentive. Rather I place blame on the system of grading and lack of feedback.

I have 2 key concerns with this course. First, I don't feel like the material presented adequately prepares you for the quizzes. For at least 2 of the 4 quizzes, I had to spend a substantial amount of time locating and reviewing other resources to answer the questions. My second concern is that for the final course assignment, there is a lack of specificity with the instructions. Not being able to answer a question is vastly different from not understanding what the question is asking and I found myself spending more time doing the latter (which is wasteful) and less time with the former.

In some weeks only about an hour of input where several topics have already been covered in R Programming. That's very little value for money.

The final course project again feels like it's done in a rush and without another review: The submitted dataset should be automatically checked. It's simply impossible to derive from it whether the student did everything right, but it could be easily done programmatically. Some of the questions have wording and grammar issues that make it hard to understand. Also there is slightly contradicting instructions between the task and review description.

I did learn a lot, but I thought the first half of the course (getting the data) was very challenging.

What does annoy me though is that links aren't clickable, sometimes they're wrong, there are typos on the slides etc. The response to these complaints in the forums is that these lectures were recorded a while ago and it takes time to change things and so on - but for $50 a month, I don't think it's too much to ask that the course materials be kept up to date!

So honestly, I feel like I'm being ripped off a bit here.

I did really enjoy the course project though.

In my opinion, the lessons are just a basic overview of some concept and do not gives you the competences you need to pass the Quiz and the Peer Graded Assignment. Therefore, for most of the questions of the assignments, you need to look for the tools you need somewhere else in the web! On one side, without the lessons, yhou would probably not know what to look for on google, however the lessons are not enough to achieve a good grade in the assignments! Also the peer graded assignment takes to long to receive the evaluation!

The most challenging so far of the 9 courses on the Data Scientist track. Would like to see some errors removed from slides. Some parts of the lectures seemed rushed. Would like to see some of the non-self-evident usage of some functions to be described a little better in more detail. I found myself having to look at multiple online areas to really understand some of the functions that were glossed over. Otherwise, this was a very helpful course that should be taught to all disciplines involving any amount or type of data.

The "Reading from..." lessons from week 1 and week2 were extremely frustrating, since we did not get much info on where we would see them most often or the benefit of using one over the others. Instead, we simply sat for hours listening to lectures moving from one type of document to the next before being handed the quiz. The dplyr and data manipulation lectures were great and I really anticipate using them frequently in the future. I think regular expressions deserved more lecture time/ practice.

The Course Design is good however what i give three stars is for the following reason

The Sound Quality is straight up very poor . i have to put my speakers to full volume to atleast make it clear and audible , which leads to other pc programs to cause loud noise with the same sound volume

Many Topics in the course like Factors etc were not clear in the tutorial videos and i had to most probably go out of my way to find the meaning and uses

Rest The Course Is Top Quality . Thank You For the course

This is really R part 2, getting into file/API handling, data frames, regular expressions etc. The specialization focuses on data frames though little coverage of data tables needed for the capstone. Some of the ordering of the materials was confusing e.g. this course revisits date/time handling which was started in the previous course. Assignments are interesting and Swirl exercises are useful. All in all, the combination of these R courses gets you up to speed.

Very challenging but rewarding. The first two weeks of material were a bit condensed I think, hard to follow how to import some obscure data types into R and too complex to be covered in a 5 minute video. Could have been spread out more or omit some that are not probably practically useful. The quizzes and the final project were difficult to navigate using only the material provided in the lectures, and had to rely a lot on Googling stuff.

The quality of this course is much better than the earlier two. Although this course still has the problem of feeling like a disjointed series of topics on singular functions, there is much more of a cohesive overall theme and structure so it feels a bit more like you're building towards an overarching goal. The final project directly relates to the lectures and felt like a solid way to connect most of the ideas to a project on real data.

I suggest changing the quizzes and assignment questions more often because they're all over the internet for this course and rest of the courses in the specialization. I understand that students who are cheating are mostly hurting themselves, but it also affects the value and credibility of the certificates you're giving out.

In terms of course modeling and content, it's very nice. I really enjoyed. The swirl package is genius. Thanks.

There were a lot of good nuggets in here, but overall this course felt somewhat disjointed compared to the others. It would be nice to have more practice with some of the different formats (e.g., JSON) and for exercises to loop back to some of the early content. I did like that the final exercise required a fair amount of investigation into understanding the documentation and relationship between the files before undertaking to code.

The data downloads for two quizes appear to have been updated, meaning that there is no way to come up with the right answer. The course project could use some minor clarifications. I was very difficult to determine what was wanted, and this lead to my having to re-submit twice. The deliverables seemed to be confusing to both me and the graders. Course was difficult because of this kind of confusion, not because of the material.

Difficult course, I had to complete it over two sessions. I came into the Data Science track with no knowledge of computer language, which has made learning R particularly difficult; however, after the previous classes I am finally able to search for the information I need to complete the assignment. The other reviewers are correct that the final assignment is a doozy - it took me several hours to complete.