]*?>[^<>]*?', '', nostyle)
notags = re.sub('<[^>]*>', '', nospan)
notags1 = re.sub('{[^}]*}', '', notags)
text = re.sub('[&][^;]*;', ' ', notags1)
text = re.sub(r'\s+', ' ', text)
return text
def html(text):
tags = re.findall(r'<[^>]*?>', text)
return tags
def main():
with open('schizo.txt', 'r', encoding = 'utf-8') as f:
text = f.read()
with open('html.txt', 'w', encoding = 'utf-8') as f:
output = f.write('\n'.join(html(text)))
with open('pure.txt', 'w', encoding = 'utf-8') as f:
output = f.write(clean(text))
if __name__ == '__main__':
main()
import re
def main():
given = input('Введите свой телефонный номер: ')
right = re.search('\+7 \([0-9]{3}\) [0-9]{3}-[0-9]{2}-[0-9]{2}', given)
if right:
print('Введённый номер совпадает с шаблоном +7 (ХХХ) ХХХ-ХХ-ХХ.')
if re.search('\(9(?:2|3)', given):
print('Это Мегафон.')
elif re.search('\(9(?:1|8)', given):
print('Это МТС.')
elif re.search('\(96', given):
print('Это Билайн.')
else:
print('Я не могу точно сказать, какой это оператор.')
else:
print('Введённый номер не совпадает с шаблоном +7 (ХХХ) ХХХ-ХХ-ХХ.')
if re.search('\(9(?:2|3)', given) or re.search('\+7 ?9(?:2|3)', given) or re.match('8 ?9(?:2|3)', given):
print('Это Мегафон.')
elif re.search('\(9(?:1|8)', given) or re.search('\+7 ?9(?:1|8)', given) or re.match('8 ?9(?:1|8)', given):
print('Это МТС.')
elif re.search('\(96', given) or re.search('\+7 ?96', given) or re.match('8 ?96', given):
print('Это Билайн.')
else:
print('Я не могу точно сказать, какой это оператор.')
if __name__ == '__main__':
main()
import re
def revert(dictionary):
reverted = {}
for key in dictionary:
reverted[dictionary[key]] = key
return reverted
def russian_to_latin_dictionary(lines):
raw = {}
rus_to_lat = {}
for i in range(len(lines)):
raw[lines[i].split(' — ')[0]] = lines[i].split(' — ')[1].strip('\n')
raw = revert(raw)
for key in raw:
if len(key.split(',')) > 1:
for i in range(len(key.split(','))):
rus_to_lat[key.split(',')[i-1].strip()] = raw[key]
i +=10
else:
rus_to_lat[key] = raw[key]
return rus_to_lat
def latin_to_russian_dictionary(lines):
raw = {}
lat_to_rus = {}
for i in range(len(lines)):
raw[lines[i].split(' — ')[0]] = lines[i].split(' — ')[1].strip('\n')
for key in raw:
if len(key.split(',')) > 1:
for i in range(len(key.split(','))):
lat_to_rus[key.split(',')[i-1].strip()] = raw[key]
i +=10
else:
lat_to_rus[key] = raw[key]
return lat_to_rus
def main():
with open ('latin.txt', 'r', encoding = 'utf-8') as f:
lines = f.readlines()
for i in range(len(lines)):
lines[i] = re.sub('(?:–|−|-)', '—', lines[i])
lines[i] = re.sub(';', ',', lines[i])
print(latin_to_russian_dictionary(lines))
print(russian_to_latin_dictionary(lines))
if __name__ == '__main__':
main()
def process(fname):
with open (fname, 'r', encoding = 'utf-8') as f:
text = f.read()
text = text.lower()
forms = text.split()
for i in range(len(forms)):
forms[i] = forms[i].strip('.,!?*()«»\'":][><')
return forms
def freqlist(forms):
freqs = {}
for i in range(len(forms)):
if forms[i] not in freqs:
freqs[forms[i]] = 1
else:
freqs[forms[i]] +=1
return freqs
def maxfreq(frequencies):
maximumfreq = []
for key in frequencies:
if frequencies[key] == max(frequencies.values()):
maximumfreq.append(key)
return maximumfreq
def averagefreq(frequencies):
total = 0
for key in frequencies:
total += frequencies[key]
average = total/len(frequencies)
return average
def main():
forms = process('text.txt')
frequencies = freqlist(forms)
print(*maxfreq(frequencies), '- самое частотное слово в тексте.')
print(averagefreq(frequencies), '- средняя частота слов в тексте.')
if __name__ == '__main__':
main()
import random
def ask():
user_info = []
name = input('Как Вас зовут? ')
surname = input('Какая у Вас фамилия? ')
age = input('Сколько Вам лет? ')
food = input('Какая у Вас любимая еда? ')
musician = input('Какая у Вас любимая музыкальная группа? ')
dream = input('Какая у Вас заветная мечта? ')
user_info.append(name+' '+surname)
user_info.append([age, food, musician, dream])
return user_info
def guess(database_dictionary):
person = random.choice(list(database_dictionary.keys()))
clue = random.choice(['его/её мечта: '+database_dictionary[person][3], 'его/её любимая музыкальная группа: '+database_dictionary[person][2], 'его/её мечта: '+database_dictionary[person][3]+'\nего/её любимая еда: '+database_dictionary[person][1], 'его/её любимая музыкальная группа: '+database_dictionary[person][2]+'\nего/её любимая еда: '+database_dictionary[person][1]])
guess = input('Угадайте, кто это (имя и фамилию)? Подсказка: '+clue+' ')
if guess == person:
return 'Правильно!'
else:
return 'Нет, неправильно, это - '+person
def main():
database = {}
i = 0
while i < 7:
answer = ask()
i += 1
database[answer[0]] = answer[1]
print(guess(database))
if __name__ == '__main__':
main()
import re
def main():
with open('Лингвистика.txt', 'r', encoding = 'utf-8') as f:
text = f.read()
lang = 'язык((?:а(?:ми?|х)?)|и|о(?:в|м)|у|е)?([\s,.!\?:"\(\)\'»])'
Lang = 'Язык((?:а(?:ми?|х)?)|и|о(?:в|м)|у|е)?([\s,.!\?:"\(\)\'»])'
new_text = re.sub(lang,'шашлык\\1\\2', text)
new_text = re.sub(Lang,'Шашлык\\1\\2', new_text)
with open('Новая лингвистика.txt', 'w', encoding = 'utf-8') as f:
f.write(new_text)
if __name__ == '__main__':
main()
import os
extension_frequency_list = {}
for root, dirs, files in os.walk('.'):
for f in files:
file_name = f.split('.')[0]
file_ext = f.split('.')[1]
if file_ext not in extension_frequency_list:
extension_frequency_list[file_ext] = 1
else:
extension_frequency_list[file_ext] += 1
max_ext = max(extension_frequency_list.values())
i = 0
for key in extension_frequency_list:
if extension_frequency_list[key] == max_ext:
if i == 0:
print('The most frequent extention is \''+key+'\'. There is(are) '+str(extension_frequency_list[key])+' file(s) with it.')
i = 1
else:
print('There is(are) also '+str(extension_frequency_list[key])+' \''+key+'\' file(s).')
def opentext(fname):
forms = []
with open (fname, 'r', encoding = 'utf-8') as f:
text = f.read()
text = text.lower()
forms = text.split()
for i in range(len(forms)):
forms[i] = forms[i].strip('.,!?*()«»\'"')
return forms
def adj_hood(fname):
words = opentext(fname)
hoods = []
for i in range(len(words)):
if len(words[i])>4:
if words[i][-1] == 'd':
if words[i][-2] == 'o':
if words[i][-3] == 'o':
if words[i][-4] == 'h':
if words[i] not in hoods:
hoods.append(words[i])
return hoods
def count_frequency(fname, word):
words = opentext(fname)
word_freq = 0
for i in range(len(words)):
if words[i] == word:
word_freq += 1
return word_freq
def main():
fname = input('Введите имя файла: ')
hoods = adj_hood(fname)
print('В тексте встретилось', len(hoods), 'прилагательных с суффиксом -hood.')
freq = []
for i in range(len(hoods)):
freq.append(count_frequency(fname, hoods[i]))
min_freq = []
for i in range(len(hoods)):
if freq[i] == min(freq):
min_freq.append(hoods[i])
print('Самые редкие прилагательные с суффиксом -hood: ', ', '.join(min_freq))
roots = []
for i in range(len(hoods)):
roots.append(hoods[i][0:-4])
print('Корни прилагательных с суффиксом -hood: ', ', '.join(roots))
if __name__ == '__main__':
main()
words = []
with open('text.txt','r', encoding = 'utf-8') as f:
text = f.read()
words_raw = text.split()
words = []
for i in range(len(words_raw)):
words.extend(words_raw[i].split('\n'))
len3 = 0
len1 = 0
for word in words:
if len(word) == 3:
len3 += 1
elif len(word) == 1:
len1 += 1
if len1 == 0:
print('В файле нет слов длины 1.')
elif len3 == 0:
print('В файле нет слов длины 3.')
else:
print('В файле в '+str(len3/len1)+' раз больше слов длины 3, чем слов длины 1.')
import random
def nom_noun():
with open('nomnouns.txt','r', encoding = 'utf-8') as f:
nomnouns = f.read().split('\n')
return random.choice(nomnouns)
def acc_noun():
with open('accnouns.txt','r', encoding = 'utf-8') as f:
accnouns = f.read().split('\n')
return random.choice(accnouns)
def adverb():
with open('adverbs.txt','r', encoding = 'utf-8') as f:
adverbs = f.read().split('\n')
return random.choice(adverbs)
def intensifier(adv):
with open('intensifiers.txt','r', encoding = 'utf-8') as f:
intensifiers = f.read().split('\n')
return random.choice(intensifiers) + ' ' + adv
def verb_of_thought(subj):
with open('thoughtverbs.txt','r', encoding = 'utf-8') as f:
thoughtverbs = f.read().split('\n')
return subj + ' ' + random.choice(thoughtverbs) + ', что ' + trans_verb(nom_noun(), acc_noun()) + '.'
def trans_verb(subj, obj):
with open('transverbs.txt','r', encoding = 'utf-8') as f:
transverbs = f.read().split('\n')
return subj + ' ' + intensifier(adverb()) + ' ' + random.choice(transverbs)+ ' ' + obj
def trans_verb_negative(subj, obj):
with open('transverbs.txt','r', encoding = 'utf-8') as f:
transverbs = f.read().split('\n')
negative_sentences = [subj + ' не ' + intensifier(adverb()) + ' ' + random.choice(transverbs)+ ' ' + obj, subj + ' ' + intensifier(adverb()) + ' не ' + random.choice(transverbs)+ ' ' + obj]
return random.choice(negative_sentences)
def verb_of_thought_negative(subj, obj):
with open('thoughtverbs.txt','r', encoding = 'utf-8') as f:
thoughtverbs = f.read().split('\n')
return subj + ' не ' + random.choice(thoughtverbs) + ', что ' + trans_verb(nom_noun(), acc_noun()) + '.'
def positive():
positive_sentences = [trans_verb(nom_noun(), acc_noun()) + '.', verb_of_thought(nom_noun())]
return random.choice(positive_sentences)
def question():
questions = ['зачем ' + trans_verb(nom_noun(), acc_noun()) + '?', 'почему ' + verb_of_thought(nom_noun())]
return random.choice(questions)
def negative():
negative_sentences = [verb_of_thought_negative(nom_noun(), acc_noun()), trans_verb_negative(nom_noun(), acc_noun())]
return random.choice(negative_sentences)
def conditional():
with open('transverbs.txt','r', encoding = 'utf-8') as f:
transverbs = f.read().split('\n')
conditional_sentences = ['если ' + positive().strip('.') + ', то ' + nom_noun() + ' ' + random.choice(transverbs)+ ' ' + acc_noun(), 'если ' + positive().strip('.') + ', то ' + nom_noun() + ' не ' + random.choice(transverbs)+ ' ' + acc_noun(), 'если ' + negative().strip('.') + ', то ' + nom_noun() + ' ' + random.choice(transverbs)+ ' ' + acc_noun(), 'если ' + negative().strip('.') + ', то ' + nom_noun() + ' не ' + random.choice(transverbs)+ ' ' + acc_noun()]
return random.choice(conditional_sentences)
def imperative():
with open('imperatives.txt','r', encoding = 'utf-8') as f:
imperatives = f.read().split('\n')
imperative_sentences = ['пусть ' + positive(), 'пусть ' + negative(), 'пусть ' + conditional(), random.choice(imperatives) + ' ' + acc_noun()]
return random.choice(imperative_sentences)
def main():
sentences = [positive(), question(), negative(), conditional(), imperative()]
random.shuffle(sentences)
for i in range(5):
print(sentences[i].capitalize())
if __name__ == '__main__':
main()
a = input("Введите первое число. ")
a = float(a)
b = input("Введите второе число. ")
b = float(b)
c = input("Введите третье число. ")
c = float(c)
if b:
if a%b == c:
print("a даёт остаток c при делении на b")
else:
print("a не даёт остаток c при делении на b")
else:
print("Делите на ноль сами!")
