How to use One hot Encoder in my code, without using categorical_features?

Question

Car	Model	Mileage	Sell Price($)	Age(yrs)
0	BMW X5	69000	18000	6
1	BMW X5	35000	34000	3
2	BMW X5	57000	26100	5
3	BMW X5	22500	40000	2
4	BMW X5	46000	31500	4
5	Audi A5	59000	29400	5
6	Audi A5	52000	32000	5
7	Audi A5	72000	19300	6
8	Audi A5	91000	12000	8
9	Mercedez Benz C class	67000	22000	6
10	Mercedez Benz C class	83000	20000	7
11	Mercedez Benz C class	79000	21000	7
12	Mercedez Benz C class	59000	33000	5

Above is my data frame and I want to Encode "Car Model" using one hot encoder.

Does this answer your question? [How can I one hot encode in Python?](https://stackoverflow.com/questions/37292872/how-can-i-one-hot-encode-in-python) — yudhiesh, Jan 31 '21 at 06:27
@yudhiesh I tried locking up few examples like these but could not fit the same in may code. I am beginner and hence have lots of confusion. — Diksha Nasa, Feb 02 '21 at 04:07
Looking at your question again, what do you mean by not using `categorial_features`? — yudhiesh, Feb 02 '21 at 05:09
@yudhiesh categorical_features is an attribute used to declare which column to encode for the one hot encoder, while watching tutorials I found a lot of people using it but it throws an error now as it is currently removed from the latest python . — Diksha Nasa, Feb 02 '21 at 05:32

yudhiesh · Answer 1 · 2021-02-02T07:06:10.123

0

You can one-hot encode the categorical variables like so.

one_hot_data = pd.get_dummies(df.Model, prefix='Model')
df = pd.concat([df, one_hot_data], axis=1)

Edit:

import pandas as pd
from sklearn.preprocessing import LabelBinarizer

jobs_encoder = LabelBinarizer()
jobs_encoder.fit(df['Model'])
transformed = jobs_encoder.transform(df['Model'])
ohe_df = pd.DataFrame(transformed)
df = pd.concat([df, ohe_df], axis=1).drop(['Model'], axis=1)

edited Feb 02 '21 at 07:06

answered Feb 02 '21 at 05:39

yudhiesh

6,383
3
16
49

Thank you so much for adding this answer but I have learned to use dummy variables and was also able to incorporate but since I am a beginner I wanted to learn about OneHotEncoder and incorporate it . – Diksha Nasa Feb 02 '21 at 07:04
@DikshaNasa try the updated answer using `LabelBinarizer()` – yudhiesh Feb 02 '21 at 07:06
@DikshaNasa please do accept and upvote my answer. – yudhiesh Feb 05 '21 at 07:22

score 0 · Answer 2 · answered Feb 05 '21 at 06:34

I solved it by using the following code:

from sklearn.preprocessing import LabelEncoder
le=LabelEncoder()
dfle['Car Model']=le.fit_transform(dfle['Car Model'])
ohe=OneHotEncoder()
dfle['Car Model']=pd.DataFrame(ohe.fit_transform(df[['Car Model']]).toarray())
dfle.head()
X=dfle[['Car Model','Mileage','Age(yrs)']].values

How to use One hot Encoder in my code, without using categorical_features?

2 Answers2