Python Sklearn make_regression

from sklearn.datasets import make_regression

import matplotlib.pyplot as plt

X, y = make_regression(n_samples=250, n_features=1, noise=50, random_state=2)

plt.scatter(X,y, s=2)

plt.show()

from sklearn.linear_model import LinearRegression

from sklearn.model_selection import train_test_split

# 한글 깨짐 없이 나오게 설정

from matplotlib import rcParams # 인코딩 폰트 설정

rcParams['font.family'] = 'New Gulim'

rcParams['font.size'] = 10

x_train, x_test, y_train, y_test = train_test_split(X,y, test_size=.20, random_state=0)

x_train.shape, x_test.shape, y_train.shape, y_test.shape

# 모델 생성

model = LinearRegression()

# 학습하기

model.fit(x_train, y_train)

# 가중치, 편향치 구하기

model.coef_, model.intercept_ # (array([90.11061494]), 2.4224269924448585)

# 결정 계수

model.score(x_train, y_train) # 0.789267454050733

# 추정

pred = model.predict(x_test)

# 산점도

plt.scatter(x_test,y_test)

plt.plot(x_test, pred, 'r-')

plt.show()

# 추정

model.predict([[3.0]]) # 학습할 때 주는 데이터의 형식을 따른다

# x의 최소값, 최대값을 계수와 절편을 사용하여 y값을 계산한다

# ymin = model.coef_ * xmin + model.intercept_

# ymax = model.coef_ * xmax + model.intercept_

ymin = model.coef_ * X.min() + model.intercept_

ymax = model.coef_ * X.max() + model.intercept_

X.min(), ymin, X.max(), ymax

(-2.6594494563834883,
 array([-237.22219892]),
 4.108692623805201,
 array([372.65924592]))

plt.scatter(X, y, s=3)

plt.plot([X.min(),X.max()], [ymin,ymax], "r-")

plt.show()