if (a*c)+b == 0:
print("c является решением линейного уравнения ax + b = 0")
else:
print("c не является решением линейного уравнения ax + b = 0")
list_list = [['l'],['s'],['d']]
def el_0(any_list):
return any_list[0]
a = ' '.join([el_0(el) for el in list_list])
print(a)
b = list(map(el_0, list_list))
print(b)
b = ' '.join(list(map(el_0, list_list)))
print(b)
c = ' '.join(list(map(lambda any_list: any_list[0], list_list)))
print(c)
number = input("print any number")
square = int(number)**0.5
if square/1 == square//1:
print ("yes")
else:
print ("no")
import codecs, re
def open_file(title):
a = codecs.open(title, 'r', 'utf-8')
words = [word.strip(' ,.?!-:;').lower() for word in a.read().split()]
return words
def find_bigramm(words):
text = ''
for word in words:
text += word + ' '
found = 0
for x in range(len(words)-1):
bigramm = words[x] + ' ' + words[x+1]
m = re.findall(bigramm, text, flags = re.U)
if len(m) > 2:
print(True)
found = 1
break
if found == 0:
print(False)
def main():
f = open_file('text.txt')
z = find_bigramm(f)
if __name__ == "__main__":
main()
import os, codecs
def open_file(title):
a = codecs.open(title, 'r', 'utf-8')
words = [word.strip(' ,.?!-:;').lower() for word in a.read().split()]
return words
def count_word_frequency(words):
freq_dict = {}
for word in words:
try:
freq_dict[word] += 1
except KeyError:
freq_dict[word] = 1
return freq_dict
def find_max_keys(dict_num_values, amount):
values_list = dict_num_values.values()
max_values = []
i = 0
while i < amount:
local_max = max(values_list)
max_values.append(local_max)
if local_max != 1:
values_list = [x for x in values_list if x != local_max]
i += 1
max_keys = []
for key in dict_num_values:
if dict_num_values[key] in max_values:
max_keys.append(key)
return max_keys
def extract_words_from_txt_in_folder(path):
words = []
for root, dirs, files in os.walk(path):
for f in files:
if len(f.split('.')) == 2:
file_name = f.split('.')[0]
file_ext = f.split('.')[1]
if file_ext == 'txt':
words += open_file(os.path.join(root, f))
return words
def main():
print(find_max_keys(count_word_frequency(extract_words_from_txt_in_folder('.')),10))
if __name__ == "__main__":
main()
import random
with open('words.txt','r', encoding = 'utf-8') as f:
lines = f.readlines()
lenlines = len(lines)
random.shuffle(lines)
score = 0
for line in lines:
line = line.strip()
word, hint = line.split(' ',1)
response = input('Какое слово я загадала?\n'+
'Подсказка: '+hint+' ')
if response == word:
print('Правильно!')
score += 1
else:
print('Нет, слово было', word)
with open('scores.txt', 'w', encoding = 'utf-8') as n:
percent = score/lenlines*100
n.write('Вот результат: ')
n.write(str(percent)+'%')
import codecs
def open_file(file_name):
f = codecs.open(file_name, 'r', 'utf-8')
words = []
for line in f:
line = line.strip()
words += line.split()
for word in words:
word = word.strip('.,!?:;()\'\"1234567890')
word = word.lower()
return words
def bigramms(words):
bi = create_list(words)
dic = {}
for j in bi:
if j not in dic:
dic[j] = 1
else:
dic[j] += 1
answer = ''
answer = [n+'\r\n' for n in dic]
for key in dic:
if dic[key] > 2:
answer = True
else:
answer = False
print(answer)
return answer
def create_list(words):
bi = []
for i in range(len(words)):
if i < len(words) - 1:
j = i+1
bi.append(words[i] + ' ' + words[j])
return bi
words = open_file('text.txt')
bigramms(words)
import re
def main():
with open ('china space programm.txt', 'r', encoding = 'utf-8') as f:
text = f.read()
reg = '«[А-ЯЁа-яё]+?-[1-9]+»'
all_matches = re.findall(reg, text)
pure_names =[]
for i in range(len(all_matches)):
if re.sub(r'-[1-9]+', '', all_matches[i]) not in pure_names:
pure_names.append(re.sub(r'-[1-9]+', '', all_matches[i]))
all_matches += pure_names
print(all_matches)
if __name__ == '__main__':
main()
def opentext(fname):
forms = []
with open (fname, 'r', encoding = 'utf-8') as f:
text = f.read()
text = text.lower()
forms = text.split()
for i in range(len(forms)):
forms[i] = forms[i].strip('.,?*()«»')
return forms
def first_letter(letter, fname = 'text.txt'):
starting_with_letter = []
forms = opentext(fname)
for i in range(len(forms)):
if forms[i][0] == letter:
starting_with_letter.append(forms[i])
return starting_with_letter
def questions():
fname = input('Введите имя файла: ')
letter = input('Введите букву: ')
number = int(input('Введите целое число: '))
starting_with_letter = first_letter(letter, fname)
answer = []
for i in range(len(starting_with_letter)):
if len(starting_with_letter[i]) > number:
answer.append(starting_with_letter[i])
return answer
def adjectives(fname):
forms = opentext(fname)
adj = []
for i in range(len(forms)):
if len(forms[i]) > 2:
if forms[i][-1] == 'й':
if forms[i][-2] == 'o' or forms[i][-2] == 'ы' or forms[i][-2] == 'и':
if i != len(forms)-1:
adj.append(forms[i]+' '+forms[i+1])
else:
adj.append(forms[i])
elif forms[i][-1] == 'я':
if forms[i][-2] == 'а' or forms[i][-2] == 'я':
if i != len(forms)-1:
adj.append(forms[i]+' '+forms[i+1])
else:
adj.append(forms[i])
elif forms[i][-1] == 'е':
if forms[i][-2] == 'o' or forms[i][-2] == 'е':
if i != len(forms)-1:
adj.append(forms[i]+' '+forms[i+1])
else:
adj.append(forms[i])
return adj
with open('information.txt', 'w', encoding = 'utf-8') as n:
name = input('Как Вас зовут? ')
n.write(name+'\n')
age = input('Сколько Вам лет? ')
n.write(str(age)+'\n')
color = input('Какой у Вас любимый цвет? ')
n.write(color+'\n')
musician = input('Какой у Вас любимый исполнитель? ')
n.write(musician+'\n')
dream = input('Какая у Вас мечта? ')
n.write(dream+'\n')
with open('information about Mary.txt','r', encoding = 'utf-8') as f:
info = f.readlines()
for line in range(len(info)):
info[line] = info[line].strip()
response = input('Как Вашего соседа зовут? ')
if response == info[0]:
print('Правильно!')
else:
print('Нет, его зовут '+info[0]+'.')
response = input('Сколько Вашему соседу лет? ')
if str(response) == info[1]:
print('Правильно!')
else:
print('Нет, ему '+info[1]+' лет.')
response = input('Какой у Вашего соседа любимый цвет?')
if response == info[2]:
print('Правильно!')
else:
print('Нет, его любимый цвет - '+info[2]+'.')
response = input('Какой у Вашего соседа любимый исполнитель?')
if response == info[3]:
print('Правильно!')
else:
print('Нет, его любимый исполнитель - '+info[3]+'.')
response = input('Какая у Вашего соседа мечта?')
if response == info[4]:
print('Правильно!')
else:
print('Нет, его мечта - '+info[4]+'.')
number = input("What's your phone number")
if '+1' in number or number.endswith("2"):
pass
elif '+7' in number or number.startswith('8'):
print("Как дела в России?")
elif '+4' in number:
print("Как дела в Англии?")
else:
print("Как дела в мире?")
import os, codecs
from math import log
def preprocess(text):
punct = '[.,!«»?&@"$\[\]\(\):;%
tabs = '\t\n'
text_wo_punct = re.sub(punct, '', text.lower())
text_wo_punct = re.sub(tabs, '', text_wo_punct)
words = text_wo_punct.strip().split()
return words
def count_tf(word, text):
n = text.count(word)
return n/len(text)
def count_df(word, texts):
i = [True for text in texts if word in text]
df = len(i)
return df
def count_idf(word, texts):
df = count_df(word, texts)
try:
idf = len(texts)/df
except ZeroDivisionError:
return 0
return idf
def count_tfidf(word, text, texts):
tf = count_tf(word, text)
idf = count_idf(word, texts)
tfidf = log(tf, 10) * log(idf, 10)
return tfidf
def extract_textS_from_folder(path):
texts = []
for root, dirs, files in os.walk(path):
for f in files:
with open(os.path.join(root, f) , "r", encoding = 'utf-8') as t:
content = t.read
text = preprocess(content)
texts.append(text)
return texts
def keywords(text, texts):
keywords = {}
dic_tfidf = {}
for word in text:
if word in dic_tfidf:
continue
tfidf = count_tfidf(word, text, texts)
dic_tfidf[word] = tfidf
i = 0
for el in sorted(dic_tfidf, key = lambda x: dic_tfidf(x)):
if i > 5:
break
else:
i += 1
keywords[el] = dic_tfidf[el]
return keywords
def main():
texts = extract_text_from_folder('wikipedia')
for t in texts:
kwords = keywords(t, texts)
for key in kwords:
print(key, kwords[key])
if __name__ == "__main__":
main()
import os
import re
from math import log
def preprocessing(text):
punct = '[.,_!«»?&@"$\/\\[\]\(\):;%
tabs = '\n\t\s'
num = '[0-9]'
text_wo_punct = re.sub(punct, '', text.lower())
text_wo_punct = re.sub(tabs, ' ', text_wo_punct)
text_wo_punct = re.sub(num, '', text_wo_punct)
words = text_wo_punct.strip().split()
return words
def count_tf(word, text):
i = 0
for w in text:
if w == word:
i += 1
tf = i / len(text)
return tf
def count_df(word, texts):
i = 0
i = [1 for text in texts if word in text]
df = sum(i)
return df
def count_idf(word, texts):
df = count_df(word, texts)
idf = len(texts)/ (1 + df)
return idf
def count_tfidf(word, text, texts):
tf = count_tf(word, text)
idf = count_idf(word, texts)
tfidf = log(tf, 10) * log(idf, 10)
return tfidf
def keywords(text, texts):
dic_tfidf = {}
kwords = {}
for word in text:
if word in dic_tfidf:
continue
tfidf = count_tfidf(word, text, texts)
dic_tfidf[word] = tfidf
i = 0
for el in sorted(dic_tfidf, key=lambda x: dic_tfidf[x]):
if i > 5:
break
else:
i += 1
kwords[el] = dic_tfidf[el]
return kwords
def main():
texts = {}
for root, dirs, files in os.walk('wikipedia'):
for f in files:
with open(os.path.join(root, f), 'r', encoding='utf-8') as t:
content = t.read()
text = preprocessing(content)
texts[f] = text
raw_texts = list(texts.values())
for t in texts:
print('\nИзвлекаем ключевые слова для текста "{}"'.format(t.split('.')[0]))
kwords = keywords(texts[t], raw_texts)
for key in kwords:
print (key, kwords[key])
if __name__ == '__main__':
main()
import re
import os
from math import log
def open_words(fname):
forms = []
with open (fname, 'r', encoding = 'utf-8') as f:
text = f.read()
text = text.lower()
punct = '[.,?!|:;*№\"\'—@
text = re.sub(punct, '', text)
text = re.sub('[\n\t]', ' ', text)
forms = text.split()
return forms
def make_freq(arr):
d = {}
for el in arr:
try:
d[el] += 1
except KeyError:
d[el] = 1
return d
def make_bigrams(arr):
bigrams = []
for i in range(len(arr)-1):
bigr = arr[i] + ' ' + arr[i+1]
bigrams.append(bigr)
return bigrams
def count_pmi(x, y):
try:
p_x = word_freq[x]/len(words)
except KeyError:
p_x = 0
try:
p_y = word_freq[x]/len(words)
except KeyError:
p_y = 0
try:
bigr = x + ' ' + y
p_xy = bigrams_freq[bigr]/len(bigrams)
except KeyError:
p_xy = 0
try:
pmi = log(p_xy/(p_x*p_y))
except ZeroDivisionError:
pmi = 0
return pmi
def calculate_pmi():
pmis = {}
for bigr in bigrams:
x, y = bigr.split()
pmi = count_pmi(x, y)
pmis[bigr] = pmi
return pmis
def calculate_pmi_cats(word, cathegory):
p_word = freq_all[word]/len(words_all)
p_cat = 1/3
if cathegory == 'anek':
d = freq_anek
w = len(corpus_anek_words)
elif cathegory == 'izvest':
d = freq_izvest
w = len(corpus_izvest_words)
elif cathegory == 'teh':
d = freq_teh
w = len(corpus_teh_words)
p_word_cat = d[word]/w
pmi = log(p_word_cat/(p_word*p_cat))
return pmi
def main():
corpus_anek_words = []
corpus_izvest_words = []
corpus_teh_words = []
for root, dirs, files in os.walk('texts'):
if 'anekdots' in root:
for f in files:
corpus_anek_words += open_words(os.path.join(root, f))
if 'teh_mol' in root:
for f in files:
corpus_teh_words += open_words(os.path.join(root, f))
if 'izvest' in root:
for f in files:
corpus_izvest_words += open_words(os.path.join(root, f))
words = corpus_anek_words + corpus_teh_words + corpus_izvest_words
freq_anek = make_freq(corpus_anek_words)
freq_izvest = make_freq(corpus_izvest_words)
freq_teh = make_freq(corpus_teh_words)
freq_all = make_freq(words)
words_cathegory_dict = {}
for w in words:
i = 0
try:
if i < 100:
pmi_anek = calculate_pmi_cats(w, 'anek')
pmi_cats(w, 'anek')
pmi_izvest = calculate_pmi_cats(w, 'izvest')
pmi_teh = calculate_pmi_cats(w, 'teh')
pmi_max = max(pmi_anek, pmi_izvest, pmi_teh)
if pmi_max == pmi_anek:
words_cathegory_dict[w] = 'anek'
if pmi_max == pmi_teh:
words_cathegory_dict[w] = 'teh'
if pmi_max == pmi_anek:
words_cathegory_dict[w] = 'teh'
i += 1
except KeyError:
pass
print(words_cathegory_dict)
if __name__ == '__main__':
main()
import shutil
import os
name = input('Print any sentence. ')
words = name.split()
path = words[0]
for i in range(1, len(words)):
path = os.path.join(path, words[i])
os.makedirs(path)
import shutil
import os
num = int(input('Print any natural number. '))
for i in range(num):
name = str(i+1)
os.makedirs(name)
for a in range(i+1):
filename = os.path.join(name,str(a+1)+'.txt')
with open(filename, 'w', encoding = 'utf-8') as f:
f.write('')
import os
import shutil
filelist = [f for f in os.listdir() if os.path.isfile(f)]
print(filelist)
import os
import shutil
path = os.path.abspath('.')
