devops/encoach_backend
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix reading exercise with more than 3 words.

Browse Source
This commit is contained in:
Cristiano Ferreira
2024-03-24 00:41:55 +00:00
parent 73532d5fed
commit 6aba83f3bb
2 changed files with 160 additions and 117 deletions
Download Patch File Download Diff File Expand all files Collapse all files

59
app.py
View File

@@ -231,7 +231,7 @@ def grade_writing_task_1():
token_count = count_tokens(message)["n_tokens"]
response = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, message, token_count,
["comment"],
GEN_QUESTION_TEMPERATURE)
GRADING_TEMPERATURE)
response['fixed_text'] = get_fixed_text(answer)
return response
else:
@@ -707,24 +707,7 @@ def get_reading_passage_1_question():
topic = request.args.get('topic', default=random.choice(topics))
req_exercises = request.args.getlist('exercises')
difficulty = request.args.get("difficulty", default=random.choice(difficulties))
if (len(req_exercises) == 0):
req_exercises = random.sample(READING_EXERCISE_TYPES, 2)
number_of_exercises_q = divide_number_into_parts(TOTAL_READING_PASSAGE_1_EXERCISES, len(req_exercises))
passage = generate_reading_passage(QuestionType.READING_PASSAGE_1, topic)
app.logger.info("Generated passage: " + str(passage))
start_id = 1
exercises = generate_reading_exercises(passage["text"], req_exercises, number_of_exercises_q, start_id, difficulty)
return {
"exercises": exercises,
"text": {
"content": passage["text"],
"title": passage["title"]
},
"difficulty": difficulty
}
return gen_reading_passage_1(topic, req_exercises, difficulty)
except Exception as e:
return str(e)
@@ -737,24 +720,7 @@ def get_reading_passage_2_question():
topic = request.args.get('topic', default=random.choice(topics))
req_exercises = request.args.getlist('exercises')
difficulty = request.args.get("difficulty", default=random.choice(difficulties))
if (len(req_exercises) == 0):
req_exercises = random.sample(READING_EXERCISE_TYPES, 2)
number_of_exercises_q = divide_number_into_parts(TOTAL_READING_PASSAGE_2_EXERCISES, len(req_exercises))
passage = generate_reading_passage(QuestionType.READING_PASSAGE_2, topic)
app.logger.info("Generated passage: " + str(passage))
start_id = 14
exercises = generate_reading_exercises(passage["text"], req_exercises, number_of_exercises_q, start_id, difficulty)
return {
"exercises": exercises,
"text": {
"content": passage["text"],
"title": passage["title"]
},
"difficulty": difficulty
}
return gen_reading_passage_2(topic, req_exercises, difficulty)
except Exception as e:
return str(e)
@@ -767,24 +733,7 @@ def get_reading_passage_3_question():
topic = request.args.get('topic', default=random.choice(topics))
req_exercises = request.args.getlist('exercises')
difficulty = request.args.get("difficulty", default=random.choice(difficulties))
if (len(req_exercises) == 0):
req_exercises = random.sample(READING_EXERCISE_TYPES, 2)
number_of_exercises_q = divide_number_into_parts(TOTAL_READING_PASSAGE_3_EXERCISES, len(req_exercises))
passage = generate_reading_passage(QuestionType.READING_PASSAGE_3, topic)
app.logger.info("Generated passage: " + str(passage))
start_id = 27
exercises = generate_reading_exercises(passage["text"], req_exercises, number_of_exercises_q, start_id, difficulty)
return {
"exercises": exercises,
"text": {
"content": passage["text"],
"title": passage["title"]
},
"difficulty": difficulty
}
return gen_reading_passage_3(topic, req_exercises, difficulty)
except Exception as e:
return str(e)

130
helper/exercises.py
View File

@@ -16,6 +16,68 @@ from wonderwords import RandomWord
nltk.download('words')
def gen_reading_passage_1(topic, req_exercises, difficulty):
if (len(req_exercises) == 0):
req_exercises = random.sample(READING_EXERCISE_TYPES, 2)
number_of_exercises_q = divide_number_into_parts(TOTAL_READING_PASSAGE_1_EXERCISES, len(req_exercises))
passage = generate_reading_passage(QuestionType.READING_PASSAGE_1, topic)
start_id = 1
