for batchIndex in xrange(nfolds):
print('\t\t Batch %d ...' % (batchIndex))
# Initial parameters
random.seed(25)
b0, a0 = set_initial(c, data.dxm + 1, data.dxr + 1)
param0 = mapOptimizationMatrices2Vector(b0, a0)
validateIds = np.arange(batchIndex * batchSize, (batchIndex + 1) * batchSize)
trainIds = list(set(np.arange(trainAndValidateXm.shape[0])) - set(validateIds))
res = mixedLogistic_EMtrain(param0=param0, c=c,
y=np.matrix(trainAndValidateY[trainIds]).T,
xm=trainAndValidateXm[trainIds, :],
xr=trainAndValidateXr[trainIds, :],
m=1)
pred = mixedLogistic_pred(res=res,
xmt=trainAndValidateXm[validateIds, :],
xrt=trainAndValidateXr[validateIds, :],
c=c,
yt=np.matrix(trainAndValidateY[validateIds]).T)
validateScores.append(pred['f1'])
print('\t\twith validation score (F1) = %f' % (pred['f1']))
avgValidateScores.append(np.mean(validateScores))
print('\tAverage validation score = %f for c = %d' % (np.mean(validateScores), c))
c_optim = c_candidates[np.array(avgValidateScores).argmax()]
print('Optimal c = %d' % (c_optim))
# Initialize parameters
b0, a0 = set_initial(c, data.dxm + 1, data.dxr + 1)
param0 = mapOptimizationMatrices2Vector(b0, a0)
# nParams = (data.dxm + 1) * (c - 1) + (data.dxr + 1) * c
# param0 = np.zeros(nParams)
# param0 = np.ones(nParams)
# res = mixedLogistic_EMtrain(param0=param0, c=c,
# y=np.matrix(data.y).T,
# xm=data.xm,
# xr=data.xr,
# m=1)
res = mixedLogistic_EMtrain_separate(param0=param0, c=c,
y=np.matrix(data.y).T,
xm=data.xm,
xr=data.xr,
m=1)
# === Check parameters ===
beta_est, alpha_est = mapOptimizationVector2Matrices(res['param'], 2, 3)
beta_est
alpha_est
data.beta
data.alpha
# === Predict ===
pred = mixedLogistic_pred(res, data.xm, data.xr, c, data.y)