path2 = os.getcwd()
universalpath = os.path.join('texts', '1.txt')
exists = os.path.exists('texts\1.txt')
exists2 = os.path.exists(os.path.join('texts', '1.txt'))
filelist = os.listdir(r'C:\My\HSE\programming\HSE_programming\HSE_programming\CWs\CW13\texts')
s = 'Hello! '
i = 1
for f in filelist:
if f.endswith('.txt'):
with open(f, 'a', encoding = 'utf-8') as w:
w.write(s*1)
i += 1
texts = [f for f in os.listdir(r'C:\My\HSE\programming\HSE_programming\HSE_programming\CWs\CW13\texts') if f.endswith('.txt')]
if not os.path.exists('ab'):
os.mkdir('ab')
if not os.path.exists(r'a\long\long\long\long\path'):
os.makedirs(r'a\long\long\long\long\path')
if os.path.exists('ab') and not os.path.exists('abc'):
os.rename('ab', 'abc')
if os.path.exists(r'a\long\long\long') and not os.path.exists(r'a\long\long\longer'):
os.rename(r'a\long\long\long', r'a\long\long\longer')
isfile = os.path.isfile(r'texts\1.txt')
isdir = os.path.isdir(r'a\long\long')
print(os.listdir())
shutil.copy(r'texts\1.txt', r'newcorpus')
shutil.copytree(r'texts', r'corpus')
shutil.move(r'texts\2.txt', r'newcorpus')
os.remove(r'corpus\2.txt')
shutil.rmtree('newcorpus')
shutil.rmtree('a')
shutil.rmtree('abc')
import os
import shutil
directory = input('Print any path working in your OS. ')
if os.path.exists(directory):
filelist = [f for f in os.listdir() if os.path.isfile(f)]
extlist = []
for f in filelist:
ext = f.split('.')[1]
if ext not in extlist:
extlist.append(ext)
extdict = {}
for ext in extlist:
for f in filelist:
if f.endswith(ext):
if ext not in extdict:
extdict[ext] = 1
else:
extdict[ext] +=1
else:
directory = os.getcwd()
print(extdict)
import re
def main():
with open ('hse.html', 'r', encoding = 'utf-8') as f:
text = f.read()
card_reg = ''
if re.search(card_reg, text):
card = re.search(card_reg, text).group()
t_reg = 'Преподаватели(?:.|\n)*?(.+?)<'
if re.search(t_reg, card):
profs = re.search(t_reg, card).group(1)
with open ('data about teachers.txt', 'a', encoding = 'utf-8') as f:
f.write(profs)
else:
print('No data about the nuber of professors found!')
with open ('data about teachers.txt', 'a', encoding = 'utf-8') as f:
f.write('No data about the nuber of professors found!')
else:
print('No card found in this article!')
with open ('data about teachers.txt', 'a', encoding = 'utf-8') as f:
f.write('No card found in this article!')
if __name__ == '__main__':
main()
import os
import re
def tagsaway(sentence):
s = ''
for word in sentence:
word = re.sub(u'<.+?>', u'', word)
s = s + word + ' '
return s
def get_bigramms(text):
bi = []
text = text.split('')
for i, word in enumerate(text):
if 'gr="A=' and 'gen' in word:
if i+1 < len(text):
w = text[i+1]
if 'gr="S,' and 'gen' in w:
result1 = re.search('(.+?)', word)
result2 = re.search('(.+?)', w)
bi.append([result1.group(1), result2.group(1), tagsaway(text)])
return bi
def newfile(arr):
f = open('bigramms.txt', 'w', encoding = 'utf8')
s = ''
for i in arr:
s = i[0] + '\t' + i[1] + '\t' + i[2] + '\n'
f.write(s)
s = ''
f.close
def filework():
folder = 'news'
for file in os.listdir(folder):
with open(os.path.join(folder, file)) as text:
text = text.read().split('')
for se in text:
newfile(get_bigramms(se))
def main ():
filework()
main()
import os
import re
def get_author (text):
for word in text:
if 'name="author"' in word:
result = re.search('content="(.+?)"', word)
return result.group(1)
def get_day (text):
for word in text:
if 'name="created"' in word:
result = re.search('content="(.+?)"', word)
return result.group(1)
def file_inf():
ff = []
folder = 'news'
for file in os.listdir(folder):
with open(os.path.join(folder, file)) as text:
text = text.read().split('<')
ff.append([file, get_author(text), get_day(text)])
return ff
def newfile(arr):
f = open('files_info.csv', 'w', encoding = 'utf8')
f.write('Название файла;Автор;Дата создания текста\n')
s = ''
for i in arr:
s = i[0] + ';' + i[1] + ';' + i[2] + '\n'
f.write(s)
s = ''
f.close
def main ():
ff = file_inf()
newfile(ff)
main()
import os
import re
def files():
ff = {}
folder = 'news'
for file in os.listdir(folder):
with open(os.path.join(folder, file)) as text:
words = re.findall('', text.read())
ff[file] = len(words)
return ff
def newfile(dic):
f = open('words_in_files.txt', 'w', encoding = 'utf8')
s = ''
for k in dic:
s = k + '\t' + str(dic[k]) + '\n'
f.write(s)
s = ''
f.close
def main ():
ff = files()
newfile(ff)
main()
import os
def findanddel (folder):
for root, dirs, files in os.walk(folder, topdown = False):
for f in files:
os.remove(os.path.join(root, f))
for d in dirs:
os.remove(os.path.join(root, d))
def main ():
folder = input()
findanddel (folder)
main ()
import os
def draw ():
for root, dirs, files in os.walk ('.'):
for d in dirs:
print ('\t'*root.count('\\'), '--',d)
for f in files:
print ('\t'*root.count('\\'), f)
def main ():
draw()
main ()
def pointsaway (file):
file = file.split()
for i, word in enumerate (file):
file[i] = file[i].strip('.,?!()*&^%$
file[i] = file[i].lower()
return file
def words (file):
slova = {}
for word in file:
if word in slova:
slova[word] += 1
else:
slova[word] = 1
return slova
def creation (dic):
f = open ('file.tsv', 'w', encoding = 'utf8')
arr = []
for k in dic:
arr.append(k)
arr.sort()
for i in arr:
f.write(i + '\t' + str(dic[i]) + '\n')
f.close()
def main ():
f = open ('file.txt', 'r', encoding = 'utf8')
file = f.read()
f.close()
text = pointsaway (file)
semua = words (text)
creation (semua)
main ()
def pointsaway (file):
file = file.split()
for i, word in enumerate (file):
file[i] = file[i].strip('.,?!()*&^%$
file[i] = file[i].lower()
return file
def creation (text):
f = open ('new.txt', 'w', encoding = 'utf8')
dic = {text[x]: x for x in range(0, len(text))}
arr = [k for k in dic]
arr.sort()
for i in arr:
f.write('{}\t{}\n'.format(i, str(dic[i])))
f.close()
def main ():
f = open ('file.txt', 'r', encoding = 'utf8')
file = f.read()
f.close()
text = pointsaway (file)
creation (text)
main ()
import re
def get_word (word):
result = re.search('.*?(\w+)', word)
if result:
return result.group(1)
else:
return None
def find_ins (text):
inst = {}
for i, word in enumerate(text):
if 'gr="S' in word:
if 'ins' in word:
inst[i]=word
return inst
def newfile (words, text):
f = open ('ins.txt', 'w', encoding = 'utf8')
s = ''
for k in words:
i = 0
j = 1
while i<3:
if get_word(text[k-j]) != None:
s = get_word(text[k-j])+ ' ' + s
i += 1
j += 1
else:
j += 1
s = s + '\t' + get_word(words[k]) + '\t'
i = 0
j = 1
while i<3:
if get_word(text[k+j]) != None:
s = s + ' ' + get_word(text[k+j])
i += 1
j += 1
else:
j +=1
f.write(s)
f.close
def main ():
f = open ('/home/woods/Загрузки/text.xml', 'r', encoding = 'utf8')
file = f.read()
text = file.split('\n')
f.close()
ss = find_ins(text)
newfile (ss, text)
main ()
import re
def find_and_count (file):
pos = {}
for word in file:
word = word.split('<')
for part in word:
result = re.search('.*?gr="(\w+)', part)
if result:
print (result.group(1))
if result.group(1) not in pos:
pos[result.group(1)] = 1
else:
pos[result.group(1)] += 1
return pos
def newfile (dic):
f = open('pos.txt', 'w', encoding = 'utf8')
s = ''
for k in dic:
s = s + k + '\t' + str(dic[k]) + '\n'
f.write(s)
f.close
def main ():
f = open ('/home/woods/Загрузки/text.xml', 'r', encoding = 'utf8')
file = f.read()
text = file.split('\n')
f.close()
pos = find_and_count(text)
newfile (pos)
main ()
import re
def find_w (file):
words = re.findall('', file)
n = len(words)
return n
def find_ana (file):
anas = re.findall('(.+?)', line)
if a:
if a.group(2) not in types:
types[a.group(2)] = 0
return types
def countthem (file, types):
words = []
sum = 0
for key in types:
words.append(key)
for el in words:
for line in file:
if '"'+el+'"' in line:
sum += 1
types[el] = sum
sum = 0
return types
def newfile (types):
s = ''
f = open('adj.txt', 'w', encoding = 'utf8')
for key in types:
s = s + key + '-' + str(types[key]) + '\n'
f.write(s)
f.close()
def main():
text = filework()
dic = findthem(text)
dic = countthem (text, dic)
newfile(dic)
main()
import random
file=open ('file_6.6.txt', 'r')
def noun():
nouns=[]
for line in file:
if ' n ' in line:
line=line.split(' ')
nouns.append(line[0])
file.seek(0, 0)
return random.choice(nouns)
def pronoun():
pronouns=[]
for line in file:
if ' pn ' in line:
line=line.split(' ')
pronouns.append(line[0])
file.seek(0, 0)
return random.choice(pronouns)
def verb():
verbs=[]
for line in file:
if ' v ' in line:
line=line.split(' ')
verbs.append(line[0])
file.seek(0, 0)
return random.choice(verbs)
def adjective ():
adjectives=[]
for line in file:
if ' adj ' in line:
line=line.split(' ')
adjectives.append(line[0])
file.seek(0, 0)
return random.choice(adjectives)
def suborob (n, adj, pn):
x=random.randint(0,1)
if x==0:
return pn
else:
y=random.randint(0,1)
if y==0:
return n+' '+adj
else:
return n+' '+pn
def declarative (subj, v, obj):
return subj.capitalize()+' '+v+' '+obj+'.'
def question (subj, v):
x=random.randint (0, 1)
if x==0:
return 'Apa'+' '+subj+' '+v+'?'
else:
return 'Siapa'+' '+v+'?'
def negative (subj, v, obj):
x=random.randint(0, 1)
if x==0:
return subj.capitalize()+' tidak '+v+' '+obj+'.'
else:
return subj.capitalize()+' bukan '+obj+'.'
def imperative (v, obj):
x=random.randint(0,1)
if x==0:
return v.capitalize()+' '+obj+'!'
else:
return 'Jangan '+v+' '+obj+'!'
def conditional (subj1, v1, obj1, subj2, v2, obj2):
return 'Kalau '+subj1+' '+v1+' '+obj1+', '+subj2+' '+v2+' '+obj2+'.'
def sequence ():
a=[1, 2, 3, 4, 5]
b=[]
for i in range (5):
x=random.choice(a)
while x in b:
x=random.choice(a)
b.append(x)
return b
def text():
seq=sequence()
for i in range (5):
if seq[i]==1:
print(declarative(suborob(noun(), adjective(), pronoun()), verb(), suborob(noun(), adjective(), pronoun())))
elif seq[i]==2:
print (question(suborob(noun(), adjective(), pronoun()), verb()))
elif seq[i]==3:
print (negative(suborob(noun(), adjective(), pronoun()), verb(), suborob(noun(), adjective(), pronoun())))
elif seq[i]==4:
print (imperative(verb(), suborob(noun(), adjective(), pronoun())))
else:
print (conditional(suborob(noun(), adjective(), pronoun()), verb(), suborob(noun(), adjective(), pronoun()), suborob(noun(), adjective(), pronoun()), verb(), suborob(noun(), adjective(), pronoun())))
text()
file.close()
import re
def search (text):
otr = re.search ('\n| Отряд: | \n(.+?) | \n
', text)
if otr:
result = otr.group(3)
return result
def main ():
f = open('file_10.6.html', 'r', encoding = 'utf8')
file = f.read()
f.close()
ans = search (file)
print (ans)
main()
def pointsaway (file):
file = file.replace('?!', '.')
file = file.split('.')
for i, word in enumerate (file):
file[i] = file[i].replace('.,?!()*&^%$
file[i] = file[i].replace('-- ', ' ')
file[i] = file[i].lower()
return file
def tenplus (text):
for sentence in text:
sentence = sentence.split()
n=0
s=0
for word in sentence:
word = word.strip('.,?!()*&^%$
s+=len(word)
n+=1
if n>10:
print ("Это предложение со словами длины %s"%(str(round(s/n, 1))))
def main ():
f = open ("file_12.6.txt", "r", encoding = "utf8")
file = f.read()
f.close()
text = pointsaway (file)
tenplus (text)
main ()
import random
def intothedic (file):
dic={}
for line in file:
line = line.split(';')
for j, word in enumerate(line):
line[j] = word.strip('\n')
dic[line[0]] = line[1]
return dic
def youchoose (dic):
keys = []
for key in dic:
keys.append(key)
return random.choice(keys)
def thegameison (noun, dic):
for key in dic:
if key == noun:
hint = dic[key]
n=key
break
print (hint, '...')
for i in range (3):
if input() == n:
print ('Победа!')
