import MLR_8regions
partition_num = int(sys.argv[1])
reg_lambda = float(sys.argv[2])
maxfun = int(sys.argv[3])
mer_len=6
data = sio.loadmat('../results/N7_A5SS_Model_Predictions/padded_6mer_matrix.mat')
A6pos = data['X']
Y = scipy.matrix(data['Y'])
partition = np.genfromtxt('../results/N7_A5SS_Model_Predictions/Ten_fold_partition.txt')
training_inds = find((partition!=partition_num) & (partition!=((partition_num-1)%10)))
test_inds = find(partition==((partition_num-1)%10))
w,wfull,w0,f,d = MLR_8regions.MLR(A6pos[training_inds[:1000],:],Y[training_inds[:1000],:],reg_lambda,mer_len,maxfun=maxfun)
B = MLR_8regions.get_energy(A6pos,wfull,w0)[test_inds,:];
# Calculate kl-divergence
Ytest = Y[test_inds,:]
vv = scipy.sum(np.multiply(B,Ytest),axis=1)
Ypl = log(Ytest)
Ypl[Ytest==0]=0
Ypl = np.multiply(Ypl,Ytest)
vv = vv-scipy.sum(Ypl,axis=1)
V = -sum(vv)/float(len(Ytest))
f = open('../results/N7_A5SS_Model_Predictions/Reg8_lambdas.txt','a')
f.write(str(partition_num)+'\t'+str(reg_lambda)+'\t'+str(V)+'\n')
f.close()
Y = scipy.matrix(data['Y'])
partition = np.genfromtxt(
'../results/N7_A5SS_Model_Predictions/Ten_fold_partition.txt')
training = (partition != partition_num)
if (partition_num == -1):
test = (partition > -1)
else:
test = (partition == partition_num)
training_inds = find(training)
test_inds = find(test)
w, wfull, w0, f, d = MLR_8regions.MLR(A6pos[training_inds, :],
Y[training_inds, :],
reg_lambda,
mer_len,
maxfun=maxfun)
Ypred = exp(MLR_8regions.get_energy(A6pos, wfull, w0))
MLR_data = {
'Mer_scores': w,
'w0': w0,
'Prediction': Ypred,
'Training': training,
'Test': test,
'Data': Y,
'Reads': reads,
'NotNull': not_null
}
if not os.path.exists('../results/N7_A5SS_Model_Predictions/Partition' +
Y = sio.loadmat(full_filepath)[filename].todense()
else:
Y += sio.loadmat(full_filepath)[filename].todense()
GT_inds = sio.loadmat('/net/shendure/vol7/abros/nobackup/Splicing_Project/Library_Files/GT_GC_Positions.mat')
Y = np.multiply(Y,GT_inds['inds'].todense())
A6pos = sio.loadmat('../results/N7_A5SS_Model_Predictions/padded_6mer_matrix.mat')['X']
training = np.loadtxt('/net/shendure/vol7/abros/nobackup/Splicing_Project/Library_Files/training.csv')==1
print shape(training)
training_inds = find(training==1)
Y = scipy.hstack((Y[:,:80],Y[:,-1:]))
reads = float64(sum(Y,axis=1))
Y = Y/reads
not_null = np.array(reads>0).reshape(len(training))
print shape(not_null)
temp_training = (training==True)
print shape(temp_training)
temp_training[not_null==False] = False
temp_training_inds = find(temp_training)[:10000]
print 'Starting MLR...'
w,wfull,w0,f,d = MLR_8regions.MLR(A6pos[temp_training_inds,:],Y[temp_training_inds,:],reg_lambda,mer_len,maxfun=maxfun)
Ypred = exp(MLR_8regions.get_energy(A6pos,wfull,w0))
MLR_data = {'mer_scores':Wss,'w0':w0,'w':w,'Prediction':Ypred,'Training':training,'Data':Y,'Reads':reads,'NotNull':not_null}
if not os.path.exists(output_path):
os.makedirs(output_path)
sio.savemat(output_path + 'Training_data.mat',MLR_data)
