Sorry but I can hardly say any nice words on this course.

1) as the 2nd course in the AI program, it jumped in very randomly without any good reason

2) it's more an advertisement on IBM platform than a machine learning course

3) the content is organized very randomly, too, sometimes statistics, sometimes algorithms, just showcasing how IBM is linked with ML, I guess

4) there's no overall introduction in the beginning of the course to let students know why we are having this course, why is it important for ML practisers, and how will it be organized

5) There are many ad-hoc corrections in the slides, I would suggest a re-making if lots of content has been out of date

6) actually I suggest IBM remove this course from the whole program and change it to something more useful and relevant for ML.

I have done some great Coursera courses before but I am disappointed by that one. The course covers some superficial topics without really explaining the basic concepts of Apache spark & big data. I had to do extra research just to understand what I was currently doing. I am sorry to say but I cannot recommend it. You get a lot of "Don't worry, you do not have to understand that coding as you will not be asked about it." But I really want to understand the coding. Looking back I do not feel comfortable in using Spark now and I guess there are more suitable courses for learning that in more detail.

I don't even know, what I learned from the course. To me, its a waste of time because of the way it was arranged and presented, almost in a hurry. I am not confident in whatever, I learned from the course. I will look for a similar course to learn spark and would not recommend this course at all. I think people end up taking this course because it is included in the specialization. It is a horrible experience and complete waste of time and effort, if anyone takes my word.

This was the worst course that I have seen on Coursera so far. The language barrier of the instructor was difficult at best. Some of the questions on the pop quizzes you would need to guess at bc he hadn't taught it yet. The end of week quizzes themselves were not that instructive. The only reason I finished this course was for the certificate. Someone needs to redo this course.

Excellent course! All the explanations are quite clear, a lot of good quality information provided from amazing teacher. Additionally, response times for any question is very fast.

After completing this course you will be able to use Apache Spark to build ML models (e.g., Linear Regression, Gaussian Mixture Model, etc.).

Thanks a lot for helping me. I would suggest that the data storage in IBM cloud should be described in detail.

The quality of the videos could be better

very low budget, just horrible. I've seen more professional content created by teenagers in udemy.

good contents and hard to follow actually if lab answers not shown directly. I have the feeling that the instructor knows a lot and it would be great if he can express that in a easily understnadable manner. Anyway its a hard job itself.Btw, some of the statistical part are consistent with scileanrn but executed in differnet methods. Modeling and testing part the underlying idea is the same. Pipeline is so powerful hope it is useful in the future. Thanks to the Instructor, and may learn his other lessons as well. I am shocked when seeing the PCA part which is so impressive, and the star ship of invader! Big likes! Cheers!

I really appreciated the course and the way the lectures were conducted. For me it was import to match some of my Pandas/ScikitLearn tools with a BigData/parallel approach. I just let here a remark: Since I'm not familiar with Spark/pyspark, it took me must longer to "correct" the code and make it work. Probably it has to do with the pyspark version I am using in February 2022. Thanks. (one example: lambda (a,b): a+b didn't work. used lamdba x: x[0]+x[1])

just awsome and very very informative ...specially the whole process was done on the spachespark environment on the IBM-watson studio where whole processing is take placd on the working-nodes of the apacheSpark cluster under the Apache driver manager parallely, and most prefereble dataset format is used here is '*.parquet'(HDFS)

all is really essential to become datascientist, in the last thanks to instructor

Loved it. I've already done the Advanced Data Science specialisation but I've found this course really useful. It is great to have new notebooks and a range of evaluators and classifiers being shown. I've already picked up things that I would want to add to my final project in the previous specialisation. Thanks again, Romeo. I hope you'll continue to make new courses as I enjoy your teaching style.

excelent teacher and he has a nice way of building up the concepts in small, understandable steps. The best part I liked is that he explains the concept of Pipeline and uses it in all the following alogorithms thereby repeating the idea of pipeline everytime. This helped me personally because I learn with repeatation. Thank you.

This is really an awesome course, I love the content of this course very much as it is very informative about the core work happen in Big Data.

I learned so much from this course like what is Big Data, how we deal with it, how to use Apache Spark & Spark ML with Pipelines.

Overall it's a good course to start learning Big Data.

Romeo explains these topics perfectly. If you take this class along with maybe one or two other applied machine learning classes I am sure you will feel very confident with the material. My only piece of advice would be to always follow along in your own notebooks and question what every.single.line does

One of The Best Course I seen that combine Machine Learning with Apache Spark with awesome tutorial along with using IBM Watson studio which really help me to complete my course with one of the best tool along with the documentations. And really help any problem what i face so far using this course.

I should not comment the way how this lecture has been carried out... HOWEVER, it does bring actual tooling skills and makes it interesting to use those instruments for real life situation. Highly recommended. Make your model maybe can be your crystal ball.

Romeo Kienzler! Thank you so much! This course showed the complexity of parallel computing and introduced Functional Programming in a very simplified and understandable way. The way statistics was explained, was something I couldn't even get from college.

Learned several new skills. Instructor did an excellent job of explaining the concepts starting with the notion of big data and showing us how to run ML algorithms on apache spark and use of pipelines.

Really really REALLY enjoyed this course! The instructor does a masterful job of going from simple examples and building up complexity in a very logical and thorough way.

I like the example given and step by step tutorial given. The explanation of why things are the way they are designed certainly helped me understand the concept. Kudos.

It was a great experience , learned a lot about Apache Spark, Programming assignments helped a lot in grasping the concepts

The videos were not so awesome, but the curse was superb overall. It really addressed the intricacies of large data.

Good course. Beginner level, it starts slow and gets better in weeks 3 and 4. Instructor is very helpful.