exercises = generate_reading_exercises(passage["text"], req_exercises, number_of_exercises_q, start_id, difficulty)
if contains_empty_dict(exercises):
return gen_reading_passage_1(topic, req_exercises, difficulty)
return {
"exercises": exercises,
"text": {
"content": passage["text"],
"title": passage["title"]
},
"difficulty": difficulty
}
def gen_reading_passage_2(topic, req_exercises, difficulty):
if (len(req_exercises) == 0):
req_exercises = random.sample(READING_EXERCISE_TYPES, 2)
number_of_exercises_q = divide_number_into_parts(TOTAL_READING_PASSAGE_2_EXERCISES, len(req_exercises))
passage = generate_reading_passage(QuestionType.READING_PASSAGE_2, topic)
start_id = 14
exercises = generate_reading_exercises(passage["text"], req_exercises, number_of_exercises_q, start_id, difficulty)
if contains_empty_dict(exercises):
return gen_reading_passage_1(topic, req_exercises, difficulty)
return {
"exercises": exercises,
"text": {
"content": passage["text"],
"title": passage["title"]
},
"difficulty": difficulty
}
def gen_reading_passage_3(topic, req_exercises, difficulty):
if (len(req_exercises) == 0):
req_exercises = random.sample(READING_EXERCISE_TYPES, 2)
number_of_exercises_q = divide_number_into_parts(TOTAL_READING_PASSAGE_3_EXERCISES, len(req_exercises))
passage = generate_reading_passage(QuestionType.READING_PASSAGE_3, topic)
start_id = 27
exercises = generate_reading_exercises(passage["text"], req_exercises, number_of_exercises_q, start_id, difficulty)
if contains_empty_dict(exercises):
return gen_reading_passage_1(topic, req_exercises, difficulty)
return {
"exercises": exercises,
"text": {
"content": passage["text"],
"title": passage["title"]
},
"difficulty": difficulty
}
def divide_number_into_parts(number, parts):
if number < parts:
return None
@@ -309,8 +371,12 @@ def generate_reading_exercises(passage: str, req_exercises: list, number_of_exer
print("Added trueFalse: " + str(question))
elif req_exercise == "writeBlanks":
question = gen_write_blanks_exercise(passage, number_of_exercises, start_id, difficulty)
if answer_word_limit_ok(question):
exercises.append(question)
print("Added write blanks: " + str(question))
else:
exercises.append({})
print("Did not add write blanks because it did not respect word limit")
elif req_exercise == "paragraphMatch":
question = gen_paragraph_match_exercise(passage, number_of_exercises, start_id)
exercises.append(question)
@@ -321,13 +387,26 @@ def generate_reading_exercises(passage: str, req_exercises: list, number_of_exer
return exercises
def generate_listening_conversation_exercises(conversation: str, req_exercises: list, number_of_exercises_q, start_id, difficulty):
def answer_word_limit_ok(question):
# Check if any option in any solution has more than three words
return not any(len(option.split()) > 3
for solution in question["solutions"]
for option in solution["solution"])
def contains_empty_dict(arr):
return any(elem == {} for elem in arr)
def generate_listening_conversation_exercises(conversation: str, req_exercises: list, number_of_exercises_q, start_id,
difficulty):
exercises = []
for req_exercise in req_exercises:
number_of_exercises = number_of_exercises_q.get()
if req_exercise == "multipleChoice":
question = gen_multiple_choice_exercise_listening_conversation(conversation, number_of_exercises, start_id, difficulty)
question = gen_multiple_choice_exercise_listening_conversation(conversation, number_of_exercises, start_id,
difficulty)
exercises.append(question)
print("Added multiple choice: " + str(question))
elif req_exercise == "writeBlanksQuestions":
@@ -351,25 +430,30 @@ def generate_listening_conversation_exercises(conversation: str, req_exercises:
return exercises
def generate_listening_monologue_exercises(monologue: str, req_exercises: list, number_of_exercises_q, start_id, difficulty):
def generate_listening_monologue_exercises(monologue: str, req_exercises: list, number_of_exercises_q, start_id,
difficulty):
exercises = []
for req_exercise in req_exercises:
number_of_exercises = number_of_exercises_q.get()
if req_exercise == "multipleChoice":
