Python Sklearn make_blobs

from sklearn.datasets import make_blobs

예제

X, y = make_blobs(n_samples=500, centers=3, n_features=2, random_state=0) # 500개의 점을 3개로 모이게 한다, 변수는 2개, 무작위 상태는 0

X.shape, y.shape # ((500, 2), (500,))

plt.scatter(X[:,0],X[:,1],c=y,s=5)

plt.show()

# 학습 데이터 나누기

from sklearn.model_selection import train_test_split

x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=.25, random_state=0)

x_train.shape, x_test.shape, y_train.shape, y_test.shape # ((375, 2), (125, 2), (375,), (125,))

# 지도 학습 하기

from sklearn.linear_model import LogisticRegression

logisticReg = LogisticRegression(max_iter=5000) # 기본 반복 100

logisticReg.fit(x_train, y_train)

# 추정하기

pred = logisticReg.predict(X)

# 결정계수

logisticReg.score(x_test, y_test) # 0.92

# 한글 깨짐 없이 나오게 설정

from matplotlib import rcParams # 인코딩 폰트 설정

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

rcParams['font.size'] = 10

# 산점도

plt.figure(figsize=(10,4))

plt.subplot(1,2, 1)

plt.scatter(X[:,0],X[:,1],c=y)

plt.title('정답')

plt.subplot(1,2, 2)

plt.scatter(X[:,0],X[:,1],c=pred)

plt.title('추정')

plt.show()