I would like to report some major issues with the new interface.

1) We don't have access to the slides anymore. This is a major issues since some of the slides content important links. These links are not shown in the transcript (I've double checked).

2) When we try to download the videos, subtitles or transcript, the resulting file name is the same for all content of the same type. More specifically, all videos are named "index.mp4", all subtitle files are named "subtitles.vtt" and all transcript files are named "subtitle.txt". This makes it more difficult for the student to save the files. In the previous version I would only right-click and saved in the right directory. Now, I have to right click, type the right name (which could be long sometimes) and then save the file.

3) In the previous interface, it was possible to see all the threads we were subscribed to. It is no more the case. It is not a problem right now, because there is not a lot of posts, but in cases where the number of post increase, it will be a pain to go through the list of threads and find the ones of interest.

Please ignore the review for now, I couldn't submit my comments without reviewing the course.

More comments may follow later...

This is a recommended course for anyone serious with data science. It is highly accessible, especially for screen-reader users who may be comfortable taking lectures using text rather than videos. I was able to successfully complete assignments on my own without problems. However, the only setback I see with the course is its over-reliance on RStudio. While Rstudio is a great IDE for R programming, it is not yet fully accessible. So questions like, "Which quadrant is at the bottom right corner" are answered as a guess-work rather than full knowledge. I suggest that command-line options be considered as this is accessible for everyone. Thus, while the GUI option is left intact, there is need to also provide command-line alternative to accomplishing the same thing. Otherwise, this course is perhaps the best when it comes to introducing the concepts on data science.

Great course! My first step into the data science world. The course not only teaches basic concepts and but helps to build a good habit for learners. Some suggestions: 1. avoid quiz on the layout of software or website (Github), as GitHub keeps changing its functions and appearances, some of the "correct answer" are no longer applicable (for example, there was a quiz "what are the three menus on the head right of a repo in Github?" the answer has changed). 2. Most of the instructions are clear and easy to follow, but I found myself constantly trapped in the section "Linking an existing Project with Git", especially how to find the right directory in Git Bash in the process of linking. I think others might have the same problem. Can you add some more instructions (such as common errors) in this section? Thank you! Over all, great course! Thank you!

The Professor's are just amazing in their knowledge. The slow bits of information and the way testing is done is so methodical and so well planned. If anybody says they are bored then I am sure they are bluffing, as I found out how enjoyable online learning can me. I am 40, working and a father of 2 children, time is scarce and this online way of learning with financial aid, I could not ask for anything more. Coursera is helping people like me find a hope of learning at their own pace, place and with their financial aid program helping poor people from developing countries like India see the light at the end of the tunnel. I really am indebted to Coursera for changing my life and helping me dream of a career transition even at this age, as in India if you tell anyone that you are studying at the age of 40, they would laugh and make fun of you.

I have completed the Data Scientist's Toolbox. I enjoyed learning this course. I learned a lot of new concepts, installation of R, R Studio, hands-on with these and GITHUB.

The lessons are well balanced and help me learn the concepts and the tool usage in a cool way. I liked the Quizzes, Assignments as these help me evaluate myself and instill confidence within me. Now, I've the confidence in work on any of these with certain amount of instructions.

However, I feel that certain guidance on progressing further with respect to R, RStudio, GITHUB could be provided as additional study material.

Thanks to Coursera for providing such a wonderful course and to Prof. Roger D. Peng, Jeff Leek and Brian D. Caffo for their meticulous effort in designing this course and helping in my learning.

Wishing my Professors and Coursera all the Success.

The course is really well organised and challenging.

It gives a good introduction to data science, as well as some currently relevant concepts related to it, such as machine learning and big data. I found it easy to understand and I enjoyed the pacing. Moreover, I really appreciated the time this course spends on teaching some of the basic tools that are needed in data analysis, namely R (and RStudio, R Markdown) and Github.

You are constantly challenged by small quizzes to make sure you really understood the material. They're not too complicated that you would get frustrated, but also not too obvious that you'd be bored by them, and more often than not you even learn other things from these quizzes.

I definitely learned a lot and would recommend it!

