sklearn库做线性回归

from numpy import *
import matplotlib.pyplot as plt

1.导入数据

# 1.导入数据
# 模型 y = wx + b
points = genfromtxt('linear_regress_lsm_data.csv', delimiter=',')
length = len(points)
print('point count %d'%length)
x = array(points[:, 0])
y = array(points[:, 1])
plt.scatter(x, y)
plt.show

point count 100





<function matplotlib.pyplot.show(close=None, block=None)>

2.损失函数

# 2.损失函数
def compute_cost(points, w, b):
    total_cost = 0
    length = len(points)
    for i in range(length):
        x = points[i, 0]
        y = points[i, 1]
        total_cost = (y - w * x - b) ** 2
    return total_cost / float (length)

3.拆分训练集和测试集

from sklearn.model_selection import train_test_split
new_x = x.reshape(-1, 1)
new_y = y.reshape(-1, 1)
x_train,x_test,y_train,y_test = train_test_split(new_x,new_y, test_size=0.2)

4. 训练

from sklearn.linear_model import LinearRegression

lr_mode = LinearRegression()

lr_mode.fit(x_train, y_train)
print("b: ", lr.intercept_)
print("w: ", lr.coef_)

b:  [7.99102098]
w:  [[1.32243102]]

5.预测

y_predict = lr_mode.predict(x_test)
print("predict shape:",y_predict.shape)
print("predict value: ",y_predict[:10])

predict shape: (20, 1)
predict value:  [[ 77.26304819]
 [ 60.95061612]
 [ 63.76912956]
 [ 61.38694704]
 [ 77.7424197 ]
 [ 87.923399  ]
 [ 73.92056411]
 [ 83.6204053 ]
 [ 75.28594104]
 [100.67536067]]

6.画拟合曲线

from sklearn.metrics import mean_squared_error
mse = mean_squared_error(y_test, y_predict)
print("均方误差: ", mse)

plt.scatter(x_test, y_test, color = 'hotpink')
plt.plot(x_test, y_predict, c = "r")

plt.scatter(x_train, y_train, color = '#88c999')
#y_predict_train = lr_mode.predict(x_train)
#plt.plot(x_train, y_predict_train, c= "g")
plt.show

均方误差:  104.5838657978367





<function matplotlib.pyplot.show(close=None, block=None)>