def communicate(call, get_ready, sos):
errors = 0
error_sos = 0
sos_time = 0
timer = core.Clock()
current_image = visual.ImageStim(mywin,
image="png/mobile.png") # set image
current_image.draw()
get_ready.text = 'You want to socialize. You can call anyone on the list using events of type "call" and values "1", "2" or "3". Right now, you want to call Livia. Note: each error will add 15s to your total time. \n\nPress any key to start'
showText(get_ready)
keys = waitForKeypress()
mywin.flip()
current_image.draw()
mywin.flip()
timer.reset()
triggerevents = ["call"]
stopevent = ("call", "end")
trlen_samp = 50
state = []
endCall = False
current_idx = 0
print("Waiting for triggers: %s and endtrigger: %s.%s" %
(triggerevents[0], stopevent[0], stopevent[1]))
while endCall is False:
# grab data after every t:'stimulus' event until we get a {t:'stimulus.training' v:'end'} event
#data, events, stopevents, state = bufhelp.gatherdata(triggerevents,trlen_samp,stopevent, state, milliseconds=False)
data, events, stopevents, state = bufhelp.gatherdata(
triggerevents, trlen_samp, [], state, milliseconds=False)
for ei in np.arange(len(events) - 1, -1, -1):
ev = events[ei]
if ev.type == "call":
if ev.value == "1":
current_image = visual.ImageStim(
mywin, "png/mobile_mom.png") # set image
if sos:
[sos_time,
error_sos] = sos_button(get_ready, current_image)
sos = False
elif ev.value == "2":
current_image = visual.ImageStim(
mywin, "png/mobile_terry.png") # set image
else:
current_image = visual.ImageStim(
mywin, "png/mobile_livia.png") # set image
current_image.draw()
mywin.flip()
if ev.value == call:
endCall = True
current_image = visual.ImageStim(
mywin, "png/mobile_done.png") # set image
current_image.draw()
mywin.flip()
core.wait(2)
else:
errors = errors + 1
return [timer.getTime(), errors, error_sos, sos_time]
def navigate(path, navigation, error, get_ready, sos):
errors = 0
error_sos = 0
sos_time = 0
timer = core.Clock()
current_image = visual.ImageStim(mywin,
image="png/navigation1.png") # set image
current_image.draw()
get_ready.text = 'Navigate from the front door to the couch using events of type "navigate" with values "left","right","down" and "up". Each dot represents one required event.\n\nNote: each error will add 15s to your total time. \n\nPress any key to start'
showText(get_ready)
keys = waitForKeypress()
mywin.flip()
current_image.draw()
mywin.flip()
timer.reset()
triggerevents = ["navigate"]
stopevent = ("navigate", "end")
trlen_samp = 50
state = []
endNavigate = False
current_idx = 0
print("Waiting for triggers: %s and endtrigger: %s.%s" %
(triggerevents[0], stopevent[0], stopevent[1]))
while endNavigate is False:
# grab data after every t:'stimulus' event until we get a {t:'stimulus.training' v:'end'} event
#data, events, stopevents, state = bufhelp.gatherdata(triggerevents,trlen_samp,stopevent, state, milliseconds=False)
data, events, stopevents, state = bufhelp.gatherdata(
triggerevents, trlen_samp, [], state, milliseconds=False)
for ei in np.arange(len(events) - 1, -1, -1):
ev = events[ei]
if ev.type == "navigate":
if ev.value == path[current_idx]:
current_idx = current_idx + 1
current_image = visual.ImageStim(
mywin, navigation[current_idx]) # set image
else:
current_image = visual.ImageStim(
mywin, error[current_idx]) # set image
errors = errors + 1
current_image.draw()
mywin.flip()
if current_idx == len(navigation) - 1:
current_image = visual.ImageStim(
mywin, "png/navigation_done.png") # set image
current_image.draw()
mywin.flip()
core.wait(2)
endNavigate = True
if current_idx > 5 and sos:
[sos_time, error_sos] = sos_button(get_ready, current_image)
sos = False
return [timer.getTime(), errors, error_sos, sos_time]
def communicate(call,get_ready,sos):
errors = 0
error_sos = 0
sos_time = 0
timer = core.Clock()
current_image = visual.ImageStim(mywin, image="png/mobile.png") # set image
current_image.draw()
get_ready.text ='You want to socialize. You can call anyone on the list using events of type "call" and values "1", "2" or "3". Right now, you want to call Livia. Note: each error will add 15s to your total time. \n\nPress any key to start'
showText(get_ready)
keys = waitForKeypress()
mywin.flip()
current_image.draw()
mywin.flip()
timer.reset()
triggerevents=["call"]
stopevent=("call","end")
trlen_samp = 50
state = []
endCall = False
current_idx = 0
print("Waiting for triggers: %s and endtrigger: %s.%s"%(triggerevents[0],stopevent[0],stopevent[1]))
while endCall is False:
# grab data after every t:'stimulus' event until we get a {t:'stimulus.training' v:'end'} event
#data, events, stopevents, state = bufhelp.gatherdata(triggerevents,trlen_samp,stopevent, state, milliseconds=False)
data, events, stopevents, state = bufhelp.gatherdata(triggerevents,trlen_samp,[], state, milliseconds=False)
for ei in np.arange(len(events)-1,-1,-1):
ev = events[ei]
if ev.type == "call":
if ev.value == "1":
current_image = visual.ImageStim(mywin, "png/mobile_mom.png") # set image
if sos:
[sos_time,error_sos] = sos_button(get_ready,current_image)
sos = False
elif ev.value == "2":
current_image = visual.ImageStim(mywin, "png/mobile_terry.png") # set image
else:
