机器学习实战：001 线形回归案例

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

# Load the diabetes dataset
diabetes = datasets.load_diabetes()
# Use only one feature
diabetes_X = diabetes.data[:, np.newaxis, 2]
# Split data into training/testing sets
diabetes_X_train = diabetes_X[:-20]
diabetes_X_test = diabetes_X[-20:]
diabetes_y_train = diabetes.target[:-20]
diabetes_y_test = diabetes.target[-20:]
# Creat line regression object
reg = linear_model.LinearRegression()
# Train the model using the training sets
reg.fit(diabetes_X_train, diabetes_y_train)
# Make the predictions use the testing set
diabetes_y_pred = reg.predict(diabetes_X_test)
# The coefficients
print('coefficients: \n', reg.coef_)
# The mean squared error
mse = mean_squared_error(diabetes_y_test, diabetes_y_pred)
print('MSE:%.2f' % mse)
# Explained variance score: 1 is perfect prediction
score = r2_score(diabetes_y_test, diabetes_y_pred)
print('score:%.2f' % score)
# 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.show()