def plot_1d_comp_Poisson(model,
data,
fig_num=None,
residual='Anscombe',
plot_masked=False,
show=True):
"""
Poisson comparison between 1d model and data.
model: 1-dimensional model SFS
data: 1-dimensional data SFS
fig_num: Clear and use figure fig_num for display. If None, an new figure
window is created.
residual: 'Anscombe' for Anscombe residuals, which are more normally
distributed for Poisson sampling. 'linear' for the linear
residuals, which can be less biased.
plot_masked: Additionally plots (in open circles) results for points in the
model or data that were masked.
show: If True, execute pylab.show command to make sure plot displays.
"""
if fig_num is None:
f = pylab.gcf()
else:
f = pylab.figure(fig_num, figsize=(7, 7))
pylab.clf()
if data.folded and not model.folded:
model = model.fold()
masked_model, masked_data = Numerics.intersect_masks(model, data)
ax = pylab.subplot(2, 1, 1)
pylab.semilogy(masked_data, '-ob', label='data')
pylab.semilogy(masked_model, '-or', label='model')
if plot_masked:
pylab.semilogy(masked_data.data, '--ob', mfc='w', zorder=-100)
pylab.semilogy(masked_model.data, '--or', mfc='w', zorder=-100)
ax.legend(loc='upper right')
pylab.subplot(2, 1, 2, sharex=ax)
if residual == 'Anscombe':
resid = Inference.Anscombe_Poisson_residual(masked_model, masked_data)
elif residual == 'linear':
resid = Inference.linear_Poisson_residual(masked_model, masked_data)
else:
raise ValueError("Unknown class of residual '%s'." % residual)
pylab.plot(resid, '-og')
if plot_masked:
pylab.plot(resid.data, '--og', mfc='w', zorder=-100)
ax.set_xlim(0, data.shape[0] - 1)
if show:
pylab.show()
def optimal_sfs_scaling(model, data):
"""
Optimal multiplicative scaling factor between model and data.
This scaling is based on only those entries that are masked in neither
model nor data.
"""
if data.folded and not model.folded:
model = model.fold()
model, data = Numerics.intersect_masks(model, data)
return data.sum() / model.sum()
def optimal_sfs_scaling(model, data):
"""
Optimal multiplicative scaling factor between model and data.
This scaling is based on only those entries that are masked in neither
model nor data.
"""
if data.folded and not model.folded:
model = model.fold()
model, data = Numerics.intersect_masks(model, data)
return data.sum()/model.sum()
def plot_1d_comp_Poisson(model, data, fig_num=None, residual='Anscombe',
plot_masked=False):
"""
Poisson comparison between 1d model and data.
model: 1-dimensional model SFS
data: 1-dimensional data SFS
fig_num: Clear and use figure fig_num for display. If None, an new figure
window is created.
residual: 'Anscombe' for Anscombe residuals, which are more normally
distributed for Poisson sampling. 'linear' for the linear
residuals, which can be less biased.
plot_masked: Additionally plots (in open circles) results for points in the
model or data that were masked.
"""
if fig_num is None:
f = pylab.gcf()
else:
f = pylab.figure(fig_num, figsize=(7,7))
pylab.clf()
if data.folded and not model.folded:
model = model.fold()
masked_model, masked_data = Numerics.intersect_masks(model, data)
ax = pylab.subplot(2,1,1)
pylab.semilogy(masked_data, '-ob')
pylab.semilogy(masked_model, '-or')
if plot_masked:
pylab.semilogy(masked_data.data, '--ob', mfc='w', zorder=-100)
pylab.semilogy(masked_model.data, '--or', mfc='w', zorder=-100)
pylab.subplot(2,1,2, sharex = ax)
if residual == 'Anscombe':
resid = Inference.Anscombe_Poisson_residual(masked_model, masked_data)
elif residual == 'linear':
resid = Inference.linear_Poisson_residual(masked_model, masked_data)
else:
raise ValueError("Unknown class of residual '%s'." % residual)
pylab.plot(resid, '-og')
if plot_masked:
pylab.plot(resid.data, '--og', mfc='w', zorder=-100)
ax.set_xlim(0, data.shape[0]-1)
pylab.show()
def plot_3d_comp_Poisson(model, data, vmin=None, vmax=None,
resid_range=None, fig_num=None, pop_ids=None,
residual='Anscombe', adjust=True):
"""
Poisson comparison between 3d model and data.