question = gen_multiple_choice_exercise_listening_monologue(monologue, number_of_exercises, start_id, difficulty)
question = gen_multiple_choice_exercise_listening_monologue(monologue, number_of_exercises, start_id,
difficulty)
exercises.append(question)
print("Added multiple choice: " + str(question))
elif req_exercise == "writeBlanksQuestions":
question = gen_write_blanks_questions_exercise_listening_monologue(monologue, number_of_exercises, start_id, difficulty)
question = gen_write_blanks_questions_exercise_listening_monologue(monologue, number_of_exercises, start_id,
difficulty)
exercises.append(question)
print("Added write blanks questions: " + str(question))
elif req_exercise == "writeBlanksFill":
question = gen_write_blanks_notes_exercise_listening_monologue(monologue, number_of_exercises, start_id, difficulty)
question = gen_write_blanks_notes_exercise_listening_monologue(monologue, number_of_exercises, start_id,
difficulty)
exercises.append(question)
print("Added write blanks notes: " + str(question))
elif req_exercise == "writeBlanksForm":
question = gen_write_blanks_form_exercise_listening_monologue(monologue, number_of_exercises, start_id, difficulty)
question = gen_write_blanks_form_exercise_listening_monologue(monologue, number_of_exercises, start_id,
difficulty)
exercises.append(question)
print("Added write blanks form: " + str(question))
@@ -379,7 +463,8 @@ def generate_listening_monologue_exercises(monologue: str, req_exercises: list,
def gen_multiple_choice_exercise(text: str, quantity: int, start_id, difficulty):
gen_multiple_choice_for_text = "Generate " + str(quantity) + " " + difficulty + " difficulty multiple choice questions for this text: " \
gen_multiple_choice_for_text = "Generate " + str(
quantity) + " " + difficulty + " difficulty multiple choice questions for this text: " \
"'" + text + "'\n" \
"Use this format: \"questions\": [{\"id\": \"9\", \"options\": [{\"id\": \"A\", \"text\": " \
"\"Economic benefits\"}, {\"id\": \"B\", \"text\": \"Government regulations\"}, {\"id\": \"C\", \"text\": " \
@@ -469,8 +554,9 @@ def gen_true_false_not_given_exercise(text: str, quantity: int, start_id, diffic
def gen_write_blanks_exercise(text: str, quantity: int, start_id, difficulty):
gen_short_answer_questions = "Generate " + str(quantity) + " " + difficulty + " difficulty short answer questions, and the possible answers " \
"(max 3 words per answer), about this text: '" + text + "'. " \
gen_short_answer_questions = "Generate " + str(
quantity) + " " + difficulty + " difficulty short answer questions, and the possible answers, " \
"must have maximum 3 words per answer, about this text: '" + text + "'. " \
"Provide your answer in this JSON format: {\"questions\": [{\"question\": question, " \
"\"possible_answers\": [\"answer_1\", \"answer_2\"]}]}"
@@ -562,7 +648,8 @@ def gen_multiple_choice_exercise_listening_conversation(text: str, quantity: int
def gen_multiple_choice_exercise_listening_monologue(text: str, quantity: int, start_id, difficulty):
gen_multiple_choice_for_text = "Generate " + str(quantity) + " " + difficulty + " difficulty multiple choice questions for this monologue: " \
gen_multiple_choice_for_text = "Generate " + str(
quantity) + " " + difficulty + " difficulty multiple choice questions for this monologue: " \
"'" + text + "'"
token_count = count_tokens(gen_multiple_choice_for_text)["n_tokens"]
mc_questions = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, gen_multiple_choice_for_text, token_count,
@@ -586,7 +673,8 @@ def gen_multiple_choice_exercise_listening_monologue(text: str, quantity: int, s
def gen_write_blanks_questions_exercise_listening_conversation(text: str, quantity: int, start_id, difficulty):
gen_write_blanks_questions = "Generate " + str(quantity) + " " + difficulty + " difficulty short answer questions, and the possible answers " \
gen_write_blanks_questions = "Generate " + str(
quantity) + " " + difficulty + " difficulty short answer questions, and the possible answers " \
