多元线性回归

多元线性回归

单特征——一元线性回归

多特征——多元线性回归

多元线性回归的公式

一元和多元的比较

程序实例：
数据

import numpy as np
from numpy import genfromtxt
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D

#读入数据
data = genfromtxt(r"Delivery.csv",delimiter=',')
print(data)

#切分数据
x_data = data[:,:-1]#取第一个列到倒数第二列
y_data = data[:,-1]#取倒数第一列
print(x_data)
print(y_data)

#学习率learning rate α
lr=0.0001

theta0=0
theta1=0
theta2=0

#最大迭代次数
epochs=1000

#最小二乘法，代价函数
def compute_error(theta0,theta1,theta2,x_data,y_data):
    totalError = 0
    for i in range(0,len(x_data)):
        totalError+=(y_data[i]-(theta0+theta1*x_data[i,0]+theta2*x_data[i,1]))**@
        return totalError/float(len(x_data))/2

def gradient_descent_runner(x_data,y_data,theta0,theta1,theta2,lr,epochs) :
    #计算总数据量
    m=float(len(x_data))
    for i in range(epochs):
        theta0_grad=0
        theta1_grad = 0
        theta2_grad = 0
        for j in range(0,len(x_data)):
            theta0_grad += -(1/m)*(y_data[j]-(theta0+theta1*x_data[j,0]+theta2*x_data[j,1]))
            theta1_grad += -(1/m)*(x_data[j,0])*(y_data[j]-(theta0+theta1*x_data[j,0]+theta2*x_data[j,1]))
            theta2_grad += -(1/m)*(x_data[j,1])*(y_data[j]-(theta0+theta1*x_data[j,0]+theta2*x_data[j,1]))
        #更新k和b
        theta0=theta0-(lr*theta0_grad)
        theta1 = theta1 - (lr * theta1_grad)
        theta2 = theta2 - (lr * theta2_grad)
    return theta0,theta1,theta2
print("Starting theta0 = {0},theta1 = {1},theta2 = {2},error={3}".format(theta0,theta1,theta2,compute_error(theta0,theta1,theta2,x_data,y_data)))
print("Running...")
theta0,theta1,theta2=gradient_descent_runner(x_data,y_data,theta0,theta1,theta2,lr,epochs)
print("After {0} iterations theta0 = {1},theta1 = {2},theta2 = {3},error={4}".format(epochs,theta0,theta1,theta2,compute_error(theta0,theta1,theta2,x_data,y_data)))

ax=plt.figure().add_subplot(111,projection='3d')
ax.scatter(x_data[:,0],x_data[:,1],y_data,c='r',marker='o',s=100)#点为红色三角形
x0=x_data[:,0]
x1=x_data[:,1]
#生成网络矩阵
x0,x1=np.meshgrid(x0,x1)
z=theta0+x0*theta1+x1*theta2
#画3D图
ax.plot_surface(x0,x1,z)
#设置坐标轴
ax.set_xlabel('Miles')
ax.set_ylabel('Num of Deliveries')
ax.set_zlabel('Time')

#显示图像
plt.show()

meshgrid函数的作用

运行结果

使用库来建立模型

import numpy as np
from numpy import genfromtxt
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
from sklearn import linear_model

#读入数据
data = genfromtxt(r"Delivery.csv",delimiter=',')
print(data)

#切分数据
x_data = data[:,:-1]#取第一个列到倒数第二列
y_data = data[:,-1]#取倒数第一列
print(x_data)
print(y_data)

#创建模型，就把，模型已经训练好了
model = linear_model.LinearRegression()
model.fit(x_data,y_data)
#系数
print("coefficients:",model.coef)
#截距
print("intercept:",model.intercept_)
#测试
x_test=[[102,4]]
predict = model.predict(x_test)
print("predict:",predict)

ax=plt.figure().add_subplot(111,projection='3d')
ax.scatter(x_data[:,0],x_data[:,1],y_data,c='r',marker='o',s=100)#点为红色三角形
x0=x_data[:,0]
x1=x_data[:,1]
#生成网络矩阵
x0,x1=np.meshgrid(x0,x1)
z=model.intercept_+x0*model.coef_[0]+x1*model.coef_[1]
#画3D图
ax.plot_surface(x0,x1,z)
#设置坐标轴
ax.set_xlabel('Miles')
ax.set_ylabel('Num of Deliveries')
ax.set_zlabel('Time')

#显示图像
plt.show()