def build_forms(begin_file,end_file):
begin_lines=tools.read_lines(begin_file,clean_text=False)
begin=parse_begin(begin_lines)
end_lines=tools.read_lines(end_file,clean_text=False)
end=parse_end(end_lines)
unified=unify_dirs(begin,end)
return FormsDict(unified)
def main(new_word):
words = tools.read_lines(FORMS_SOURCE, clean_text=False)
#words=distance.eff_heuristic(new_word,words)
correct_word = distance.curry_correct(words)
print(correct_word(new_word))
def main_loop():
full_words = tools.read_lines(FORMS_SOURCE, clean_text=False)
words = [distance.code_digraphs(word_i) for word_i in full_words]
correct_word = distance.curry_correct(words, full_words)
tools.ui_loop(correct_word, get_word)
def clustering(filename):
lines=tools.read_lines(filename,clean_text=True)
text=" ".join(lines)
ngram_metric=ngrams.make_ngram_metric(text,n=2)
return cluster_lines(lines,metric=ngram_metric)
def clustering(filename):
lines = tools.read_lines(filename, clean_text=True)
text = " ".join(lines)
ngram_metric = ngrams.make_ngram_metric(text, n=2)
return cluster_lines(lines, metric=ngram_metric)
def main(new_word):
words=tools.read_lines(FORMS_SOURCE,clean_text=False)
#words=distance.eff_heuristic(new_word,words)
correct_word=distance.curry_correct(words)
print(correct_word(new_word))
def main_loop():
full_words=tools.read_lines(FORMS_SOURCE,clean_text=False)
words=[distance.code_digraphs(word_i)
for word_i in full_words]
correct_word=distance.curry_correct(words,full_words)
tools.ui_loop(correct_word,get_word)