Data Science: Natural Language Processing (NLP) in Python
4.6 (4,919 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.
21,418 students enrolled

Data Science: Natural Language Processing (NLP) in Python

Practical Applications of NLP: spam detection, sentiment analysis, article spinners, and latent semantic analysis.
4.6 (4,919 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.
21,418 students enrolled
Last updated 10/2018
English
English [Auto-generated], Indonesian [Auto-generated], 5 more
  • Polish [Auto-generated]
  • Portuguese [Auto-generated]
  • Romanian [Auto-generated]
  • Spanish [Auto-generated]
  • Thai [Auto-generated]
Current price: $11.99 Original price: $119.99 Discount: 90% off
30-Day Money-Back Guarantee
This course includes
  • 8 hours on-demand video
  • Full lifetime access
  • Access on mobile and TV
  • Certificate of Completion
Training 5 or more people?

Get your team access to Udemy's top 3,000+ courses anytime, anywhere.

Try Udemy for Business
What you'll learn
  • 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
Requirements
  • Install Python, it's free!
  • You should be at least somewhat comfortable writing Python code
  • 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
Description

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 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.



HARD PREREQUISITES / KNOWLEDGE YOU ARE ASSUMED TO HAVE:

  • 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.


WHAT ORDER SHOULD I TAKE YOUR COURSES IN?:

  • 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.
Course content
Expand all 62 lectures 07:58:05
+ Natural Language Processing - What is it used for?
4 lectures 16:05

NLP is very practical, so it's worth listing out what it is used for. Here we give brief overviews of things like spam detection, POS tagging, NER, sentiment analysis, machine translation, summarization, the Turing test, and more.

NLP Applications
06:40

In this lecture some examples of ambiguity of language are given, to make it clear why NLP is not a straightforward problem.

Why is NLP hard?
03:59
The Central Message of this Course
02:22
+ Course Preparation
3 lectures 08:40
How to Succeed in this Course
03:13
Where to get the code and data
02:42
Do you need a review of machine learning?
02:45
+ Build your own spam detector
10 lectures 01:02:52
Build your own spam detector - description of data
02:08
Build your own spam detector using Naive Bayes and AdaBoost - the code
06:16
Key Takeaway from Spam Detection Exercise
05:56
Naive Bayes Concepts
09:56
AdaBoost Concepts
05:11

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
01:30
Spam Detection FAQ (Remedial #1)
08:45
What is a Vector? (Remedial #2)
06:04
SMS Spam Example
06:23
SMS Spam in Code
10:43
+ 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
03:12
Preprocessing: Tokenization
04:48
Preprocessing: Tokens to Vectors
06:20

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

Sentiment Analysis in Python using Logistic Regression
19:48
Sentiment Analysis Extension
06:01
How to Improve Sentiment Analysis & FAQ
12:19
+ 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
02:00

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

NLTK Exploration: Stemming and Lemmatization
02:06

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

NLTK Exploration: Named Entity Recognition
03:13
Want more NLTK?
01:59
+ 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?
02:30
SVD - The underlying math behind LSA
15:49
Latent Semantic Analysis in Python
10:08
What is Latent Semantic Analysis Used For?
09:40
Extending LSA
06:16
+ 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
02:43
More about Language Models
09:53

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

Trigram Model
02:11
Precode Exercises
05:05
Writing an article spinner in Python
11:33
Article Spinner Extension Exercises
05:42
+ 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
02:45
+ Machine Learning Basics Review
11 lectures 01:33:58
(Review) Machine Learning: Section Introduction
07:47
(Review) What is Classification?
12:22
(Review) Classification in Code
14:38
(Review) What is Regression?
12:13
(Review) Regression in Code
08:29
(Review) What is a Feature Vector?
06:48
(Review) Machine Learning is Nothing but Geometry
04:50
(Review) All Data is the Same
05:23
(Review) Comparing Different Machine Learning Models
09:46
(Review) Machine Learning and Deep Learning: Future Topics
05:55
(Review) Section Summary
05:47
+ Appendix
11 lectures 02:22:57
What is the Appendix?
02:48
Windows-Focused Environment Setup 2018
20:20
How to install Numpy, Scipy, Matplotlib, Pandas, IPython, Theano, and TensorFlow
17:32
How to Code by Yourself (part 1)
15:54
How to Code by Yourself (part 2)
09:23
How to Succeed in this Course (Long Version)
10:24
Is this for Beginners or Experts? Academic or Practical? Fast or slow-paced?
22:04
Proof that using Jupyter Notebook is the same as not using it
12:29
Python 2 vs Python 3
04:38
What order should I take your courses in? (part 1)
11:18
What order should I take your courses in? (part 2)
16:07