# Product Classification API Part 2: Data Preparation

DevFeed: [Product Classification API Part 2: Data Preparation](<https://devfeed.tech/articles/product-classification-api-part-2-data-preparation-46522.md>)

Original publisher: [Read original article](<https://eugeneyan.com//writing/product-categorization-api-part-2-data-preparation/>)

Author: Eugene Yan

Published: 2016-12-11T00:00:00Z

Content type: tutorial

Language: en

Sources: [Eugene Yan](<https://devfeed.tech/sources/eugene-yan.md>)

Topics: [data](<https://devfeed.tech/topics/data.md>), [API](<https://devfeed.tech/topics/api.md>), [datasets](<https://devfeed.tech/topics/datasets.md>), [Code](<https://devfeed.tech/topics/code.md>), [ASCII](<https://devfeed.tech/topics/ascii.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [ascii](<https://devfeed.tech/tags/ascii.md>), [code](<https://devfeed.tech/tags/code.md>), [data](<https://devfeed.tech/tags/data.md>), [machinelearning](<https://devfeed.tech/tags/machinelearning.md>), [processing](<https://devfeed.tech/tags/processing.md>), [python](<https://devfeed.tech/tags/python.md>)

## AI overview

Part 2 of a series on building a product classification API, focused on preparing product titles and descriptions before model training. It covers identifying dirty or miscategorized data, measuring data purity, normalizing non-ASCII characters, lowercasing text, and tokenizing with regular expressions.

## Source excerpt

Cleaning up text and messing with ascii (urgh!)