This repository accompanies the book Getting Started with Natural Language Processing, which you can get from Manning. Use the coupon code "slkochmar" to get a 42% discount there. It is also available on Amazon.

Here you will also find an NLP course that uses this book.

• Chapter 1 – Introduction
• Chapter 2 – Your first NLP example
• Chapter 3 – Introduction to Information Search
• Chapter 4 – Information Extraction
• Chapters 5 & 6 – Author Attribution and User Profiling
• Chapters 7 & 8 – Sentiment Analysis
• Chapter 9 – Topic Analysis
• Chapter 10 – Topic Modeling
• Chapter 11 – Named Entity Recognition

To run the notebooks on your machine, check if Python 3 is installed (all code was written and tested with Python 3.7). In addition, you will need the following libraries (notebooks tested with the versions indicated in the brackets):

• NLTK (v 3.5): check installation instructions for the toolkit at https://www.nltk.org/install.html and the accompanying data at https://www.nltk.org/data.html
• SpaCy (v 3.1.3): check installation instructions at https://spacy.io/usage. You will also need to install models (e.g., en_core_web_sm, en_core_web_md, and en_core_web_lg) using the instructions on the website.
• Gensim (v 3.8.0): check installation instructions at https://radimrehurek.com/gensim/
• Matplotlib (v 3.1.3): check installation instructions at https://matplotlib.org/users/installing.html
• Scikit-learn (v 0.22.1): check installation instructions at http://scikit-learn.org/stable/install.html
• NumPy (v 1.18.1): check installation instructions at https://www.scipy.org/install.html
• Pandas (v 1.0.1) check installation instructions at https://pandas.pydata.org/pandas-docs/stable/getting_started/install.html

Alternatively, a number of these libraries can be installed in one go through Anaconda distribution.

For more information on Jupyter notebooks, check https://jupyter.org.