机器学习入门 ————》实现线性回归

一元线性回归

import numpy as np
import matplotlib.pyplot as plt
# 载入数据
data = np.genfromtxt("data.csv", delimiter=",")#以逗号分隔符，提取出来
x_data = data[:,0]#第0列，所有行
y_data = data[:,1]#第1列，所有行
plt.scatter(x_data,y_data)#画散点图
plt.show()

数据 

# 学习率learning rate
lr = 0.0001
# 截距
b = 0 
# 斜率
k = 0 
# 最大迭代次数
epochs = 50

# 最小二乘法，损失函数
def compute_error(b, k, x_data, y_data):
    totalError = 0
    for i in range(0, len(x_data)):
        totalError += (y_data[i] - (k * x_data[i] + b)) ** 2   #对照公式
    return totalError / float(len(x_data)) / 2.0    #m因变量个数

def gradient_descent_runner(x_data, y_data, b, k, lr, epochs):   #梯度下降法 对照公式
    # 计算总数据量  
    m = float(len(x_data))
    # 循环epochs次
    for i in range(epochs):
        b_grad = 0
        k_grad = 0
        # 计算梯度的总和再求平均
        for j in range(0, len(x_data)):
            b_grad += (1/m) * (((k * x_data[j]) + b) - y_data[j])
            k_grad += (1/m) * x_data[j] * (((k * x_data[j]) + b) - y_data[j])
        # 更新b和k
        b = b - (lr * b_grad)
        k = k - (lr * k_grad)
        # 每迭代5次，输出一次图像
        if i % 5==0:
            print("epochs:",i)
            plt.plot(x_data, y_data, 'b.')
            plt.plot(x_data, k*x_data + b, 'r')
            plt.show()
    return b, k

print("Starting b = {0}, k = {1}, error = {2}".format(b, k, compute_error(b, k, x_data, y_data)))
print("Running...")
b, k = gradient_descent_runner(x_data, y_data, b, k, lr, epochs)
print("After {0} iterations b = {1}, k = {2}, error = {3}".format(epochs, b, k, compute_error(b, k, x_data, y_data)))

 

 

skleran实现

from sklearn.linear_model import LinearRegression
import numpy as np
import matplotlib.pyplot as plt
# 载入数据
data = np.genfromtxt("data.csv", delimiter=",")
x_data = data[:,0]
y_data = data[:,1]
plt.scatter(x_data,y_data)
plt.show()
print(x_data.shape)

x_data = data[:,0,np.newaxis]  #newaxis不理解，可以看前面的SVM函数理解
y_data = data[:,1,np.newaxis]
# 创建并拟合模型
model = LinearRegression()
model.fit(x_data, y_data)
# 画图
plt.plot(x_data, y_data, 'b.')
plt.plot(x_data, model.predict(x_data), 'r')
plt.show()

 

sklearn，多元线性回归

import numpy as np
from numpy import genfromtxt
from sklearn import linear_model
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，因变量x两个，自变量y一个
x_data = data[:,:-1]
y_data = data[:,-1]
print(x_data)
print(y_data)

# 创建模型，和一元的一样
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]
# 生成网格矩阵
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()