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

218
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)
exercises.append(question)
print("Added write blanks: " + str(question))
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))
@@ -379,13 +463,14 @@ 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: " \
"'" + text + "'\n" \
"Use this format: \"questions\": [{\"id\": \"9\", \"options\": [{\"id\": \"A\", \"text\": " \
"\"Economic benefits\"}, {\"id\": \"B\", \"text\": \"Government regulations\"}, {\"id\": \"C\", \"text\": " \
"\"Concerns about climate change\"}, {\"id\": \"D\", \"text\": \"Technological advancement\"}], " \
"\"prompt\": \"What is the main reason for the shift towards renewable energy sources?\", " \
"\"solution\": \"C\", \"variant\": \"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\": " \
"\"Concerns about climate change\"}, {\"id\": \"D\", \"text\": \"Technological advancement\"}], " \
"\"prompt\": \"What is the main reason for the shift towards renewable energy sources?\", " \
"\"solution\": \"C\", \"variant\": \"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,
None,
@@ -416,7 +501,7 @@ def gen_summary_fill_blanks_exercise(text: str, quantity: int, start_id, difficu
gen_words_to_replace = "Select " + str(
quantity) + " " + difficulty + " difficulty words, it must be words and not expressions, from the summary and respond in this " \
"JSON format: { \"words\": [\"word_1\", \"word_2\"] }. The summary is: " + text_summary
"JSON format: { \"words\": [\"word_1\", \"word_2\"] }. The summary is: " + text_summary
token_count = count_tokens(gen_words_to_replace)["n_tokens"]
words_to_replace = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, gen_words_to_replace, token_count,
["words"],
@@ -442,13 +527,13 @@ def gen_summary_fill_blanks_exercise(text: str, quantity: int, start_id, difficu
def gen_true_false_not_given_exercise(text: str, quantity: int, start_id, difficulty):
gen_true_false_not_given = "Generate " + str(
quantity) + " " + difficulty + " difficulty statements in JSON format (True, False, or Not Given) " \
"based on the provided text. Ensure that your statements " \
"accurately represent information or inferences from the " \
"text, and provide a variety of responses, including, at least one of each True, " \
"False, and Not Given, as appropriate, in the JSON structure " \
"{\"prompts\":[{\"prompt\": \"statement_1\", \"solution\": " \
"\"true/false/not_given\"}, {\"prompt\": \"statement_2\", " \
"\"solution\": \"true/false/not_given\"}]}. Reference text: " + text
"based on the provided text. Ensure that your statements " \
"accurately represent information or inferences from the " \
"text, and provide a variety of responses, including, at least one of each True, " \
"False, and Not Given, as appropriate, in the JSON structure " \
"{\"prompts\":[{\"prompt\": \"statement_1\", \"solution\": " \
"\"true/false/not_given\"}, {\"prompt\": \"statement_2\", " \
"\"solution\": \"true/false/not_given\"}]}. Reference text: " + text
token_count = count_tokens(gen_true_false_not_given)["n_tokens"]
questions = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, gen_true_false_not_given, token_count,
@@ -469,10 +554,11 @@ 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 + "'. " \
"Provide your answer in this JSON format: {\"questions\": [{\"question\": question, " \
"\"possible_answers\": [\"answer_1\", \"answer_2\"]}]}"
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\"]}]}"
token_count = count_tokens(gen_short_answer_questions)["n_tokens"]
questions = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, gen_short_answer_questions, token_count,
@@ -492,9 +578,9 @@ def gen_write_blanks_exercise(text: str, quantity: int, start_id, difficulty):
def gen_paragraph_match_exercise(text: str, quantity: int, start_id):
paragraphs = assign_letters_to_paragraphs(text)
heading_prompt = (
'For every paragraph of the list generate a minimum 5 word heading for it. Provide your answer in this JSON format: '
'{"headings": [ {"heading": "first paragraph heading"}, {"heading": "second paragraph heading"}]}\n'
'The paragraphs are these: ' + str(paragraphs))