current_image = visual.ImageStim(mywin, "png/mobile_livia.png") # set image
current_image.draw()
mywin.flip()
if ev.value == call:
endCall = True
current_image = visual.ImageStim(mywin, "png/mobile_done.png") # set image
current_image.draw()
mywin.flip()
core.wait(2)
else:
errors = errors+1
return [timer.getTime(),errors,error_sos,sos_time]
def navigate(path,navigation,error,get_ready,sos):
errors = 0
error_sos = 0
sos_time = 0
timer = core.Clock()
current_image = visual.ImageStim(mywin, image="png/navigation1.png") # set image
current_image.draw()
get_ready.text ='Navigate from the front door to the couch using events of type "navigate" with values "left","right","down" and "up". Each dot represents one required event.\n\nNote: each error will add 15s to your total time. \n\nPress any key to start'
showText(get_ready)
keys = waitForKeypress()
mywin.flip()
current_image.draw()
mywin.flip()
timer.reset()
triggerevents=["navigate"]
stopevent=("navigate","end")
trlen_samp = 50
state = []
endNavigate = False
current_idx = 0
print("Waiting for triggers: %s and endtrigger: %s.%s"%(triggerevents[0],stopevent[0],stopevent[1]))
while endNavigate is False:
# grab data after every t:'stimulus' event until we get a {t:'stimulus.training' v:'end'} event
#data, events, stopevents, state = bufhelp.gatherdata(triggerevents,trlen_samp,stopevent, state, milliseconds=False)
data, events, stopevents, state = bufhelp.gatherdata(triggerevents,trlen_samp,[], state, milliseconds=False)
for ei in np.arange(len(events)-1,-1,-1):
ev = events[ei]
if ev.type == "navigate":
if ev.value == path[current_idx]:
current_idx = current_idx + 1
current_image = visual.ImageStim(mywin, navigation[current_idx]) # set image
else:
current_image = visual.ImageStim(mywin, error[current_idx]) # set image
errors = errors+1
current_image.draw()
mywin.flip()
if current_idx == len(navigation)-1:
current_image = visual.ImageStim(mywin, "png/navigation_done.png") # set image
current_image.draw()
mywin.flip()
core.wait(2)
endNavigate = True
if current_idx > 5 and sos:
[sos_time,error_sos] = sos_button(get_ready,current_image)
sos = False
return [timer.getTime(),errors, error_sos, sos_time]
def processBufferEvents():
global running
trlen_ms = 600
events = bufhelp.buffer_newevents()
for evt in events:
if str(evt.type) == 'calibrate' and evt.value == 'start':
print('Calibration phase, gathering data...')
data, events, stopevents = bufhelp.gatherdata("stimulus.target",
750,
("calibrate", "end"),
milliseconds=True)
pickle.dump({
"events": events,
"data": data
}, open("subject_data", "w"))
else:
print(str(evt.sample) + ": " + str(evt))
#!/usr/bin/env python3
# Set up imports and paths
import sys, os
# Get the helper functions for connecting to the buffer
try: pydir=os.path.dirname(__file__)
except: pydir=os.getcwd()
sigProcPath = os.path.join(os.path.abspath(pydir),'../../python/signalProc')
sys.path.append(sigProcPath)
import bufhelp
import pickle
import h5py
# connect to the buffer, if no-header wait until valid connection
ftc,hdr=bufhelp.connect()
# grab data
data, events, stopevents, pending = bufhelp.gatherdata()
# save the calibration data
pickle.dump({"events":events,"data":data,'hdr':hdr}, open(dname+'.pk','wb'))#N.B. to pickle open in binary mode
CLASSIFIER_FILENAME = cfg['p300']['classifier_filename']
SAMPLING_TIME = cfg['p300']['sampling_time']
#load the trained classifier
with open(os.path.join(DATA_PATH, CLASSIFIER_FILENAME), 'rb') as f:
p = pickle.load(f)
classifier = p['classifier']
goodch = p['goodch']
# connect to the buffer, if no-header wait until valid connection
ftc, hdr = bufhelp.connect()
while True:
# wait for data after a trigger event
data, events, stopevents, _ = bufhelp.gatherdata(
["p300.flash"],
SAMPLING_TIME, [("p300.singleseq", "end"), ("p300.seq", "end")],
milliseconds=True)
data = np.array(data)
# stop processing if needed
if "p300.seq" in [s.type for s in stopevents]:
break
# 0: Remove extra channels
data = data[:, :, :NUM_OF_CHANNELS]
# 1: detrend
data = preproc.detrend(data)
# 2: bad-channel removal; channels are last
data = data[:, :, goodch]
# 3: apply spatial filter
import pickle
bufhelp.connect()
trlen_ms = 600
run = True
print ("Waiting for startPhase.cmd event.")
while run:
e = bufhelp.waitforevent("startPhase.cmd",1000, True)
print("Got startPhase event: %s"%e)
if e is not None:
if e.value == "calibration":
print("Calibration phase")
data, events, stopevents = bufhelp.gatherdata("stimulus.tgtFlash",trlen_ms,("stimulus.training","end"), milliseconds=True)
pickle.dump({"events":events,"data":data}, open("subject_data", "w"))
elif e.value == "train":
print("Training classifier")
data = preproc.detrend(data)
data, badch = preproc.badchannelremoval(data)
data = preproc.spatialfilter(data)
data = preproc.spectralfilter(data, (0, .1, 10, 12), bufhelp.fSample)
data, events, badtrials = preproc.badtrailremoval(data, events)
mapping = {('stimulus.tgtFlash', '0'): 0, ('stimulus.tgtFlash', '1'): 1}
linear.fit(data,events,mapping)
bufhelp.update()
bufhelp.sendevent("sigproc.training","done")
elif e.value =="testing":
bufhelp.connect()
trlen_ms = 600
run = True
print("Waiting for startPhase.cmd event.")
