1、机器学习笔记之二元一次方程

直接上代码

import numpy as np
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error
from sklearn.model_selection import train_test_split

def test1():
    # ax=y 求a
    x = np.arange(1, 10)
    x = x.reshape((9, 1))
    y = np.arange(10, 100, 10)
    y = y.reshape((9, 1))
    # 数据划分
    x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=22)
    estimator = LinearRegression()  # 线性回归(正规方程)
    estimator.fit(x_train, y_train)
    # 模型保存
    # joblib.dump(estimator, './test.pkl')
    # 模型加载
    # estimator = joblib.load('./test.pkl')
    y_predict = estimator.predict(x_test)
    print(y_predict[:3])
    print(y_test[:3])
    print("系数:", estimator.coef_)
    print('偏置:', estimator.intercept_)
    error = mean_squared_error(y_test, y_predict)
    print("误差为：", error)

# y=2x+7
def test2():
    x = [2,3,4,5,6]
    x = np.asarray(x)
    x = x.reshape(5, 1)
    y = [11,13,15,17,19]
    y = np.asarray(y)
    y = y.reshape(5, 1)
    z = [7,8,9]
    z = np.asarray(z)
    z = z.reshape(1, 1)
   # x_train, x_test, y_train, y_test = train_test_split(x, y, random_state=20)
    estimator = LinearRegression()  # 线性回归(正规方程)
    estimator.fit(x, y)
    # estimator.fit(x_train, y_train)
    y_predict = estimator.predict(z)
    print(y_predict[:3])
    print(y_predict.reshape(1, 3))
    # print("系数:", estimator.coef_)
    # print('偏置:', estimator.intercept_)
    # error = mean_squared_error(y_test, y_predict)
    # print("误差为：", error)

if __name__ == '__main__':
    test1()
    test2()

预测7,8,9的结果为

[[21. 23. 25.]]