In [29]:
clear all
In [30]:
import matplotlib
import numpy as np
import matplotlib.pyplot as plt
from scipy import stats
from scipy import io
import scipy.io as sio
%matplotlib inline
import pylab
import csv
from Tkinter import Tk
from tkFileDialog import askopenfilename
from tkFileDialog import askdirectory
import nibabel as nb
from scipy import io
import nibabel as nb
from scipy.interpolate import interp1d
from scipy import ndimage
In [31]:
from sklearn import linear_model
In [32]:
# from http://stackoverflow.com/questions/3579568/choosing-a-file-in-python-with-simple-dialog
Tk().withdraw() # we don't want a full GUI, so keep the root window from appearing
filename = askopenfilename() # show an "Open" dialog box and return the path to the selected file
print(filename)
In [33]:
Ua=sio.loadmat(filename)
DT=Ua['TSo']
DT.shape
Out[33]:
In [34]:
# from http://stackoverflow.com/questions/3579568/choosing-a-file-in-python-with-simple-dialog
Tk().withdraw() # we don't want a full GUI, so keep the root window from appearing
filename2 = askopenfilename() # show an "Open" dialog box and return the path to the selected file
print(filename2)
In [35]:
img1 = nb.load(filename2)
data = img1.get_data()
S=data.shape
S
Out[35]:
Z-score
In [36]:
Demean=np.zeros(S)
Dmaps=np.zeros(S)
Dvar=np.zeros(S)
Var=np.zeros(S[3])
D2=np.zeros([S[0],S[1],5,S[3]])
Tvar=np.zeros(S[3])
In [37]:
for i in range(S[3]):
Demean[:,:,:,i]=data[:,:,:,i]-np.mean(np.mean(np.mean(data[:,:,:,i],0),0),0)
In [38]:
for i in range(S[3]):
Dsq=np.reshape(Demean[:,:,:,i],S[0]*S[1]*S[2])
Var[i]=np.sqrt(np.var(Dsq))
Dvar=Demean[:,:,:,i]/Var[i]
Dmaps[:,:,:,i]=Dvar-2
Tvar[i]=np.var(DT[i,:])
Dmaps[Dmaps<0]=0
In [39]:
# from http://stackoverflow.com/questions/3579568/choosing-a-file-in-python-with-simple-dialog
Tk().withdraw() # we don't want a full GUI, so keep the root window from appearing
filename = askopenfilename() # show an "Open" dialog box and return the path to the selected file
print(filename)
In [40]:
Ua=sio.loadmat(filename)
Xk=Ua['Xk']
In [41]:
# from http://stackoverflow.com/questions/3579568/choosing-a-file-in-python-with-simple-dialog
from Tkinter import Tk
from tkFileDialog import askopenfilename
Tk().withdraw() # we don't want a full GUI, so keep the root window from appearing
filenamet = askopenfilename() # show an "Open" dialog box and return the path to the selected file
print(filenamet)
nimt=nb.load(filenamet)
Dtemp=np.squeeze(nimt.get_data())
Dtemp.shape
Out[41]:
In [44]:
%%javascript
IPython.OutputArea.auto_scroll_threshold =4000;
In [45]:
if S[2]>5:
Nstack=5
Int100=[(i+1)*100/Nstack for i in range(Nstack)]
Percs=np.percentile(range(S[2]),Int100)
Indices=np.split(range(S[2]),Percs)
D1=np.zeros([S[0],S[1],Nstack])
Dmean=np.squeeze(data[:,:,range(Nstack),2])
for i in range(Nstack):
Vmean=np.mean(Dtemp[:,:,Indices[i]],2)
Dmean[:,:,i]=Vmean
else:
Nstack=S[2]
D1=np.zeros([S[0],S[1],S[2]])
Dmean=data[:,:,range(S[2])]
Dmean=np.squeeze(Dtemp[:,:,:])
In [46]:
for j in range(S[3]):
a=''
if S[2]>5:
for i in range(Nstack):
V=Dmaps[:,:,Indices[i],j]
D1[:,:,i]=np.max(V,2)