while run:
e = bufhelp.waitforevent("startPhase.cmd", 1000, True)
print("Got startPhase event: %s" % e)
if e is not None:
if e.value == "calibration":
print("Calibration phase")
data, events, stopevents = bufhelp.gatherdata(
"stimulus.tgtFlash",
trlen_ms, ("stimulus.training", "end"),
milliseconds=True)
pickle.dump({
"events": events,
"data": data
}, open("subject_data", "w"))
elif e.value == "train":
print("Training classifier")
data = preproc.detrend(data)
data, badch = preproc.badchannelremoval(data)
data = preproc.spatialfilter(data)
data = preproc.spectralfilter(data, (0, .1, 10, 12),
bufhelp.fSample)
data, events, badtrials = preproc.badtrailremoval(data, events)
mapping = {
freqbands = f['freqbands']
classifier = f['classifier']
fs = f['fSample']
# connect to the buffer, if no-header wait until valid connection
ftc, hdr = bufhelp.connect()
# clear event history
pending = []
while True:
# wait for data after a trigger event
# exitevent=None means return as soon as data is ready
# N.B. be sure to propogate state between calls
data, events, stopevents, pending = bufhelp.gatherdata(["stimulus.char"],
trlen_ms,
None,
pending,
milliseconds=True)
# get all event type labels
event_types = [e.type[0] for e in events]
event_letters = [e.value[0] for e in events]
# stop processing if needed
if "stimulus.feedback" in event_types:
break
# get data in correct format
data = np.transpose(data)
# 1: detrend
bufhelp.connect()
trlen_ms = 700
run = True
print("Waiting for startPhase.cmd event.")
while run:
e = bufhelp.waitforevent("startPhase.cmd", 1000, True)
print("Got startPhase event: %s" % e)
if e is not None:
if e.value == "calibrate":
print("Calibration phase")
data, events, stopevents = bufhelp.gatherdata(
"stimulus.hybrid",
trlen_ms, ("stimulus.training", "end"),
milliseconds=True)
pickle.dump({
"events": events,
"data": data
}, open("subject_data", "wb"))
elif e.value == "training":
print("Training classifier")
data = preproc.detrend(data)
data, badch = preproc.badchannelremoval(data)
data = preproc.spatialfilter(data)
data = preproc.spectralfilter(data, (1, 10, 15, 25),
bufhelp.fSample)
def watch_tv(channel,min_time,get_ready,sos):
errors = 0
error_sos = 0
sos_time = 0
timer = core.Clock()
current_image = visual.ImageStim(mywin, image="png/tv.png") # set image
current_image.draw()
get_ready.text ='You want to watch tv. First go through each channel using events of type "tv" and value "1", "2" and "3". Then, go through each channel for a second time until you see a channel with a green mark next to it. This is the preferred channel. Look at this channel for at least 30s without changing channels. After 30s, turn off the tv using an event of type "tv" with the value "end". \n\nNote: each error will add 5s to your total time.\n\nPress any key to start'
showText(get_ready)
keys = waitForKeypress()
mywin.flip()
current_image.draw()
mywin.flip()
timer.reset()
triggerevents=["tv"]
stopevent=("tv","end")
trlen_samp = 50
state = []
endTV = False
current_idx = 0
channels_seen = [False, False, False]
channel_timer = core.Clock()
start_counting = False
print("Waiting for triggers: %s and endtrigger: %s.%s"%(triggerevents[0],stopevent[0],stopevent[1]))
while endTV is False:
# grab data after every t:'stimulus' event until we get a {t:'stimulus.training' v:'end'} event
#data, events, stopevents, state = bufhelp.gatherdata(triggerevents,trlen_samp,stopevent, state, milliseconds=False)
data, events, stopevents, state = bufhelp.gatherdata(triggerevents,trlen_samp,[], state, milliseconds=False)
channel_update = False
for ei in np.arange(len(events)-1,-1,-1):
ev = events[ei]
if ev.type == "tv":
if ev.value == "1":
current_image = visual.ImageStim(mywin, "png/tv_nature.png") # set image
if channels_seen[0] is False:
channels_seen[0] = True
channel_update = True
elif ev.value == "2":
current_image = visual.ImageStim(mywin, "png/tv_mes_op_tafel.png") # set image
if channels_seen[1] is False:
channels_seen[1] = True
channel_update = True
if sos:
[sos_time,error_sos] = sos_button(get_ready,current_image)
sos = False
elif ev.value == "3":
current_image = visual.ImageStim(mywin, "png/tv_sesamstraat.png") # set image
if channels_seen[2] is False:
channels_seen[2] = True
channel_update = True
current_image.draw()
mywin.flip()
if (channel_update is False) and (False not in channels_seen):
if ev.value == channel:
if start_counting is False:
current_image = visual.ImageStim(mywin, "png/tv_done.png") # set image
current_image.draw()
mywin.flip()
start_counting = True
channel_timer.reset() # start counting time
elif ev.value == "end":
if channel_timer.getTime >= min_time:
endTV = True
else:
start_counting = False
print("error!")
