The content and the instruction were great: just the right level for someone like me with experience in other programming languages a decent familiarity with stats.

There were a few glitches with the auto-grader for the assignments, but nothing to onerous.

A great intro to pandas. Challenging even for those with experience using the library. There were some struggles with the autogravder, but they were being worked out, and the integration of the Jupyter notebook system directly into the class is fantastic.

While the course was great, the Jupyter notebooks and the background shells gave me several unnecessary errors. While this was a smaller issue, I think the practice Notebooks should be somewhat in line with the assignments. I struggles on Assignment #3.

The course was a unnecessarily hard because of the lack of feedback from the grader, unclear requirements / function definition in the final project and difference in the file downloaded for the project and the one used in the Coursera python notebook.

Good materials and videos, iteresting exercises - the only thing I would improve is the exercises description - not for all of the exerisises it was clear enough for me (especially as I'm not from the US and I'm not familiar with your census data :) )

I learned a lot through the challenging assignments, but the course materials (videos) are not very useful. They only cover the very basics for the assignments, so be prepared to study a lot on your own. Knowing pandas beforehand helps a lot too IMO.

This is an exceptional undertaking by the university of Michigian for benefit of the students in the field of data science and Machine Learning.This is perhaps the only course which focuses on real world application of data science skills to practice

Good explanations, well structured. However, I wish the weekly content would have prepared better for the assignments. If I have to add another 3h per week to find the right advice on stack overflow, that must be stated somewhere so I can plan ahead.

Very good course with a lot of material and challenging assignments. Gave it only 4 stars because in some assignments is more difficult to agree with the autograder than to get the correct answer (e.g., data type mismatch between float and float64).

Excellent explanatory videos and lot is covered in just four week of course but it definitely need good grasp of pandas and numpy libraries for passing the assignnments. I definitely recommend this course as it will push you to learn and do more.

The content is really not good for novices. But the challenges I faced during assessments, did a lot of help. I can now understand the topics much better and at the least I am able to plan to clean the data and work on it much better than earlier.

The course content is great. However, basic knowledge of python programming language is required. Since I didn't know python coding rules, I really struggled for a while. Maybe, basics of python in additional resources will help a lot of learners.

In my view, It is recommended to study a book on Python data analysis tool-kit panda and numpy. The course video quality is very good, instructor voice is clear and load. I highly recommended to take this course who wants to be a Data Scientist.

This course would be recommended for anyone who has got good python skills already and want to do data analysis using python at a quick pace. Overall, It is fun doing the assignments and thinking more in a pandas way rather than in pythonic way.

The projects were extremely helpful to learn various concepts . The videos could have been a little more descriptive to equip us with a little more knowledge so as to tackle the projects with a little ease .apart from that it was really great

Class was good, and the information was presented in a way that was straightforward to understand and apply. I wish the exercise autograder provided more feedback. Sometimes the lack of actionable information made it difficult to solve problems.

The course is a good introduction for data science and helps me learn pandas and numpy. You may not learn how to use these tools only form this online lesson, but you can be aware of what you need to know if you would like to work on this field.

Good, comprehensive course. At the end you are ready to get and clean data and make some simple analysis on your own. But you need a lot of effort to do programming assignments. Save double amount of time than it is estimated for this course.

This course provides good material. The assignments could be very difficult because the instructions were not clear. In real life, you would have a chance to clarify while it is difficult to do so in coursera.

Overall, it is a good course.

The course was great - the lectures were clear and simple; I learned a great deal! However, instructions for the assessments could have been clearer, and there were a few issues with the autograder (though I'm sure those will be weeded out).

Generally good - with challenging assignments, explanation could be better and grading unit tests more flexible.

Some of the content is rushed - but it is comprehensive and you need to have some python programming behind you before you start.

it's a good, but challenging course as Introduction to Data Science. It will require the student to read pandas documentation and/or search for help on Stack Overflow. If you're stuck, there is usually good help on the course forums though.

Nice course but the assignment is too hard for the beginner, and the assignment and the course materials are not match enough. We have to do a lot self-study when doing the homework. But the skills I learnt from the course is really useful.

This course worked better as a guide than it did as a course. I learned very little from the lectures and had to do most of my learning on my own. One of the assignment even explicitly told students they would have to go learn on their own.

Pretty descent course, however it felt like most of the course consisted of the assignments and self-learning rather than instruction. That's probably ok given the content was more oriented around tools and less around concepts and ideas.