def handle_dry(self, options):
info = self.load_environment_info(options['initial'], options['config_name'], True)
environment = InMemoryEnvironment()
environment = self.load_environment(info)
users, items = self.load_user_and_item_ids(info, options['batch_size'])
items += list(set(flatten(Item.objects.get_reachable_parents(items).values())))
environment.prefetch(users, items)
predictive_model = get_predictive_model(info.to_json())
with closing(connection.cursor()) as cursor:
cursor.execute('SELECT COUNT(*) FROM proso_models_answer')
answers_total = cursor.fetchone()[0]
if options['limit'] is not None:
answers_total = min(answers_total, options['limit'])
print('total:', answers_total)
processed = 0
prediction = numpy.empty(answers_total)
correct = numpy.empty(answers_total)
while processed < answers_total:
cursor.execute(
'''
SELECT
id,
user_id,
item_id,
item_asked_id,
item_answered_id,
time,
response_time,
guess
FROM proso_models_answer
ORDER BY id
OFFSET %s LIMIT %s
''', [processed, options['batch_size']])
for (answer_id, user, item, asked, answered, time, response_time, guess) in cursor:
correct[processed] = asked == answered
prediction[processed] = predictive_model.predict_and_update(
environment,
user,
item,
asked == answered,
time,
item_answered=answered,
item_asked=asked,
guess=guess,
answer_id=answer_id,
response_time=response_time,
)
environment.process_answer(user, item, asked, answered, time, answer_id, response_time, guess)
processed += 1
if processed >= answers_total:
break
print('processed:', processed)
filename = settings.DATA_DIR + '/recompute_model_report_{}.json'.format(predictive_model.__class__.__name__)
model_report = report(prediction, correct)
with open(filename, 'w') as outfile:
json.dump(model_report, outfile)
print('Saving report to:', filename)
brier_graphs(model_report['brier'], predictive_model)
def write(self, key, value, user=None, item=None, item_secondary=None, time=None, symmetric=True, permanent=False, answer=None):
prefetched_key = self._prefetched_key(key, user, item, item_secondary, symmetric)
prefetched = self._prefetched.get(prefetched_key)
if prefetched is not None:
self._to_delete.append(prefetched[2])
del self._prefetched[prefetched_key]
InMemoryEnvironment.write(
self, key, value, user=user, item=item,
item_secondary=item_secondary, time=time,
symmetric=symmetric, permanent=permanent, answer=answer
)
def write(self, key, value, user=None, item=None, item_secondary=None, time=None, audit=True, symmetric=True, permanent=False, answer=None):
prefetched_key = self._prefetched_key(key, user, item, item_secondary, symmetric)
prefetched = self._prefetched.get(prefetched_key)
if prefetched is not None:
self._to_delete.append(prefetched[2])
del self._prefetched[prefetched_key]
InMemoryEnvironment.write(
self, key, value, user=user, item=item,
item_secondary=item_secondary, time=time, audit=audit,
symmetric=symmetric, permanent=permanent, answer=answer
)
def time(self, key, user=None, item=None, item_secondary=None, symmetric=True):
prefetched = self._get_prefetched(key, user, item, item_secondary, symmetric)
if prefetched:
return prefetched[0]
else:
return InMemoryEnvironment.time(
self, key, user=user, item=item,
item_secondary=item_secondary, symmetric=symmetric
)
def read(self, key, user=None, item=None, item_secondary=None, default=None, symmetric=True):
prefetched = self._get_prefetched(key, user, item, item_secondary, symmetric)
if prefetched:
return prefetched[1]
else:
return InMemoryEnvironment.read(
self, key, user=user, item=item, item_secondary=item_secondary,
default=default, symmetric=symmetric
)
def time(self, key, user=None, item=None, item_secondary=None, symmetric=True):
prefetched = self._get_prefetched(key, user, item, item_secondary, symmetric)
if prefetched:
return prefetched[0]
else:
return InMemoryEnvironment.time(
self, key, user=user, item=item,
item_secondary=item_secondary, symmetric=symmetric
)
def read(self, key, user=None, item=None, item_secondary=None, default=None, symmetric=True):
prefetched = self._get_prefetched(key, user, item, item_secondary, symmetric)
if prefetched:
return prefetched[1]
else:
return InMemoryEnvironment.read(
self, key, user=user, item=item, item_secondary=item_secondary,
default=default, symmetric=symmetric
)
def read_all_with_key(self, key):
found = []
for k, v in self._prefetched.items():
if k[0] == key:
found.append((k[1], k[2], k[3], v[1]))
return found + InMemoryEnvironment.read_all_with_key(self, key)
def __init__(self, info):
# key -> user -> item_primary -> item_secondary -> [(time, value)]
InMemoryEnvironment.__init__(self)
self._prefetched = {}
self._info_id = info.id
self._to_delete = []
def __init__(self, info):
# key -> user -> item_primary -> item_secondary -> [(time, value)]
InMemoryEnvironment.__init__(self)
self._prefetched = {}
self._info_id = info.id
self._to_delete = []
def handle_dry(self, options):
info = self.load_environment_info(options['initial'],
options['config_name'], True)
environment = InMemoryEnvironment(audit_enabled=False)
environment = self.load_environment(info)
users, items = self.load_user_and_item_ids(info, options['batch_size'])
items += list(
set(flatten(Item.objects.get_reachable_parents(items).values())))
environment.prefetch(users, items)
predictive_model = get_predictive_model(info.to_json())
with closing(connection.cursor()) as cursor:
cursor.execute('SELECT COUNT(*) FROM proso_models_answer')
answers_total = cursor.fetchone()[0]
if options['limit'] is not None:
answers_total = min(answers_total, options['limit'])
print('total:', answers_total)
processed = 0
prediction = numpy.empty(answers_total)
correct = numpy.empty(answers_total)
while processed < answers_total:
cursor.execute(
'''
SELECT
id,
user_id,
item_id,
item_asked_id,
item_answered_id,
time,
response_time,
guess
FROM proso_models_answer
ORDER BY id
OFFSET %s LIMIT %s
''', [processed, options['batch_size']])
for (answer_id, user, item, asked, answered, time,
response_time, guess) in cursor:
correct[processed] = asked == answered
prediction[
processed] = predictive_model.predict_and_update(
environment,
user,
item,
asked == answered,
time,
item_answered=answered,
item_asked=asked,
guess=guess,
answer_id=answer_id,
response_time=response_time,
)
environment.process_answer(user, item, asked, answered,
time, answer_id, response_time,
guess)
processed += 1
if processed >= answers_total:
break
print('processed:', processed)
filename = settings.DATA_DIR + '/recompute_model_report_{}.json'.format(
predictive_model.__class__.__name__)
model_report = report(prediction, correct)
with open(filename, 'w') as outfile:
json.dump(model_report, outfile)
print('Saving report to:', filename)
brier_graphs(model_report['brier'], predictive_model)