model: 3-dimensional model SFS
data: 3-dimensional data SFS
vmin, vmax: Minimum and maximum values plotted for sfs are vmin and
vmax respectively.
resid_range: Residual plot saturates at +- resid_range.
fig_num: Clear and use figure fig_num for display. If None, an new figure
window is created.
pop_ids: If not None, override pop_ids stored in Spectrum.
residual: 'Anscombe' for Anscombe residuals, which are more normally
distributed for Poisson sampling. 'linear' for the linear
residuals, which can be less biased.
adjust: Should method use automatic 'subplots_adjust'? For advanced
manipulation of plots, it may be useful to make this False.
"""
if data.folded and not model.folded:
model = model.fold()
masked_model, masked_data = Numerics.intersect_masks(model, data)
if fig_num is None:
f = pylab.gcf()
else:
f = pylab.figure(fig_num, figsize=(8,10))
pylab.clf()
if adjust:
pylab.subplots_adjust(bottom=0.07, left=0.07, top=0.95, right=0.95)
modelmax = max(masked_model.sum(axis=sax).max() for sax in range(3))
datamax = max(masked_data.sum(axis=sax).max() for sax in range(3))
modelmin = min(masked_model.sum(axis=sax).min() for sax in range(3))
datamin = min(masked_data.sum(axis=sax).min() for sax in range(3))
max_toplot = max(modelmax, datamax)
min_toplot = min(modelmin, datamin)
if vmax is None:
vmax = max_toplot
if vmin is None:
vmin = min_toplot
extend = _extend_mapping[vmin <= min_toplot, vmax >= max_toplot]
# Calculate the residuals
if residual == 'Anscombe':
resids = [Inference.\
Anscombe_Poisson_residual(masked_model.sum(axis=2-sax),
masked_data.sum(axis=2-sax),
mask=vmin) for sax in range(3)]
elif residual == 'linear':
resids =[Inference.\
linear_Poisson_residual(masked_model.sum(axis=2-sax),
masked_data.sum(axis=2-sax),
mask=vmin) for sax in range(3)]
else:
raise ValueError("Unknown class of residual '%s'." % residual)
min_resid = min([r.min() for r in resids])
max_resid = max([r.max() for r in resids])
if resid_range is None:
resid_range = max((abs(max_resid), abs(min_resid)))
resid_extend = _extend_mapping[-resid_range <= min_resid,
resid_range >= max_resid]
if pop_ids is not None:
if len(pop_ids) != 3:
raise ValueError('pop_ids must be of length 3.')
data_ids = model_ids = resid_ids = pop_ids
else:
data_ids = masked_data.pop_ids
model_ids = masked_model.pop_ids
if model_ids is None:
model_ids = data_ids
if model_ids == data_ids:
resid_ids = model_ids
else:
resid_ids = None
for sax in range(3):
marg_data = masked_data.sum(axis=2-sax)
marg_model = masked_model.sum(axis=2-sax)
curr_ids = []
for ids in [data_ids, model_ids, resid_ids]:
if ids is None:
ids = ['pop0', 'pop1', 'pop2']
if ids is not None:
ids = list(ids)
del ids[2-sax]
curr_ids.append(ids)
ax = pylab.subplot(4,3,sax+1)
plot_colorbar = (sax == 2)
plot_single_2d_sfs(marg_data, vmin=vmin, vmax=vmax, pop_ids=curr_ids[0],
extend=extend, colorbar=plot_colorbar)
pylab.subplot(4,3,sax+4, sharex=ax, sharey=ax)
plot_single_2d_sfs(marg_model, vmin=vmin, vmax=vmax,
pop_ids=curr_ids[1], extend=extend, colorbar=False)
resid = resids[sax]
pylab.subplot(4,3,sax+7, sharex=ax, sharey=ax)
plot_2d_resid(resid, resid_range, pop_ids=curr_ids[2],
extend=resid_extend, colorbar=plot_colorbar)
ax = pylab.subplot(4,3,sax+10)
flatresid = numpy.compress(numpy.logical_not(resid.mask.ravel()),
resid.ravel())
ax.hist(flatresid, bins=20, normed=True)
ax.set_yticks([])
pylab.show()
def plot_2d_comp_Poisson(model, data, vmin=None, vmax=None,
resid_range=None, fig_num=None,
pop_ids=None, residual='Anscombe',
adjust=True, saveplot=False,
nomplot="plot_2d_comp_Poisson",
showplot=True):
"""
Poisson comparison between 2d model and data.