'For every paragraph of the list generate a minimum 5 word heading for it. Provide your answer in this JSON format: '
'{"headings": [ {"heading": "first paragraph heading"}, {"heading": "second paragraph heading"}]}\n'
'The paragraphs are these: ' + str(paragraphs))
token_count = count_tokens(heading_prompt)["n_tokens"]
headings = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, heading_prompt, token_count,
@@ -519,13 +605,13 @@ def gen_paragraph_match_exercise(text: str, quantity: int, start_id):
})
return {
"id": str(uuid.uuid4()),
"allowRepetition": False,
"options": options,
"prompt": "Choose the correct heading for paragraphs from the list of headings below.",
"sentences": sentences[:quantity],
"type": "matchSentences"
}
"id": str(uuid.uuid4()),
"allowRepetition": False,
"options": options,
"prompt": "Choose the correct heading for paragraphs from the list of headings below.",
"sentences": sentences[:quantity],
"type": "matchSentences"
}
def assign_letters_to_paragraphs(paragraphs):
@@ -539,7 +625,7 @@ def assign_letters_to_paragraphs(paragraphs):
def gen_multiple_choice_exercise_listening_conversation(text: str, quantity: int, start_id, difficulty):
gen_multiple_choice_for_text = "Generate " + str(
quantity) + " " + difficulty + " difficulty multiple choice questions of 4 options of for this conversation: " \
"'" + text + "'"
"'" + 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,
None,
@@ -562,8 +648,9 @@ 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: " \
"'" + text + "'"
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,
None,
@@ -586,11 +673,12 @@ 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 " \
"(max 3 words per answer), about a monologue and" \
"respond in this JSON format: {\"questions\": [{\"question\": question, " \
"\"possible_answers\": [\"answer_1\", \"answer_2\"]}]}." \
"The monologue is this: '" + text + "'"
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\"]}]}." \
"The monologue is this: '" + text + "'"
token_count = count_tokens(gen_write_blanks_questions)["n_tokens"]
questions = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, gen_write_blanks_questions, token_count,
@@ -608,11 +696,12 @@ 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 " \
"(max 3 words per answer), about a monologue and" \
"respond in this JSON format: {\"questions\": [{\"question\": question, " \
"\"possible_answers\": [\"answer_1\", \"answer_2\"]}]}." \
"The monologue is this: '" + text + "'"
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\"]}]}." \
"The monologue is this: '" + text + "'"
token_count = count_tokens(gen_write_blanks_questions)["n_tokens"]
questions = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, gen_write_blanks_questions, token_count,
@@ -630,8 +719,9 @@ 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 " \
"JSON format: { \"notes\": [\"note_1\", \"note_2\"] }. The monologue is this: '" + text + "'"
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"]
questions = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, gen_write_blanks_notes, token_count,
@@ -655,8 +745,9 @@ 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 " \
"JSON format: { \"notes\": [\"note_1\", \"note_2\"] }. The monologue is this: '" + text + "'"
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"]
questions = make_openai_instruct_call(GPT_3_5_TURBO_INSTRUCT, gen_write_blanks_notes, token_count,
@@ -680,8 +771,9 @@ 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. " \
"The conversation is this: '" + text + "'"
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,
None,
@@ -703,8 +795,9 @@ 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. " \
"The monologue is this: '" + text + "'"
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,
None,
@@ -739,8 +832,8 @@ def gen_multiple_choice_level(quantity: int, start_id=1):
token_count = count_tokens(gen_multiple_choice_for_text)["n_tokens"] - 300
mc_questions = make_openai_call(GPT_4_PREVIEW, messages, token_count,
None,
GEN_QUESTION_TEMPERATURE)
None,
GEN_QUESTION_TEMPERATURE)
if not '25' in mc_questions:
return gen_multiple_choice_level(quantity, start_id)
else:
@@ -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()),