def fit(self, tasks):
alt, unver = "чередующаяся", "непроверяемая"
for task in tasks:
task = standardize_task(task)
text = task["text"]
if alt in text:
type_ = "alternations"
elif unver in text:
type_ = "unverifiable"
else:
type_ = "verifiable"
correct = (
task["solution"]["correct_variants"][0]
if "correct_variants" in task["solution"]
else task["solution"]["correct"]
)
for correct_id in correct:
for word in task["choices"][int(correct_id) - 1]["parts"]:
word_sub = re.sub(
r"^[\w|\)]\d\)",
"",
re.sub(
r"^\d\)",
"",
re.sub(r" *(?:^\d\)|\(.*?\)) *", "", word.strip()).strip(),
).strip(),
).strip()
self.known_examples[type_].append(word_sub)
def predict_from_model(self, task):
task = standardize_task(task)
text, choices = task["text"], task["question"]["choices"]
alt, unver = "чередующаяся", "непроверяемая"
type_ = "alternations" if alt in text else "unverifiable" if unver in text else "verifiable"
nice_option_ids = list()
for option in choices:
parsed_option = re.sub(r"^\d\)", "", option["text"]).split(", ")
if all(self.is_of_type(word, type_) for word in parsed_option):
nice_option_ids.append(option["id"])
if choices[0]["text"].count(", ") == 0:
if len(nice_option_ids) == 0:
return [random.choice([str(i + 1) for i in range(5)])]
elif len(nice_option_ids) == 1:
return nice_option_ids
else:
return [random.choice(nice_option_ids)]
else:
if len(nice_option_ids) == 0:
return sorted(random.sample([str(i + 1) for i in range(5)], 2))
elif len(nice_option_ids) == 1:
return sorted(nice_option_ids + [
random.choice([
str(i + 1)
for i in range(5) if str(i + 1) != nice_option_ids[0]
])
])
elif len(nice_option_ids) in [2, 3]:
return sorted(nice_option_ids)
else:
return sorted(random.sample(nice_option_ids, 2))
def predict_from_model(self, task):
task = standardize_task(task)
sentences = [
re.sub(r"^\d\) ?", "", sentence['text'])
for sentence in task["question"]["choices"]
]
sentences = self.strs_to_pos_tags(sentences)
vector = self.count_vectorizer.transform(sentences).toarray()
proba = self.classifier.predict_proba(vector)[:, 1]
two_highest = sorted([str(i + 1) for i in np.argsort(proba)[-2:]])
return two_highest
def predict_from_model(self, task):
result, task = [], standardize_task(task)
match = re.search(r'буква ([ЭОУАЫЕЁЮЯИ])', task["text"])
if match:
letter = match.group(1)
return self.get_answer_by_vowel(task["choices"], letter.lower())
elif "одна и та же буква" in task["text"]:
for vowel in "эоуаыеёюяидтсз":
result_with_this_vowel = self.get_answer_by_vowel(
task["choices"], vowel)
result.extend(result_with_this_vowel)
return sorted(list(set(result)))
def predict_from_model(self, task):
#print('-'*40,task['id'],'-'*40)
words = [word for word in task['text'].split("\n") if (1 < len(word))]
if task['question']['type'] == 'multiple_choice':
words = []
num = 1
for ans in task['question']['choices']:
words.append(ans['text'])
else:
num = 0
words = words[1:]
#print(words)
result = []
match = re.search(r'буква ([ЭОУАЫЕЁЮЯИ])', task['text'])
if match:
letter = match.group(1)
return self.get_answer_by_vowel_10(words, letter.lower(), num)
elif "одна и та же" in task['text']:
for vowel in "эоуаыеёюяидтсзьъ":
result_with_this_vowel = self.get_answer_by_vowel_10(
words, vowel, num)
if num == 1:
result.extend(result_with_this_vowel)
elif result_with_this_vowel:
result = result_with_this_vowel
break
#print('я',result)
if not result:
result, task = [], standardize_task(task)
#print(task)
match = re.search(r'буква ([ЭОУАЫЕЁЮЯИ])', task["text"])
if match:
letter = match.group(1)
