Natural Language Processing (NLP) with Python — Review

Our review

Natural Language Processing with Python is Jose Portilla's focused, practical introduction to working with text data, and it carries the same clear, exercise-driven teaching that made his Python and SQL courses so widely trusted. Across 12 efficient hours it covers the classical NLP toolkit — text processing with NLTK and spaCy, tokenisation, part-of-speech tagging, named-entity recognition, classification, sentiment analysis and topic modelling — and finishes with an introduction to deep learning for text.

The course's strength is that it makes text data approachable for anyone who already knows Python. NLP can feel like a maze of specialised libraries and linguistic jargon; Portilla cuts a clean path through it, showing you how to clean text, turn it into features a model can use, and then build practical tools like a sentiment classifier. Every concept is grounded in a runnable notebook, so you learn by doing rather than watching.

This suits Python users moving into language and text work, data scientists who want to add NLP to their toolkit, and anyone with a concrete goal like building a sentiment or text-classification tool. The scope is well judged for its length — you come away able to handle real text-processing tasks end to end.

The honest limitation is currency at the cutting edge. The course is strongest on the classical and early-deep-learning NLP stack; it predates the current wave of large language models and transformer-based tooling that now dominates production NLP. The fundamentals it teaches — how to represent and clean text, how classification works — remain essential and transfer directly, but you'll want a separate, current resource for transformers and LLM APIs.

The clear prerequisite is Portilla's own Python Bootcamp, and it pairs naturally with Machine Learning A-Z for the broader modelling context. If your interest in language is really about using today's generative models rather than building classical NLP pipelines, the ChatGPT Complete Guide is the more relevant starting point.

A practical framing that helps: think of this course as teaching you to prepare and reason about text, which is a prerequisite skill no matter how the modelling layer evolves. Even in an LLM-dominated world, real projects still need cleaning, tokenising, classifying and evaluating text, and doing that well is exactly what Portilla drills here. The classical techniques age gracefully precisely because they're about the data, not any one model's API.

Verdict: at $13.99 this is good value for a clean, practical grounding in NLP fundamentals from an excellent teacher — just pair it with a current transformers resource for the modern LLM layer. Have your Python solid, buy on sale, and use it to get comfortable with text data. Our editorial score: 9/10.