Some mistakes/ typos in the exercises and slides, but great overall

An assignment should have been included

This course is decent but lacks more thoughtful and detailed explanations about its topics. For instance, it is severely lacking a glossary (what is exactly "actual values", "predicted values", "target values", "fitted values", "free parameter", "hyperparameter" and "estimators". I only know what these concepts mean because I looked them up on the internet, but their meanings should be in a 40 dollar a month course. They are essential for an enough understanding of the job of a Data Scientist.

Despite IBM telling us this certificate does not require previous Mathematical and statistical knowledge, if you do not know what is a reduction of a first degree equation, cartesian plan, ANOVA test, t-test, correlation, polynomials, R^2, Mean Squared Error, etc., get ready for a wild ride in another sources of study becayse this course throw this concepts at you very quickly with explanations lasting one minute sometimes.

The monitors at the forum are very helpful and knowledgable though.

Pros: The labs (guided worksheets that ran in Jupyter) were good, and were how I learned the material. The final project was also pretty good, with clear instructions and a reasonable challenge level. Cons: The video lectures were not at all engaging, and I mostly skipped those, or just skimmed the transcript. Occasionally there was a lack of alignment between the videos and the labs, such as a different method being used than that presented, or the videos on Python DB API which never showed up in the labs. Also, the multiple choice assessments were terrible - most questions were trivial, a few obscure, but almost none effectively tested either programming skills or conceptual understanding.

This is an excellent course... which you will have to teach yourself 60% of the way. It's a shame, such potential with topics like Polynomial Transformation and Ridge Regression, all treated with minimum detail and little information. I found myself reaching for additional videos and books to keep up with the notebooks and homework. If you need a refresher course, this is fine. Else, get ready for much frustration covering way too much theory with too little content.

So far the other courses in the Data science specialisation contained a final graded assignment. I found them really useful. This course didnt. Also, instead of telling us about all the tools available in the libraries, maybe explaining why we would use them would be better. I could code these functions myself if I understood them, but just using a library seems like it could lead to laziness and a lack of understanding.

There where some typos in the labs that could confuse most learners. I didn't feel like the course prepared people for real applications. The final project was quite hard because of this .

But it does give you a wide vision on hoy pandas work and some basic but apparently often used tools.

I see this course as a complement to a more detailed data analysis resource or perhaps as simply as an introductory view.

Hello,

in this course there were some errors on the slides, and some quite complicated topics (almost every time related to statistics) was given in a very over-viewed way. Also, some of the python codes were not explained very well, with some terms of them seem to be kind of arbitrary for those who are beginners in the language. My impression is that this course should be longer and more detailed.

Overall I benefitted the course material as a beginner in python and data analysis. The questions were too trivial but maybe that helped me remain engaged with the course and complete it in a short time frame. There were some bugs, typos and minor quality issues that did not really effect my overall experience.

Many typos in videos, stats explained on a very rudimentary way (and often inaccurate), Watson environment is awful as it takes ages for some simple regression plots to be made, it freezes and the interface is not user-friendly, yet we have to use it.

Seems like there are quite a few errors in the labs that confuse the heck out of a student. The labs need to be fixed else the material becomes useless.

Course content does not give proper understanding of the different approaches. For the person who is not from mathematics background it is confusing.

Definitely not a beginner class. I understood all concepts, but it went way too fast, with not enough practice to really embed them and practice.

The statistics background needed for the course need to be better explained. or at least reference to related learning materials to be given

Too many errors in the lab examples can be rather confusing.

Also, the Seaborn code was not working in IBM Watson Studio

Great course but some of the concepts are not explained very well. I got lost towards the end but overall i like it.

Lot of information, but offered in a very choppy manner. Was hard to follow, will need to review many many times

the course content is excellent but some Technical issues occurred in doing the lab exercises

The lesson need more explanations on Polynomial Regression, Pipeline, Ridge Regression.

Good content, but I wish the assignments and exams were more challenging.

The evaluation formats of these courses are very weak.

explanations are often very short or missing.

too much content all at once

Begins relatively clear. The practice labs were coherent and straightforward.

Around Week 4, things started to get convoluted. Small things, things that you don't notice at first.

Week 5 was where it really started to fall apart. You could tell whoever made this course lost interest or just did not have the capacity to teach the information effectively.

A great example of the lack of understanding or knowledge of how Coursera works is something you can view yourself.

Week 6 is the Final Project

Week 7 is one statement about your certificate.

Usually in most courses, the final project will be in end of the final week. That week having multiple modules that you have to complete leading up to the final. It was worrying for me as I thought the approach to this was on accident, but it seems likely that it was just due to ignorance.

Just as well, the Final Project was botched, the software and questions were depreciated and even written wrong by the creator. And when you would upload your pictures in the end to show you had worked out the problem, one of the upload buttons was missing in lieu of the letter "Y"....

Y indeed. Y was the ending of this course so terrible? A little more investment in the people you are teaching would go a long way. Very disappointed.

The quality of the course is quite low - there are mistakes in the code shown in the videos, and some libraries are outdated, causing issues with the code in labs. The way they explain things... I don't like it. I completed this course with a score of 100%, but I still don't have a clear understanding of Data Analysis. I feel like I only gained bits and pieces of knowledge - some from here, another from there, but they didn't provide a solid foundation. Unfortunately, I will have to find other courses... 

So, if you're willing to spend a significant amount of time Googling and chatting with ChatGPT to make the example code work, then you can choose this course. It's not that bad of an option either. 😅