机器学习与深度学习：模型的保存和加载

我们再建模完毕以后，并不需要每次都把数据重新执行，而是将数据模型给保留下来

from sklearn.externals import joblib
#保存：
joblib.dump(estimator, 'test.m')
#加载：
estimator = joblib.load('test.m')

详细案例：

import numpy as np
import pandas as pd
import pickle as pk
from sklearn.externals import joblib

cancer=pd.read_csv('cancer.csv',sep='\t')

fea = cancer.select_dtypes(include=['float64'])
lab = cancer.select_dtypes(include=['object'])

#加载模型
with open('best_knn.m','rb') as fp:
    best_knn = pk.load(fp)
    
with open('std_model.m','rb') as fp:
    STD = pk.load(fp)

STD=joblib.load(filename='std_model.m')

best_knn=joblib.load(filename='best_knn.m')

fea_std = STD.transform(fea)

best_knn.score(fea_std,lab)