Capstone did provide a true test of Data Analytics skills. Its like a being left alone in a jungle to survive for a month. Either you succumb to nature or come out alive with a smile and confidence.
Wow i finally managed to finish the specialization!! definitely learned a lot and also found out difficulties in building predictors by trying to balancing speed, accuracy and memory constraints!!!
創建者 Max D•
NLP module should definitely be included into JHU Data Science specialization.
創建者 Michael N•
Had to learn a lot on our own but very valuable content once acquired.
創建者 Pradnya C•
Most stressful but interesting. Not enough material was provided
創建者 Adam B•
I liked every course in this specialization except
創建者 Tracy S•
it could've given more instructions!
創建者 Jeffrey G•
With the exception of R Shiny programming, there was nothing about this course that required any real knowledge of anything in any course of the JHU Data Science certificate track. Why do you ask? Well, most of the class was just about learning natural language processing (NLP), which wasn't covered. What about R programming, you ask? Most of the NLP packages in R that I tested out couldn't process a 200MB text file in a reasonable amount of time or with a reasonable memory footprint. I ran Python and R programs in parallel to do sentence and word tokenization, and Python's nltk was (not exaggerating) 100x faster than R's NLP package, and R's tm package took 4GB of memory to parse the same 200MB corpus. In 2018, that's just unacceptable. There's no way you could ever write production-quality NLP code using these R packages. After the course was finished, someone pointed out an R package that could adequately accomplish the task, but by then it was far too late. Even R's basic data structures themselves weren't up to the challenge. I ended up building my model in Python, exporting it as JSON, and then importing that into my Shiny app. Comparing basic data structures in Python and R to represent the same JSON file (i.e., just read in the file and measure the size of the resulting object), R's list was nearly 2x as large in RAM than Python's dict. All of this combined with really very little reference to most of the material in the other nine classes in this track left me very disappointed. The reason I gave the class two stars and not one was because what we did learn about NLP was useful. Having to solve a gnarly, real-world problem starting from raw data is useful. Having to write an app with actual users interacting with it is useful. But could just about everything about this class have been done a lot better? Yes. I think a machine learning project that tied together everything that we'd worked on up until this point would have been a lot more fun and rewarding.
創建者 Leo C•
Sadly disappointed. I can see how this worked before, when most people were active on the forums, but now it's extremely frustrating. Not because it's hard, I do not mind that, but because you really have to DIG through the forums to find vital information.
For instance, there are two quizes, you need 80 % or more to pass. However, the app you are simulating only get 20-30 % on such quizes, and you're not REALLY supposed to get that high. That's in the forums, but not on the quiz itself.
Also, very few things you've learned in the ML part of the specialization is actually used, and they specifically points you to a MOOC by another university. That's not very comforting.
The good part though is that the actual final exam does not really need good predictions to work, just an app that functions as you say it does. My tip? Look at the NLP, google a bit and learn the basics, then make an app that's as simple as possible - Then learn NLP with some guidance.
創建者 Michael S•
Of all the offerings in the specialization, this one felt like it was thrown together in less than hour. I expected to have to learn quite a bit of material on my own, but even the references to additional materials were very thin.
I could have saved many days if more guidance on the project workflow would have been given. The pre-processing of the data was quite extensive (9 steps before generating the ngram tables I used in my model) and was the key to getting decent results IMHO, but one had to step on a quite a few landmines to figure this out.
The problem was an interesting one and I ended up reworking it after passing with 95% (the only class in the specialization I didn't get 100% on) because I didn't have time to implement much of what I had to figure out by 'hard-knocks'
創建者 Ken W•
To tell you the truth, when I started this capstone, I felt like I was thrown into the deep end of the pool. You are asked to build a NLP app using Shiny and, unfortunately, most, if not all, of the concepts required to design and build the app are not covered in the earlier courses in the specialization. Can you say 'Google'? I would have liked to have seen the instructors walk through the relevant concepts required to successfully complete this project. The videos consist of Dr. Peng basically saying "Good luck!"...a little lame if you ask me.
創建者 Marco S C•
Unfortunately this project is not fully aligned with all the previous program, which is a shame. Ideally, the project was more related to quantitative data, or have compulsory module NPL. It was certainly a very important learning, but very stressful to have to grasp NPL and do the project in a short time.
Learning NPL in short time in a DIY way without any help it was very negative and stressful.
創建者 Sandro R•
As other reviewers said, the Capstone is too unconnected to the rest of the specialization. In the end, there is no metric as to what makes your model successful, it's just the Slides and the appearance of the Shiny app that counts towards the total mark. Also, the topic (Natural Language Processing) is just too unconnected to anything seen in the other courses. It was fun, but felt a bit off.
創建者 Tavin C•
The series leading up to the capstone was excellent but the capstone itself was a disappointment. Very little instruction was provided and the grading criteria were flawed. Also, most of what we learned in the first 9 courses about statistics and machine learning turned out to be irrelevant to the capstone project.
創建者 Clara B•
The course has nearly nothing to do with the previous themes. I already have had enough knowledge, but as there is no support by the team it seems to be rather time consuming for others.
創建者 WONG L C•
I hope it will involve statistics analysis in the capstone project. It is kind of bias to apply NLP knowledge and develop data product in the capstone project.
創建者 Sevdalena L•
Not enough information on how to approach the final project. The project itself is very time consuming with lots of self learning and unclear specifications.
創建者 Lee M S•
The capstone project doesn't fully utilise d knowledge from earlier modules such as Machine Learning, statistical analysis, regression models n etc.
No physical way to complete the class within one session. Little is learned, no instruction is given, just build a thing that sort of works.
創建者 Dmitri P•
The course is outdated and abandoned by the teachers.
SwiftKey engineers are nowhere to be seen.
There is no guidance.
創建者 Yohan A H•
Thanks for the guide but I did the hole course without instructions, there were new thing that could be tougth.
need more details
創建者 Joerg L•
I currently taking this capstone and I must unfortunately say that this is the most worst course in the whole specialization. Of course the topic NLP and word prediction is interesting, but the problem is, that this is a dead course. A couple of students in the forum strugeling with details, but there is NO Mentor, no Professor or other course staff and no SwiftKey engineer as announced in the Project Overview.
So everything you have to figure out completely by yourself and this takes a lot of more time than the 4-9 hours. And also why should you pay for a course where you learn anyway only ba your own.
Pick any intersting topic you would like to work on and invest the time in this instead of paying for this Capstone without any support form Coursera, JHU or SwiftKey.
創建者 Aleksey K•
None of the previous classes will prepare you for this one. This is not really a class, but rather a project on a topic NEVER covered in any of the previous classes in this specialization.
創建者 Stephen E•
A poor end to a poor Coursera specializations.
創建者 Runhao Z•