scikit-learn
diff --git a/‎examples/semi_supervised/plot_label_propagation_digits_active_learning.py
+27-13 b/‎examples/semi_supervised/plot_label_propagation_digits_active_learning.py
+27-13
@@ -9,7 +9,10 @@
 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.
+four times to have a model trained with 30 labeled examples. Note you can
+increase this to label more than 30 by changing `max_iterations`. Labeling
+more than 30 can be useful to get a sense for the speed of convergence of
+this active learning technique.
 
 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
@@ -39,11 +42,15 @@
 
 n_total_samples = len(y)
 n_labeled_points = 10
+max_iterations = 5
 
 unlabeled_indices = np.arange(n_total_samples)[n_labeled_points:]
 f = plt.figure()
 
-for i in range(5):
+for i in range(max_iterations):
+    if len(unlabeled_indices) == 0:
+        print("No unlabeled items left to label.")
+        break
     y_train = np.copy(y)
     y_train[unlabeled_indices] = -1
 
@@ -56,7 +63,7 @@
     cm = confusion_matrix(true_labels, predicted_labels,
                           labels=lp_model.classes_)
 
-    print('Iteration %i %s' % (i, 70 * '_'))
+    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))
 
@@ -69,29 +76,36 @@
     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:]
+    # select up to 5 digit examples that the classifier is most uncertain about
+    uncertainty_index = np.argsort(pred_entropies)[::-1]
+    uncertainty_index = uncertainty_index[
+        np.in1d(uncertainty_index, unlabeled_indices)][: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 more than 5 iterations, visualize the gain only on the first 5
+    if i < 5:
+        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')
+        # for more than 5 iterations, visualize the gain only on the first 5
+        if i < 5:
+            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
+    n_labeled_points += len(uncertainty_index)
 
 f.suptitle("Active learning with Label Propagation.\nRows show 5 most "
            "uncertain labels to learn with the next model.")