It's a good first step into getting the right programs, learning key vocabulary, and interacting with important websites/programs at a very introductory level.

If you are not from a math/statistics background you can still complete the course but you will not understand the previews for later courses completely, that is ok! But consider getting the eBook with this course.

My only complaint is the quizzes, it often feels impossible to get a 5/5 based on only what you get from the lectures, there's always 1 question that is completely over the top compared to the other 4, but you can do the quizzes 3 times every 8 hours and just trial and error the 1 gotcha question on each quiz.

The Data Scientist's Toolbox is the first course of the Data Science course by Johns Hopkins University. The course contains constituents which are needed to build a base for future data scientists. 4 weeks of the course contains the basics of data science, Installing R and Rstudio, working on Github and many more things. The course is suitable for people who have no prior knowledge of data science and are looking to find something which contains the basics of the topic. If you're in a dilemma of studying something which is related to data science and you're not aware of the basics of it then I recommend you to select this course and study. All the best!

It was interesting to see how a University is approaching topics which are considered "Core IT" and present them to non-IT people. Though I consider myself very strong as an IT with a master's degree and heavy experience in databases, Matlab and some R, it still had many things to give me and most of all, a methodology in setting up a lab environment. Although I was graded lower in the last assignment because I use Visual Studio Extension for R, by someone who does not know that R is one in the system and the shell may differ, I strongly believe that the rest of the courses will provide the methodology needed to approach complex data science problems.

Very interesting intro to data science, but the focus on command line Git may drive people away (although it was a great contribution for me!) I would use that time and effort to delve deeper in the concepts that a person must grasp in order to understand the challenges that are better tackled by using data science.

I believe there is a big and harmful disconnect between the ideas that decision makers have of their understanding of world "out there", and the real possibilities of observing and making sense of it. If this course would help narrow that gap, even a little bit, then I believe more people would be using the insights of this discipline.

This course was exactly what I was looking for as a first step to learning R, It gives you an overview of data science and then installing R, Rstudio and R packages. It introduces version control and again takes you through using this in a step by step manner. If you are not familiar with R and want an introduction I would recommend this course. The assignments are based on the work already done and as such act to reinforce the week's learning. The time per week is about 4 hours. My experience is that I always spend at least a couple of hours longer so it was ideal as I am fitting it around a full-time job.

Great introduction. The lessons were clear and easy to follow. Github is a new tool. I used to be shy about using Github because I didn't understand all the commands, but I'm confident I'll pick it up easily during the rest of the course. I already feel more comfortable with it.

I'm a mechanical engineer, so this is a different way of thinking for me. I was amused by the lesson on what data is and about the kinds of data analysis because the data I look at always comes a CSV file / Excel file, and I only do mechanistic analysis. So I'm looking forward to expanding my definition of data and analysis.

This course is a good first into to the topic. I think that the additional reading from the book and the Git manual will supplement it very well.

My only complain is that in the first quiz, there was a question regarding some R packages used in Machine Learning that were not covered in the slides. It took me a while to find those so I had to take the first quiz 3 times. I think this question should be revised to guide the student as to how to find these packages. Another alternative would be that in the slides there some guidance in this matter.

Otherwise, I liked to course and the final assignments.

This was a great opening course for the Data Science specialization because it talked about the tools that will be used to illustrate the concepts that are coming later. In other classes, the education on the subject matter is presented in the primary position, with tool instruction woven into those lessons. That model gives me two different priorities ( learn the topic and learn the tool ) and that competition for attention is suboptimal for me. I find myself having to revisit course content if it takes extra effort to learn some piece of technology used to demonstrate it.

Overall the coverage of github was at an appropriate level for me to understand and for that I am very grateful, as I was too lazy to force myself into learning how to use it up to this point. The coverage of installation of important programs was also a great way to introduce a subject before diving into the details. The broad coverage of the overall core curriculum was nice, and I am excited to learn how to use R as it seems like it will be around for a while (even though i'll always be faithful to my C/C++/fortran roots). I look forward to enjoying the rest of the program.

