def emit_features(user_states, theta, options, split_desc):
"""Emit a CSV data file of correctness, prediction, and abilities."""
f = open("%s_split=%s.csv" % (options.output, split_desc), 'w+')
for user_state in user_states:
# initialize
abilities = np.zeros((options.num_abilities, 1))
correct = user_state['correct']
log_time_taken = user_state['log_time_taken']
exercise_ind = user_state['exercise_ind']
# NOTE: I currently do not output features for the first problem
for i in xrange(1, correct.size):
# TODO(jace) this should probably be the marginal estimation
_, _, abilities, _ = mirt_util.sample_abilities_diffusion(
theta,
exercise_ind[:i],
correct[:i],
log_time_taken[:i],
abilities_init=abilities,
num_steps=200)
prediction = mirt_util.conditional_probability_correct(
abilities, theta, exercise_ind[i:(i + 1)])
f.write("%d, " % correct[i])
f.write("%.4f, " % prediction[-1])
f.write(",".join(["%.4f" % a for a in abilities]))
f.write('\n')
f.close()
def emit_features(user_states, theta, options, split_desc):
"""Emit a CSV data file of correctness, prediction, and abilities."""
f = open("%s_split=%s.csv" % (options.output, split_desc), 'w+')
for user_state in user_states:
# initialize
abilities = np.zeros((options.num_abilities, 1))
correct = user_state['correct']
log_time_taken = user_state['log_time_taken']
exercises_ind = user_state['exercises_ind']
# NOTE: I currently do not output features for the first problem
for i in xrange(1, correct.size):
# TODO(jace) this should probably be the marginal estimation
_, _, abilities, _ = mirt_util.sample_abilities_diffusion(
theta, exercises_ind[:i], correct[:i], log_time_taken[:i],
abilities_init=abilities, num_steps=200)
prediction = mirt_util.conditional_probability_correct(
abilities, theta, exercises_ind[i:(i + 1)])
f.write("%d, " % correct[i])
f.write("%.4f, " % prediction[-1])
f.write(",".join(["%.4f" % a for a in abilities]))
f.write('\n')
f.close()
def eval_conditional_probability(x, parameters, exercise_ind):
"""Evaluate the conditional probability of answering each question
accurately for a student with ability x
"""
return mirt_util.conditional_probability_correct(
np.ones((parameters.num_abilities, 1)) * x,
parameters,
exercise_ind)
def attempt(self, item):
"""Return whether the student responds correctly to the item.
This is probabilistic - we get the probability that the student will
respond correctly, and then generate a random number to see if they
succeed.
"""
p_correct = mirt_util.conditional_probability_correct(
self.student.abilities, item, 0)
if random.random() <= p_correct:
return True
else:
return False
def attempt(self, item):
"""Return whether the student responds correctly to the item.
This is probabilistic - we get the probability that the student will
respond correctly, and then generate a random number to see if they
succeed.
"""
p_correct = mirt_util.conditional_probability_correct(
self.student.abilities,
item,
0)
if random.random() <= p_correct:
return True
else:
return False
def estimated_exercise_accuracy(self, history, exercise_name,
update_abilities=True, ignore_analytics=False):
"""Returns the expected probability of getting a future question
correct on the specified exercise.
"""
if update_abilities:
self._update_abilities(history, ignore_analytics=ignore_analytics)
try:
exercise_ind = mirt_util.get_exercise_ind(
exercise_name, self.exercise_ind_dict)
except KeyError:
# If we don't have this exercise, predict the mean predicted
# accuracy over all exercises we do have.
return self.score(history)
return mirt_util.conditional_probability_correct(
self.abilities, self.theta, exercise_ind)[0]
