1 sklearn模型的保存和加载API

  • from sklearn.externals import joblib

    • 保存：joblib.dump(estimator, ‘test.pkl’)

    • 加载：estimator = joblib.load(‘test.pkl’)

      2 线性回归的模型保存加载案例

      1. def load_dump_demo():
      2. """
      3. 线性回归:岭回归
      4. :return:
      5. """
      6. # 1.获取数据
      7. data = load_boston()
      9. # 2.数据集划分
      10. x_train, x_test, y_train, y_test = train_test_split(data.data, data.target, random_state=22)
      12. # 3.特征工程-标准化
      13. transfer = StandardScaler()
      14. x_train = transfer.fit_transform(x_train)
      15. x_test = transfer.fit_transform(x_test)
      17. # 4.机器学习-线性回归(岭回归)
      18. # # 4.1 模型训练
      19. # estimator = Ridge(alpha=1)
      20. # estimator.fit(x_train, y_train)
      21. #
      22. # # 4.2 模型保存
      23. # joblib.dump(estimator, "./data/test.pkl")
      25. # 4.3 模型加载
      26. estimator = joblib.load("./data/test.pkl")
      28. # 5.模型评估
      29. # 5.1 获取系数等值
      30. y_predict = estimator.predict(x_test)
      31. print("预测值为:\n", y_predict)
      32. print("模型中的系数为:\n", estimator.coef_)
      33. print("模型中的偏置为:\n", estimator.intercept_)
      35. # 5.2 评价
      36. # 均方误差
      37. error = mean_squared_error(y_test, y_predict)
      38. print("误差为:\n", error)