One-Hot Encoding with Python

In [1]:

from sklearn.preprocessing import OneHotEncoder
import numpy as np
import pandas as pd

In [16]:

cat_list = ['cat1', 'cat2', 'cat3']
value = np.random.randint(1,100,size = 20)
cat_value = np.random.choice(cat_list, size = 20)

In [18]:

df = pd.DataFrame({'value':value,'cat_value':cat_value})
print(df.head())

   value cat_value
0     74      cat1
1     47      cat3
2     73      cat2
3     79      cat1
4     57      cat1

In [27]:

categorical_columns = df.select_dtypes(include=['object']).columns.tolist()
encoder = OneHotEncoder(sparse_output=False)
x_encoded = encoder.fit_transform(df[categorical_columns])

x_encoded_df = pd.DataFrame(x_encoded, columns= encoder.get_feature_names_out(categorical_columns))
df_encoded = pd.concat([df,x_encoded_df],axis = 1)
df_encoded = df_encoded.drop(categorical_columns,axis = 1)

print(df_encoded.head())

   value  cat_value_cat1  cat_value_cat2  cat_value_cat3  cat_value_cat4
0     74             1.0             0.0             0.0             0.0
1     47             0.0             0.0             1.0             0.0
2     73             0.0             1.0             0.0             0.0
3     79             1.0             0.0             0.0             0.0
4     57             1.0             0.0             0.0             0.0