"(max 3 words per answer), about a monologue and" \
"respond in this JSON format: {\"questions\": [{\"question\": question, " \
"\"possible_answers\": [\"answer_1\", \"answer_2\"]}]}." \
@@ -608,7 +696,8 @@ def gen_write_blanks_questions_exercise_listening_conversation(text: str, quanti
def gen_write_blanks_questions_exercise_listening_monologue(text: str, quantity: int, start_id, difficulty):
gen_write_blanks_questions = "Generate " + str(quantity) + " " + difficulty + " difficulty short answer questions, and the possible answers " \
gen_write_blanks_questions = "Generate " + str(
quantity) + " " + difficulty + " difficulty short answer questions, and the possible answers " \
"(max 3 words per answer), about a monologue and" \
"respond in this JSON format: {\"questions\": [{\"question\": question, " \
"\"possible_answers\": [\"answer_1\", \"answer_2\"]}]}." \
@@ -630,7 +719,8 @@ def gen_write_blanks_questions_exercise_listening_monologue(text: str, quantity:
def gen_write_blanks_notes_exercise_listening_conversation(text: str, quantity: int, start_id, difficulty):
gen_write_blanks_notes = "Generate " + str(quantity) + " " + difficulty + " difficulty notes taken from the conversation and and respond in this " \
gen_write_blanks_notes = "Generate " + str(
quantity) + " " + difficulty + " difficulty notes taken from the conversation and and respond in this " \
"JSON format: { \"notes\": [\"note_1\", \"note_2\"] }. The monologue is this: '" + text + "'"
token_count = count_tokens(gen_write_blanks_notes)["n_tokens"]
@@ -655,7 +745,8 @@ def gen_write_blanks_notes_exercise_listening_conversation(text: str, quantity:
def gen_write_blanks_notes_exercise_listening_monologue(text: str, quantity: int, start_id, difficulty):
gen_write_blanks_notes = "Generate " + str(quantity) + " " + difficulty + " difficulty notes taken from the monologue and respond in this " \
gen_write_blanks_notes = "Generate " + str(
quantity) + " " + difficulty + " difficulty notes taken from the monologue and respond in this " \
"JSON format: { \"notes\": [\"note_1\", \"note_2\"] }. The monologue is this: '" + text + "'"
token_count = count_tokens(gen_write_blanks_notes)["n_tokens"]
@@ -680,7 +771,8 @@ def gen_write_blanks_notes_exercise_listening_monologue(text: str, quantity: int
def gen_write_blanks_form_exercise_listening_conversation(text: str, quantity: int, start_id, difficulty):
gen_write_blanks_form = "Generate a form with " + str(quantity) + " " + difficulty + " difficulty key-value pairs about the conversation. " \
gen_write_blanks_form = "Generate a form with " + str(
quantity) + " " + difficulty + " difficulty key-value pairs about the conversation. " \
"The conversation is this: '" + text + "'"
token_count = count_tokens(gen_write_blanks_form)["n_tokens"]
form = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, gen_write_blanks_form, token_count,
@@ -703,7 +795,8 @@ def gen_write_blanks_form_exercise_listening_conversation(text: str, quantity: i
def gen_write_blanks_form_exercise_listening_monologue(text: str, quantity: int, start_id, difficulty):
gen_write_blanks_form = "Generate a form with " + str(quantity) + " " + difficulty + " difficulty key-value pairs about the monologue. " \
gen_write_blanks_form = "Generate a form with " + str(
quantity) + " " + difficulty + " difficulty key-value pairs about the monologue. " \
"The monologue is this: '" + text + "'"
token_count = count_tokens(gen_write_blanks_form)["n_tokens"]
form = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, gen_write_blanks_form, token_count,
@@ -775,7 +868,8 @@ def gen_multiple_choice_level(quantity: int, start_id=1):
all_exams = get_all("level")
seen_keys = set()
for i in range(len(question["questions"])):
question["questions"][i], seen_keys = replace_exercise_if_exists(all_exams, question["questions"][i], question,
question["questions"][i], seen_keys = replace_exercise_if_exists(all_exams, question["questions"][i],
question,
seen_keys)
return {
"id": str(uuid.uuid4()),