bpe_4.py

#computer frequency of a pair of characters or character sequences
#accepts corpus and return frequency of each pair
def get_stats(corpus):
    pairs = collections.defaultdict(int)
    for word, freq in corpus.items():
        symbols = word.split()
        for i in range(len(symbols)-1):
            pairs[symbols[i],symbols[i+1]] += freq
    return pairs