break
else:
if i == 0:
print ('Ещё 2 попытки')
continue
elif i == 1:
print ('Ещё 1 попытка')
continue
else:
print ('GAME OVER')
f = open('file_8.6.csv', 'r', encoding = 'utf8')
file = f.readlines()
f.close()
words = intothedic(file)
word = youchoose(words)
thegameison(word, words)
import re
def pointsaway (file):
file = file.split()
for i, word in enumerate (file):
file[i] = file[i].strip('.,?!()*&^%$
file[i] = file[i].lower()
return file
def findverbs (file):
verbs = []
for word in file:
if re.search ('загру(з(и.*|ят.*)|ж(у.*|ен.*))', word) != None:
if word not in verbs:
verbs.append(word)
return verbs
f = open ('file_9.6.txt', 'r', encoding = 'utf8')
file = f.read()
f.close()
file = pointsaway(file)
verbs = findverbs(file)
print (verbs)
def filework ():
f = open('corpus.txt', 'r', encoding = 'utf8')
file = f.readlines()
f.close()
return file
def newfile (text):
f = open('lines.txt', 'w', encoding = 'utf8')
f.write(str(len(text)))
f.close
def main():
text = filework()
newfile(text)
main()
import os
def names(array):
names = []
for name in array:
if os.path.isfile(name):
names.append(name)
return names
def haspoints(array):
points = ',!_-'
s = 0
su = 0
for name in array:
for c in name:
if c in points:
s += 1
if s > 0:
su += 1
s = 0
print ("Знаки препинания есть в названии такого количества файлов: ", su)
def main():
files = names (os.listdir('.'))
print (os.listdir('.'))
haspoints (files)
main()
a=input ('Введите число ')
for i in range (1, 11):
print (i, '*', a, '=', i*int(a))
xs=[]
for i in range (7):
xs.append(int(input()))
for i in range (7):
if xs[i]>0:
for j in range (xs[i]):
print ('x', end='')
print ('\n')
else:
print ('\n')
word=input()
l=len(word)
while l>0:
word=list(word)
x=word.pop(0)
print (''.join(word))
l=len(word)
def pointsaway (file):
file = file.split()
for i, word in enumerate (file):
file[i] = file[i].strip('.,?!()*&^%$
file[i] = file[i].lower()
return file
def findomni (file):
omni = []
for word in file:
if word.startswith('omni'):
w = word.replace('omni', '')
omni.append([word, w])
return omni
def findwords (array, file):
n = 0
m = 0
for i, k in enumerate (array):
for word in file:
if word == array[i][0]:
n += 1
if word == array[i][1]:
m += 1
print (array[i][0], n, '-', array[i][1], m)
n = 0
m = 0
def main ():
name = input('Введите имя файла ')
f = open (name, "r")
file = f.read()
f.close()
file = pointsaway (file)
findwords(findomni(file), file)
main()
import re
def filework():
f = open('corpus.txt', 'r', encoding = 'utf8')
file = f.readlines()
f.close()
return file
def findthem (file):
types = {}
for line in file:
a = re.search('(.+?)', line)
if a:
if a.group(2) not in types:
types[a.group(2)] = 0
return types
def countthem (file, types):
words = []
sum = 0
for key in types:
words.append(key)
for el in words:
for line in file:
if '"'+el+'"' in line:
sum += 1
types[el] = sum
sum = 0
return types
def newfile (types):
s = ''
f = open('types.txt', 'w', encoding = 'utf8')
for key in types:
s = s + key + '\n'
f.write(s)
f.close()
def main():
text = filework()
dic = findthem(text)
dic = countthem (text, dic)
newfile(dic)
main()
capital='АБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯ'
s=0
cap=0
f=open('file_5.6.txt', 'r', encoding='utf8')
file=f.readlines()
l=len(file)
for i in range (0, l):
file[i]=file[i].split(' ')
for i in range (0, l):
m=len(file[i])
for j in range (0, m):
if file[i][j][0] in capital:
cap+=1
s+=1
print ((cap/s)*100)
f.close()
import xml.etree.ElementTree as a
from os import walk
def sent(filename):
tree = a.parse('./news/'+file)
root = tree.getroot()
tmp = root.findall('.//se')
return(len(tmp))
def move(res,filename):
res_file = open(filename, 'w')
for item in res:
res_file.write(item+'\n')
f = []
words = []
p = './news';
for (dirpath, dirnames, filenames) in walk(p):
f.extend(filenames)
break
for file in f:
words.append(file+'\t'+str(sent(file)))
move(words,'counted.txt')
n=[]
while True:
word = input ('word:')
if word ==(''):break
elif word.endswith ('tur'):
n.append(word)
print ('/n'. join(n))
d={'Germany':'Berlin','France':'Paris',
'USA':'Washington DC',
'Russia':'Moscow'}
for key in d:
print (key+"*"+d[key])
def capital(a):
a=input("Country:")
if a in d:
return (d[a])
else: print ("oops")
def revert ():
k={}
countries=d.keys()
for key in countries:
k[d[key]]=key
return (k)
a=revert()
print(a)
with open ('fr.txt', 'r', encoding = 'utf-8') as a:
text=a.readlines()
for line in text:
if 'союз' in line:
print (line)
n = input("WORD: ")
m = len(n)//2
print (n[:m], n[:m-1:(-1)])
import os
import shutil
name=input ('напишите што-нибудь')
f_name=name.replace(' ', '\\')
os.makedirs(f_name)
n = input ('word:')
for i in range (len(n)):
print(n [-i-1::])
import re
def open_html('xenokeryx.html'):
with open ('xenokeryx.html', 'r', encoding='utf-8') as f:
content=f.read()
return content
def find_links (content):
reg=r'(.*?)'
links=re.findall (reg, content)
return links
text=open_html ('xenokeryx.html')
links=find_links(text)
for link in links [:20]:
print (link[1], '-->', link[0])
a=open (input(), 'r', encoding='utf-8')
b=0
c=0
for line in a:
arr=line.split()
b=b+len(arr)
for d in arr:
if len(d)>10:
c=c+1
a.close()
e=c/b*100
print (e, '%')
import os
def sup():
for root,dirs,files in os.walk('.'):
num=root.count('\\')
root+ root.split('\\')[-1]
print ('\t'*(num), root, sep='--')
for f in files:
print ('\t'*(num+1), f)
sup()
def opentext (file.txt):
forms = []
with open (file.txt, 'r', encoding='utf-8') as a:
text=a.read()
forms=text.split()
for i in range(len(forms)):
forms[i]=forms[i].strip(.,?!:;())
return forms
def word ():
a=opentext(file.txt)
b=[]
for i in range (len(a)):
if a[i][-1]=='s':
if a[i][-2]=='u':
if a[i][-3]=='o':
b.append(a[i])
print (b)
c=b.split()
d=str.count(c)
return d
import random
def noun ():
file=open('Mnoun.txt', 'r', encoding='utf-8')
f=readlines()
nouns=[]
for line in f:
nouns.append(line.split(" "))
return random.choise(nouns)
def verb ():
file=open ('verb1.txt', 'r', encoding='utf-8')
f=readlines()
verbs=[]
for line in f:
verbs.append(line.split(" "))
return random.choise(verbs)
def adj ():
file=open ('adj.txt', 'r', encoding='utf-8')
f=readlines()
adjectives=[]
for line in f:
adjectives.append(line.split(" "))
return random.choise(adjectives)
def noun2 ():
file=open ('noun2.txt','r', encoding='utf-8')
f=readlines()
plnouns=[]
for line in f:
plnouns.append(line.split(" "))
return random.choise(plnouns)
def conj():
conjs=["и", "или", "но", "да", "однако", "зато", "когда", "пока", "потому что", "чтобы", "то есть"]
return "," + random.choise(conjs)
def noun3 ():
file=open ('noun3.txt', 'r', encoding='utf-8')
f=readlines ()
fnouns=[]
for line in f:
fnouns.append (line.split(" "))
return random.choise(fnouns)
def 2verb ():
file=open ('2verb.txt', 'r', encoding ='utf-8')
f=readlines ()
2verbs=[]
for line in f:
2verbs.append (line.split(" "))
return random.choise (2verbs)
def sen ():
return (noun+" "+verb+" "+adj+" "+noun2+" "+conj+" "+noun3+" "+2verb+"."
for i in range(5):
print (sen())
import xml.etree.ElementTree as a
from os import walk
def sent(filename):
tree = a.parse('./news/'+file)
root = tree.getroot()
tmp = root.findall('.//se')
return(len(tmp))
def move(res,filename):
res_file = open(filename, 'w')
for item in res:
res_file.write(item+'\n')
f = []
words = []
p = './news';
for (dirpath, dirnames, filenames) in walk(p):
f.extend(filenames)
break
for file in f:
words.append(file+'\t'+str(sent(file)))
move(words,'counted.txt')
import xml.etree.ElementTree as a
from os import walk
import pandas as q
def second(filename):
tree = a.parse('./news/'+file)
root = tree.getroot()
name = root.find(".//*[@name='author']")
topic = root.find(".//*[@name='topic']")
return(name.attrib['content']+":"+topic.attrib['content'])
f = []
d = []
p = './news';
for (dirpath, dirnames, filenames) in walk(p):
f.extend(filenames)
for file in f:
tmp = second(file).split(':')
tmp_arr = [file,tmp[0],tmp[1]]
d.append(tmp_arr)
df = q.DataFrame(d,columns=["название","автор","тема"])
df.to_csv("2.csv", sep=';', encoding='windows-1251')
import re
def main ():
with open('F.xml', 'r', encoding='utf-8') as f:
text=f.readlines()
return text
n=main ()
m=len(n)
print (m)
import re
dic = {}
with open('f.xml') as f:
for row in f:
if(re.match(r'.*',row)):
arr = row.split("\"")
key = arr[3]
if key in dic:
dic[key]=dic[key]+1
else:
dic[key] = 1;
for key in dic.items():
print(key+" "+"\r\n")
import os
import shutil
folder='.'
print (os.listdir('.'))
for f in os.listdir('.'):
with open (os.path.join(folder, f)) as text:
print('file: ', f)
a=str_word_count(f, ' ')
filelist = [f for f in os.listdir('.') if os.path.isfile(f)]
if a>1:
print(filelist)
def open_format(crab):
a = []
with open (crab.txt, 'r', encoding = 'utf-8') as f:
text = f.read()
text = re.sub('\.\.\.|[\.\?]', '!', text)
a = text.split('!')[:-1]
for i in range(len(a)):
a[i] = re.sub('[<>\*\.«»,\'\"]','', a[i])
a[i] = a[i].strip()
return a
def repeat():
work=open_format (crab.txt)
words=re.findall(r'([a-zA-Z]+(?:[?:[\'-][a-zA-Z]+)*)',s)
res=[]
for x in range (a,z):
res.append (x)
print (res)
import os
os.listdir('.')
file_tree=os.walk('.')
names = {}
for root, dirs, files in os.walk('.'):
for f in files:
name = f.split('.')[0]
if name not in names:
names[name]=1
print(len(names))
import random
def noun ():
file=open('Mnoun.txt', 'r', encoding='utf-8')
f=readlines()
nouns=[]
for line in f:
nouns.append(line.split(" "))
return random.choise(nouns)
def verb ():
file=open ('verb1.txt', 'r', encoding='utf-8')
f=readlines()
verbs=[]
for line in f:
verbs.append(line.split(" "))
return random.choise(verbs)
def adj ():
file=open ('adj.txt', 'r', encoding='utf-8')
f=readlines()
adjectives=[]
for line in f:
adjectives.append(line.split(" "))
return random.choise(adjectives)
def noun2 ():
file=open ('noun2.txt','r', encoding='utf-8')
f=readlines()
plnouns=[]
for line in f:
plnouns.append(line.split(" "))
return random.choise(plnouns)
def conj():
conjs=["и", "или", "но", "да", "однако", "зато", "когда", "пока", "потому что", "чтобы", "то есть"]
return "," + random.choise(conjs)
def noun3 ():
file=open ('noun3.txt', 'r', encoding='utf-8')
f=readlines ()
fnouns=[]
for line in f:
fnouns.append (line.split(" "))
return random.choise(fnouns)
def 2verb ():
file=open ('2verb.txt', 'r', encoding ='utf-8')
f=readlines ()
2verbs=[]
for line in f:
2verbs.append (line.split(" "))
return random.choise (2verbs)
def sen ():
return (noun+" "+verb+" "+adj+" "+noun2+" "+conj+" "+noun3+" "+2verb+"."
for i in range(5):
print (sen())
import re
def main():
with open ('lemon.html', 'r', encoding='utf-8') as f:
text=f.read()
a='+?
'
if re.search (a, text):
card = re.search(a, text).group()
b='Семейство(?:.|\n)*?(.+?)'
if re.search(b, a):
с = re.search(b, a).group(1)
with open ('family.txt', 'a', encoding = 'utf-8') as f:
f.write(с)
else:
print('Family type not found.')
with open ('family.txt', 'a', encoding = 'utf-8') as f:
f.write('Family type not found.')
else:
print('Error!')
with open ('family.txt', 'a', encoding = 'utf-8') as f:
f.write('Error!')
import os
import re
def count_words():
with open('answer1.txt', 'w', encoding='utf-8') as fout:
for root, dirs, files in os.walk('./news'):
for f in files:
count = 0
with open(os.path.join(root, f), 'r') as fin:
f1 = fin.read().split()
for line in f1:
if '' in line:
count += 1
fout.write('%s \t %d \n' %(f, count))
def annot():
with open('answer2.csv', 'w', encoding='utf-8') as fout:
fout.write('Название файла \t Автор \t Дата создания')
for root, dirs, files in os.walk('./news'):
for f in files:
with open(os.path.join(root, f), 'r') as fin:
f2 = fin.read()
nam = f
reg1 = ''
reg2 = ''
auth = re.search(reg1, f2).group(1)
date = re.search(reg2, f2).group(1)
fout.write('%s \t %s \t %s \n' %(f, auth, date))
def bigramms():
with open('answer3.txt', 'w', encoding='utf-8') as fout:
for root, dirs, files in os.walk('./news'):
for f in files:
with open(os.path.join(root, f), 'r') as fin:
f3 = fin.read().split('\n')
reg = '(.+?)'
