This repo contains the work completed while going through the 'NLP with Python for Machine Learning Essential Trainig' course on LinkedIn; taught by Derek Jedamski. The course provides an introduction to NLP fundamentals that serves as a valuable foundation for going deeper into the NLP field.
- Working with textual data (importing, reading, cleaning, exploring)
- Tokenizing data
- Vectorizing data (Count Vectorizer, TD-IDF are the 2 used in the course)
- Build and evaluate ML models (Random Forest & Gradient Boosting are introduced in the course)
- Some ML terminilogy and concepts (splitting data into train/test data, Cross Validation, Hyperparameter tuning, general ML pipeline, etc.)
There are a ton of other little topics that are mentioned that can learned by researching on your own.
I would recommend taking this course if you have an understanding of the fundamental processes involved in ML as well as some experience with Python. While not necessary, it will save time and allow you to focus on the MLP topics, rather than trying to understand ML terminilogy or Python code. The instructor does a good job of explaining what is going on but it is much easier if you have some prior knowledge.
- Research each individual topic mentioned in the course separately
- This way you will learn a lot more than what is offered in the course
- While explained well, this is still an introductory course, so even the main topics should be researched separately for thorough understanding
- It will take longer to finish the course this way but it will significantly improve your learning
- Type out all of the code shown in the video, compared to just copy/pasting from the provided files
- Google any concepts or code you do not understand
- Take notes of concepts introduced to revise at a later time
- This can be particularly helpful when working on a future NLP project