Python-сообщество

import codecs, re
f = codecs.open(u'text.txt', 'r', 'utf-8')
words = []
d = {}
frequency = 0
for line in f:
   for word in line.split():
        word = word.lower()
        word = word.strip(u'.,:;-()?!')
        words.append(word)
f.close()
for i in range(len(words)):
    v = u'(^[аеёиоуыэюя]{2,})|([аеёиоуыэюя]{2,}$)'
    m = re.findall(v, words[i])
if m != []:
    for key in words:
        if key in d:
            value = d[key]
            
f = open(u'dict.csv', 'w', 'utf')
f.close()

# -*- coding: utf-8 -*-
import codecs, re
d = {}
v=u'([аеёиоуыэюя]{2,}.*[аеёиоуыэюя]{2,})' 
with codecs.open(u'text.txt', 'r', 'utf-8') as f:
    for line in f:
        for word in line.split():
            word = word.lower().strip(u'.,:;-()?!')
            
            if re.match(v, word):
                if d.has_key(word):
                    d[word]+=1
                else:
                    d[word]=1
for key, value in d.items():
    print '{} = {}'.format(key, value)

import csv

for key, value in sorted(d.items(), key=lambda x: x[1], reverse=True):
    print '{} = {}'.format(key, value)

# -*- coding: utf-8 -*-
import codecs, re
from collections import defaultdict, Counter
from operator import itemgetter
def words(fname):
    with codecs.open(fname, 'r', 'utf-8') as f:
        for line in f:
            for word in line.split():
                yield word.lower().strip(u'.,:;-()?!')
# вариант с defaultdict
def  freuqency(words):
    template = re.compile(u'([аеёиоуыэюя]{2,}.*[аеёиоуыэюя]{2,})').match
    result = defaultdict(int)
    for word in filter(template, words):
        result[word] += 1
    return result
# вариант с Counter
def  freuqency(words):
    template = re.compile(u'([аеёиоуыэюя]{2,}.*[аеёиоуыэюя]{2,})').match
    return Counter(filter(template, words))

# вывод результата
for key, value in sorted(freuqency(words('text.txt')).items(), key=itemgetter(1), reverse=True):
    print '{} = {}'.format(key, value)

import re
s = 'коала, коа, котовый, акоазм'
print(re.sub(r'\bкоа\b', 'пёс', s))