def plotFit(lnp, p0, p1, p2, ax=None, **kwargs):
if ax == None:
ax = figure.gca()
mody = lnp.mod(lnp.x, p2)
ax.plot(lnp.x, mody, label="Best fit", **kwargs)
figure.draw_if_interactive()
def plotResiduals(lnp, sampler, p0, p1, p2, ax=None, **kwargs):
""" Plot the residuals of the fit """
if ax == None:
_ax = figure.gca()
else:
_ax = ax
_ax.errorbar(lnp.x, lnp.y - lnp.mod(lnp.x, p2), yerr=lnp.yerr, **kwargs)
if ax == None:
_ax.set_xlabel("X")
_ax.set_ylabel("Residuals [Data-Model]")
figure.theme(ax=_ax)
figure.draw_if_interactive()
def plotCI(lnp, sampler, ax=None, **kwargs):
""" Plot confidence interval (fill_between) """
if ax == None:
_ax = figure.gca()
else:
_ax = ax
for k in range(min(len(sampler.flatchain), 100)):
mody = lnp.mod(lnp.x, sampler.flatchain[k, :])
_ax.plot(lnp.x, mody, color="0.", ls="solid", alpha=0.2)
figure.draw_if_interactive()
def plotData(lnp, ax=None, **kwargs):
""" Do the actual plot of the imput data """
if ax == None:
_ax = figure.gca()
else:
_ax = ax
_ax.errorbar(lnp.x, lnp.y, yerr=lnp.yerr, **kwargs)
if ax == None:
_ax.set_xlabel("X")
_ax.set_ylabel("Y")
figure.theme(ax=_ax)
figure.draw_if_interactive()