Preparing textual Data

[Rosie93]

Hello


for the past 3 months I have been trying to learn Machine Learning, Neural Network and Natural language processing. However, I found out that im lacking in a major aspect which is preparing the data and then splitting it for NLP problems. Im lost and confused since all the tutorials always provide already ( ready-to-use ) dataset.


also when I moved to studying examples with NN and TensorflowI don't see methods applied such, lemmetizaion, stop words, stemming and normalisation. it just Tokenize--> turn to sequence --> padding what about the initial tasks?


I would appreciate an advice

[lazyprogrammer]

Thanks for your inquiry.

Why not check out one of my NLP courses?

https://deeplearningcourses.com/o/deep-learning-nlp

[Rosie93]

thanks for your reply . I have already took your free most important Python libraries.. aren't these the same?

and excuse me but how is it related to NLP ..

[lazyprogrammer]

> I have already took your free most important Python libraries.. aren't these the same?

I am not sure what you mean by "free most important Python libraries", but I'll assume you're referring to the free course.

I have over 30 courses. The free course doesn't cover everything, that's why there are 30 more courses to take.

As the title and course ordering suggests, it's only a prerequisite to all of the other courses.

> and excuse me but how is it related to NLP ..

NLP is the field of machine learning which concerns text. You should read about NLP and other fields if you don't yet know about them (for ex the articles at lazyprogrammer.me).