errors = errors + 1
return [timer.getTime(),errors,error_sos,sos_time]
# invert the value dict to get a key->value map
ivaluedict = {k: v for k, v in valuedict.items()}
# connect to the buffer, if no-header wait until valid connection
ftc, hdr = bufhelp.connect()
fs = hdr.fSample
pending = []
while True:
# wait for data after a trigger event
# exitevent=None means return as soon as data is ready
# N.B. be sure to propogate state between calls
data, events, stopevents, pending = bufhelp.gatherdata(["stimulus.flash"],
trlen_ms,
None,
pending,
milliseconds=True,
verbose=True)
# get all event type labels
event_types = [e.type[0] for e in events]
# stop processing if needed
if "stimulus.feedback" in event_types:
break
print("Applying classifier to %d events" % (len(events)))
# get data in correct format
data = np.transpose(data) # make it [d x tau]
classifier = f['classifier']
fs = f['fSample']
# invert the value dict to get a key->value map
ivaluedict = { k:v for k,v in valuedict.items() }
# connect to the buffer, if no-header wait until valid connection
ftc,hdr=bufhelp.connect()
# clear event history
pending = []
while True:
# wait for data after a trigger event
# exitevent=None means return as soon as data is ready
# N.B. be sure to propogate state between calls
data, events, stopevents, pending = bufhelp.gatherdata(["stimulus.target"], trlen_ms, None, pending, milliseconds=True)
# get all event type labels
event_types = [e.type[0] for e in events]
# stop processing if needed
if "stimulus.feedback" in event_types:
break
# get data in correct format
data = np.transpose(data)
# 1: detrend
data = preproc.detrend(data)
# 2: bad-channel removal (as identifed in classifier training)
data = data[goodch,:,:]
# init connection to the buffer
ftc,hdr=bufhelp.connect();
#define variables
trlen_samp = 50
nSymbols = 2
nr_channels = 4 # in debug mode
erp = np.zeros((nr_channels,trlen_samp,nSymbols))
nTarget = np.zeros((nSymbols,1))
# read in the capfile
Cname,latlong,xy,xyz,capfile= readCapInf.readCapInf('sigproxy_with_TRG')
fig=plt.figure()
# grab data after every t:'stimulus' event until we get a {t:'stimulus.training' v:'end'} event
data, events, stopevents = bufhelp.gatherdata(["stimulus","experiment"],trlen_samp,("sequence","end"), milliseconds=False)
# loop through all recorded events (last to first)
for ei in np.arange(len(events)-1,-1,-1):
# detrend erp, so we can see stuff
erp = preproc.detrend(erp)
image3d(erp) # plot the ERPs
plt.show()
def sos_button(get_ready, previous_image):
errors = 0
sos = ["png/sos_food.png", "png/sos_pain.png", "png/sos_toilet.png"]
# choose random sos
r = np.random.randint(len(sos))
timer = core.Clock()
current_image = visual.ImageStim(mywin, image=sos[r]) # set image
current_image.draw()
get_ready.text = 'Emergency! You are in pain, need to go to the toilet or want food. What help you need is indicated by an icon on the screen. First press the SOS button by sending an event of type "sos" and value "on". Once the button is activated and help is on the way, select what type of help you need. You can do so with events of type "sos" and values "toilet", "pain" and "food".\n\nNote: each error will add 60s to your total time. \n\nPress any key to start'
showText(get_ready)
keys = waitForKeypress()
mywin.flip()
current_image.draw()
mywin.flip()
timer.reset()
triggerevents = ["sos"]
stopevent = ("sos", "end")
trlen_samp = 50
state = []
endSOS = False
current_idx = 0
print("Waiting for triggers: %s and endtrigger: %s.%s" %
(triggerevents[0], stopevent[0], stopevent[1]))
while endSOS is False:
# grab data after every t:'stimulus' event until we get a {t:'stimulus.training' v:'end'} event
#data, events, stopevents, state = bufhelp.gatherdata(triggerevents,trlen_samp,stopevent, state, milliseconds=False)
data, events, stopevents, state = bufhelp.gatherdata(
triggerevents, trlen_samp, [], state, milliseconds=False)
for ei in np.arange(len(events) - 1, -1, -1):
ev = events[ei]
if ev.type == "sos":
if ev.value == "on":
current_image = visual.ImageStim(
mywin, "png/alarm_done.png") # set image
endSOS = True
else:
current_image = visual.ImageStim(
mywin, "png/alarm_error.png") # set image
errors = errors + 1
current_image.draw()
mywin.flip()
core.wait(1)
current_image = visual.ImageStim(mywin,
image=sos[r]) # set image
current_image.draw()
mywin.flip()
current_image = visual.ImageStim(mywin, "png/sos_choice.png") # set image
current_image.draw()
mywin.flip()
endSOS = False
while endSOS is False:
# grab data after every t:'stimulus' event until we get a {t:'stimulus.training' v:'end'} event
#data, events, stopevents, state = bufhelp.gatherdata(triggerevents,trlen_samp,stopevent, state, milliseconds=False)
data, events, stopevents, state = bufhelp.gatherdata(
triggerevents, trlen_samp, [], state, milliseconds=False)
for ei in np.arange(len(events) - 1, -1, -1):
ev = events[ei]
if ev.type == "sos":
if ev.value == "food":
if r == 0:
current_image = visual.ImageStim(
mywin, "png/food.png") # set image
endSOS = True
