100 lines
3.3 KiB
Python
100 lines
3.3 KiB
Python
"""
|
|
========================================
|
|
Label Propagation digits active learning
|
|
========================================
|
|
|
|
Demonstrates an active learning technique to learn handwritten digits
|
|
using label propagation.
|
|
|
|
We start by training a label propagation model with only 10 labeled points,
|
|
then we select the top five most uncertain points to label. Next, we train
|
|
with 15 labeled points (original 10 + 5 new ones). We repeat this process
|
|
four times to have a model trained with 30 labeled examples.
|
|
|
|
A plot will appear showing the top 5 most uncertain digits for each iteration
|
|
of training. These may or may not contain mistakes, but we will train the next
|
|
model with their true labels.
|
|
"""
|
|
print(__doc__)
|
|
|
|
# Authors: Clay Woolam <clay@woolam.org>
|
|
# License: 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()
|
|
rng = np.random.RandomState(0)
|
|
indices = np.arange(len(digits.data))
|
|
rng.shuffle(indices)
|
|
|
|
X = digits.data[indices[:330]]
|
|
y = digits.target[indices[:330]]
|
|
images = digits.images[indices[:330]]
|
|
|
|
n_total_samples = len(y)
|
|
n_labeled_points = 10
|
|
|
|
unlabeled_indices = np.arange(n_total_samples)[n_labeled_points:]
|
|
f = plt.figure()
|
|
|
|
for i in range(5):
|
|
y_train = np.copy(y)
|
|
y_train[unlabeled_indices] = -1
|
|
|
|
lp_model = label_propagation.LabelSpreading(gamma=0.25, max_iter=5)
|
|
lp_model.fit(X, y_train)
|
|
|
|
predicted_labels = lp_model.transduction_[unlabeled_indices]
|
|
true_labels = y[unlabeled_indices]
|
|
|
|
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()
|