def act(self, action, record=True, format=True):
assert (self.context.strip() + action.strip())
assert (settings.getint('top-keks') is not None)
result = self.generator.generate(
self.get_story() + action,
self.context + ' '.join(self.memory),
temperature=settings.getfloat('temp'),
top_p=settings.getfloat('top-p'),
top_k=settings.getint('top-keks'),
repetition_penalty=settings.getfloat('rep-pen'))
if record:
self.actions.append(format_input(action))
self.results.append(format_input(result))
return format_result(result) if format else result
def input_fn(serialized_input_data, content_type='text/csv'):
print('Deserializing the input data.')
if content_type == 'text/csv':
try:
data = serialized_input_data.decode('utf-8')
except:
data = serialized_input_data
print(data)
print(type(data))
#calling lookuptable
vector_table = get_lookup_table()
# process input data and turn to numpy array using lookup table
formatted_input_data = format_input(data)
print(formatted_input_data)
print(type(formatted_input_data))
vectorised_input = lookup_table(vector_table, formatted_input_data)
return vectorised_input
raise Exception('Requested unsupported ContentType in content_type: ' +
content_type)
def predict_fn(input_data, model):
print('Determining nearest cluster.')
#calling lookuptable
lookup_table = get_lookup_table()
# process input data and turn to numpy array using lookup table
formatted_input_data = format_input(input_data)
vectorised_input = lookup_table(search_table=lookup_table,
formatted_input_data)
output = sagemaker_model.predict(vectorised_input)
return result
def new_chat(update: Update, context: CallbackContext) -> int:
interest = format_input(update.message.text)
if interest in conversation_json:
for answer in conversation_json[interest]['respostas']:
answer_user(update, answer)
time.sleep(0.8)
if 'conversa' in conversation_json[interest]:
context.user_data['conversation_json'] = conversation_json[
interest]['conversa']
return KEEP_CHATING
else:
update.message.reply_text(
f'Não ouvi falar sobre {interest}, me conta mais!')
return NEW_CHAT
def __init__(self, crib):
self.crib = utils.format_input(crib)
self.ciphertext = ""
self.logger = logging.getLogger()
stimuli_arr, actions_arr, stim_sides_arr, session_uuids = [], [], [], []
# select particular mice
mouse_name = 'KS016'
for i in range(len(sess_id)):
if mice_names[i] == mouse_name: # take only sessions of first mice
data = utils.load_session(sess_id[i])
if data['choice'] is not None and data['probabilityLeft'][0] == 0.5:
stim_side, stimuli, actions, pLeft_oracle = utils.format_data(data)
stimuli_arr.append(stimuli)
actions_arr.append(actions)
stim_sides_arr.append(stim_side)
session_uuids.append(sess_id[i])
# format data
stimuli, actions, stim_side = utils.format_input(stimuli_arr, actions_arr,
stim_sides_arr)
session_uuids = np.array(session_uuids)
# import models
from models.expSmoothing_stimside import expSmoothing_stimside as exp_stimside
from models.expSmoothing_prevAction import expSmoothing_prevAction as exp_prevAction
from models.optimalBayesian import optimal_Bayesian as optBay
from models.biasedApproxBayesian import biased_ApproxBayesian as baisedApproxBay
from models.biasedBayesian import biased_Bayesian
'''
If you are interested in fitting (and the prior) of the mice behavior
'''
model = exp_prevAction('./results/inference/', session_uuids, mouse_name,
actions, stimuli, stim_side)
model.load_or_train(remove_old=False)
param = model.get_parameters() # if you want the parameters