#
# µû¶óÇÏ¸ç ¹è¿ì´Â ÆÄÀ̽ã°ú µ¥ÀÌÅÍ°úÇÐ(»ý´ÉÃâÆÇ»ç 2020)
# 14.13 ¾Ë°í¸®ÁòÀÌ °¡Áö´Â ¿ÀÂ÷, 383ÂÊ
#
from sklearn import datasets
from sklearn import linear_model
import numpy as np
from sklearn.model_selection import train_test_split
import matplotlib.pyplot as plt
from sklearn.metrics import mean_squared_error
# ´ç´¢º´ µ¥ÀÌÅÍ ¼¼Æ®¸¦ sklearnÀÇ µ¥ÀÌÅÍÁýÇÕÀ¸·ÎºÎÅÍ ÀоîµéÀδÙ.
diabetes = datasets.load_diabetes()
regr = linear_model.LinearRegression()
X_train, X_test, y_train, y_test = train_test_split(diabetes.data, diabetes.target,
test_size = 0.2)
regr.fit(X_train, y_train)
y_pred = regr.predict(X_test)
plt.scatter(y_pred, y_test)
# Æò±Õ Á¦°ö ¿ÀÂ÷¸¦ ±¸ÇÏ´Â ÇÔ¼ö
print('Mean squared error:', mean_squared_error(y_test, y_pred))
#plt.scatter(y_pred, y_test, color='black')
x = np.linspace(0, 330, 100) # ƯÁ¤ ±¸°£ÀÇ Á¡
plt.plot(x, x, linewidth=3, color='blue')
plt.show()