一元线性线性回归
# 导入matplotlib库,主要用于可视化
import numpy as np
from matplotlib.font_manager import FontProperties
import matplotlib.pyplot as plt
%matplotlib inline
# 引入本地字体文件,否则中文会有乱码
# font_set = FontProperties(fname=r"./work/ simsun.ttc", size=12)
# 构造用于训练的数据集
x_train = [4, 8, 5, 10, 12]
y_train = [20, 50, 30, 70, 60]
# 画图函数
def draw(x_train, y_train):
plt.scatter(x_train, y_train)
# 定义函数求得斜率w和截距b
# 使用最小二乘法对斜率和截距求导并使得导数值等于0求解出斜率和截距
def fit(x_train, y_train):
size = len(x_train)
numerator = 0 # 初始化分子
denominator = 0 # 初始化分母
for i in range(size):
numerator += (x_train[i] - np.mean(x_train)) * \
(y_train[i] - np.mean(y_train))
denominator += (x_train[i] - np.mean(x_train)) ** 2
w = numerator / denominator
b = np.mean(y_train) - w * np.mean(x_train)
return w, b
# 根据斜率w和截距b,输入x计算输出值
def predict(x, w, b):
# 预测模型
y = w * x + b
return y
# 根据W,B画图
def fit_line(w, b):
# 测试集进行测试,并作图
# linspace 创建等差数列的函数 #numpy.limspace(start,stop,num,endpoint=True,retstep=False,dtype=None,axis=0#)
x = np.linspace(4, 15, 9)
y = w * x + b
plt.plot(x, y)
plt.show()
if __name__ == "__main__":
draw(x_train, y_train)
w, b = fit(x_train, y_train)
print(w, b) # 输出斜率和截距
fit_line(w, b) # 绘制预测函数图像
多元线性回归
# 多元线性回归的实现
# 导入模块
import numpy as np
import pandas as pd
# 构造数据,前三列表示自变量X,最后一列表示因变量Y
data = np.array([[3, 2, 9, 20],
[4, 10, 2, 72],
[3, 4, 9, 21],
[12, 3, 4, 20]])
print("data:", data, "\n")
X = data[:, :-1]
Y = data[:, -1]
X = np.mat(np.c_[np.ones(X.shape[0]), X]) # 为系数矩阵增加常数项系数
Y = np.mat(Y) # 数组转化为矩阵
print("X:", X, "\n")
print("Y:", Y, "\n")
# 根据最小二乘法的目标函数求导为0得到最优参数向量B的解析解公式如下,可以直接求取最优参数向量
B = np.linalg.inv(X.T * X) * (X.T) * (Y.T)
print("B:", B, "\n") # 输出系数,第一项为常数项,其他为回归系数
print("1,60,60,60预测结果:", np.mat([1, 60, 60, 60]) * B, "\n") # 预测结果
# 相关系数
Q_e = 0
Q_E = 0
Y_mean = np.mean(Y)
for i in range(Y.size):
Q_e += pow(np.array((Y.T)[i] - X[i] * B), 2)
Q_E += pow(np.array(X[i] * B) - Y_mean, 2)
R2 = Q_E / (Q_e + Q_E)
print("R2", R2)
**
回归库实现
# 导入sklearn下的LinearRegression 方法
from sklearn.linear_model import LinearRegression
import numpy as np
model = LinearRegression()
# 构造用于训练的数据集
x_train = np.array([[2, 4], [5, 8], [5, 9], [7, 10], [9, 12]])
y_train = np.array([20, 50, 30, 70, 60])
# 训练模型并输出模型系数和训练结果
model.fit(x_train, y_train)
# fit(x,y,sample_weight=None)x:训练集 y:目标值 sample_weight:每个样本的个数
# coef_ 系数w,intercept_截距
print(model.coef_) # 输出系数w
print(model.intercept_) # 输出截距b
print(model.score(x_train, y_train)) # 输出模型的评估分数R2