def plotERP(X, Y):
'plot the class averages'
global Cnames, Cpos, ylabel, yvals
erp = np.stack((X[:, :, Y > 0].mean(2), X[:, :, Y <= 0].mean(2)),
2) #compute the ERP
image3d(erp, 0, plotpos=Cpos, xvals=Cnames, ylabel=ylabel,
yvals=yvals) # plot the ERPs
def plotTrials(X, trls=range(3)):
'Plot the single-trial data'
global Cnames, Cpos, ylabel, yvals
image3d(X[:, :, 1:3],
0,
plotpos=Cpos,
xvals=Cnames,
ylabel=ylabel,
yvals=yvals)
Cpos = Cpos[:, goodch]
updatePlots()
# 3: apply spatial filter
X = preproc.spatialfilter(X, type='car')
updatePlots()
# 4 & 5: map to frequencies and select frequencies of interest
X = preproc.fftfilter(X, 1, [8, 10, 28, 30], fs)
updatePlots()
# 6 : bad-trial removal, trials in dim=2
goodtr, badtr = preproc.outlierdetection(X, dim=2)
X = X[:, :, goodtr]
Y = Y[goodtr]
updatePlots()
# 7: train linear least squares classifier, with cross-validation
from sklearn.linear_model import LinearRegression
clsfr = sklearn.linear_model.RidgeCV()
X2d = np.reshape(
X, (-1, X.shape[2])).T # sklearn needs x to be [nTrials x nFeatures]
clsfr.fit(X2d, Y)
clsfr.score
#8: plot the classifier weights
# plot the classifier weight vector
W = clsfr.coef_
W = np.reshape(clsfr.coef_, (X.shape[1], X.shape[0]))
image3d(W, 0, plotpos=Cpos, xvals=Cnames)
#load the datafile, and extract the variables
data=loadmat('ERPdata.mat')
X =data['X']
Y =data['Y'].reshape(-1) # ensure is 1d
fs =data['fs'][0] # ensure is scalar
Cnames=data['Cnames']
Cpos =data['Cpos']
ylabel='time (s)'
yvals =np.range(0,X.shape[1])/fs # element labels for 2nd dim of X
def plotTrials(X,trls=0:3):
'Plot the single-trial data'
global Cnames, Cpos, ylabel, yvals
image3d(X[:,:,1:3],0,plotpos=Cpos,xvals=Cnames,ylabel=ylabel,yvals=yvals)
def plotERP(X,Y):
'plot the class averages'
global Cnames, Cpos, ylabel, yvals
erp=np.stack((X[:,:,Y>0].mean(2),X[:,:,Y<=0].mean(2)),2) #compute the ERP
image3d(erp,0,plotpos=Cpos,xvals=Cnames,ylabel=ylabel,yvals=yvals) # plot the ERPs
def updatePlots:
global X,Y
# Plot the raw data
fig=plt.figure()
plotTrials(X) # single trial
fig=plt.figure()
plotERP(X,Y) # class averages
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()
# 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()
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);
nTarget[classlabel]= nTarget[classlabel]+1;
# detrend erp, so we can see stuff in the viewer
plterp = preproc.detrend(erp)
image3d(plterp,plotpos=xy,xvals=Cnames) # plot the ERPs
drawnow()
def plotERP(X,Y):
'plot the class averages'
global Cnames, Cpos, ylabel, yvals
erp=np.stack((X[:,:,Y>0].mean(2),X[:,:,Y<=0].mean(2)),2) #compute the ERP
image3d(erp,0,plotpos=Cpos,xvals=Cnames,ylabel=ylabel,yvals=yvals) # plot the ERPs
def plotTrials(X,trls):
'Plot the single-trial data'
global Cnames, Cpos, ylabel, yvals
image3d(X[:,:,1:3],0,plotpos=Cpos,xvals=Cnames,ylabel=ylabel,yvals=yvals)
from image3d import *
from scipy.io import loadmat
#load the datafile, and extract the variables
data=loadmat('ERSPdata.mat')
X =data['X']; print("X= [channels x timepoints x trials]");print(X.shape)
Y =data['Y'].reshape(-1); print("Y=[trials]");print(Y.shape)
fs =float(data['fs'][0])
Cnames=data['Cnames'].reshape(-1);
Cnames=np.array([item for sublist in Cnames for item in sublist]) #flatten the list of lists of names and make array
print("Channel names : ");print(Cnames)
Cpos =data['Cpos']; print("Cpos= [ 3 x channels]");print(Cpos.shape);
# plot the data
image3d(X[:,:,1:3],0,plotpos=Cpos);
# plot the class averages
erp=np.stack((X[:,:,Y>0].mean(2),X[:,:,Y<=0].mean(2)),2) #compute the ERP
image3d(erp,0,plotpos=Cpos,xvals=Cnames); # plot the ERPs
# define some utility functions to simplify plotting of data
ylabel='time (s)'
yvals =np.arange(0,X.shape[1])/fs # element labels for 2nd dim of X
def plotTrials(X,trls):
'Plot the single-trial data'
global Cnames, Cpos, ylabel, yvals
image3d(X[:,:,1:3],0,plotpos=Cpos,xvals=Cnames,ylabel=ylabel,yvals=yvals)
def plotERP(X,Y):