Extracting features from text

In Chapter 11, Extracting Features from Text Variables, we will discuss various features that we can extract from pieces of text utilizing pandas and scikit-learn. We can also extract multiple features from text automatically by utilizing Featuretools.

Featuretools supports the creation of two basic features from text as part of its default functionality, which are the number of characters and the number of words in a piece of text. In addition, there is an accompanying Python library, Natural Language Processing (NLP) primitives, which contains a lot more functionality to create more advanced features for use with text. Among these functions, we find primitives for counting the number of stop words and punctuation and calculating the amount of whitespace and uppercase, as well as more complex functions for deriving the diversity score or the polarity score.

Note

For a complete list of the functions available, visit https://featuretools.alteryx...