model: 2-dimensional model SFS
data: 2-dimensional data SFS
vmin, vmax: Minimum and maximum values plotted for sfs are vmin and
vmax respectively.
resid_range: Residual plot saturates at +- resid_range.
fig_num: Clear and use figure fig_num for display. If None, an new figure
window is created.
pop_ids: If not None, override pop_ids stored in Spectrum.
residual: 'Anscombe' for Anscombe residuals, which are more normally
distributed for Poisson sampling. 'linear' for the linear
residuals, which can be less biased.
adjust: Should method use automatic 'subplots_adjust'? For advanced
manipulation of plots, it may be useful to make this False.
"""
if data.folded and not model.folded:
model = model.fold()
masked_model, masked_data = Numerics.intersect_masks(model, data)
if fig_num is None:
f = pylab.gcf()
else:
f = pylab.figure(fig_num, figsize=(7,7))
pylab.clf()
if adjust:
pylab.subplots_adjust(bottom=0.07, left=0.07, top=0.94, right=0.95,
hspace=0.26, wspace=0.26)
max_toplot = max(masked_model.max(), masked_data.max())
min_toplot = min(masked_model.min(), masked_data.min())
if vmax is None:
vmax = max_toplot
if vmin is None:
vmin = min_toplot
extend = _extend_mapping[vmin <= min_toplot, vmax >= max_toplot]
if pop_ids is not None:
data_pop_ids = model_pop_ids = resid_pop_ids = pop_ids
if len(pop_ids) != 2:
raise ValueError('pop_ids must be of length 2.')
else:
data_pop_ids = masked_data.pop_ids
model_pop_ids = masked_model.pop_ids
if masked_model.pop_ids is None:
model_pop_ids = data_pop_ids
if model_pop_ids == data_pop_ids:
resid_pop_ids = model_pop_ids
else:
resid_pop_ids = None
ax = pylab.subplot(2,2,1)
plot_single_2d_sfs(masked_data, vmin=vmin, vmax=vmax,
pop_ids=data_pop_ids, colorbar=False)
ax.set_title('data')
ax2 = pylab.subplot(2,2,2, sharex=ax, sharey=ax)
plot_single_2d_sfs(masked_model, vmin=vmin, vmax=vmax,
pop_ids=model_pop_ids, extend=extend )
ax2.set_title('model')
if residual == 'Anscombe':
resid = Inference.Anscombe_Poisson_residual(masked_model, masked_data,
mask=vmin)
elif residual == 'linear':
resid = Inference.linear_Poisson_residual(masked_model, masked_data,
mask=vmin)
else:
raise ValueError("Unknown class of residual '%s'." % residual)
if resid_range is None:
resid_range = max((abs(resid.max()), abs(resid.min())))
resid_extend = _extend_mapping[-resid_range <= resid.min(),
resid_range >= resid.max()]
ax3 = pylab.subplot(2,2,3, sharex=ax, sharey=ax)
plot_2d_resid(resid, resid_range, pop_ids=resid_pop_ids,
extend=resid_extend)
ax3.set_title('residuals')
ax = pylab.subplot(2,2,4)
flatresid = numpy.compress(numpy.logical_not(resid.mask.ravel()),
resid.ravel())
ax.hist(flatresid, bins=20, normed=True)
ax.set_title('residuals')
ax.set_yticks([])
if saveplot:
nomplot=nomplot + ".png"
pylab.savefig(nomplot)
if showplot:
pylab.show()
def plot_2d_meta_resid(s_resid,ns_resid,resid_range=None,
fig_num=None, pop_ids=None,
adjust=True, show=True):
"""
Comparison between 2d nonsynonymous residual and 2d synonymous residual.
