Merge pull request #80 from denizs/denizs-patch-1

Added `vocab` and `vocab_size` to CBOW exercise

Author: chsasank

beginner_source/nlp/word_embeddings_tutorial.py

@@ -309,7 +309,12 @@ def forward(self, inputs):
 The evolution of a process is directed by a pattern of rules
 called a program. People create programs to direct processes. In effect,
 we conjure the spirits of the computer with our spells.""".split()
-word_to_ix = {word: i for i, word in enumerate(raw_text)}
+
+# By deriving a set from `raw_text`, we deduplicate the array
+vocab = set(raw_text)
+vocab_size = len(vocab)
+
+word_to_ix = {word: i for i, word in enumerate(vocab)}
 data = []
 for i in range(2, len(raw_text) - 2):
     context = [raw_text[i - 2], raw_text[i - 1],