import numpy as np
import matplotlib.pyplot as plt
np.random.seed(666)
X = np.random.normal(0, 1, size=(200,2))
y = np.array(X[:,0]**2 + X[:,1]<1.5, dtype='int')
for _ in range(20):
y[np.random.randint(200)] = 1
plt.scatter(X[y==0,0],X[y==0,1])
plt.scatter(X[y==1,0],X[y==1,1])
plt.show()
from sklearn.linear_model import LogisticRegression
log_reg = LogisticRegression()
log_reg.fit(X_train, y_train)
log_reg.score(X_train, y_train) # 0.79333
log_reg.score(X_test, y_test) # 0.86
plot_decision_boundary(log_reg, [-4, 4, -4, 4]) # 使用8-6中的边界绘制算法
plt.scatter(X[y==0,0],X[y==0,1])
plt.scatter(X[y==1,0],X[y==1,1])
plt.show()
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import PolynomialFeatures
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
def PolynomialLogisticRegression(degree, C=1.0, penalty='l2'):
return Pipeline([
('poly', PolynomialFeatures(degree=degree)),
('std_scaler', StandardScaler()),
('log_reg', LogisticRegression(C=C, penalty=penalty)) # 遵循sklearn标准构建的类可以无缝结合到管道中
])
