机器学习---半监督学习简单示例（标签传播算法）

1. 使用半监督学习方法 Label Spreading 在一个生成的二维数据集上进行标签传播

import numpy as np
import matplotlib.pyplot as plt
from sklearn.semi_supervised import label_propagation
from sklearn.datasets import make_circles

# generate ring with inner box
n_samples = 200
X, y = make_circles(n_samples=n_samples, shuffle=False) 
# sklearn.datasets.make_circles(n_samples=100, shuffle=True, noise=None, random_state=None, factor=0.8)
# make_circle和make_moom产生二维二元分类数据集来测试某些算法的性能，可以为数据集添加噪声，可以为二元分类器产生一些球形判决界面的数据
outer, inner = 0, 1
labels = np.full(n_samples, -1.) # 形状n_samples，数据-1
labels[0] = outer
labels[-1] = inner

# Learn with LabelSpreading
label_spread = label_propagation.LabelSpreading(kernel='knn', alpha=0.8) # kernel : {‘knn’, ‘rbf’, callable}
label_spread.fit(X, labels)

# Plot output labels
output_labels = label_spread.transduction_
plt.figure(figsize=(8.5, 4))
plt.subplot(1, 2, 1)
plt.scatter(X[labels == outer, 0], X[labels == outer, 1], color='navy', # s点的大小,lw线宽
            marker='s', lw=0, label="outer labeled", s=10)
plt.scatter(X[labels == inner, 0], X[labels == inner, 1], color='c',
            marker='s', lw=0, label='inner labeled', s=10)
plt.scatter(X[labels == -1, 0], X[labels == -1, 1], color='darkorange',
            marker='.', label='unlabeled')
plt.legend(scatterpoints=1, shadow=False, loc='upper right')
plt.title("Raw data (2 classes=outer and inner)")

plt.subplot(1, 2, 2)
output_label_array = np.asarray(output_labels) # 将结构数据转化为ndarray
outer_numbers = np.where(output_label_array == outer)[0]
inner_numbers = np.where(output_label_array == inner)[0]
plt.scatter(X[outer_numbers, 0], X[outer_numbers, 1], color='navy',
            marker='s',