Nice

Gud

yes

na

NA

很棒

ok

Ok

P

5

The quality of this course is very good. It helped me to get a basic understanding of exploratory data analysis. Whereas the first weeks topic was more or less early for me, the seconds weeks topic about statistics was more challenging and I also had to do some own research to deepen the contents discussed in the lectures.

The course is very good and provides a detailed knowlegde of exploratory data analysis and a very basic revision of statistics and hipothesis testing. Only some of the iPython labs have minor errors in their content and need a review, which don't affect the learning experience much, however.

I like the part that how to work on feature engineering. I understand machine learning is statistic, but I felt week3 week 4 are teaching me how to use python to analyze the data. I was hoping to learn more about machine learning models and optimize their outcome.

I really liked this course, has been extremely useful for me as a starting point for next IBM courses. One suggestion to improve - some concepts are covered a bit superficially, in my view, e.g. Hypothesis Testing. Maybe going a bit more into theory would help.

1- The Lab videos are not clear enough, the font is too small, so hard for eyes to see what is written on the screen. 2- Most of the time Jupyter lab (individual work) was not opened. moving to Spyder is easy but why not to fix this problem? Thanks.

The information was good though basic. I thought the info on hypothesis testing and probability was probably not necessary for an ML course where this should be assumed. The teacher was clearly reading off a script which was at times not so engaging.

The first part of the course was very good, in the second (week 4) I had a hard time understanding it and it seemed to me that too many concepts were given for just one week. I loved that application examples were made to reinforce the concepts.

The course is great but in my opinion the teaching material will be even better and more exciting if it has less text and more graphical visualization of the topic being explained. I feel like the instructor read the slides for me.

The course was great, but as around Week 4, I faced difficulty in understanding the concept, especially when it was implemented in code. I hope that more brief description, especially for code can be included in Week 4.

It is fairly difficult for a beginner - although the level is intermediate for this course and there are a few prerequisites, somehow I still feel that a lot is pending to be explained, esp. in the DEMO/LAB exercises

Excellent content and examples. Would be great if another example for hypothesis testing is added to demonstrate this concept with a typical ML dataset (maybe use one of the previous datasets used during the course)

Great instructions, wonderful demos and insightful comments on the results. The only part that I did not find well explained is the part on hypothesis testing. Some details could be added on t-test and z-test.

Well explained concepts and spoke at the right speed. But, some of the hypothesis testing, probability, and Bayesian statistics material could've been explained better with more visuals perhaps.

Overall insightful and a good introduction to the field, but could spend more time teaching about Python libraries and their functions. Jupyter Notebooks often failed to run (broken URLs?).

It was a very code course, however, it would be nice if the code was available on a notepad while videos played to make things faster. Also, some of the online notebooks were not working.