def get_questions(self):
Question = get_model("Question")
Paper = get_model("Paper")
return object_session(self)\
.query(Question)\
.filter(
(Paper.course_id == self.id) &
(Question.paper_id == Paper.id)
).all()
def get_questions(self):
Question = get_model("Question")
Paper = get_model("Paper")
return object_session(self)\
.query(Question)\
.filter(
(Paper.course_id == self.id) &
(Question.paper_id == Paper.id)
).all()
def find_similar_questions(self, question):
# Compute the tf-idf if not already completed
if not self.vectorizer:
self.vectorize()
# Grab the question we have to find similar for's index
question_index = 0
for i, q in enumerate(self.questions):
if question.id == q.id:
question_index = i
break
# Grab our question vector
query = self.tfidf_documents[question_index, :]
# Compute the similarity and return a gram matrix
# of D_n x Query and stick it in a datafram
similarity = cosine_similarity(self.tfidf_documents, query).flatten()
# Grab the similiar model
Similar = get_model("Similar")
# Generate the similarity objects
return [
Similar(question_id=question.id,
similar_question_id=q.id,
similarity=s) for q, s in zip(self.questions, similarity)
]
def popular_questions(self):
"""Find the most popular questions.
This loops through all the questions, find's the similar questions
and ranks them by sum(similarity)
"""
session = object_session(self)
Similar = get_model("Similar")
Question = get_model("Question")
Paper = get_model("Paper")
# SQL:
# exam_papers=# select question_id, sum(similarity) as similarity from similar_questions
# where similarity > 0.6 and question_id != similar_question_id
# group by question_id order by similarity DESC;
popular = (session.query(
Similar.question_id.label("question_id"),
func.sum(Similar.similarity).label("cum_similarity")).group_by(
Similar.question_id)).subquery()
questions = session.query(Question)\
.join(popular, Question.id == popular.c.question_id)\
.join(Paper, Paper.id == Question.paper_id)\
.filter(Paper.course_id == self.id)\
.order_by(popular.c.cum_similarity.desc())\
.limit(25)\
.all()
# Now we pick only one of a similar group of questions
# A graph DB would be handy right about now
grouped = []
for question in questions:
inside = False
# Loop over each similar questions in the already selected questions
for grouped_question in grouped:
inside = bool(
find(grouped_question.similar,
lambda q: q.similar_question_id == question.id))
if not inside or len(grouped) == 0:
grouped.append(question)
return grouped
def popular_questions(self):
"""Find the most popular questions.
This loops through all the questions, find's the similar questions
and ranks them by sum(similarity)
"""
session = object_session(self)
Similar = get_model("Similar")
Question = get_model("Question")
Paper = get_model("Paper")
# SQL:
# exam_papers=# select question_id, sum(similarity) as similarity from similar_questions
# where similarity > 0.6 and question_id != similar_question_id
# group by question_id order by similarity DESC;
popular = (session.query(
Similar.question_id.label("question_id"),
func.sum(Similar.similarity).label("cum_similarity")
).group_by(Similar.question_id)).subquery()
questions = session.query(Question)\
.join(popular, Question.id == popular.c.question_id)\
.join(Paper, Paper.id == Question.paper_id)\
.filter(Paper.course_id == self.id)\
.order_by(popular.c.cum_similarity.desc())\
.limit(25)\
.all()
# Now we pick only one of a similar group of questions
# A graph DB would be handy right about now
grouped = []
for question in questions:
inside = False
# Loop over each similar questions in the already selected questions
for grouped_question in grouped:
inside = bool(find(grouped_question.similar, lambda q: q.similar_question_id == question.id))
if not inside or len(grouped) == 0:
grouped.append(question)
return grouped
def find_similar_questions(self, question):
# Compute the tf-idf if not already completed
if not self.vectorizer:
self.vectorize()
# Grab the question we have to find similar for's index
question_index = 0
for i, q in enumerate(self.questions):
if question.id == q.id:
question_index = i
break
# Grab our question vector
query = self.tfidf_documents[question_index, :]
# Compute the similarity and return a gram matrix
# of D_n x Query and stick it in a datafram
similarity = cosine_similarity(self.tfidf_documents, query).flatten()
# Grab the similiar model
Similar = get_model("Similar");
# Generate the similarity objects
return [Similar(question_id=question.id, similar_question_id=q.id, similarity=s) for q, s in zip(self.questions, similarity)]
