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:
for phi in m_ps.phis:
print "\tPoly3ps: phi= %s " % phi.ve()
models.append(m_ps)
# =============================================================================
logger.info("Test positive spline: order 3 with 4 inner knots ")
# =============================================================================
s3 = cpp.Gaudi.Math.PositiveSpline(x.xmin(), x.xmax(), 4, 3)
m_s3 = Models.PSpline_pdf('S3', x, s3)
with rooSilent():
result, f = m_s3.fitTo(dataset2)
result, f = m_s3.fitTo(dataset2)
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:
for phi in m_s3.phis:
print "\tSpline3: phi= %s " % phi.ve()
models.append(m_s3)
## logger.info ( 'Positive pars: %s' % positive .pdf.function().pars() )
## logger.info ( 'Decreasing pars: %s' % decreasing.pdf.function().pars() )
## logger.info ( 'Convex pars: %s' % dec_convex.pdf.function().pars() )
for i in (positive, decreasing, dec_convex, convex):
pars = i.pdf.function().bernstein().pars()
pars = list(pars)
logger.info('Common pars: %s' % list(pars))
pos_sp_ = cpp.Gaudi.Math.PositiveSpline(x.getMin(), x.getMax(), 1, 3)
inc_sp_ = cpp.Gaudi.Math.MonothonicSpline(x.getMin(), x.getMax(), 1, 3, True)
dec_sp_ = cpp.Gaudi.Math.MonothonicSpline(x.getMin(), x.getMax(), 1, 3, False)
ix_sp_ = cpp.Gaudi.Math.ConvexSpline(x.getMin(), x.getMax(), 1, 3, True, True)
dx_sp_ = cpp.Gaudi.Math.ConvexSpline(x.getMin(), x.getMax(), 1, 3, False, True)
pos_sp = Models.PSpline_pdf('SP', mass4, pos_sp_)
inc_sp = Models.MSpline_pdf('SI', mass4, inc_sp_)
dec_sp = Models.MSpline_pdf('SD', mass4, dec_sp_)
ix_sp = Models.CSpline_pdf('SIX', mass4, ix_sp_)
dx_sp = Models.CSpline_pdf('SDX', mass4, dx_sp_)
with timing('Spline Positive 5'), rooSilent():
r5, f = pos_sp.fitTo(dataset5)
with timing('Spline Increasing 5'), rooSilent():
i4, f = inc_sp.fitTo(dataset5)
with timing('Spline Convex 5'), rooSilent():
x4, f = ix_sp.fitTo(dataset5)
## logger.info ( 'Positive pars: %s' % pos_sp.pdf.function().pars() )
## logger.info ( 'Increasing pars: %s' % inc_sp.pdf.function().pars() )
## logger.info ( 'Convex pars: %s' % ix_sp.pdf.function().pars() )