1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
|
from lib import minimum_edit_distance
def load():
words = {}
for line in open("alphabetical.csv", "r").readlines():
word, freq = line.split(",")
words[word] = int(freq)
return words
def main(words):
"""Repeatedly ask the user for word and autocomplete/-correct it."""
word = ""
while word != "q":
word = input("Type word: ").lower()
print("Autocompletion finished: ", autocomplete(words, word))
print("Sorted autocompletion: ", autocomplete_best(words, word))
print("Best three: ", autocomplete_best(words, word, 3))
print("Autocorrect: ", autocorrect(words, word))
def autocomplete(words, search_word):
"""Return autocomplete suggestions."""
for word in words.keys():
if word.startswith(search_word):
return word
return None
def autocomplete_best(words, search_word, amount=None):
"""Return the /amount/ most common autocompletions."""
matching_words = {word: freq for word, freq in words.items()
if word.startswith(search_word)}
matching_words_sorted = sorted(matching_words.items(),
key=lambda item: item[1], # sort by freq
reverse=True) # sort most frequent first
matching_words_sorted_words = [word for word, freq in matching_words_sorted]
if amount:
return ", ".join(list(matching_words_sorted_words)[:amount])
else:
return ", ".join(list(matching_words_sorted_words))
def autocorrect(words, search_word):
"""Return the word with the smallest Levhenstein distance"""
best = None
for word, _ in words.items():
edit_distance = minimum_edit_distance(search_word, word)
if not best:
best = (edit_distance, word)
if edit_distance < best[0]:
best = (edit_distance, word)
return best[1]
main(load())
|