for indx, sentence in enumerate(f3):
if '' in sentence:
f3[indx] = [re.search(reg, sentence).group(1), re.search(reg, sentence).group(2)]
else:
f3.remove(sentence)
temp = True
for indx, word in enumerate(f3):
try:
if 'A' in word[0]:
if 'gen' in word[0]:
if 'S' in f3[indx + 1][0]:
if 'gen' in f3[indx + 1][0]:
fout.write('%s %s \n' %(word[1], f3[indx + 1][1]))
except IndexError:
temp = False
def main():
count_words()
annot()
bigramms()
if __name__ == '__main__':
main()
def done_text():
f = open('ostin.txt', 'r', encoding='utf-8')
s = f.read().lower().split()
f.close()
for indx, word in enumerate(s):
s[indx] = word.strip('.,:;№-*!?/|\[]{}()\'"1234567890«»><')
return s
def count_words(arr):
d = {}
for word in arr:
if word in d:
d[word] += 1
else:
d[word] = 1
return d
def count_letters(arr):
dic = {}
alpha = 'абвгдеёжзийклмнопрстуфхцчшщъыьэюя'
for letter in alpha:
dic[letter] = 0
for word in arr:
if word and word[0] in dic:
dic[word[0]] += 1
return dic
def count_pos(arr):
dic = {key:ind for ind, key in enumerate(arr)}
return dic
def create_antw(dic):
f = open('answer_keys2.tsv', 'w', encoding='UTF-8')
for key in sorted(dic):
f.write('{0}\t{1}\n'.format(key, str(dic[key])))
f.close()
def main():
textik = done_text()
create_antw(count_pos(textik))
if __name__ == '__main__':
main()
my_num = 9
your_num = int(input('Write a number from 1 to 10, please: '))
if your_num == my_num:
print('You\'re lucky one :D')
else:
if your_num > my_num:
print('Your number is too big')
else:
print('Your number is too small')
your_num = int(input('Try again: '))
if your_num == my_num:
print('You\'re lucky one :D')
else:
print('You\'re hopeless')
import re
def split_txt():
f = open('test1.txt', 'r', encoding='UTF-8')
s = f.read()
s.replace('\n', ' ')
s1 = re.sub('(\?|!|\.\.\.|([а-яa-z.]+ [а-яa-zА-ЯA-Z]{2,}\.))', '\\1^', s)
print(s1)
def main():
split_txt()
main()
import re
def find_space(fname):
f = open(fname, 'r', encoding='UTF-8')
s = f.read().split()
regex = '«[a-zA-ZА-Яа-я]+?-[0-9]'
wlist = re.findall(regex, s)
print(', '.join(wlist))
def main():
find_space('test.txt')
main()
coinc = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyzАБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯабвгдеёжзийклмнопрстуфхцчшщъыьэюя'
while True:
s = input('Введите текст: ')
if s == '':
break
s = s.split()
res = ''
if s[0] == 'decode':
s.pop(0)
s = ' '.join(s)
for letter in s:
if letter == '!':
res += ' '
else:
for indx, i in enumerate(coinc):
if i == letter:
if i == 'A':
res += 'Z'
elif i == 'a':
res += 'z'
elif i == 'А':
res += 'Я'
elif i == 'а':
res += 'я'
else:
res += coinc[indx - 1]
else:
if s[0] == 'code':
s.pop(0)
s = ' '.join(s)
for letter in s:
if letter == ' ':
res += '!'
else:
for indx, i in enumerate(coinc):
if i == letter:
if i == 'Z':
res += 'A'
elif i == 'z':
res += 'a'
elif i == 'Я':
res += 'А'
elif i == 'я':
res += 'а'
else:
res += coinc[indx + 1]
print (res)
print('Программа завершила свою работу!')
words=[]
check = True
while check is True:
inp = input("Введите слово: ")
if inp == "":
check = False
else:
words.append(inp)
for indx in range(len(words) - 1, -1, -1):
print(words[indx])
check = True
while check is True:
s = input("Введите текст: ")
if s == "":
check = False
else:
res = ""
for letter in s:
if ord(letter) == 90:
res += chr(65)
elif ord(letter) == 122:
res += chr(97)
elif ord(letter) == 1071:
res += chr(1040)
elif ord(letter) == 1103:
res += chr(1072)
else:
res += chr(ord(letter) + 1)
print (res)
print("Программа завершила работу")
names = ['Оля','Маша','Коля','Костя','Нина','Ира']
surnames=['Кузнецова', 'Сидорова', 'Семенов', 'Иванов', 'Илларионова']
if len(names) >= len(surnames):
for i in range(len(surnames)):
strng = names[i] + ' ' + surnames[i]
print(strng)
check = len(surnames)
while check < len(names):
print(names[check])
check += 1
else:
for i in range(len(names)):
strng = names[i] + ' ' + surnames[i]
print(strng)
check = len(names)
while check < len(surnames):
print(surnames[check])
check += 1
def doneText(fname):
f = open(fname, 'r')
s = f.read().split(' ')
for indx, word in enumerate(s):
s[indx] = word.lower().strip('.,:;№-*!?/|\[]{}()\'"')
f.close
return s
fnm = input('Введите имя файла: ')
arr = doneText(fnm)
print('Количество слов в тексте = {0}'.format(arr.len()))
my_num = 9
check = False
while (check == False):
try:
your_num = int(input('Write a number from 1 to 10, please: '))
except ValueError:
print("It's not a number, I'm out")
break
if your_num == my_num:
print('You\'re lucky one :D')
check = True
else:
if your_num > my_num:
print('Your number is too big')
else:
print('Your number is too small')
print("End of programme")
check = True
while check == True:
word = input('Write a word in cyrillic: ')
if word == "":
check = False
print("Empty word, I'm out")
else:
if word.endswith('о') or word.endswith('н') or word.endswith('р'):
print('Possible forms: Nom. Sg. / Acc. Sg.')
elif word.endswith('а'):
print('Possible forms: Gen. Sg. / Nom. Pl. / Acc. Pl.')
elif word.endswith('у'):
print('Possible forms: Dat. Sg.')
elif word.endswith('ом'):
print('Possible forms: Instrum. Sg. / Nom. Sg.')
elif word.endswith('е'):
print('Possible forms: Prep. Sg.')
elif word.endswith('ам'):
print('Possible forms: Dat. Pl.')
elif word.endswith('ами'):
print('Possible forms: Instrum. Pl.')
elif word.endswith('ах'):
print('Possible forms: Prep. Pl.')
elif word.endswith('и'):
print('Possible forms: Nom. Pl.')
else:
print('Possible forms: Gen. Pl.')
print('Thanks for using!')
import os
import re
def rem_dir(name_dir):
for root, dirs, files in os.walk('.', topdown=False):
if re.findall(os.sep + name_dir, root):
for f in files:
os.remove(os.path.join(root, f))
for d in dirs:
os.rmdir(os.path.join(root, d))
for d in dirs:
if name_dir == d:
os.rmdir(os.path.join(root, d))
def print_root():
s = '--'
for root, dirs, files in os.walk('.'):
print (s + root)
if len(dirs):
s = '\t' + s
for f in files:
print('\t{0}'.format(f))
def main():
rem_dir('wrong')
print_root()
if __name__ == '__main__':
main()
word = input('Write a word in cyrillic: ')
if word.endswith('о'):
print('Possible forms: Nom. Sg. / Acc. Sg.')
elif word.endswith('а'):
print('Possible forms: Gen. Sg. / Nom. Pl. / Acc. Pl.')
elif word.endswith('у'):
print('Possible forms: Dat. Sg.')
elif word.endswith('ом'):
print('Possible forms: Instrum. Sg.')
elif word.endswith('е'):
print('Possible forms: Prep. Sg.')
elif word.endswith('ам'):
print('Possible forms: Dat. Pl.')
elif word.endswith('ами'):
print('Possible forms: Instrum. Pl.')
elif word.endswith('ах'):
print('Possible forms: Prep. Pl.')
else:
print('Possible forms: Gen. Pl.')
import re
def done_text(fname):
f = open(fname, 'r', encoding='UTF-8')
s = f.read().split()
for indx, word in enumerate(s):
s[indx] = word.lower().strip('.,:;№-*!?/|\[]{}()\'"1234567890«»”“><')
f.close
return s
def print_words(s):
regex = '.*[ауоиыеюя].*[ауоиыеюя].*[ауоиыеюя].*'
for word in s:
if re.search(regex, word):
print(word)
def main():
textik = done_text(input('Введите имя файла с расширением: '))
print_words(textik)
main()
import os
import re
import math
from math import log
PUNCT = '[.,!«»?&@"$\[\]\(\):;%
def preprocessing(text):
text_wo_punct = re.sub(PUNCT, '', text.lower())
words = text_wo_punct.strip().split()
return words
def count_tf(word, text):
return text.count(word) / len(text)
def count_df(word, texts):
n = [1 for text in texts if word in text]
return sum(n)
def count_idf(word, texts):
n = len(texts) / (1 + count_df(word, texts))
return n
def count_tfidf(word, text, texts):
tf = count_tf(word, text)
idf = count_idf(word, texts)
return log(tf, 10) * log(idf, 10)
def get_texts():
texts_dic = {}
for root, dirs, files in os.walk('wikipedia'):
for f in files[:50]:
with open(os.path.join(root, f), 'r', encoding='utf-8') as t:
text = preprocessing(t.read())
texts_dic[f.split('.')[0]] = text
texts = list(texts_dic.values())
return texts_dic, texts
def fin_output(texts_dic, texts):
for text in texts_dic:
print("Top words in document {}".format(text))
scores = {}
for word in texts_dic[text]:
scores[word] = count_tfidf(word, texts_dic[text], texts)
sorted_words = sorted(scores.items(), key=lambda x: x[1])
for word, score in sorted_words[:5]:
print("\tWord: {}, TF-IDF: {}".format(word, round(score, 5)))
def main():
a = get_texts()
fin_output(a[0], a[1])
if __name__ == '__main__':
main()
check = True
coinc = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyzАБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯабвгдеёжзийклмнопрстуфхцчшщъыьэюя'
while check is True:
s = input('Введите текст: ')
if s == '':
check = False
else:
res = ''
for letter in s:
if letter == ' ':
res += ' '
else:
for indx, i in enumerate(coinc):
if i == letter:
if i == 'A':
res += 'Z'
elif i == 'a':
res += 'z'
elif i == 'А':
res += 'Я'
elif i == 'а':
res += 'я'
else:
res += coinc[indx - 1]
print (res)
print('Программа завершила свою работу!')
def done_text(fname):
f = open(fname, 'r')
s = f.read().split()
for indx, word in enumerate(s):
s[indx] = word.lower().strip('.,:;№-*!?/|\[]{}()\'"1234567890«»”“><')
f.close
return s
def freq_dic(arr):
dic = {}
for word in arr:
if word not in dic:
dic[word] = 1
else:
dic[word] += 1
return dic
def print_dic(dic):
for word in dic:
if dic[word] >= 10:
print(word, dic[word])
def main():
my_text = done_text(input('Введите имя файла с расшриением: '))
print_dic(freq_dic(my_text))
main()
def done_text(fname):
f = open(fname, 'r')
s = f.read().split()
for indx, word in enumerate(s):
s[indx] = word.lower().strip('.,:;№-*!?/|\[]{}()\'"1234567890«»><')
f.close
return s
def count_syll(arr, n):
res = []
voc = 'аоуыиеёюя'
for word in arr:
num = 0
for letter in word:
if letter in voc:
num += 1
if num == n:
res.append(word)
return res
def first_letter(arr, letter):
res = []
for word in arr:
if word.startswith(letter):
res.append(word)
return res
def choice():
fnm = input('Введите имя файла: ')
textik = done_text(fnm)
make_choice = input('Если хотите, чтобы программа считала слоги, введите syllables; иначе - letter: ')
if make_choice == 'syllables':
numb = int(input('Введите количество слогов в словах: '))
print(' '.join(count_syll(textik, numb)))
else:
lett = input('Введите желаемую первую букву: ')
print(' '.join(first_letter(textik, lett)))
def main():
choice()
main()
import os
def mk_ppk(s):
s = s.split()
pth = '.'
for word in s:
pth += os.sep + word
if not os.path.exists(pth):
os.makedirs(pth)
def mk_fls(num):
pth = '.'
for ppk in range(num):
pth += os.sep + str(ppk+1)
if not os.path.exists(pth):
os.makedirs(pth)
for pp_quant in range(ppk+1):
f = open(pth + os.sep + str(pp_quant + 1) + '.txt', 'w')
f.close()
pth = '.'
def prnt_dir(nm_dir):
for fl in os.listdir(nm_dir):
if os.path.isdir(fl):
print(fl)
def main():
mk_ppk(input('Введите приложение: '))
mk_fls(int(input('Введите число: ')))
prnt_dir('.')
if __name__ == '__main__':
main()
my_num = 9
check = False
your_num = int(input('Write a number from 1 to 10, please: '))
while(your_num != my_num):
if your_num > my_num:
print('Your number is too big')
else:
print('Your number is too small')
try:
your_num = int(input('Try again: '))
except ValueError:
print("Not a number")
check = True
break
if check == True:
print("See you next time")
else:
print("You're right")
check = True
coinc = 'ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyzАБВГДЕЁЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯабвгдеёжзийклмнопрстуфхцчшщъыьэюя'
while check is True:
s = input('Введите текст: ')
if s == '':
check = False
else:
res = ''
for letter in s:
if letter == ' ':
res += ' '
else:
for indx, i in enumerate(coinc):
if i == letter:
if i == 'Z':
res += 'A'
elif i == 'z':
res += 'a'
elif i == 'Я':
res += 'А'
elif i == 'я':
res += 'а'
else:
res += coinc[indx + 1]
print (res)
print('Программа завершила свою работу!')
f = open('freq_crlf.txt', 'r', encoding='utf-8')
s = f.read().split('\n')
f.close()
for line in s:
line = line.split(' | ')
if line[1] == 'союз':
print(' | '.join(line))
f = open('freq_crlf.txt', 'r', encoding='utf-8')
s = f.read().split('\n')
f.close()
arr = []
while True:
word = input('Введите слово: ')
if word == '':
print('Результаты:')
break
else:
arr.append(word)
for word in arr:
check = False
for line in s:
line = line.split(' | ')
if word == line[0]:
print(' | '.join(line))
check = True
if check is False:
print(u'{0}: Такого слова в словаре нет.'.format(word))
print('Завершение работы программы')f = open('freq_crlf.txt', 'r', encoding='utf-8')
s = f.read().split('\n')
f.close()
while True:
word = input('Введите слово: ')
if word == '':
print('Завершение работы программы')
break
else:
check = False
for line in s:
line = line.split(' | ')
if word == line[0]:
print(' | '.join(line))
check = True
if check is False:
print('Такого слова в словаре нет.')
