bpe_9.py

num_merges = 10
for i in range(num_merges):
    
    #compute frequency of bigrams in a corpus
    pairs = get_stats(corpus)
    
    #compute the best pair
    best = max(pairs, key=pairs.get)
    
    #merge the frequent pair in corpus
    corpus = merge_vocab(best, corpus)
    
    #append to merge list and vocabulary
    merges.append(best)
    vocab.append(best)

#convert a tuple to a string
merges_in_string = ["".join(list(i)) for i in merges]
print("BPE Merge Operations:",merges_in_string)