Numbers and Natural Language Processing: Numerizer

Photo by Raphael Schaller on Unsplash

Numerizer is that Python library which will convert figures written in English in accordance with the International Number System. It can convert inputs composed of up to four periods which are one’s period, thousand’s period, million’s period and trillion’s period. Each period will be composed of three digits i.e. ones place, tens place and hundreds place. It is a widely used library that can be incredibly useful for both Natural Language Processing and Data Science. To get started using this package you can install it using the snippet in the cell below.

pip install numerizer

Once your install is complete you will need to import the numerize function into your project or notebook. This can be done using the following code.

from numerizer import numerize

After you have made sure to install and import Numerizer, you can begin to convert any written number you’d like to into an integer in the following fashion.

Output:
60040020406