机器学习基础之《回归与聚类算法（6）—模型保存与加载》

一、背景

现在我们预测每次都要重新运行一遍模型。完整的流程应该是不断调整阈值重复计算。
当训练或者计算好一个模型之后，那么如果别人需要我们提供结果预测，就需要保存模型（主要是保存算法的参数）。

二、sklearn模型的保存和加载API

1、import joblib
保存：joblib.dump(rf, "test.pkl")
    rf：是预估器estimator
    test.pkl：是保存的名字
    将预估器序列化保存在本地    
加载：estimator = joblib.load("test.pkl")

2、代码

from sklearn.datasets import load_boston
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LinearRegression, SGDRegressor, Ridge
from sklearn.metrics import mean_squared_error
import joblib

def linear1():
  """
  正规方程的优化方法对波士顿房价进行预测
  """
  # 1、获取数据
  boston = load_boston()

  # 2、划分数据集
  x_train,x_test, y_train, y_test = train_test_split(boston.data, boston.target, random_state=10)

  # 3、标准化
  transfer = StandardScaler()
  x_train = transfer.fit_transform(x_train)
  x_test = transfer.transform(x_test)
  
  # 4、预估器
  estimator = LinearRegression()
  estimator.fit(x_train, y_train)

  # 5、得出模型
  print("正规方程-权重系数为：\n", estimator.coef_)
  print("正规方程-偏置为：\n", estimator.intercept_)

  # 6、模型评估
  y_predict = estimator.predict(x_test)
  print("预测房价：\n", y_predict)
  error = mean_squared_error(y_test, y_predict)
  print("正规方程-均方误差为：\n", error)
  return None

def linear2():
  """
  梯度下降的优化方法对波士顿房价进行预测
  """
  # 1、获取数据
  boston = load_boston()

  # 2、划分数据集
  x_train,x_test, y_train, y_test = train_test_split(boston.data, boston.target, random_state=10)

  # 3、标准化
  transfer = StandardScaler()
  x_train = transfer.fit_transform(x_train)
  x_test = transfer.transform(x_test)
  
  # 4、预估器
  estimator = SGDRegressor()
  estimator.fit(x_train, y_train)

  # 5、得出模型
  print("梯度下降-权重系数为：\n", estimator.coef_)
  print("梯度下降-偏置为：\n", estimator.intercept_)

  # 6、模型评估
  y_predict = estimator.predict(x_test)
  print("预测房价：\n", y_predict)
  error = mean_squared_error(y_test, y_predict)
  print("梯度下降-均方误差为：\n", error)
  return None

def linear3():
  """
  岭回归对波士顿房价进行预测
  """
  # 1、获取数据
  boston = load_boston()

  # 2、划分数据集
  x_train,x_test, y_train, y_test = train_test_split(boston.data, boston.target, random_state=10)

  # 3、标准化
  transfer = StandardScaler()
  x_train = transfer.fit_transform(x_train)
  x_test = transfer.transform(x_test)
  
  # 4、预估器
  estimator = Ridge()
  estimator.fit(x_train, y_train)

  # 保存模型
  joblib.dump(estimator, "my_ridge.pkl")

  # 5、得出模型
  print("岭回归-权重系数为：\n", estimator.coef_)
  print("岭回归-偏置为：\n", estimator.intercept_)

  # 6、模型评估
  y_predict = estimator.predict(x_test)
  print("预测房价：\n", y_predict)
  error = mean_squared_error(y_test, y_predict)
  print("岭回归-均方误差为：\n", error)
  return None

def linear4():
  """
  岭回归对波士顿房价进行预测
  """
  # 1、获取数据
  boston = load_boston()

  # 2、划分数据集
  x_train,x_test, y_train, y_test = train_test_split(boston.data, boston.target, random_state=10)

  # 3、标准化
  transfer = StandardScaler()
  x_train = transfer.fit_transform(x_train)
  x_test = transfer.transform(x_test)

  # 加载模型
  estimator = joblib.load("my_ridge.pkl")

  # 5、得出模型
  print("岭回归-权重系数为：\n", estimator.coef_)
  print("岭回归-偏置为：\n", estimator.intercept_)

  # 6、模型评估
  y_predict = estimator.predict(x_test)
  print("预测房价：\n", y_predict)
  error = mean_squared_error(y_test, y_predict)
  print("岭回归-均方误差为：\n", error)
  return None

if __name__ == "__main__":
  # 代码1：正规方程的优化方法对波士顿房价进行预测
  linear1()
  # 代码2：梯度下降的优化方法对波士顿房价进行预测
  linear2()
  # 代码3：岭回归对波士顿房价进行预测
  linear3()
  # 代码4：加载模型
  linear4()