else:
current_image = visual.ImageStim(
mywin, "png/food_error.png") # set image
errors = errors + 1
elif ev.value == "pain":
if r == 1:
current_image = visual.ImageStim(
mywin, "png/pain.png") # set image
endSOS = True
else:
current_image = visual.ImageStim(
mywin, "png/pain_error.png") # set image
errors = errors + 1
elif ev.value == "toilet":
if r == 2:
current_image = visual.ImageStim(
mywin, "png/toilet.png") # set image
endSOS = True
else:
current_image = visual.ImageStim(
mywin, "png/toilet_error.png") # set image
errors = errors + 1
current_image.draw()
mywin.flip()
if endSOS is True:
core.wait(3)
previous_image.draw() # set image
mywin.flip()
return [timer.getTime(), errors]
import pickle
dname = 'training_data'
cname = 'clsfr'
trlen_ms = 3000
#load the trained classifier
if os.path.exists(cname + '.pk'):
f = pickle.load(open(cname + '.pk', 'rb'))
classifier = f['classifier']
# connect to the buffer, if no-header wait until valid connection
ftc, hdr = bufhelp.connect()
while True:
# wait for data after a trigger event
data, events, stopevents, state = bufhelp.gatherdata(
["stimulus.target"],
trlen_ms, [("stimulus.feedback", "end")],
milliseconds=True)
# YOUR CODE HERE #
# apply classifier, default is a linear-least-squares-classifier
predictions = linear.predict(data)
# send the prediction events
for pred in predictions:
bufhelp.sendEvent("classifier.prediction", pred)
#!/usr/bin/env python3
# Set up imports and paths
import sys, os
# Get the helper functions for connecting to the buffer
try: pydir=os.path.dirname(__file__)
except: pydir=os.getcwd()
sigProcPath = os.path.join(os.path.abspath(pydir),'../../python/signalProc')
sys.path.append(sigProcPath)
import bufhelp
# connect to the buffer, if no-header wait until valid connection
bufhelp.connect()
trlen_ms = 600
print("Calibration phase")
# grab data after every t:'stimulus.target' event until we get a {t:'stimulus.training' v:'end'} event
data, events, stopevents, state = bufhelp.gatherdata()
# save the calibration data
pickle.dump({"events":events,"data":data}, open("subject_data", "w"))
# connect to the buffer, if no-header wait until valid connection
ftc, hdr = bufhelp.connect()
fs = hdr.fSample
pending = []
while True:
# wait for data after a trigger event
# exitevent=None means return as soon as data is ready
# N.B. be sure to propagate state between calls
try:
print("ErrP classifier waiting for data...")
bufhelp.sendEvent('errp_clsfr.state', 'listening')
data, events, stopevents, pending = bufhelp.gatherdata(
['stimulus.prediction'],
trlen_ms,
None,
pending,
milliseconds=True,
verbose=False)
# get all event type labels
events = [(e.type, e.value) for e in events]
# stop processing if testing ends
##if ('feedback.testing', 'end') in events:
## print("Stopping signal processing.")
## break
print("Applying ErrP classifier to %d events" % len(events))
# get data in correct format
data = np.asarray(data) # [ nTrials x time x d ]
def sos_button(get_ready,previous_image):
errors = 0
sos = ["png/sos_food.png", "png/sos_pain.png", "png/sos_toilet.png"]
# choose random sos
r = np.random.randint(len(sos))
timer = core.Clock()
current_image = visual.ImageStim(mywin, image=sos[r]) # set image
current_image.draw()
get_ready.text ='Emergency! You are in pain, need to go to the toilet or want food. What help you need is indicated by an icon on the screen. First press the SOS button by sending an event of type "sos" and value "on". Once the button is activated and help is on the way, select what type of help you need. You can do so with events of type "sos" and values "toilet", "pain" and "food".\n\nNote: each error will add 60s to your total time. \n\nPress any key to start'
showText(get_ready)
keys = waitForKeypress()
mywin.flip()
current_image.draw()
mywin.flip()
timer.reset()
triggerevents=["sos"]
stopevent=("sos","end")
trlen_samp = 50
state = []
endSOS = False
current_idx = 0
print("Waiting for triggers: %s and endtrigger: %s.%s"%(triggerevents[0],stopevent[0],stopevent[1]))
while endSOS is False:
# grab data after every t:'stimulus' event until we get a {t:'stimulus.training' v:'end'} event
#data, events, stopevents, state = bufhelp.gatherdata(triggerevents,trlen_samp,stopevent, state, milliseconds=False)
data, events, stopevents, state = bufhelp.gatherdata(triggerevents,trlen_samp,[], state, milliseconds=False)
for ei in np.arange(len(events)-1,-1,-1):
ev = events[ei]
if ev.type == "sos":
if ev.value == "on":
current_image = visual.ImageStim(mywin, "png/alarm_done.png") # set image
endSOS = True
else:
current_image = visual.ImageStim(mywin, "png/alarm_error.png") # set image
errors = errors + 1
current_image.draw()
mywin.flip()
core.wait(1)
current_image = visual.ImageStim(mywin, image=sos[r]) # set image
current_image.draw()
mywin.flip()
current_image = visual.ImageStim(mywin, "png/sos_choice.png") # set image
current_image.draw()
mywin.flip()
endSOS = False
while endSOS is False:
