def test_laplace():
logger.info('Test Asymmetric Laplace shape')
model = Models.Fit1D(
signal=Models.AsymmetricLaplace_pdf(name='AL',
xvar=mass,
mean=signal_gauss.mean,
slope=signal_gauss.sigma),
background=None,
S=S,
B=B)
signal = model.signal
signal.slope.release()
signal.mean.fix()
model.S.setVal(5000)
model.B.setVal(500)
with rooSilent():
result, frame = model.fitTo(dataset0)
result, frame = model.fitTo(dataset0)
model.draw(dataset0)
if 0 != result.status() or 3 != result.covQual():
logger.warning('Fit is not perfect MIGRAD=%d QUAL=%d ' %
(result.status(), result.covQual()))
logger.info("asymmetric Laplace function\n%s" % result.table(prefix="# "))
models.add(model)
def test_laplace():
logger.info ('Test Asymmetric Laplace shape' )
laplace = Models.AsymmetricLaplace_pdf ( name = 'AL',
xvar = x ,
mean = 5 ,
slope = 1 )
from ostap.fitting.convolution import Convolution_pdf
## constant resolution
laplace_1 = Convolution_pdf ( name = 'L1' , pdf = laplace, resolution = 0.75 )
## resolution PDF
from ostap.fitting.resolution import ResoApo2
rAp = ResoApo2 ( 'A' , x , 0.75 )
## resolution as PDF
laplace_2 = Convolution_pdf ( name = 'L2' , pdf = laplace, resolution = rAp )
laplace.draw( silent = True )
laplace_1.draw( silent = True )
laplace_2.draw()
models.add ( laplace )
models.add ( laplace_1 )
models.add ( laplace_2 )
def test_laplace():
logger.info('Test Asymmetric Laplace shape')
model = Models.Fit1D(
signal=Models.AsymmetricLaplace_pdf(name='AL',
xvar=mass,
mean=signal_gauss.mean,
slope=signal_gauss.sigma),
background=None)
signal = model.signal
signal.slope.release()
signal.mean.fix()
model.S.setVal(5000)
model.B.setVal(500)
with rooSilent():
result, frame = model.fitTo(dataset0)
result, frame = model.fitTo(dataset0)
if 0 != result.status() or 3 != result.covQual():
logger.warning('Fit is not perfect MIGRAD=%d QUAL=%d ' %
(result.status(), result.covQual()))
print result
else:
logger.info('Signal & Background are: %-28s & %-28s ' %
(result('S')[0], result('B')[0]))
logger.info('Mean is: %-28s ' % result(signal.mean)[0])
logger.info('Slope is: %-28s ' %
result(signal.slope)[0])
logger.info('Asymmetry is: %-28s ' % result(signal.asym)[0])
models.add(model)