import decimal
f = open('freq_crlf.txt', 'r', encoding='utf-8')
s = f.read().split('\n')
f.close()
ress = ''
ipm_sum = 0
for line in s:
line = line.split(' | ')
if line[1].find('ед жен') != -1:
ress += line[0]
ress += ', '
ipm_sum += decimal.Decimal(line[2])
print(ress)
print(u'Суммарное значение ipm = {0}'.format(ipm_sum))import re
def open_file():
f = open('islandic.xml', 'r', encoding='UTF-8')
s = f.read()
f.close()
return s
def count_lines():
s = open_file()
s = s.split('\n')
f = open('answer_length.txt', 'w', encoding='UTF-8')
f.write(str(len(s)))
f.close()
def my_diction(arr):
dix = {}
for word in arr:
if word in dix:
dix[word] += 1
else:
dix[word] = 1
return dix
def create_diction():
s = open_file()
regex = ''
arr = re.findall(regex, s)
dix = my_diction(arr)
f = open('answer_keys.txt', 'w', encoding='UTF-8')
f.write('Отсортированный список морфологических разборов:\n')
for key in sorted(dix):
f.write(key + '\n')
f.close()
def count_adj():
s = open_file()
regex = ''
arr = re.findall(regex, s)
dix = my_diction(arr)
f = open('answer_adj.txt', 'w', encoding='UTF-8')
for key in sorted(dix):
f.write(key + ' ' + str(dix[key]) + '\n')
f.close()
def create_csv():
s = open_file()
print(s)
regex1 = '(.+?)'
regex2 = '<.+?>\n'
s = re.sub(regex1, '\\1, \\2, \\3', s)
s = re.sub(regex2, '', s)
s = re.sub('( )+?', '', s)
s = s.split('\n')
f = open('answer_dict.csv', 'w', encoding='UTF-8')
for line in s:
f.write(line + '\n')
f.close()
def main():
count_lines()
create_diction()
count_adj()
create_csv()
if __name__ == '__main__':
main()
check = True
words = []
while check is True:
s = input("Введите слово: ")
if s == "":
check = False
else:
temp = []
for letter in s:
temp.append(letter)
words.append(temp)
for wrd in words:
for letterindx in range(2, len(wrd), 2):
if letterindx >= len(wrd):
break
wrd.pop(letterindx)
s = ""
for letterindx in range(len(wrd) - 1, -1, -1):
s += wrd[letterindx]
print(s)f = open('input.txt', 'r', encoding='UTF-8')
s = f.read().split('\n')
f.close()
avgsum = 0
for indx, line in enumerate(s):
s[indx] = line.split()
avgsum += len(s[indx])
print(u'Среднее количество слов в строке = {0}'.format(avgsum / len(s)))import re
word = input("Введите слово на кириллице: ")
pattern1 = r'[А-Яа-я]'
pattern2 = r'[1-9A-Za-z]'
if re.match(pattern1, word) and re.search(pattern2, word) is None:
for indx, letter in enumerate(word):
if indx % 2 != 0:
if letter != "а" and letter != "к":
print(letter)
else:
print("Вводить можно только кириллицу :Р")temp = False
while (temp == False):
try:
a = float(input('Введите первое число (a) '))
b = float(input('Введите второе число (b) '))
c = float(input('Введите третье число (c) '))
temp = True
except (TypeError, ValueError):
print('Просила же только числа вводить!')
if a + b == c:
print('Поздравляю! a + b = c')
else:
print('Прошу прощения, но a + b != c')
if a*c + b == 0:
print('Поздравляю! a*c + b = 0')
else:
print('Прошу прощения, но a*c + b != 0')import random
def ask_name():
return input('Введите имя файла с расширением: ')
def get_words():
f = open(ask_name(), 'r', encoding='UTF-8')
s = f.read().split('\n')
f.close()
dic = {}
for ln in s:
temp = ln.split(',')
dic[temp[0]] = temp[1:]
return dic
def guess_word(word):
num = len(word)
if num <= 4:
print('У вас {0} попытки'.format(num))
else:
print('У вас {0} попыток'.format(num))
while num > 0:
temp = input('Введите слово: ')
if temp == word:
print('Вы угадали!')
break
else:
print('Попробуйте еще раз!')
num -= 1
if num == 0:
print('Повезет в другой раз!')
def game(d):
num_check = 0
for k in d:
print('Подсказка! {0} ...'.format(random.choice(d[k])))
guess_word(k)
num_check += 1
if num_check == len(d):
print('Это было последнее слово. Приходите еще')
break
ask = input('Хотите попробовать еще раз? Введите только "да" или "нет": ')
if ask == 'нет':
break
def main():
d = get_words()
game(d)
main()def done_text(fname):
f = open(fname, 'r')
s = f.read().split()
for indx, word in enumerate(s):
s[indx] = word.lower().strip('.,:;№-*!?/|\[]{}()\'"1234567890«»><')
f.close
return s
def get_fname():
return input("Введите имя файла с расширением: ")
def count_ing(arr):
res = 0
for word in arr:
if word.endswith('ing'):
res += 1
return res
def count_form(arr, form):
res = 0
for word in arr:
if word == form:
res += 1
return res
def main():
textik = done_text(get_fname())
print('Всего в тексте {0} форм на -ing'.format(count_ing(textik)))
form = input('Введите форму, количество вхождений которой хотите найти: ')
print('Эта форма встречается {0} раз'.format(count_form(textik, form)))
main()import re
def search_inf(fname):
f = open(fname, 'r', encoding='UTF-8')
s = f.read()
f.close()
regex = '>Столица.*?([А-Яа-я]+(-[А-Яа-я]+)*)'
res = re.search(regex, s, re.DOTALL)
if res:
k = open('answer.txt', 'w', encoding='UTF-8')
print(res.group(1))
k.write(res.group(1))
k.close()
def main():
search_inf(input('Введите имя файла: '))
if __name__ == '__main__':
main()import re
def change_text():
f = open('mosq1.txt', 'r', encoding='UTF-8')
s = f.read()
f.close()
s1 = re.sub('Комар(»| |а|ы|у|ом|е|ов|ам|ами|ах)', 'Слон\\1', s)
s1 = re.sub('комар(»| |а|ы|у|ом|е|ов|ам|ами|ах)', 'слон\\1', s1)
f = open('antwort.txt', 'w', encoding='UTF-8')
f.write(s1)
f.close()
def main():
change_text()
if __name__ == '__main__':
main()import random
def generate_adj():
f = open('adj.txt', 'r')
s = f.read().split()
f.close()
return random.choice(s)
def generate_noun(num):
if num == 'sg':
f_name = 'noun_sg.txt'
else:
f_name = 'noun_pl.txt'
f = open(f_name, 'r')
s = f.read().split()
f.close()
return random.choice(s)
def generate_verb():
f = open('verbs.txt', 'r')
s = f.read().split()
f.close()
return random.choice(s)
def generate_punct(pos):
if pos == 'end':
f_name = 'end_punct.txt'
else:
f_name = 'mid_punct.txt'
f = open(f_name, 'r')
s = f.read().split()
f.close()
punct = random.choice(s)
if punct == '-':
punct = ' ' + punct
return punct
def generate_pronoun():
f = open('pronouns.txt', 'r')
s = f.read().split()
f.close()
return random.choice(s)
def generate_intj():
f = open('intj.txt', 'r')
s = f.read().split('\n')
f.close()
return random.choice(s)
def generate_line(num):
if num == 1:
return generate_adj() + ' ' + generate_noun('sg') + generate_punct('end') + '\n'
elif num == 2:
return generate_verb() + ' ' + generate_noun('pl') + ' и' + '\n'
else:
return generate_pronoun() + generate_punct('mid') + ' ' + generate_intj() + generate_punct('end') + '\n'
def generate_haiku():
return generate_line(1) + generate_line(2) + generate_line(3)
print(generate_haiku())import re
def done_text(fname):
f = open(fname, 'r', encoding='UTF-8')
s = f.read().lower()
rez1 = '(,|:|№|-|\*|/|\||\[|\]|{|}|\\|(|)|\'|"|[0-9]|«|»|>|<|V|I|X)+'
s = re.sub(rez1, ' ', s)
rez = '\.|\?|!|\.\.\.'
s = re.split(rez, s)
f.close()
for indx, sent in enumerate(s):
s[indx] = sent.split()
if len(s[indx]) == 0:
s.pop(indx)
return s
def count_letters(arr):
mlist = [(indx + 1, word, len(word)) for indx, senten in enumerate(arr) for word in senten if len(word) >= 7]
f = open('answer_sheet12.txt', 'w', encoding='UTF-8')
for k in mlist:
f.write('предложение {0}, {1}-------{2}\n'.format(k[0], k[1], k[2]))
f.close()
def main():
count_letters(done_text('tolstoy.txt'))
if __name__ == '__main__':
main()import os
import re
def count_dirs():
res = '[0-9]'
arr = [thing for thing in os.listdir('.') if os.path.isdir(thing) and len(re.findall(res, thing))]
return arr
def print_answer(arr):
fout = open('answer_sheet13.txt', 'w', encoding='UTF-8')
fout.write('Всего папок с цифрами в названии - {0}.'.format(str(len(arr))))
fout.write('Все имена в директории (без повторений):\n')
clear_names = []
for thing in os.listdir('.'):
temp = thing
if os.path.isfile(thing):
temp = re.sub('\..+', '', thing)
if temp not in clear_names:
clear_names.append(temp)
for nme in clear_names:
if nme:
fout.write(nme + '\n')
fout.close()
def main():
print_answer(count_dirs())
if __name__ == '__main__':
main()import os
def count_dep():
count = 0
for root, dirs, files in os.walk('.', topdown=False):
if len(root.split(os.sep)) - 1 > count:
count = len(root.split(os.sep)) - 1
with open('answer_sheet14.txt', 'w', encoding='UTF-8') as answer:
answer.write(str(count))
def main():
count_dep()
if __name__ == '__main__':
main()while True:
s = input("Введите строку: ")
if s == "":
break
for indx, part in enumerate(s):
print(s[:len(s) - indx])s = input("Введите строку: ")
for indx, part in enumerate(s):
print(s[:len(s) - indx])import re
def ask_name():
return input('Введите имя файла с расширением: ')
def get_words():
f = open(ask_name(), 'r', encoding='UTF-8')
s = f.read().split()
for indx, word in enumerate(s):
s[indx] = word.lower().strip('.,:;№-*!?/|\[]{}()\'"1234567890«»><')
f.close
return s
def count_words(words):
regex = 'откр(ы|о)((т(ый|ая|ое|ые|ого|ой|ых|ому|ым|ую|ом|ою)|в(ш(ий?|ая|ее|ие|его|ей|их|ему|им|ую|ею))?)|(л(а|о|и)?)|(й(те)?)|(ют?|е(шь|м|те?)))(ся|сь)?'
wlist = []
for word in words:
if re.fullmatch(regex, word):
if word not in wlist:
wlist.append(word)
return wlist
def main():
print(', '.join(count_words(get_words())))
main()word = input('Введите слово: ')
if word == '':
print ('Слово не введено')
word2 = ''
for i in range(len(word)):
for k in range(len(word)):
if k + i < len(word):
word2 += word[k + i]
else:
word2 += word[k + i - len(word)]
print (word2)
word2 = ''
import re
def open_and_edit():
f = open("verbs.txt", 'r', encoding = "utf-8")
s = f.read()
f.close()
s1 = s.lower()
a = s1.split()
for i, word in enumerate(a):
a[i] = word.strip('.,!?();:*/\|<>-_%&
return a
def find_and_print(a):
arr = []
for word in a:
if re.search('^программир((у(ю(т|щ(и(й|ми?|е|х)|е(го|му?|й)|ая|ую))?|я|е(шь|те?))|ова(л(а|и)?|ть))(с(я|ь))?|уем(ы(й|ми?|е|х)?|о(го|му?|й)|ая?|ую))', word):
if word not in arr:
arr.append(word)
for verb in arr:
print(verb)
def main():
text = open_and_edit()
find_and_print(text)
main()
import re
import os
def task1():
for root, dirs, files in os.walk('.\\news'):
s = ''
for f in files:
file = open(os.path.join(root, f), 'r', encoding = "WINDOWS-1251")
text = file.readlines()
words = 0
for line in text:
reg = ''
r = re.search(reg,line)
if r:
words += 1
s += f + '\t' + str(words) + '\n'
f2 = open("words_in_files.txt", 'w', encoding = "utf-8")
f2.write(s)
def task2():
for root, dirs, files in os.walk('.\\news'):
s = ''
for f in files:
file = open(os.path.join(root, f), 'r', encoding = "WINDOWS-1251")
text = file.readlines()
author = ''
date = ''
for line in text:
reg_author = 'content="([ |(а-яА-яa-zA-Z)]+)" name="author"'
reg_date = 'content="([0-9]+\.[0-9]+\.[0-9]+)" name="created"'
r1 = re.search(reg_author, line)
if r1:
author = r1.group(1)
r2 = re.search(reg_date, line)
if r2:
date = r2.group(1)
s += f + '\t' + author + '\t' + date + '\n'
f3 = open("words_in_files.csv", 'w', encoding = "utf-8")
f3.write(s)
def task3():
for root, dirs, files in os.walk('.\\news'):
s = ''
for f in files:
file = open(os.path.join(root, f), 'r', encoding = "WINDOWS-1251")
text = file.readlines()
for i, line in enumerate(text):
reg_adj = 'A=.+gen.+>?'
reg_sumj = 'S,.+gen.+>?'