# grab data after every t:'stimulus' event until we get a {t:'stimulus.training' v:'end'} event
#data, events, stopevents, state = bufhelp.gatherdata(triggerevents,trlen_samp,stopevent, state, milliseconds=False)
data, events, stopevents, state = bufhelp.gatherdata(triggerevents,trlen_samp,[], state, milliseconds=False)
for ei in np.arange(len(events)-1,-1,-1):
ev = events[ei]
if ev.type == "sos":
if ev.value == "food":
if r == 0:
current_image = visual.ImageStim(mywin, "png/food.png") # set image
endSOS = True
else:
current_image = visual.ImageStim(mywin, "png/food_error.png") # set image
errors = errors + 1
elif ev.value == "pain":
if r == 1:
current_image = visual.ImageStim(mywin, "png/pain.png") # set image
endSOS = True
else:
current_image = visual.ImageStim(mywin, "png/pain_error.png") # set image
errors = errors + 1
elif ev.value == "toilet":
if r == 2:
current_image = visual.ImageStim(mywin, "png/toilet.png") # set image
endSOS = True
else:
current_image = visual.ImageStim(mywin, "png/toilet_error.png") # set image
errors = errors + 1
current_image.draw()
mywin.flip()
if endSOS is True:
core.wait(3)
previous_image.draw() # set image
mywin.flip()
return [timer.getTime(),errors]
def watch_tv(channel, min_time, get_ready, sos):
errors = 0
error_sos = 0
sos_time = 0
timer = core.Clock()
current_image = visual.ImageStim(mywin, image="png/tv.png") # set image
current_image.draw()
get_ready.text = 'You want to watch tv. First go through each channel using events of type "tv" and value "1", "2" and "3". Then, go through each channel for a second time until you see a channel with a green mark next to it. This is the preferred channel. Look at this channel for at least 30s without changing channels. After 30s, turn off the tv using an event of type "tv" with the value "end". \n\nNote: each error will add 5s to your total time.\n\nPress any key to start'
showText(get_ready)
keys = waitForKeypress()
mywin.flip()
current_image.draw()
mywin.flip()
timer.reset()
triggerevents = ["tv"]
stopevent = ("tv", "end")
trlen_samp = 50
state = []
endTV = False
current_idx = 0
channels_seen = [False, False, False]
channel_timer = core.Clock()
start_counting = False
print("Waiting for triggers: %s and endtrigger: %s.%s" %
(triggerevents[0], stopevent[0], stopevent[1]))
while endTV is False:
# grab data after every t:'stimulus' event until we get a {t:'stimulus.training' v:'end'} event
#data, events, stopevents, state = bufhelp.gatherdata(triggerevents,trlen_samp,stopevent, state, milliseconds=False)
data, events, stopevents, state = bufhelp.gatherdata(
triggerevents, trlen_samp, [], state, milliseconds=False)
channel_update = False
for ei in np.arange(len(events) - 1, -1, -1):
ev = events[ei]
if ev.type == "tv":
if ev.value == "1":
current_image = visual.ImageStim(
mywin, "png/tv_nature.png") # set image
if channels_seen[0] is False:
channels_seen[0] = True
channel_update = True
elif ev.value == "2":
current_image = visual.ImageStim(
mywin, "png/tv_mes_op_tafel.png") # set image
if channels_seen[1] is False:
channels_seen[1] = True
channel_update = True
if sos:
[sos_time,
error_sos] = sos_button(get_ready, current_image)
sos = False
elif ev.value == "3":
current_image = visual.ImageStim(
mywin, "png/tv_sesamstraat.png") # set image
if channels_seen[2] is False:
channels_seen[2] = True
channel_update = True
current_image.draw()
mywin.flip()
if (channel_update is False) and (False not in channels_seen):
if ev.value == channel:
if start_counting is False:
current_image = visual.ImageStim(
mywin, "png/tv_done.png") # set image
current_image.draw()
mywin.flip()
start_counting = True
channel_timer.reset() # start counting time
elif ev.value == "end":
if channel_timer.getTime >= min_time:
endTV = True
else:
start_counting = False
print("error!")
errors = errors + 1
return [timer.getTime(), errors, error_sos, sos_time]
#!/usr/bin/env python3
# Set up imports and paths
import sys, os
# Get the helper functions for connecting to the buffer
try: pydir=os.path.dirname(__file__)
except: pydir=os.getcwd()
sigProcPath = os.path.join(os.path.abspath(pydir),'../../python/signalProc')
sys.path.append(sigProcPath)
import bufhelp
import pickle
# connect to the buffer, if no-header wait until valid connection
ftc,hdr=bufhelp.connect()
trlen_ms = 600
dname ='training_data';
cname ='clsfr';
print("Calibration phase")
# grab data after every t:'stimulus.target' event until we get a {t:'stimulus.training' v:'end'} event
data, events, stopevents, pending = bufhelp.gatherdata("stimulus.tgtFlash",trlen_ms,("stimulus.training","end"), milliseconds=True)
# save the calibration data
pickle.dump({"events":events,"data":data,'hdr':hdr}, open(dname+'.pk','wb'))#N.B. to pickle open in binary mode
# # also as a hdf5 / .mat v7.3 fi
# # doesn't work.... need to unpack objects into basic types for hdf5
# f = h5py.File(dname+'.mat','w')
# f.create_dataset('data',data=data)
# f.create_dataset('events',data=events)
# f.create_dataset('hdr',data=hdr)
#!/usr/bin/env python3
# Set up imports and paths
import sys, os
# Get the helper functions for connecting to the buffer
try:
pydir = os.path.dirname(__file__)
except:
pydir = os.getcwd()
sigProcPath = os.path.join(os.path.abspath(pydir), '../../python/signalProc')
sys.path.append(sigProcPath)
import bufhelp
import pickle
import h5py
# connect to the buffer, if no-header wait until valid connection
ftc, hdr = bufhelp.connect()
# grab data
data, events, stopevents, pending = bufhelp.gatherdata()
# save the calibration data
pickle.dump({
"events": events,
"data": data,
'hdr': hdr
}, open(dname + '.pk', 'wb')) #N.B. to pickle open in binary mode
import sys
sys.path.append('../../python/signalProc')
import pickle
import bufhelp
_, hdr = bufhelp.connect()
data, events, _ = bufhelp.gatherdata('stimulus.type',
600,
'experiment.end',
milliseconds=True)
pickle.dump({
'data': data,
'events': events,
'hdr': hdr,
}, open('training_data.pkl', 'wb'))
import preproc
import linear
import pickle
dname ='training_data'
cname ='clsfr'
trlen_ms = 3000
#load the trained classifier
if os.path.exists(cname+'.pk'):
f =pickle.load(open(cname+'.pk','rb'))
classifier = f['classifier']
# connect to the buffer, if no-header wait until valid connection
ftc,hdr=bufhelp.connect()
while True:
# wait for data after a trigger event
data, events, stopevents, state = bufhelp.gatherdata(["stimulus.target"],trlen_ms,[("stimulus.feedback","end")], milliseconds=True)
# YOUR CODE HERE #
# apply classifier, default is a linear-least-squares-classifier
predictions = linear.predict(data)
# send the prediction events
for pred in predictions:
bufhelp.sendEvent("classifier.prediction",pred)
#!/usr/bin/env python3
# Set up imports and paths
import sys, os
# Get the helper functions for connecting to the buffer
try:
pydir = os.path.dirname(__file__)
except:
pydir = os.getcwd()
sigProcPath = os.path.join(os.path.abspath(pydir), '../../python/signalProc')
sys.path.append(sigProcPath)
import bufhelp
# connect to the buffer, if no-header wait until valid connection
bufhelp.connect()
trlen_ms = 600
print("Calibration phase")
# grab data after every t:'stimulus.target' event until we get a {t:'stimulus.training' v:'end'} event
data, events, stopevents = bufhelp.gatherdata()
# save the calibration data
pickle.dump({"events": events, "data": data}, open("subject_data", "w"))
from image3d import *
# init connection to the buffer
ftc, hdr = bufhelp.connect()
#define variables
trlen_samp = 50
nSymbols = 2
nr_channels = 4 # in debug mode
erp = np.zeros((nr_channels, trlen_samp, nSymbols))
nTarget = np.zeros((nSymbols, 1))
# read in the capfile
Cname, latlong, xy, xyz, capfile = readCapInf.readCapInf('sigproxy_with_TRG')
fig = plt.figure()
# grab data after every t:'stimulus' event until we get a {t:'stimulus.training' v:'end'} event
data, events, stopevents = bufhelp.gatherdata(["stimulus", "experiment"],
trlen_samp, ("sequence", "end"),
milliseconds=False)
# loop through all recorded events (last to first)
for ei in np.arange(len(events) - 1, -1, -1):
# detrend erp, so we can see stuff
erp = preproc.detrend(erp)
image3d(erp) # plot the ERPs
plt.show()
"""
Listens for stimulus.target events until it sees
the (stimulus.training, end) event. Then saves all data in a pickle.
"""
# Imports
import sys
import pickle
sys.path.append('../signalProc/')
import bufhelp
import h5py
# connect to buffer
ftc, hdr = bufhelp.connect()
# Constants
trlen_ms = 3000
dname = 'training_data'
cname = 'clsfr'
data, events, stopevents = bufhelp.gatherdata("stimulus.target",
trlen_ms,
("stimulus.training", "end"),
milliseconds=True)
pickle.dump({'events': events,
'data': data,
'hdr': hdr
}, open(dname+'.pk', 'wb')
)
#!/usr/bin/env python3
BUFFERBCI_PATH = '../../buffer_bci/python/signalProc/'
import sys
import os
sys.path.append(BUFFERBCI_PATH)
import pickle
import yaml
import bufhelp
DATA_PATH = 'data'
if not os.path.exists(DATA_PATH):
os.makedirs(DATA_PATH)
cfg = yaml.load(open('config.yml', 'r'), Loader=yaml.FullLoader)
SAMPLING_TIME = cfg['p300']['sampling_time']
DATA_FILENAME = cfg['p300']['subject_data_filename']
print("Calibration phase")
# Connect to buffer_bci
ftc, hdr = bufhelp.connect()
# Grab data after every t:'stimulus.cue' event until we get a {t:'stimulus.training' v:'end'} event
data, events, stopevents, _ = bufhelp.gatherdata(
trigger='stimulus.cue',
time=SAMPLING_TIME,
stoptrigger=('stimulus.seq', 'end'),
milliseconds=True)
# Save the calibration data
with open(os.path.join(DATA_PATH, DATA_FILENAME), 'wb') as f:
pickle.dump({"events":events,"data":data, "hdr": hdr}, f)
#!/usr/bin/env python3
# Set up imports and paths
import sys, os
# Get the helper functions for connecting to the buffer
try:
pydir = os.path.dirname(__file__)
except:
pydir = os.getcwd()
sigProcPath = os.path.join(os.path.abspath(pydir), '../../python/signalProc')
sys.path.append(sigProcPath)
import bufhelp
import pickle
# connect to the buffer, if no-header wait until valid connection
ftc, hdr = bufhelp.connect()
trialLength = 3000
dname = 'training_data_imagined_movement'
cname = 'classifier_imagined_movement'