Conforme o proposto o curso é muito bom, a didática é muito boa. Mas, gostaria de deixar uma observação, em um determinado momento senti a curva de explicação muito alta. Por exemplo, no ultimo curso da semana 3 ficou muito complicado de entender, achei que entrou em alguns assuntos ainda complicado para quem está iniciando, até essa aula estava subindo numa constante mas depois parece que deu um salto muito grande, para mim, que fiquei um pouco "perdido". Fora esse ponto, gostei muito, parabéns pelo trabalho. Espero aprender tudo da maneira correta, Muito obrigado novamente.

Es un buen curso introductorio, aprendes como instalar R y RStudio en Windows y Mac, si lo haces sobre Linux (mi caso) te tocará investigar por tu cuenta. También aprendes un poco de su interfaz, paquetes que se usan y su integración con Git y GitHub (si estas en Linux también deberás investigar por tu cuenta). Al momento de mi comentario esta todo en inglés y eso no es una desventaja pero si no eres bueno con el idioma como yo tocará hacer algunos pasos extra para traducir el texto, sin embargo no es algo que impida el aprendizaje.

I love the course and the material provided. however the mechanical voice in the video is somewhat a weak point. when some real person read or present they use voice modulation as per various circumstances in the presentation, which is recognize by the listeners' brain and perceived accordingly. however, as you have mentioned the reason for use of this voice due to rapid changes, it a worth compromise. I had fun and learned a lot. Thanks to creators for their efforts and time they have put. Thanks to Coursera to bring this course.

Nice course. I got basic idea about data science, R and Rstudio. I have previous knowledge about Git. Apart from the contents, the new way of presentation is not impressing, many of the lengthy videos, it was annoying. Like, if it is a real human video, the instructor will change the tunes and it is more important in the communication. I am suggesting the same method with a human voice instead of computer generated audio/explanation. I rated 5 star for the way of progress, the context of each lesson. I felt I learned new things.

Excelente curso!! Te brinda todas las herramientas y un muy buen material de estudio, además de enseñarte minuciosamente los conceptos y partes básicas para poder aprovechar bien los primeros recursos. Y me parece un buen enfoque ya que considero que no solo se debe tratar de una "transferencia de conocimiento", sino que los alumnos debemos despertar la curiosidad y hambre por investigar para profundizar más en la diversidad de temas que tenemos por estudiar.

Muchas gracias por su dedicación y esfuerzo al elaborar el curso.

I really appreciated that the instructors took the time to go into theory and history before writing a line of code. I think an introduction or more reference to necessary statistical/mathematical knowledge would be good, but I understand if that's outside the purview of the course.

I also love the amount of extra, supplemental material you can review, whether it's a linked article or Leanpub book written by the lecturers. Would definitely recommend this course to other people interested in data.

Providing feedback means giving students an explanation of what they are doing correctly AND incorrectly. However, the focus of the feedback should be based essentially on what the students is doing right. It is most productive to a student’s learning when they are provided with an explanation and example as to what is accurate and inaccurate about their work.

Use the concept of a “feedback sandwich” to guide your feedback: Compliment, Correct, Compliment.

It's a great way to start the course. It provides basic knowledge and understanding of the tools. Instruction are clear and easy to follow.

Peer review can be challenging as I notice on my work that the answers were correct but the other peers are saying is wrong. What I notice is this https://www.datascience.com will be considered correct but if the text is datascience with a hyperlink, it is considred wrong. It will be good if this will be reviewed.

Very helpful and well organised, easy to follow and I believe it sets you up very well for the following courses.

If you are looking to learn R and have some previous statistical analysis background (I have learned Minitab 19 for about 3 years now) but have no coding knowledge, I would reccomend not skipping this course as it will help you set up R and introduce you to its basic functions, otherwise it could seem a bit overwhelming.

God bless

I think that the course is effectively introduces students to the basic toolkit of data science--informative materials, good explanations, and the accessibility to knowledge sharing through the discussion forums.

One suggestion please: It would be very convenient if you could put the links in all the videos in a place where the students could readily access them (contrary to needing to donwload the slide first to be able to access the links).