sklearn代码20 1-线性回归boston房价预测

import numpy as np

from sklearn.linear_model import LinearRegression

import matplotlib.pyplot as plt
%matplotlib inline

from sklearn import datasets

# 波士顿房价
boston = datasets.load_boston()

X = np.linspace(0,10,50).reshape(-1,1)
X

array([[  0.        ],
       [  0.20408163],
       [  0.40816327],
       [  0.6122449 ],
       [  0.81632653],
       [  1.02040816],
       [  1.2244898 ],
       [  1.42857143],
       [  1.63265306],
       [  1.83673469],
       [  2.04081633],
       [  2.24489796],
       [  2.44897959],
       [  2.65306122],
       [  2.85714286],
       [  3.06122449],
       [  3.26530612],
       [  3.46938776],
       [  3.67346939],
       [  3.87755102],
       [  4.08163265],
       [  4.28571429],
       [  4.48979592],
       [  4.69387755],
       [  4.89795918],
       [  5.10204082],
       [  5.30612245],
       [  5.51020408],
       [  5.71428571],
       [  5.91836735],
       [  6.12244898],
       [  6.32653061],
       [  6.53061224],
       [  6.73469388],
       [  6.93877551],
       [  7.14285714],
       [  7.34693878],
       [  7.55102041],
       [  7.75510204],
       [  7.95918367],
       [  8.16326531],
       [  8.36734694],
       [  8.57142857],
       [  8.7755102 ],
       [  8.97959184],
       [  9.18367347],
       [  9.3877551 ],
       [  9.59183673],
       [  9.79591837],
       [ 10.        ]])

y = np.random.randint(2,8,size = 1)*X
y

array([[  0.        ],
       [  0.40816327],
       [  0.81632653],
       [  1.2244898 ],
       [  1.63265306],
       [  2.04081633],
       [  2.44897959],
       [  2.85714286],
       [  3.26530612],
       [  3.67346939],
       [  4.08163265],
       [  4.48979592],
       [  4.89795918],
       [  5.30612245],
       [  5.71428571],
       [  6.12244898],
       [  6.53061224],
       [  6.93877551],
       [  7.34693878],
       [  7.75510204],
       [  8.16326531],
       [  8.57142857],
       [  8.97959184],
       [  9.3877551 ],
       [  9.79591837],
       [ 10.20408163],
       [ 10.6122449 ],
       [ 11.02040816],
       [ 11.42857143],
       [ 11.83673469],
       [ 12.24489796],
       [ 12.65306122],
       [ 13.06122449],
       [ 13.46938776],
       [ 13.87755102],
       [ 14.28571429],
       [ 14.69387755],
       [ 15.10204082],
       [ 15.51020408],
       [ 15.91836735],
       [ 16.32653061],
       [ 16.73469388],
       [ 17.14285714],
       [ 17.55102041],
       [ 17.95918367],
       [ 18.36734694],
       [ 18.7755102 ],
       [ 19.18367347],
       [ 19.59183673],
       [ 20.        ]])

y/X

C:\Users\LXQ\Anaconda3\lib\site-packages\ipykernel_launcher.py:1: RuntimeWarning: invalid value encountered in true_divide
  """Entry point for launching an IPython kernel.





array([[ nan],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.],
       [  2.]])

lr = LinearRegression()

lr.fit(X,y)
# coeficient  效率，斜率
# w ------> weight 权重
lr.coef_

array([[ 2.]])

$$\hat{w}=(X^{T}X{)}^{-1}{X}^{T}y$$

# 线性代数中的矩阵运算
np.linalg.inv(X.T.dot(X)).dot(X.T).dot(y)

array([[ 2.]])