reg_word = '([а-яА-Я]+|`)\n'
r1 = re.search(reg_adj, line)
if r1:
r2 = re.search(reg_word, line)
word1 = r2.group(1)
r3 = re.search(reg_subj, text[i+1])
if r3:
word2 = r3.group(1)
def main():
task1()
task2()
main()
import re
def open_and_edit():
f = open("linguistics.txt", 'r', encoding = "utf-8")
s = f.read()
f.close()
return s
def replace_and_output(s):
s1 = re.sub('язык([а-я]{,3}( |\.|,|\)))','шашлык\\1', s)
s2 = re.sub('Язык([а-я]{,3}( |\.|,|\)))','Шашлык\\1', s1)
f = open("shashlyk.txt", 'w', encoding = "utf-8")
f.write(s2)
print('Текст записан в файл shashlyk.txt')
f.close()
def main():
text = open_and_edit()
replace_and_output(text)
main()
import os
import re
def count_folders():
result = 0
for f in os.listdir('.'):
if os.path.isdir(f):
if re.search('^([а-яА-Я]| )+$',f):
result += 1
print('Найдено папок:',result)
def print_names():
names = {}
file_name = '^(.+)(\.[a-z]+)$'
for f in os.listdir('.'):
if os.path.isdir(f):
if f not in names:
names[f] = 1
if os.path.isfile(f):
r = re.search(file_name,f)
if r:
name = r.group(1)
if name not in names:
names[name] = 1
for name in sorted(names):
print(name)
def main():
count_folders()
print_names()
main()
def read_file():
f = open("words.csv", 'r', encoding = "utf-8")
a = f.readlines()
f.close()
return(a)
def make_dict(a):
words = {}
for line in a:
a2 = line.split(';')
for i, h in enumerate(a2):
a2[i] = h.strip()
words[a2[1]] = a2[0]
return words
def guess(dic):
for noun in dic:
print(dic[noun], '...')
attempt = 0
while attempt != len(dic[noun]):
print('Осталось попыток: ', len(dic[noun]) - attempt )
attempt += 1
if input() == noun:
print('Маладэц!')
attempt = len(dic[noun])
elif len(dic[noun]) - attempt == 0:
print('Не угадал :(')
def main():
text = read_file()
words = make_dict(text)
print(words)
guess(words)
main()
import re
def open_and_edit():
f = open("hse.html", 'r', encoding = "utf-8")
s = f.read()
f.close()
return s
def find_and_print(s):
reg1 = 'Преподаватели.*?\n.*?\n[0-9]+ ?[0-9]+'
reg2 = 'Преподаватели.*?\n.*?\n
'
res1 = re.findall(reg1,s)
res2 = re.findall(reg2,s)
number = res1[0].replace(res2[0], '')
print('Число преподавателей:',number)
f = open("found_number.txt", 'w', encoding = "utf-8")
f.write(number)
f.close()
def main():
text = open_and_edit()
find_and_print(text)
main()
words = []
while True:
newword = input('Введите слово: ')
if newword == '':
break
else:
words.append(newword)
for i in range(len(words)):
string = words[i]
if (i+1) >= len(string):
print('В этом слове не осталось символов')
else:
print(string[i+1:])
a = input ('Введите число a: ')
b = input ('Введите число b: ')
c = input ('Введите число c: ')
a = int (a)
b = int (b)
c = int (c)
if a % b == c:
print ('a дает остаток c при делении на b')
else:
print ('a не дает остаток c при делении на b')
if a * c + b == 0:
print ('c является решением линейного уравнения ax + b = 0')
else:
print ('c не является решением линейного уравнения ax + b = 0')
import random
def open_file():
f = open("words.txt", 'r', encoding = "utf-8")
text = f.readlines()
f.close()
return(text)
def find_words(word,text):
for i in range(len(text)):
line = []
line = text[i].split()
for l, w in enumerate(line):
line[l] = w.strip('.,!?();:*/\|<>-_%&
if line[0] == word:
words = []
for j in range(len(line)):
if j > 0:
words.append(line[j])
return(words)
def noun():
find = 'существительное'
nouns = find_words(find, text)
return random.choice(nouns)
def imperative():
find = 'императив'
imper = find_words(find, text)
return random.choice(imper)
def adverb(imp):
find = 'наречие'
adverbs = find_words(find, text)
return random.choice(adverbs) + ' ' + imp
def verb():
find = 'глагол'
verbs = find_words(find, text)
return random.choice(verbs)
def adjective():
find = 'прилагательное'
adj = find_words(find, text)
return random.choice(adj)
def question_word():
find = 'вопрос'
quest = find_words(find, text)
return random.choice(quest)
def pos_sentence():
sentence = adjective() + ' ' + noun() + ' ' + verb() +\
' ' + adjective() + ' ' + noun() + '.'
sentence = sentence.capitalize()
return(sentence)
def neg_sentence():
sentence = adjective() + ' ' + noun() + ' не ' + verb() +\
' ' + adjective() + ' ' + noun() + '.'
sentence = sentence.capitalize()
return(sentence)
def quest_sentence():
sentence = question_word()+ ' ' + adjective() + ' ' + noun() +\
' ' + verb() + ' ' + adjective() + ' ' + noun() + '?'
sentence = sentence.capitalize()
return(sentence)
def imper_sentence():
sentence = adverb(imperative()) + ' ' + noun() + '!'
sentence = sentence.capitalize()
return(sentence)
def if_sentence():
sentence = 'если бы ' + noun() + ' ' + verb() + ' ' + noun() +\
', то ' + noun() + ' ' + verb() + ' бы ' + noun() + '.'
sentence = sentence.capitalize()
return(sentence)
def random_print():
spisok = [pos_sentence(), neg_sentence(), quest_sentence(),\
imper_sentence(), if_sentence()]
random.shuffle(spisok)
for i in range(len(spisok)):
print(spisok[i], end = ' ')
text = open_file()
random_print()
word = input ('Введите слово: ')
indx = len(word)-1
while indx >= 0:
if (word[indx]!= 'я') & (word[indx]!= 'з') :
print (word[indx])
indx -= 1
import os
import re
def extensions():
ext_count = {}
for root, dirs, files in os.walk('.'):
for file in files:
ext = re.findall('\.[a-z0-9A-Z]+$', file)
if ext[0] not in ext_count:
ext_count[ext[0]] = 1
else:
ext_count[ext[0]] += 1
numb = 0
found_ext = ''
for ext in ext_count:
if ext_count[ext] > numb:
numb = ext_count[ext]
found_ext = ext
print(found_ext)
def main():
extensions()
main()
import re
def open_and_read():
f = open("animal_farm.txt", 'r', encoding = "utf-8")
s = f.read()
f.close()
return s
def read_sentences(s):
s1 = re.sub('[a-z](\.|!|\?)','\\1@@', s)
a = s1.split('@@')
return a
def split_and_count(a):
for i in range(len(a)):
words = a[i].split()
words2 = [words[j].strip('.,!?();:*/\|<>-_%&
for word in range(len(words2)):
print('%s_%s' %(words2[word], len(words2[word])))
def main():
text = open_and_read()
sent = read_sentences(text)
split_and_count(sent)
main()
f = open("1.txt", 'r', encoding = "utf-8")
word1 = 0
word3 = 0
for line in f:
words = line.split()
for i in range(len(words)):
if len(words[i]) == 3:
word3 += 1
elif len(words[i]) == 1:
word1 += 1
words = []
if word1 == 0:
print("Нет слов длинны 1")
else:
print(float(word3)/float(word1))
def open_and_edit():
name = input('Введите название файла: ')
f = open(name, 'r', encoding = "utf-8")
s = f.read()
f.close()
s1 = s.lower()
a = s1.split()
for i, word in enumerate(a):
a[i] = word.strip('.,!?();:*/\|<>-_%&
return a
def find_in_text(t):
hood = []
for word in t:
if word.endswith('hood'):
hood.append(word)
print('В тексте нашлось ', len(hood), ' существительных с суффиксом -hood')
return hood
def short_list(arr):
short = []
arr2 = []
for k in arr:
arr2.append(k)
for i in range(len(arr2)-1):
if arr2[i]:
short.append(arr2[i])
x = 1
for j in range(i+1, len(arr2)):
if arr2[i]:
if arr2[i] == arr2[j]:
x += 1
arr2[j] = []
short.append(x)
return short
def min_freq(arr):
short = short_list(arr)
min = short[1]
index = 1
for k in range(1, len(short), 2):
if short[k] < min:
index = k
min = short[k]
print('Минимальную частотность имеет существительное', short[index-1])
def print_nouns(arr):
nouns = []
short = short_list(arr)
for word in short:
if type(word) != int:
nouns.append(word.replace('hood', ''))
all_nouns = ', '.join(nouns)
print('Найденный слова образованы от существительных ', all_nouns)
def main():
text = open_and_edit()
found = find_in_text(text)
min_freq(found)
print_nouns(found)
main()
f = open("aphor.txt", 'r', encoding = "utf-8")
a = f.readlines()
f.close()
for i in range(len(a)):
words = []
words = a[i].split()
numb = 0
for j in range(len(words)):
if words[j] != '—':
numb += 1
if numb < 16:
print(a[i])
author = []
um = 0
for i in range(len(a)):
words = []
words = a[i].split()
for l, word in enumerate(words):
words[l] = word.strip('.,!?();:*/\|<>-_%&
for j in range(len(words)):
if words[j] == 'ум':
um += 1
povtor = 0
for k in range(len(author)):
if author[k] == words[len(words)-1]:
povtor += 1
if povtor == 0:
author.append(words[len(words)-1])
out = ''
out = ', '.join(author)
print('Количество цитат = ', um)
print('Источники: ', out)
inp_words = []
while True:
newword = input('Введите слово: ')
if newword == '':
break
else:
inp_words.append(newword)
for j in range(len(inp_words)):
found = 0
print(inp_words[j])
for i in range(len(a)):
words = []
words = a[i].split()
for l, word in enumerate(words):
words[l] = word.strip('.,!?();:*/\|<>-_%&
for k in range(len(words)):
if inp_words[j] == words[k]:
print(a[i])
found += 1
break
if found == 0:
print('Цитата с этим словом не найдена')
import re
def open_file():
f = open("file.txt", 'r', encoding = "utf-8")
a = []
for line in f:
a.append(line)
f.close()
return a
def open_new_file():
f = open("created_file.txt", 'w', encoding = "utf-8")
return f
def write_lines_number(a,f):
i = 0
for line in a:
i += 1
f.write(str(i))
f.write('\n')
def create_dictionary(a,f):
dic = {}
for line in a:
if '= 5:\n'))
while n < 5:
n = int(input('Введённое число < 5. Пожалуйста, введите число >= 5:\n'))
return n
def func3(dic, n):
for i in range(n):
key = random.choice(list(dic.keys()))
m = 3
print(i + 1, '-ое слово. ', 'Подсказка: ', random.choice(dic[key]), ' ...', sep = '')
fl = 0
while fl != 1 and m != 0:
print('Попыток осталось: ', m, sep = '')
if input('Введите ниже ваш ответ:\n').lower() == key:
fl = 1
print('Молодец! Всё верно!')
else:
print('Неверно. ', end = '')
if m != 1:
print('Ещё одна подсказка: ', random.choice(dic[key]), ' ...', sep = '')
m -= 1
if fl == 0:
print('Вы не угадали. Правильный ответ: ', key, sep = '')
def main():
dic = func1(input('Введите, пожалуйста, название файла:\n'))
n = func2()
func3(dic, n)
main()
def func1(name):
f = open(name, 'r', encoding = 'utf-8', errors = 'ignore')
words = f.read().replace('\n', ' ').split()
f.close()
for i, word in enumerate(words):
words[i] = word.lower().strip('.”“,/1234567890@
return words
def func3(words, word):
fl = 0
num = 0
while fl != 1:
try:
ind = words.index(word)
except ValueError:
fl = 1
continue
num += 1
words.pop(ind)
print(word, ': frequency = ', num, sep = '')
return words
def func2(words):
prefix = 'omni'
length = len(prefix)
for word in words:
if word.startswith(prefix) and length < len(word):
words = func3(words, word)
words = func3(words, word[length:])
print('-------------------------------------')
def main():
func2(func1('file.txt'))
main()
def func1(name):
f = open(name, 'r', encoding = 'utf-8', errors = 'ignore')
words = f.read().replace('\n', ' ').split()
f.close()
for i, word in enumerate(words):
words[i] = word.lower().strip('.”“,/1234567890@
return words
def func3(words, word):
num = 0
for elem in words:
if elem == word:
num += 1
print(word, ': frequency = ', num, sep = '')
def func2(words):
prefix = 'under'
length = len(prefix)
l = []
for word in words:
if word.startswith(prefix) and length < len(word) and word not in l:
func3(words, word)
func3(words, word[length:])
print('-------------------------------------')
l.append(word)
def main():
func2(func1('file.txt'))
main()
import os
def files_and_folders():
lst = os.listdir('.')
