---
type: learning
area: learning
status: learning
date: 2026-05-03
created: 2026-05-03
updated: 1980-01-01
tags:
  - learning
---
Columns that contain intergers who describe a category should always be type 'category'

When working with new data, you should always check the data types of your columns using the `.dtypes` attribute or the `.info()`
#### Handle Out of range Data
- Dropping Data (if affected number of date is small)
- Setting custom min and max (like if we have some rating above 5 we can set them to 5)
- Treat as missing and impute
- Setting custom value depending on business assumptions
#### Handle duplicates
- Dropping duplicates
- Combining duplicates using statical measure like (max, avg, min) using agg() or groupby()
#### Dealing with inconsistent data
- Using joins to filter data that is not in categorical data to filter data