12、在iris数据集上的多类SGD决策曲面
import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.linear_model import SGDClassifier
plt.rcParams['font.sans-serif'] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
# 导入一些数据
iris = datasets.load_iris()
# 采取前两个特征
X = iris.data[:, :2]
y = iris.target
colors = "bry"
idx = np.arange(X.shape[0])
np.random.seed(13)
np.random.shuffle(idx)
X = X[idx]
y = y[idx]
# 标准化
mean = X.mean(axis=0)
std = X.std(axis=0)
X = (X - mean) / std
h = .02 # 网格中的步长
clf = SGDClassifier(alpha=0.001, max_iter=100).fit(X, y)
# 创建要绘制的网格
x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
np.arange(y_min, y_max, h))
#绘制决策边界
Z = clf.predict(np.c_[xx.ravel(), yy.ravel()])
# 将结果放入彩色图中
Z = Z.reshape(xx.shape)
cs = plt.contourf(xx, yy, Z, cmap=plt.cm.Paired)
plt.axis('tight')
# 绘制训练要点
for i, color in zip(clf.classes_, colors):
idx = np.where(y == i)
plt.scatter(X[idx, 0], X[idx, 1], c=color, label=iris.target_names[i],
cmap=plt.cm.Paired, edgecolor='black', s=20)
plt.title("在iris数据集上的多类SGD决策曲面")
plt.axis('tight')
# 绘制三个一反全分类器
xmin, xmax = plt.xlim()
ymin, ymax = plt.ylim()
coef = clf.coef_
intercept = clf.intercept_
def plot_hyperplane(c, color):
def line(x0):
return (-(x0 * coef[c, 0]) - intercept[c]) / coef[c, 1]
plt.plot([xmin, xmax], [line(xmin), line(xmax)],
ls="--", color=color)
for i, color in zip(clf.classes_, colors):
plot_hyperplane(i, color)
plt.legend()
plt.show()