s_resid: residual SFS from synonymous data
ns_resid: residual SFS from nonsynonymous data
resid_range: Residual plot saturates at +- resid_range. This range applies to both
the residual SFS's supplied as well as the meta-residual plot.
fig_num: Clear and use figure fig_num for display. If None, an new figure
window is created.
pop_ids: If not None, override pop_ids stored in Spectrum.
adjust: Should method use automatic 'subplots_adjust'? For advanced
manipulation of plots, it may be useful to make this False.
show: Display the plot? False can be useful when plotting many in a loop.
"""
if ns_resid.folded and not s_resid.folded:
s_resid = s_resid.fold()
masked_s, masked_ns = Numerics.intersect_masks(s_resid,ns_resid)
if fig_num is None:
f = pylab.gcf()
else:
f = pylab.figure(fig_num, figsize=(7,7))
pylab.clf()
if adjust:
pylab.subplots_adjust(bottom=0.07, left=0.07, top=0.94, right=0.95,
hspace=0.26, wspace=0.26)
max_toplot = max(masked_s.max(), masked_ns.max())
min_toplot = min(masked_s.min(), masked_ns.min())
if pop_ids is not None:
ns_pop_ids = s_pop_ids = resid_pop_ids = pop_ids
if len(pop_ids) != 2:
raise ValueError('pop_ids must be of length 2.')
else:
ns_pop_ids = masked_ns.pop_ids
s_pop_ids = masked_s.pop_ids
if masked_s.pop_ids is None:
s_pop_ids = ns_pop_ids
if s_pop_ids == ns_pop_ids:
resid_pop_ids = s_pop_ids
else:
resid_pop_ids = None
if resid_range is None:
resid_range = max((abs(masked_s.max()), abs(masked_s.min())))
resid_extend = _extend_mapping[-resid_range <= masked_s.min(),
resid_range >= masked_s.max()]
ax = pylab.subplot(2,2,1)
plot_2d_resid(masked_s, resid_range=resid_range, pop_ids=resid_pop_ids,
extend=resid_extend)
ax.set_title('Synonymous Residuals')
if resid_range is None:
resid_range = max((abs(masked_ns.max()), abs(masked_ns.min())))
resid_extend = _extend_mapping[-resid_range <= masked_ns.min(),
resid_range >= masked_ns.max()]
ax2 = pylab.subplot(2,2,2, sharex=ax, sharey=ax)
plot_2d_resid(masked_ns, resid_range=resid_range, pop_ids=resid_pop_ids,
extend=resid_extend)
ax2.set_title('Nonsynonymous Residuals')
resid = masked_s-masked_ns
if resid_range is None:
resid_range = max((abs(resid.max()), abs(resid.min())))
resid_extend = _extend_mapping[-resid_range <= resid.min(),
resid_range >= resid.max()]
ax3 = pylab.subplot(2,2,3, sharex=ax, sharey=ax)
plot_2d_resid(resid, resid_range, pop_ids=resid_pop_ids,
extend=resid_extend,cmap=pylab.cm.PuOr_r)
ax3.set_title('Meta-residuals')
ax = pylab.subplot(2,2,4)
flatresid = numpy.compress(numpy.logical_not(resid.mask.ravel()),
resid.ravel())
ax.hist(flatresid, bins=20, normed=True,color='purple')
resid.data[resid.mask==True]=0
sum_squares=numpy.sum(resid.data**2)
ax.set_title(r'$res^2$ = '+'{0:.3f}'.format(sum_squares))
ax.set_yticks([])
if show:
pylab.show()
def optimal_sfs_scaling(model,data):
data = numerics.fold(data)
model = numerics.fold(data)
model, data = Numerics.intersect_masks(model, data)
return data.sum()/model.sum()
