def is_word_char(char):
    return char not in '".,:;\'@$%^&*/+-=<>[]{}'

# function modifies freq_dict
# adds frequencies of all trigrams from word
def freq_bigrams(freq_dict, word):
    # last beginning of a bigram is the index len(word)-2
    for i in range(0, len(word)-1):
        freq_dict[w[i:i+2]] = freq_dict.get(w[i:i+2], 0) + 1

f = open('alice.txt','r')
freq = {}
for line in f.readlines():
    line = "".join(filter(is_word_char, line))
    line = line.lower()
    word_list = line.split() # default delimiter is space " "
    for w in word_list:
        freq_bigrams(freq, w)
f.close()

k = 10 # we want output k most frequent
keys_list = list(freq.keys())
keys_list.sort(key=freq.get, reverse=True)
for w in keys_list[:k]:
    print(w, "\t", freq[w])