It's not immediately clear why this is better (other than the problem I mentioned above), and that's because there's no clear reason. Like many things in machine learning, we won't use it in every situation; it's not better than label encoding. It simply fixes a problem you'll encounter with label encoding when working with categorical data.
One hot encoding in the Code (Get it? It's a play on words)
It's always helpful to see how this is done in code, so let's do an example. Normally, I'm a firm believer that we should do something without libraries to learn it, but just for this tedious pre-process, we iraq email list don't really need it. Libraries can make this so simple. We're going to use numpy, sklearn, and pandas, as you'll find yourself using those 3 libraries in a lot of your projects.
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
import numpy as np
import pandas as pd
Now that we have the tools, let's get started. We'll be working with a made-up dataset. Feed the dataset with the pandas .read_csv feature:Meg Summers, 31, of Alabama, had frequent ovarian cysts and endometriosis since she was a teenager.
When she had her first ovary removed, she was told she would never conceive without IVF, but she soon gave birth to a baby girl.
After removing her second ovary, it grew back and formed another cyst.
Meg was told she had Ovarian Remnant Syndrome, a very rare disorder
An Alabama woman was certain that removing her ovaries would mean the end of her problems with ovarian cysts — that is, until one of those ovaries grew back.
