Data Science: Natural Language Processing (NLP) in Python
4.5 (8,631 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
33,760 students enrolled

Data Science: Natural Language Processing (NLP) in Python

Applications: decrypting ciphers, spam detection, sentiment analysis, article spinners, and latent semantic analysis.
4.5 (8,631 ratings)
Course Ratings are calculated from individual students’ ratings and a variety of other signals, like age of rating and reliability, to ensure that they reflect course quality fairly and accurately.
33,758 students enrolled
Last updated 7/2020
English [Auto], German [Auto], 3 more
  • Polish [Auto]
  • Portuguese [Auto]
  • Spanish [Auto]
Current price: $139.99 Original price: $199.99 Discount: 30% off
5 hours left at this price!
30-Day Money-Back Guarantee
This course includes
  • 10 hours on-demand video
  • 1 article
  • Full lifetime access
  • Access on mobile and TV
  • Certificate of Completion
Training 5 or more people?

Get your team access to 4,000+ top Udemy courses anytime, anywhere.

Try Udemy for Business
What you'll learn
  • Write your own cipher decryption algorithm using genetic algorithms and language modeling with Markov models
  • Write your own spam detection code in Python
  • Write your own sentiment analysis code in Python
  • Perform latent semantic analysis or latent semantic indexing in Python
  • Have an idea of how to write your own article spinner in Python
Course content
Expand all 77 lectures 09:44:57
+ Natural Language Processing - What is it used for?
3 lectures 21:59
Why Learn NLP?
The Central Message of this Course (Big Picture Perspective)
+ Course Preparation
4 lectures 13:03
How to Succeed in this Course
Where to get the code and data
Do you need a review of machine learning?
How to Open Files for Windows Users
+ Decrypting Ciphers
13 lectures 01:29:02
Section Introduction
Language Models
Genetic Algorithms
Code Preparation
Link to Cipher Notebook
Code pt 1
Code pt 2
Code pt 3
Code pt 4
Code pt 5
Code pt 6
Section Conclusion
+ Build your own spam detector
11 lectures 01:04:53
Build your own spam detector - description of data
Build your own spam detector using Naive Bayes and AdaBoost - the code
Key Takeaway from Spam Detection Exercise
Naive Bayes Concepts
AdaBoost Concepts

In addition to the word frequencies we looked at previously, this lecture looks at bag-of-words in general and different ways to implement that, including raw counts and binary indicator variables. We also briefly mention TF-IDF.

Other types of features
Spam Detection FAQ (Remedial #1)
What is a Vector? (Remedial #2)
SMS Spam Example
SMS Spam in Code
Suggestion Box
+ Build your own sentiment analyzer
7 lectures 01:00:00

What is sentiment analysis? In this lecture we'll look at the data we'll be using to build our sentiment analysis tool, and talk about how we can manually pre-process the data so that we can plug it into a machine learning classifier.

Description of Sentiment Analyzer
Logistic Regression Review
Preprocessing: Tokenization
Preprocessing: Tokens to Vectors

In this lecture we'll write our sentiment analyzer in Python to predict sentiment on Amazon reviews.

Sentiment Analysis in Python using Logistic Regression
Sentiment Analysis Extension
How to Improve Sentiment Analysis & FAQ
+ NLTK Exploration
4 lectures 09:18

How do we tag the tokens of a sentence by their parts-of-speech? i.e. Is this token a noun, verb, adjective, adverb, or something else?

NLTK Exploration: POS Tagging

How do we turn words into their "base form"? i.e. plural to singular

NLTK Exploration: Stemming and Lemmatization

Can we also tag parts of a sentence as a "person", "organization", or "location"?

NLTK Exploration: Named Entity Recognition
Want more NLTK?
+ Latent Semantic Analysis
5 lectures 44:23

What is synonymy and polysemy and how can LSA / LSI help?

Latent Semantic Analysis - What does it do?
SVD - The underlying math behind LSA
Latent Semantic Analysis in Python
What is Latent Semantic Analysis Used For?
Extending LSA
+ Write your own article spinner
6 lectures 37:07

What is article spinning and how is it related to search engines, SEO (search engine optimization), and Internet marketing?

Article Spinning Introduction and Markov Models

What will be our strategy for creating an article spinner? We'll create a trigram model.

