本文使用了经典的鸢尾花数据训练logistic回归。感兴趣的同学可以自己试一下。
#使用SKlearn来训练logistic 回归
from sklearn import datasets
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
import matplotlib.pyplot as plt
from matplotlib.colors import ListedColormap
from sklearn.linear_model import LogisticRegression
iris = datasets.load_iris()
x = iris.data[:, [2,3]]
y = iris.target
x_train,x_test,y_train,y_test = train_test_split(x,y,test_size = 0.3, random_state = 0)
sc = StandardScaler()
sc.fit(x_train)
x_train_std = sc.transform(x_train)
x_test_std = sc.transform(x_test)
def plot_decision_regions(x,y,classifier,test_idx = None,resolution=0.02):
#定义marker generator and color ma
markers = ('s','x','o','^','v')
colors = ('red','blue','lightgreen','gray','cyan')
cmap = ListedColormap(colors[:len(np.unique(y))])
#plot the decision surface
x1_min,x1_max = x[:,0].min() - 1, x[:,0].max() + 1
x2_min,x2_max = x[:,1].min() - 1, x[:,1].max() + 1
xx1,xx2 = np.meshgrid(np.arange(x1_min,x1_max,resolution),np.arange(x2_min,x2_max,resolution))
z = classifier.predict(np.array([xx1.ravel(),xx2.ravel()]).T)
z = z.reshape(xx1.shape)
plt.contourf(xx1,xx2,z,alpha=0.4,cmap=cmap)
plt.xlim(xx1.min(),xx1.max())
plt.xlim(xx2.min(),xx2.max())
#plot class samples
for idx, cl in enumerate(np.unique(y)):
plt.scatter(x=x[y == cl, 0],
y=x[y == cl, 1],
alpha = 0.6, c = cmap(idx), edgecolor = 'black',marker = markers[idx], label = cl)
lr = LogisticRegression(C=1000.0, random_state=0)
lr.fit(x_train_std,y_train)
x_combined_std = np.vstack((x_train_std,x_test_std))
y_combined = np.hstack((y_train,y_test))
plot_decision_regions(x = x_combined_std, y=y_combined,classifier=lr, test_idx = range(105, 150))
plt.xlabel('petal length')
plt.ylabel('petal width')
plt.legend(loc = 'upper left')
plt.show()
出图