def _demo_fusion():
len_alp = 4
evidence_names = ['LM', 'ERP', 'FRP']
num_series = 4
num_inquiries = 10
conjugator = EvidenceFusion(evidence_names, len_dist=len_alp)
print('Random Series!')
for idx_ep in range(num_series):
prior = np.abs(np.random.randn(len_alp))
prior = prior / np.sum(prior)
conjugator.update_and_fuse({'LM': prior})
for idx in range(num_inquiries):
# Generate random inquiries
evidence_erp = 10 * np.abs(np.random.randn(len_alp))
evidence_frp = 10 * np.abs(np.random.randn(len_alp))
conjugator.update_and_fuse(
{'ERP': evidence_erp, 'FRP': evidence_frp})
print('Series: {}'.format(idx_ep))
print(conjugator.evidence_history['ERP'])
print(conjugator.evidence_history['FRP'])
print(conjugator.evidence_history['LM'])
print('Posterior:{}'.format(conjugator.likelihood))
# Reset the conjugator before starting a new series for clear history
conjugator.reset_history()
def _demo_decision_maker():
alp = ['T', 'H', 'I', 'S', 'I', 'S', 'D', 'E', 'M', 'O']
len_alp = len(alp)
evidence_names = ['LM', 'ERP', 'FRP']
num_series = 10
conjugator = EvidenceFusion(evidence_names, len_dist=len_alp)
decision_maker = DecisionMaker(
min_num_inq=1,
max_num_inq=10,
state='',
alphabet=alp)
for idx_series in range(num_series):
while True:
# Generate random inquiries
evidence_erp = np.abs(np.random.randn(len_alp))
evidence_erp[idx_series] += 1
evidence_frp = np.abs(np.random.randn(len_alp))
evidence_frp[idx_series] += 3
p = conjugator.update_and_fuse(
{'ERP': evidence_erp, 'FRP': evidence_frp})
d, arg = decision_maker.decide(p)
if d:
break
# Reset the conjugator before starting a new series for clear history
conjugator.reset_history()
print('State:{}'.format(decision_maker.state))
print('Displayed State: {}'.format(decision_maker.displayed_state))
def __init__(self,
min_num_seq,
max_num_seq,
signal_model=None,
fs=300,
k=2,
alp=None,
evidence_names=['LM', 'ERP'],
task_list=[('I_LOVE_COOKIES', 'I_LOVE_')],
lmodel=None,
is_txt_stim=True,
device_name='LSL',
device_channels=None,
stimuli_timing=[1, .2],
decision_threshold=0.8,
backspace_prob=0.05,
backspace_always_shown=False,
filter_high=45,
filter_low=2,
filter_order=2,
notch_filter_frequency=60):
self.conjugator = EvidenceFusion(evidence_names, len_dist=len(alp))
seq_constants = []
if backspace_always_shown and BACKSPACE_CHAR in alp:
seq_constants.append(BACKSPACE_CHAR)
self.decision_maker = DecisionMaker(
min_num_seq,
max_num_seq,
decision_threshold=decision_threshold,
state=task_list[0][1],
alphabet=alp,
is_txt_stim=is_txt_stim,
stimuli_timing=stimuli_timing,
seq_constants=seq_constants)
self.alp = alp
# non-letter target labels include the fixation cross and calibration.
self.nonletters = ['+', 'PLUS', 'calibration_trigger']
self.valid_targets = set(self.alp)
self.signal_model = signal_model
self.sampling_rate = fs
self.downsample_rate = k
self.filter_high = filter_high
self.filter_low = filter_low
self.filter_order = filter_order
self.notch_filter_frequency = notch_filter_frequency
self.mode = 'copy_phrase'
self.task_list = task_list
self.lmodel = lmodel
self.channel_map = analysis_channels(device_channels, device_name)
self.backspace_prob = backspace_prob
def setUp(self):
"""Set up decision maker object for testing """
self.decision_maker = DecisionMaker(
1,
3,
state='',
alphabet=list(string.ascii_uppercase) + ['<'] + [SPACE_CHAR],
is_txt_stim=True,
stimuli_timing=[1, .2],
seq_constants=None)
self.evidence_fusion = EvidenceFusion(list_name_evidence=['A', 'B'],
len_dist=2)
def setUp(self):
"""Set up decision maker object for testing """
alphabet = list(string.ascii_uppercase) + ['<'] + [SPACE_CHAR]
stopping_criteria = CriteriaEvaluator(
continue_criteria=[MinIterationsCriteria(min_num_inq=1)],
commit_criteria=[
MaxIterationsCriteria(max_num_inq=10),
ProbThresholdCriteria(threshold=0.8)
])
stimuli_agent = NBestStimuliAgent(alphabet=alphabet, len_query=10)
self.decision_maker = DecisionMaker(
stimuli_agent=stimuli_agent,
stopping_evaluator=stopping_criteria,
state='',
alphabet=alphabet,
is_txt_stim=True,
stimuli_timing=[1, .2],
inq_constants=None)
self.evidence_fusion = EvidenceFusion(list_name_evidence=['A', 'B'],
len_dist=2)
def __init__(self,
min_num_inq,
max_num_inq,
signal_model=None,
fs=300,
k=2,
alp=None,
evidence_names=['LM', 'ERP'],
task_list=[('I_LOVE_COOKIES', 'I_LOVE_')],
lmodel=None,
is_txt_stim=True,
device_name='LSL',
device_channels=None,
stimuli_timing=[1, .2],
decision_threshold=0.8,
backspace_prob=0.05,
backspace_always_shown=False,
filter_high=45,
filter_low=2,
filter_order=2,
notch_filter_frequency=60):
self.conjugator = EvidenceFusion(evidence_names, len_dist=len(alp))
inq_constants = []
if backspace_always_shown and BACKSPACE_CHAR in alp:
inq_constants.append(BACKSPACE_CHAR)
# Stimuli Selection Module
stopping_criteria = CriteriaEvaluator(
continue_criteria=[MinIterationsCriteria(min_num_inq)],
commit_criteria=[
MaxIterationsCriteria(max_num_inq),
ProbThresholdCriteria(decision_threshold)
])
# TODO: Parametrize len_query in the future releases!
stimuli_agent = NBestStimuliAgent(alphabet=alp, len_query=10)
self.decision_maker = DecisionMaker(
stimuli_agent=stimuli_agent,
stopping_evaluator=stopping_criteria,
state=task_list[0][1],
alphabet=alp,
is_txt_stim=is_txt_stim,
stimuli_timing=stimuli_timing,
inq_constants=inq_constants)
self.alp = alp
# non-letter target labels include the fixation cross and calibration.
self.nonletters = ['+', 'PLUS', 'calibration_trigger']
self.valid_targets = set(self.alp)
self.signal_model = signal_model
self.sampling_rate = fs
self.downsample_rate = k
self.filter_high = filter_high
self.filter_low = filter_low
self.filter_order = filter_order
self.notch_filter_frequency = notch_filter_frequency
self.mode = 'copy_phrase'
self.task_list = task_list
self.lmodel = lmodel
self.channel_map = analysis_channels(device_channels, device_name)
self.backspace_prob = backspace_prob