Trigram Model
More about Language Models
Precode Exercises
Writing an article spinner in Python
Article Spinner Extension Exercises
+ How to learn more about NLP
1 lecture 02:45

Important NLP topics you should "know of" but that we didn't cover, and where you can learn more.

What we didn't talk about
+ Machine Learning Basics Review
11 lectures 01:33:58
(Review) Machine Learning: Section Introduction
(Review) What is Classification?
(Review) Classification in Code
(Review) What is Regression?
(Review) Regression in Code
(Review) What is a Feature Vector?
(Review) Machine Learning is Nothing but Geometry
(Review) All Data is the Same
(Review) Comparing Different Machine Learning Models
(Review) Machine Learning and Deep Learning: Future Topics
(Review) Section Summary
  • Install Python, it's free!
  • You should be at least somewhat comfortable writing Python code
  • Know how to install numerical libraries for Python such as Numpy, Scipy, Scikit-learn, Matplotlib, and BeautifulSoup
  • Take my free Numpy prerequisites course (it's FREE, no excuses!) to learn about Numpy, Matplotlib, Pandas, and Scikit-Learn, as well as Machine Learning basics
  • Optional: If you want to understand the math parts, linear algebra and probability are helpful

In this course you will build MULTIPLE practical systems using natural language processing, or NLP - the branch of machine learning and data science that deals with text and speech. This course is not part of my deep learning series, so it doesn't contain any hard math - just straight up coding in Python. All the materials for this course are FREE.

After a brief discussion about what NLP is and what it can do, we will begin building very useful stuff. The first thing we'll build is a cipher decryption algorithm. These have applications in warfare and espionage. We will learn how to build and apply several useful NLP tools in this section, namely, character-level language models (using the Markov principle), and genetic algorithms.

The second project, where we begin to use more traditional "machine learning", is to build a spam detector. You likely get very little spam these days, compared to say, the early 2000s, because of systems like these.

Next we'll build a model for sentiment analysis in Python. This is something that allows us to assign a score to a block of text that tells us how positive or negative it is. People have used sentiment analysis on Twitter to predict the stock market.

We'll go over some practical tools and techniques like the NLTK (natural language toolkit) library and latent semantic analysis or LSA.

Finally, we end the course by building an article spinner. This is a very hard problem and even the most popular products out there these days don't get it right. These lectures are designed to just get you started and to give you ideas for how you might improve on them yourself. Once mastered, you can use it as an SEO, or search engine optimization tool. Internet marketers everywhere will love you if you can do this for them!

This course focuses on "how to build and understand", not just "how to use". Anyone can learn to use an API in 15 minutes after reading some documentation. It's not about "remembering facts", it's about "seeing for yourself" via experimentation. It will teach you how to visualize what's happening in the model internally. If you want more than just a superficial look at machine learning models, this course is for you.

Suggested Prerequisites:

  • Python coding: if/else, loops, lists, dicts, sets

  • Take my free Numpy prerequisites course (it's FREE, no excuses!) to learn about Numpy, Matplotlib, Pandas, and Scikit-Learn, as well as Machine Learning basics

  • Optional: If you want to understand the math parts, linear algebra and probability are helpful

TIPS (for getting through the course):

  • Watch it at 2x.

  • Take handwritten notes. This will drastically increase your ability to retain the information.

  • Ask lots of questions on the discussion board. The more the better!

  • Realize that most exercises will take you days or weeks to complete.

  • Write code yourself, don't just sit there and look at my code.


  • Check out the lecture "What order should I take your courses in?" (available in the Appendix of any of my courses, including the free Numpy course)

Who this course is for:
  • Students who are comfortable writing Python code, using loops, lists, dictionaries, etc.
  • Students who want to learn more about machine learning but don't want to do a lot of math
  • Professionals who are interested in applying machine learning and NLP to practical problems like spam detection, Internet marketing, and sentiment analysis
  • This course is NOT for those who find the tasks and methods listed in the curriculum too basic.
  • This course is NOT for those who don't already have a basic understanding of machine learning and Python coding (but you can learn these from my FREE Numpy course).
  • This course is NOT for those who don't know (given the section titles) what the purpose of each task is. E.g. if you don't know what "spam detection" might be useful for, you are too far behind to take this course.