1.3 标记编码

# 1.3 标记编码-标记编码就是要把单词标记转换成数值形式
# 方法-循环去标记
from sklearn import preprocessing
label_encoder = preprocessing.LabelEncoder()
input_classes = ['audi', 'ford', 'audi', 'toyota', 'ford', 'bmw']
label_encoder.fit(input_classes)
print("\nClass mapping:")
# 按照排序进行编码
for i, item in enumerate(label_encoder.classes_):
    print(item, '-->', i)

#~~~~~~~~~~~~~ 进行编码 label_encoder.transform
labels = ['toyota', 'ford', 'audi']
encoded_labels = label_encoder.transform(labels)
print("\nLabels =", labels)
print("Encoded labels =", list(encoded_labels))
#~~~~~~反向检查 label_encoder.inverse_transform
encoded_labels = [2, 1, 0, 3, 1 ]
decoded_labels = label_encoder.inverse_transform(encoded_labels)
print("\nEncoded labels =", encoded_labels)
print("Decoded labels =", list(decoded_labels))

运行结果

Class mapping:
audi --> 0
bmw --> 1
ford --> 2
toyota --> 3

Labels = ['toyota', 'ford', 'audi']
Encoded labels = [3, 2, 0]

Encoded labels = [2, 1, 0, 3, 1]
Decoded labels = ['ford', 'bmw', 'audi', 'toyota', 'bmw']