one_hot_encoding_using_sklearn.py

from numpy import array
from numpy import argmax
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import OneHotEncoder
# define example
# data = ['cold', 'cold', 'warm', 'cold', 'hot', 'hot', 'warm', 'cold', 'warm', 'hot']


doc1 = "Can I eat the Pizza".lower()
doc2 = "You can eat the Pizza".lower()
doc1 = doc1.split()
doc2 = doc2.split()
doc1_array = array(doc1)
doc2_array = array(doc2)
doc3 = doc1+doc2
# doc3 = set(doc3)
data = list(doc3)


values = array(data)
print(values)
# integer encode
label_encoder = LabelEncoder()
integer_encoded = label_encoder.fit_transform(values)
print(integer_encoded)

# binary encode
onehot_encoder = OneHotEncoder(sparse=False)
integer_encoded = integer_encoded.reshape(len(integer_encoded), 1)
onehot_encoded = onehot_encoder.fit_transform(integer_encoded)
print(onehot_encoded)


# invert first example
inverted = label_encoder.inverse_transform([argmax(onehot_encoded[0, :])])
print(inverted)


"""
OUTPUT:
['can' 'i' 'eat' 'the' 'pizza' 'you' 'can' 'eat' 'the' 'pizza']
[0 2 1 4 3 5 0 1 4 3]
[[1. 0. 0. 0. 0. 0.]
 [0. 0. 1. 0. 0. 0.]
 [0. 1. 0. 0. 0. 0.]
 [0. 0. 0. 0. 1. 0.]
 [0. 0. 0. 1. 0. 0.]
 [0. 0. 0. 0. 0. 1.]
 [1. 0. 0. 0. 0. 0.]
 [0. 1. 0. 0. 0. 0.]
 [0. 0. 0. 0. 1. 0.]
 [0. 0. 0. 1. 0. 0.]]
['can']
"""