def gen_samples(wdir,nsamples=100,nsize=10):
load_config('%s/input.py'%wdir)
conf['bootstrap']=False
istep=core.get_istep()
core.mod_conf(istep) #--set conf as specified in istep
resman=RESMAN(nworkers=5,parallel=True,datasets=True)
parman=resman.parman
order=parman.order
obsres={}
if 'idis' in conf['datasets'] : obsres['idis'] = resman.idisres
if 'pidis' in conf['datasets'] : obsres['pidis'] = resman.pidisres
if 'sidis' in conf['datasets'] : obsres['sidis'] = resman.sidisres
if 'psidis' in conf['datasets'] : obsres['psidis'] = resman.psidisres
if 'dy' in conf['datasets'] : obsres['dy'] = resman.dyres
if 'sia' in conf['datasets'] : obsres['sia'] = resman.siares
print('\ngen ml samples using the setup as in %s\n'%wdir)
checkdir('%s/mlsamples'%wdir)
data=gen_dataframe(parman.order,obsres,nsize)
for _ in range(nsamples):
lprint('progress: %d/%d'%(_,nsamples))
par=parman.gen_flat(setup=True)
res,rres,nres=resman.get_residuals(par)
#--fill dataframe
i=data['size']
data['params'][i]=par
for reaction in obsres:
for idx in data['reactions'][reaction]:
prediction=copy.copy(obsres[reaction].tabs[idx]['prediction'])
data['reactions'][reaction][idx][i]=prediction
data['size']+=1
if data['size']==nsize:
save(data,'%s/mlsamples/%s'%(wdir,id_generator(12)))
data=gen_dataframe(parman.order,obsres,nsize)
print
#--close resman
resman.shutdown()
# define datasets (kinematics) to perform the simulation
conf['datasets']={}
conf['datasets']['sidis']={}
conf['datasets']['sidis']['xlsx']={}
conf['datasets']['sidis']['xlsx'][1000]='./template.xlsx' # | proton | pi+
conf['datasets']['sidis']['norm']={}
for idx in conf['datasets']['sidis']['xlsx']: conf['datasets']['sidis']['norm'][idx]={'value':1,'fixed':True,'min':0,'max':1}
conf['datasets']['sidis']['filters']={}
############################################################################
# run simulation
resman = RESMAN()
parman = conf['parman']
resman.get_residuals(parman.par)
print
############################################################################
# prepare the new pseudo data set and save it as xlsx file
simdata=pd.DataFrame(conf['sidis tabs'][1000])
simdata['value']=simdata['thy']
simdata['stat_u']=pd.Series(simdata['thy']*simdata['%stat']/100,index=simdata.index)
simdata['syst_u']=pd.Series(simdata['thy']*simdata['%syst']/100,index=simdata.index)
simdata=simdata.drop(['r-residuals','shift','alpha','residuals','yp','yh','W2','Shift','N','thy','%stat','%syst'],axis=1)
print simdata[:10]
writer = pd.ExcelWriter('simulation.xlsx')
simdata.to_excel(writer,'Sheet1',index=False)
writer.save()
