sklearn线性回归算法实现

官方文档参考

导入库

import matplotlib.pyplot as plt
import numpy as np
from sklearn import datasets,linear_model
from sklearn.metrics import mean_squared_error,r2_score

加载数据

diabetes=datasets.load_diabetes()

## 查看数据集
>>>diabetes['data']
array([[ 0.03807591,  0.05068012,  0.06169621, ..., -0.00259226,
         0.01990842, -0.01764613],
       [-0.00188202, -0.04464164, -0.05147406, ..., -0.03949338,
        -0.06832974, -0.09220405],
       [ 0.08529891,  0.05068012,  0.04445121, ..., -0.00259226,
         0.00286377, -0.02593034],
       ...,
       [ 0.04170844,  0.05068012, -0.01590626, ..., -0.01107952,
        -0.04687948,  0.01549073],
       [-0.04547248, -0.04464164,  0.03906215, ...,  0.02655962,
         0.04452837, -0.02593034],
       [-0.04547248, -0.04464164, -0.0730303 , ..., -0.03949338,
        -0.00421986,  0.00306441]]
>>>diabetes['target']
array([151.,  75., 141., 206., 135.,  97., 138.,  63., 110., 310., 101.,
        69., 179., 185., 118., 171., 166., 144.,  97., 168.,  68.,  49.,
        ......,
       220.,  57.])

划分数据集

np.newaxis用法参考

diabetes_x=diabetes.data[:,np.newaxis,2]
diabetes_x_train=diabetes_x[:-20]
diabetes_x_test=diabetes_x[-20:]
diabetes_y_train=diabetes.target[:-20]
diabetes_y_test=diabetes.target[-20:]

模型的训练

reg=linear_model.LinearRegression()
reg.fit(diabetes_x_train,diabetes_y_train)
diabetes_y_pred=reg.predict(diabetes_x_test)
reg.score(diabetes_x_test,diabetes_y_test)
plt.scatter(diabetes_x_test,diabetes_y_test,color='black')
plt.plot(diabetes_x_test,diabetes_y_pred,color='blue')

模型的结果

>>>reg.score(diabetes_x_test,diabetes_y_test)
0.4725754479822712
>>>r2_score(diabetes_y_test,diabetes_y_pred)
0.4725754479822712
>>>plt.scatter(diabetes_x_test,diabetes_y_test,color='black')
>>>plt.plot(diabetes_x_test,diabetes_y_pred,color='blue')