Python Feature Engineering Cookbook

How to do it...

Let's begin with the recipe by importing the required libraries and dataset:

1. Load pandas, the sentence tokenizer from NLTK, and the dataset from scikit-learn:

import pandas as pdfrom nltk.tokenize import sent_tokenizefrom sklearn.datasets import fetch_20newsgroups

2. To understand the functionality of the sentence tokenizer from NLTK, let's create a variable that contains a string with multiple sentences:

text = """The alarm rang at 7 in the morning as it usually did on Tuesdays. She rolled over,stretched her arm, and stumbled to the button till she finally managed to switch it off.Reluctantly, she got up and went for a shower. The water was cold as the day before the engineersdid not manage to get the boiler working. Good ...