D2[:,:,:,j]=D1
D1[D1==0]=np.nan
In [47]:
plt.imshow(Dmean[:,:,1],cmap=plt.cm.gray)
Out[47]:
In [48]:
my_cmap=plt.cm.jet
my_cmap.set_bad(alpha=0)
Good_ICs=np.zeros(S[3])
Label_ICs=[]
pylab.rcParams['figure.figsize'] = (15, 2.5)
In [49]:
algorithm = linear_model.LinearRegression()
In [50]:
Sxk=Xk.shape
In [51]:
Sxk
Out[51]:
In [52]:
X=np.zeros((Sxk[0],2))
In [53]:
X[:,0]=(Xk[:,0]-np.mean(Xk[:,0]))/np.std(Xk[:,0])
X[:,1]=(Xk[:,1]-np.mean(Xk[:,1]))/np.std(Xk[:,1])
#X[:,2]=(Xk[:,3]-np.mean(Xk[:,3]))/np.std(Xk[:,3])
#X[:,3]=(Xk[:,4]-np.mean(Xk[:,4]))/np.std(Xk[:,4])
#X[:,4]=(Xk[:,6]-np.mean(Xk[:,6]))/np.std(Xk[:,6])
#X[:,5]=(Xk[:,7]-np.mean(Xk[:,7]))/np.std(Xk[:,7])
In [54]:
plt.plot(X[:,0])
plt.plot(X[:,1])
#plt.plot(X[:,2])
#plt.plot(X[:,3])
#plt.plot(X[:,4])
#plt.plot(X[:,5])
Out[54]:
In [55]:
Rsq=np.zeros((1,S[3]))
Betas=np.zeros((2,S[3]))
In [56]:
X.shape
Out[56]:
In [57]:
DT.shape
Out[57]:
In [58]:
for j in range(S[3]):
model = algorithm.fit(X, DT[:,j])
Betas[:,j] = model.coef_
Rsq[:,j] = model.score(X,DT[:,j])
In [59]:
RsqUni=np.zeros((6,S[3]))
BetaUni=np.zeros((6,S[3]))
In [60]:
Sx=X.shape
In [61]:
for k in range(2):
for j in range(S[3]):
model = algorithm.fit(np.reshape(X[:,k],(Sx[0],1)), DT[:,j])
BetaUni[k,j] = model.coef_
RsqUni[k,j] = model.score(np.reshape(X[:,k],(Sx[0],1)),DT[:,j])
In [62]:
plt.plot(RsqUni[0,:])
Out[62]:
In [114]:
import random
In [158]:
del Final_map
del Fmaps
In [159]:
if S[2]>5:
Final_map=np.zeros([S[0],S[1],5,3])
Fmaps=np.zeros([S[0],S[1],5,3])
else:
Final_map=np.zeros([S[0],S[1],3])
Fmaps=np.zeros([S[0],S[1],3])
C=np.zeros([S[3],3])
C1=np.zeros([6,3])
C1[0][:]=(1,0,0)
C1[1][:]=(0,1,0)
C1[2][:]=(0,0,1)
C1[3][:]=(0.8,0.8,0)
C1[4][:]=(0,1,1)
C1[5][:]=(1,0,1)
S1=DT.shape
In [160]:
C=np.zeros((S[3],3))
i=0
l=0
Betas2=Betas
for j in range(S[3]):
if Betas2[0,j]>0.87*np.max(Betas2[0,:]):
#if 1>0.1:
#C[j,:]=C1[i%6][:]
C[j,2]=1
C[j,1]=random.uniform(0,1)
#C[j,2]=1
for k in range(3):
M=np.max(np.squeeze(np.reshape(D2[:,:,:,j],S[0]*S[1]*5)))
Fmaps[:,:,:,k]=0.8*D2[:,:,:,j]*C[j,k]/M
Final_map=Final_map+Fmaps
#Betas[0,j]=0
#print(Indexo[j])
i=i+1
l=l+1
print(j+1)
#if l==2:
#break
In [161]:
C=np.zeros((S[3],3))
i=0
l=0
Betas2=Betas
for j in range(S[3]):
if Betas2[1,j]>0.78*np.max(Betas2[1,:]):
#if 1>0.1:
#C[j,:]=C1[i%6][:]
C[j,0]=1
C[j,1]=random.uniform(0,1)
#C[j,2]=1
for k in range(3):
M=np.max(np.squeeze(np.reshape(D2[:,:,:,j],S[0]*S[1]*5)))
Fmaps[:,:,:,k]=0.8*D2[:,:,:,j]*C[j,k]/M
Final_map=Final_map+Fmaps
#Betas2[1,j]=0
#print(Indexo[j])
i=i+1
l=l+1
print(j+1)
#if l==2:
# break
In [162]:
pylab.rcParams['figure.figsize'] = (15, 6)
C2=np.zeros(3)
Df=np.zeros([S[0],S[1],5,3])
for i in range(3):
Df[:,:,:,i]=Final_map[:,:,:,i]+Dmean/30
#Df=Df/(np.max(np.max(np.max(Df),3)))
if S[2]>5:
N=Nstack
else:
N=S[2]
for i in range(N):
#if Good_ICs[j]:
plt.subplot(1,N,i+1)
plt.imshow(Df[:,:,i],cmap=plt.cm.gray)
plt.imshow(Df[:,:,i,:],cmap=my_cmap,interpolation='none')
frame1 = plt.gca()
frame1.axes.get_xaxis().set_visible(False)
frame1.axes.get_yaxis().set_visible(False)
plt.tight_layout(pad=0,w_pad=0,h_pad=0)
In [ ]: