机器学习 scikit-learn（2）

标签传播（label Propagation）

强调一种主动学习工具去学习手写数字。开始训练一个只有10个标签的标签传播模型，然后我们选择5个最不确定的去标记。之后我们训练15个标签点。重复4次，最后得到一个拥有30个标签的例子。例子来自于scikit-learn官网

print(__doc__)

# Authors: Clay Woolam <clay@woolam.org>
# Licence: BSD

import numpy as np
import matplotlib.pyplot as plt
from scipy import stats

from sklearn import datasets
from sklearn.semi_supervised import label_propagation
from sklearn.metrics import classification_report, confusion_matrix

digits = datasets.load_digits() #导入数据集
rng = np.random.RandomState(0)  
indices = np.arange(len(digits.data)) #indices是索引号为0-1788的数组
rng.shuffle(indices)  #随机

X = digits.data[indices[:330]]    #取索引号为前330的数据
y = digits.target[indices[:330]]  #取索引号为前330的目标数据
images = digits.images[indices[:330]]

n_total_samples = len(y)          #共330个
n_labeled_points = 10

unlabeled_indices = np.arange(n_total_samples)[n_labeled_points:]	#没有标记后320个索引
f = plt.figure()

for i in range(5):	#循环5次
    y_train = np.copy(y)		#索引号为前330个的目标数据
    y_train[unlabeled_indices] = -1	#后面320个都是-1

    lp_model = label_propagation.LabelSpreading(gamma=0.25, max_iter=5)	#自定义标签传播模型
    lp_model.fit(X, y_train)		# 应用，进行训练

    predicted_labels = lp_model.transduction_[unlabeled_indices]	#进行传播，之后得到预测的值
    true_labels = y[unlabeled_indices]	#真实值

    cm = confusion_matrix(true_labels, predicted_labels,
                          labels=lp_model.classes_)

    print('Iteration %i %s' % (i, 70 * '_'))
    print("Label Spreading model: %d labeled & %d unlabeled (%d total)"
          % (n_labeled_points, n_total_samples - n_labeled_points, n_total_samples))

    print(classification_report(true_labels, predicted_labels))

    print("Confusion matrix")
    print(cm)

    # compute the entropies of transduced label distributions
    pred_entropies = stats.distributions.entropy(
        lp_model.label_distributions_.T)

    # select five digit examples that the classifier is most uncertain about
    uncertainty_index = uncertainty_index = np.argsort(pred_entropies)[-5:]

    # keep track of indices that we get labels for
    delete_indices = np.array([])

    f.text(.05, (1 - (i + 1) * .183),
           "model %d\n\nfit with\n%d labels" % ((i + 1), i * 5 + 10), size=10)
    for index, image_index in enumerate(uncertainty_index):
        image = images[image_index]

        sub = f.add_subplot(5, 5, index + 1 + (5 * i))
        sub.imshow(image, cmap=plt.cm.gray_r)
        sub.set_title('predict: %i\ntrue: %i' % (
            lp_model.transduction_[image_index], y[image_index]), size=10)
        sub.axis('off')

        # labeling 5 points, remote from labeled set
        delete_index, = np.where(unlabeled_indices == image_index)
        delete_indices = np.concatenate((delete_indices, delete_index))

    unlabeled_indices = np.delete(unlabeled_indices, delete_indices)
    n_labeled_points += 5

f.suptitle("Active learning with Label Propagation.\nRows show 5 most "
           "uncertain labels to learn with the next model.")
plt.subplots_adjust(0.12, 0.03, 0.9, 0.8, 0.2, 0.45)
plt.show()