使用sklearn实现类别编码和onehot编码

from numpy import array
from numpy import argmax
from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import OneHotEncoder
values = array(['cold', 'cold', 'warm', 'cold', 'hot', 'hot', 'warm', 'cold', 'warm', 'hot'])

进行类别编码（哑变量）

label_encoder = LabelEncoder()
integer_encoded = label_encoder.fit_transform(values)
print(integer_encoded)

#数据处理
all_data['test'] = pd.qcut(all_data['gaphum'],4)
label_encoder = LabelEncoder()
all_data['test_test'] =label_encoder.fit_transform(all_data['test'])

进行Onehot编码

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)