Clarify label encoding comment in char_rnn_classification_tutorial

The previous comment 'Cache the tensor representation of the labels' was
misleading, especially for beginners. The code actually creates a numerical
representation by storing unique labels in alphabetical order and converting
each label to its corresponding index as a tensor.

Updated the comment to clearly explain what's happening: creating numerical
representations rather than caching.

Author: patrocinio

intermediate_source/char_rnn_classification_tutorial.py

@@ -179,7 +179,8 @@ def __init__(self, data_dir):
                 self.data_tensors.append(lineToTensor(name))
                 self.labels.append(label)
 
-        #Cache the tensor representation of the labels
+        # Create numerical representation of labels
+        # Store unique labels in alphabetical order and convert each label to its index
         self.labels_uniq = list(labels_set)
         for idx in range(len(self.labels)):
             temp_tensor = torch.tensor([self.labels_uniq.index(self.labels[idx])], dtype=torch.long)