files = []
folders = []
for f in lst:
if os.path.isfile(f):
files.append(f)
else:
folders.append(f)
d_files = {}
for f in files:
f_name, f_ext = os.path.splitext(f)
if f_name not in d_files:
d_files[f_name] = 1
else:
d_files[f_name] += 1
return d_files, folders
def counting(d_files):
num = 0
punct_marks = '.!?:;,-()"\'<>'
for key in d_files:
fl = 0
i = 0
while fl != 1 and i < len(punct_marks):
if punct_marks[i] in key:
fl = 1
i += 1
if fl == 1:
num += d_files[key]
return num
def output(num, d_files, d_folders):
print('Количество файлов, названия которых содержит знаки препинания = ', num)
print('Названия файлов и папок в данной папке следующие:')
i = 1
for key in d_files:
print('%s) %s' % (str(i), str(key)))
i += 1
for key in d_folders:
if key not in d_files:
print('{}) {}'.format(str(i), str(key)))
i += 1
def main():
d_files, folders = files_and_folders()
num = counting(d_files)
output(num, d_files, folders)
if __name__ == '__main__':
main()
import os
def walking():
num = 0
for root, dirs, files in os.walk('.'):
d_files = {}
flag = False
for file in files:
file_name, file_ext = os.path.splitext(file)
if file_ext not in d_files:
d_files[file_ext] = 1
else:
flag = True
break
if flag:
num += 1
return num
def main():
num = walking()
print('Количество папок, в которых встречаются несколько файлов с одним\
и тем же расширением = {}.'.format(num))
if __name__ == '__main__':
main()
import os
def walking():
num = 0
for root, dirs, files in os.walk('.'):
d_files = {}
flag = False
for file in files:
file_name, file_ext = os.path.splitext(file)
if file_ext not in d_files:
d_files[file_ext] = 1
else:
flag = True
print(file)
break
if not flag:
num += 1
return num
def main():
num = walking()
print('Количество папок, в которых встречаются несколько файлов с одним\
и тем же расширением = {}.'.format(num))
if __name__ == '__main__':
main()
import re
def reading(name):
f = open(name, 'r', encoding = 'utf-8')
words = f.read().split(' ')
f.close()
return words
def cleaning(words):
for i, word in enumerate(words) :
words[i] = word.lower().strip('.,/1234567890@
return words
def printing(words):
l = []
for word in words:
if re.search('кот', word) and word not in l:
l.append(word)
print(word)
def main():
words = reading(input('Введите, пожалуйста, название файла:\n'))
words = cleaning(words)
printing(words)
if __name__ == '__main__':
main()
n = float(input('Введите любое число\n'))
print('число | ', n)
for i in range(9 + len(str(round(n * 10, 3)))) :
print('-', end = '')
print()
for i in range(1,11) :
if i != 10 :
print(i, ' | ', round(i * n, 3), end = '\n')
else :
print(i, ' | ', round(i * n, 3), end = '\n')
n = float(input('Введите любое число\n'))
for i in range(1,11) :
print(i, '*', n, '=', i * n, end = '\n')
import re
def reading(name):
f = open(name, 'r', encoding = 'utf-8')
lines = f.readlines()
f.close()
return lines
def array(lines):
text = ''.join(lines)
text = re.sub('((.|\n)*)', '\\1', text)
text = re.sub('<[wc](.*?)>(.*?)', '\\1 \\2', text)
print(text)
l = re.findall('lemma="(.*?)" type="(.*?)" (.*)', text)
return l
def recording1(d, n):
f = open(input('Введите, пожалуйста, название выходного файла\n'), 'a', encoding = 'utf-8')
f.write(str(n) + '\n')
for key in d.keys():
f.write(key + '\n')
f.close()
def recording2(d):
f = open(input('Введите, пожалуйста, название выходного файла\n'), 'a', encoding = 'utf-8')
for key, value in d.items():
if re.search('l.f.*', key):
f.write(key + ' - ' + str(value) + '\n')
f.close()
def recording3(l):
name = input('Введите, пожалуйста, название выходного файла в формате csv\n')
while not name.endswith('.csv'):
name = input('Введите, пожалуйста, название выходного файла в формате csv\n')
f = open(name, 'a', encoding = 'utf-8')
for i, elem in enumerate(l):
f.write(elem[0] + ',' + elem[1] + ',' + elem[2] + '\n')
f.close()
def dictionary(lines):
d = {}
for line in lines:
r = re.search('lemma=".*" type="(.*)"', line)
if r:
key = r.group(1)
if key in d:
d[key] += 1
else:
d[key] = 1
return d
def main():
name = input('Введите, пожалуйста, название входного файла\n')
lines = reading(name)
n = len(lines)
d = dictionary(lines)
recording1(d, n)
recording2(d)
l = array(lines)
recording3(l)
if __name__== '__main__':
main()
import random
def noun() :
f = open('nouns.txt', 'r', encoding = 'utf-8')
nouns = f.read().split()
f.close()
return random.choice(nouns)
def personal_pronoun() :
f = open('personal_pronouns.txt', 'r', encoding = 'utf-8')
pronouns = f.read().split()
f.close()
return random.choice(pronouns)
def adjective_before_noun() :
f = open('adjectives_before_noun.txt', 'r', encoding = 'utf-8')
adj = f.read().split()
f.close()
return random.choice(adj)
def adjective_after_noun() :
f = open('adjectives_after_noun.txt', 'r', encoding = 'utf-8')
adj = f.read().split()
f.close()
return random.choice(adj)
def adverb() :
f = open('adverbs.txt', 'r', encoding = 'utf-8')
adverbs = f.read().split()
f.close()
return random.choice(adverbs)
def intensifier(adv):
f = open('intensifiers.txt', 'r', encoding = 'utf-8')
intensifiers = f.read().split()
f.close()
return random.choice(intensifiers) + ' ' + adv
def transitive_infinitive() :
f = open('transitive_infinitives.txt', 'r', encoding = 'utf-8')
inf = f.read().split()
f.close()
return random.choice(inf)
def intransitive_infinitive() :
f = open('intransitive_infinitives.txt', 'r', encoding = 'utf-8')
inf = f.read().split()
f.close()
return random.choice(inf)
def temporary_marker() :
f = open('temporary_markers.txt', 'r', encoding = 'utf-8')
temporary_markers = f.read().split()
f.close()
return random.choice(temporary_markers)
def interrogative() :
f = open('interrogatives.txt', 'r', encoding = 'utf-8')
interrogatives = f.read().split()
f.close()
return random.choice(interrogatives)
def number() :
f = open('numbers.txt', 'r', encoding = 'utf-8')
numbers = f.read().split()
f.close()
return random.choice(numbers)
def declension(noun, adjective, number) :
f = open('declension_of_nouns.txt', 'r', encoding = 'utf-8')
g = open('declension_of_adjectives.txt', 'r', encoding = 'utf-8')
nouns = dict()
adjectives = dict()
for line in f.readlines() :
s = line.split(' ', maxsplit = 1)
nouns[s[0]] = s[1].split()
for line in g.readlines() :
s = line.split(' ', maxsplit = 1)
adjectives[s[0]] = s[1].split()
f.close()
g.close()
if nouns[noun][0] == 'm' and number == 'sg' :
return noun, adjective, random.choice(['le', 'un'])
elif nouns[noun][0] == 'm' and number == 'pl' :
return nouns[noun][1], adjectives[adjective][1], random.choice(['les', 'des'])
elif nouns[noun][0] == 'f' and number == 'sg' :
return noun, adjectives[adjective][0], random.choice(['la', 'une'])
elif nouns[noun][0] == 'f' and number == 'pl' :
return nouns[noun][1], adjectives[adjective][2], random.choice(['les', 'des'])
def collocation_bef(noun, adj_before_noun, article) :
return article + ' ' + adj_before_noun + ' ' + noun
def collocation_aft(noun, adj_after_noun, article) :
return article + ' ' + noun + ' ' + adj_after_noun
def conjugation(pronoun, infinitive) :
f = open('conjugations.txt', 'r', encoding = 'utf-8')
verbs = dict()
for line in f.readlines() :
s = line.split(' ', maxsplit = 1)
verbs[s[0]] = s[1].split()
f.close()
if pronoun == 'je' :
return verbs[infinitive][0]
elif pronoun == 'tu' :
return verbs[infinitive][1]
elif pronoun == 'il' or pronoun == 'elle' :
return verbs[infinitive][2]
elif pronoun == 'nous' :
return verbs[infinitive][3]
elif pronoun == 'vous' :
return verbs[infinitive][4]
else :
return verbs[infinitive][5]
def affirmative_sequence(pronoun, verb) :
if verb[0] in 'aàâeéèêiîoôuùûy' and pronoun == 'je' :
return "j'" + verb
else :
return pronoun + ' ' + verb
def interrogative_sequence(pronoun, verb) :
if verb[len(verb) - 1] in 'aàâeéèêiîoôuùûy' and pronoun[0] in 'aàâeéèêiîoôuùûy' :
return verb + '-t-' + pronoun
else :
return verb + '-' + pronoun
def affirmative_sentence() :
pron = personal_pronoun()
noun1, adj1, art1 = declension(noun(), adjective_before_noun(), 'sg')
noun2, adj2, art2 = declension(noun(), adjective_before_noun(), 'pl')
return affirmative_sequence(pron, conjugation(pron, transitive_infinitive())) + ' ' + collocation_bef(noun1, adj1, art1) + ' et ' + number() + ' ' + adj2 + ' ' + noun2 + '.'
def interrogative_sentence() :
pron = personal_pronoun()
return interrogative() + ' ' + interrogative_sequence(pron, conjugation(pron, intransitive_infinitive())) + ' ' + temporary_marker() + '?'
def negative_sentence() :
noun1, adj1, art1 = declension(noun(), adjective_before_noun(), 'pl')
noun2, adj2, art2 = declension(noun(), adjective_before_noun(), 'sg')
return collocation_aft(noun1, adj1, art1) + ' ne ' + conjugation('elle', transitive_infinitive()) + ' pas ' + collocation_bef(noun2, adj2, art2) + ' ' + temporary_marker() + ' ' + intensifier(adverb()) + '.'
def conditional_sentence() :
return '[Здесь должно быть условное предложение, но я пока не представляю, как оно устроено во французском :( ].'
def imperative_sentence() :
return 'ne ' + conjugation('vous', intransitive_infinitive()) + ' pas' +'!'
def random_sentence(n) :
if n == 1 :
return affirmative_sentence()
elif n == 2 :
return interrogative_sentence()
elif n == 3 :
return negative_sentence()
elif n == 4 :
return conditional_sentence()
else :
return imperative_sentence()
def text_print() :
a = set('12345')
for n in a :
print(random_sentence(int(n)).capitalize(), end = ' ')
text_print()
import re
def reading(name):
f = open(name, 'r', encoding = 'utf-8')
words = f.read().replace('\n', ' ').split()
f.close()
return words
def cleaning(words):
for i, word in enumerate(words) :
words[i] = word.lower().strip('.,/1234567890@
return words
def printing(words):
for word in words:
if re.search('загру(з(ят(ся)?|и(шь(ся)?|(сь)?|м(ся)?|л((ся)?|а(сь)?|и(сь)?|о(сь)?)|т((ся)?|е(сь)?|ь(ся)?)|в(ш(ую(ся)?|ая(ся)?|е(го(ся)?|му?(ся)?|й(ся)?|е(ся)?|ю(ся)?)|и((сь)?|й(ся)?|м(и)?(ся)?|е(ся)?|х(ся)?)))?))|ж(у(сь)?|ен(а|о|ы)?|ён|(е|ё)нн(ая|ую|о(м(у)?|ю|е|го|й)|ы(м(и)?|й|е|х))))$', word):
print(word)
def main():
words = cleaning(reading(input('Введите, пожалуйста, название файла:\n')))
printing(words)
main()
import re
def reading(name):
f = open(name, 'r', encoding = 'utf-8')
text = f.read()
f.close()
return text
def find(text):
r = re.search('\= 0 :
bigw += 1
else :
j = 0
while j < len(l[i]) and alph.find(l[i][j]) == -1 :
j += 1
if j == len(l[i]) :
allw -= 1
elif alphUP.find(l[i][j]) >= 0 :
bigw += 1
if allw != 0 :
print('The percentage of words, which start with uppercase equals to ', round(bigw / allw * 100, 3), '%', sep = '')
else :
if fl == 0 :
print('There are no words at all! Try to use another file.')
else :
print('There are some symbols, but no words in Russian. Try to use another file!')
f.close()
fl = 0
while fl != 1 :
word = input('Please input one word:\n')
ind = word.find(' ')
if ind == -1 :
fl = 1
else :
if ind == 0 :
word = word[1:]
flag = word.find(' ')
while flag == 0 :
word = word[1:]
flag = word.find(' ')
if flag > 0 :
subword = word[flag:]
ind = subword.find(' ')
while ind == 0 :
subword = subword[1:]
ind = subword.find(' ')
if subword != '' :
print('There is more than one word. Please try again!')
else :
word = word[:flag]
fl = 1
else :
if word != '' :
fl = 1
else :
print("You didn't type any word! Please try again!")
else :
subword = word[ind:]
flag = subword.find(' ')
while flag == 0 :
subword = subword[1:]
flag = subword.find(' ')
if subword != '' :
print('There is more than one word. Please try again!')
else :
word = word[:ind]
fl = 1
for i in range(len(word)) :
print(word[i:])
fl = 0
while fl != 1 :
word = input('Please input one word:\n')
word = word.strip()
ind = word.find(' ')
if ind == -1 :
if word != '' :
fl = 1
else :
print("You didn't type any word! Please try again")
else :
print('There is more than one word. Please try again!')
for i in range(len(word)) :
print(word[i:])
a = float(input('enter the first number\n'))
b = float(input('enter the second number\n'))
c = float(input('enter the third number\n'))
if b == 0. :
print('you can\'t divide by zero')
elif a % b == c and a / b == c :
print('YES')
else :
print('NO')
a = float(input('enter the first number\n'))
b = float(input('enter the second number\n'))
c = float(input('enter the third number\n'))
if b == 0. :
print('you can\'t divide by zero')
else :
if a % b == c :
print('YES, a % b == c')
else :
print('NO, a % b != c')
if a / b == c :
print('YES, a / b == c')
else :
print('NO, a / b != c')
a = int(input('enter the first number\n'))
b = int(input('enter the second number\n'))
c = int(input('enter the third number\n'))
if b == 0 :
print('you can\'t divide by zero')
elif a % b == c and a / b == c :
print('YES')
else :
print('NO')
a = int(input('enter the first number\n'))
b = int(input('enter the second number\n'))
c = int(input('enter the third number\n'))
if b == 0 :
print('you can\'t divide by zero')
else :
if a % b == c :
print('YES, a % b == c')
else :
print('NO, a % b != c')
if a / b == c :
print('YES, a / b == c')
else :
print('NO, a / b != c')
import re
import os
import csv
def printing(d1, d2, arr):
f = open('output1.txt', 'w', encoding = 'cp1251')
for key, value in sorted(d1.items()):
f.write(key + '\t' + str(value) + '\n')
f.close()
with open('output2.csv', 'w', encoding = 'cp1251') as csv_file:
writer = csv.writer(csv_file, delimiter = ';')
writer.writerow(['Название файла', 'Автор', 'Дата создания текста'])
for key, value in sorted(d2.items()):
lst = [str(key), str(value[0]), str(value[1])]
writer.writerow(lst)
f = open('output3.txt', 'w', encoding = 'cp1251')
for elem in arr:
f.write(elem + '\n')
f.close()
def dictionary(name):
d1 = {}
d2 = {}
arr = []
for file in os.listdir(name):
with open(os.path.join(name, file), 'r', encoding = 'cp1251') as text:
text = text.read()
a = re.findall('(.*?)', text)
d1[file] = len(a)
b = re.findall('<.*?>