sklearn-least squares(data set of diabetes)

Posted 2020-10-23 shiyiandchuixue

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

# Load the dataset 糖尿病 看源码呗
diabetes = datasets.load_diabetes()

# use only one featrue np.newaxis：(:,) 变成（:,1)的矩阵，增加维数
diabetes_x = diabetes.data[:,np.newaxis,2]

# splite the data into training/testing sets
diabetes_x_train = diabetes_x[:-20]
diabetes_x_test =  diabetes_x[-20:]
# splite the targets into training/testing sets
diabetes_y_train = diabetes.target[:-20]
diabetes_y_test = diabetes.target[-20:]

# create linear regression object
regr = linear_model.LinearRegression()

# training the model
regr.fit(diabetes_x_train,diabetes_y_train)

# make predictions using the testiong set
diabetes_y_pred = regr.predict(diabetes_x_test)

# the cofficients
print(regr.coef_)
print(diabetes_y_pred)
print("mean squared error:%.2f"%mean_absolute_error(diabetes_x_test,diabetes_y_pred))
print("variance scor:%.2f"%r2_score(diabetes_y_test,diabetes_y_pred))
# Plot outputs
plt.scatter(diabetes_x_test, diabetes_y_test,  color=‘black‘)
plt.plot(diabetes_x_test, diabetes_y_pred, color=‘blue‘, linewidth=3)
plt.xticks(())
plt.yticks(())
plt.show()

remark:
　　>>>X[:, 1][:, np.newaxis] #索引数组的一列 如果没有[:,np.newaxis]索引的结果是一行，X[:, 1][:, np.newaxis]可以简化为：X[:, np.newaxis, 1]