# grab data after every t:'stimulus.target' event until we get a {t:'stimulus.training' v:'end'} event
data, events, stopevents, pending = bufhelp.gatherdata(
"stimulus.target",
trialLength, ("stimulus.training", "end"),
milliseconds=True)
# save the calibration data
pickle.dump({
"events": events,
"data": data,
'hdr': hdr
}, open(dname + '.pk', 'wb')) #N.B. to pickle open in binary mode
sigProcPath = os.path.join(os.path.abspath(pydir), '../../python/signalProc')
sys.path.append(sigProcPath)
import bufhelp
import pickle
# connect to the buffer, if no-header wait until valid connection
ftc, hdr = bufhelp.connect()
trlen_ms = 600
dname = 'training_data'
cname = 'clsfr'
print("Calibration phase")
# grab data after every t:'stimulus.target' event until we get a {t:'stimulus.training' v:'end'} event
data, events, stopevents, pending = bufhelp.gatherdata(
"stimulus.tgtFlash",
trlen_ms, ("stimulus.training", "end"),
milliseconds=True)
# save the calibration data
pickle.dump({
"events": events,
"data": data,
'hdr': hdr
}, open(dname + '.pk', 'wb')) #N.B. to pickle open in binary mode
# # also as a hdf5 / .mat v7.3 fi
# # doesn't work.... need to unpack objects into basic types for hdf5
# f = h5py.File(dname+'.mat','w')
# f.create_dataset('data',data=data)
# f.create_dataset('events',data=events)
# f.create_dataset('hdr',data=hdr)
valuedict = f['valuedict']
classifier = f['classifier']
# invert the value dict to get a key->value map
ivaluedict = { k:v for k,v in valuedict.items() }
# connect to the buffer, if no-header wait until valid connection
ftc,hdr=bufhelp.connect()
fs = hdr.fSample
pending = []
while True:
# wait for data after a trigger event
# exitevent=None means return as soon as data is ready
# N.B. be sure to propogate state between calls
data, events, stopevents, pending = bufhelp.gatherdata(["stimulus.flash"], trlen_ms, None, pending, milliseconds=True, verbose=True)
# get all event type labels
event_types = [e.type[0] for e in events]
# stop processing if needed
if "stimulus.feedback" in event_types:
break
print("Applying classifier to %d events"%(len(events)))
# get data in correct format
data = np.transpose(data) # make it [d x tau]
# 1: detrend
data = preproc.detrend(data)
if verbose: print('Loading normalizer file....')
if os.path.exists(Normalizer_name + '.pk'):
f = pickle.load(open(Normalizer_name + '.pk', 'rb'))
scaler = f['normalizer']
if verbose: print('Normalizer loaded #')
else:
print('Debug mode')
while True:
if not DEBUG:
if verbose: print('Collecting data...')
data, events, stopevents, pending = bufhelp.gatherdata(
"errp.trigger", recording_lenght, [], milliseconds=True)
data = np.array(data)
# get data in correct format
data = np.moveaxis(data, 1, 2)
# preprocess pipeline
# 1: detrend
data = preproc.detrend(data)
# 2: bad-channel removal (as identifed in classifier training)
data = data[:, goodch, :]
# 3: apply spatial filter (as in classifier training)
data = preproc.spatialfilter(data, type=spatialfilter)
# 4 & 5: spectral filter (TODO: check fs matches!!)
data = preproc.fftfilter(data, 1, freqbands, fs)
##### Gathering data from the events ######
# In this part the programs enters in a loop, it will wait for events telling it to collect data, it'll process it and wait for
# events again untill the program is closed
while True:
if verbose: print('Collecting data...') # Information in terminal, verbose option
data, events_im, stopevents, pending = bufhelp.gatherdata(["stimulus.target", "stimulus.last_target"],im_length,[], milliseconds=True)
data = np.array(data) # data contains the signal sampled, 750 samples for 32 channels
data_rec = np.copy(data)
if verbose: print(events_im[0].value) # Information in terminal, verbose option, for debugging purposes
if verbose: print(data.shape) # Information in terminal, verbose option, for debugging purposes
data = data[:,:,:]
if verbose: print(data.shape) # Information in terminal, verbose option, for debugging purposes
data = np.array(data) #data support variable
data = np.transpose(data)
fig.canvas.draw()
plt.pause(1e-3) # wait for draw.. 1ms
plt.ion()
fig=plt.figure()
drawnow()
triggerevents=["stimulus","experiment"]
stopevent=('sequence','end')
state = []
endTest = False
print("Waiting for triggers: %s and endtrigger: %s"%(triggerevents[0],stopevent[0]))
while endTest is False:
# grab data after every t:'stimulus' event until we get a {t:'stimulus.training' v:'end'} event
#data, events, stopevents, state = bufhelp.gatherdata(triggerevents,trlen_samp,stopevent, state, milliseconds=False)
data, events, stopevents, state = bufhelp.gatherdata(triggerevents,trlen_samp,[], state, milliseconds=False)
for ei in np.arange(len(events)-1,-1,-1):
ev = events[ei]
# check for exit event
if (ev.type == "experiment") and (ev.value == "end"):
endTest = True
print("end experiment")
break
# update ERP
if ev.value is '+':
classlabel = 1
else:
classlabel = 0
erp[:,:,classlabel] = (erp[:,:,classlabel]*nTarget[classlabel] + np.transpose(data[ei]))/(nTarget[classlabel]+1);