return self.get_answer_by_vowel(task["question"]["choices"],
letter.lower(), num)
elif "одна и та же буква" in task["text"]:
for vowel in "эоуаыеёюяидтсз":
result_with_this_vowel = self.get_answer_by_vowel(
task["question"]["choices"], vowel, num)
result.extend(result_with_this_vowel)
#print('не я',result)
#print(num,result)
if num == 1:
answer = sorted(list(set(result)))
else:
answer = result
return answer
def predict_from_model(self, task):
task["text"] = re.sub("[^а-яА-яЁё\.\,\! ]|_", "", task["text"])
result, task = [], standardize_task(task)
match = re.search(r"буква ([ЭОУАЫЕЁЮЯИ])*", task["text"], re.IGNORECASE)
if match:
letter = match.group(1)
return self.get_answer_by_letter(
task["question"]["choices"], letter.lower()
)
elif "одна и та же буква" in task["text"]:
for vowel in self.alphabet:
result_with_this_vowel = self.get_answer_by_letter(
task["question"]["choices"], vowel
)
result.extend(result_with_this_vowel)
return sorted(list(set(result)))
def fit(self, tasks):
X, y = [], []
for task in tasks:
task = standardize_task(task)
correct = (task["solution"]["correct_variants"][0]
if "correct_variants" in task["solution"] else
[task["solution"]["correct"]])
sentences = [
re.sub(r"^\d\) ?", "", sentence["text"])
for sentence in task["question"]["choices"]
]
sentences = self.strs_to_pos_tags(sentences)
X.extend(sentences)
y.extend([1 if str(i + 1) in correct else 0 for i in range(5)])
X = self.count_vectorizer.fit_transform(X).toarray()
X_train, X_dev, y_train, y_dev = train_test_split(X, y, train_size=0.9)
self.classifier.fit(X_train, y_train, eval_set=(X_dev, y_dev))
def predict_from_model(self, task):
task = standardize_task(task)
text, choices = task["text"], task["question"]["choices"]
alt, unver = "чередующаяся", "непроверяемая"
type_ = "alternations" if alt in text else "unverifiable" if unver in text else "verifiable"
nice_option_ids = list()
for option in choices:
parsed_option = re.sub(r"^\d\)", "", option["text"]).split(", ")
pos_count = 0
neg_count = 0
for word in parsed_option:
for k in self.known_examples:
if self.is_of_type(word, k):
if k == type_:
pos_count += 1
else:
neg_count += 1
nice_option_ids.append(
(pos_count if neg_count == 0 else -neg_count, option["id"]))
nice_option_ids.sort()
if choices[0]["text"].count(", ") == 0:
if len(nice_option_ids) == 0:
return [random.choice([str(i + 1) for i in range(5)])]
elif len(nice_option_ids) == 1:
return [nice_option_ids[0][1]]
else:
return [nice_option_ids[-1][1]]
else:
if len(nice_option_ids) == 0:
return sorted(random.sample([str(i + 1) for i in range(5)], 2))
elif len(nice_option_ids) == 1:
return sorted([nice_option_ids[0][1]] + [
random.choice([
str(i + 1) for i in range(5)
if str(i + 1) != nice_option_ids[0][1]
])
])
elif len(nice_option_ids) in [2, 3]:
return sorted([el[1] for el in nice_option_ids])
else:
return sorted([el[1] for el in nice_option_ids[-2:]])
def fit(self, tasks):
alt, unver, ver = "чередующаяся", "непроверяемая", "проверяемая"
for task in tasks:
#if 'hint' in task:
#continue
task = standardize_task(task)
text = task["text"]
if alt in text:
type_ = "alternations"
elif unver in text:
type_ = "unverifiable"
elif ver in text:
type_ = "verifiable"
else:
continue
correct = task["solution"]["correct_variants"][0] if "correct_variants" in task["solution"] \
else task["solution"]["correct"]
for correct_id in correct:
for word in task["choices"][int(correct_id) - 1]["parts"]:
word_sub = re.sub(r" *(?:^\d\)|\(.*?\)) *", "", word)
self.known_examples[type_].append(word_sub)
return self
