def dual_analysis(labels, pop, migration_fun, migration_outofbounds_fun,
startparams, migration_fun_name):
""" Analyse a population using a given migration function, with both the
composite and classical models.
"""
## 1a. the composite demographic model.
# Get the information about the tracts out of the population object, and
# split the population into 2 groups, in order to perform an analysis as a
# composite demographic model.
bins, group_data = pop.get_global_tractlengths(npts=50, split_count=2)
# The actual groups that we're splitting the population into.
groups = pop.split_by_props(2)
# Compute the counts of individuals in each group and the average ancestry
# proportions across individuals. The counts of individuals in each groups
# should differ by no more than one.
ninds, group_ancestry_averages = zip(*map(
lambda p: (
len(p.indivs),
p.get_mean_ancestry_proportions(ancestry_labels)),
groups))
# Rearrange the data for each group into a list ordered in the same way as
# the population labels.
group_data = [
[g[ancestry_label] for ancestry_label in ancestry_labels]
for g in group_data]
## Optimize the model parameters using COBYLA
#composite_model_parameters = tracts.optimize_cob_multifracs(
# startparams, bins, pop.Ls, group_data, ninds, migration_fun,
# group_ancestry_averages, outofbounds_fun=migration_outofbounds_fun,
# cutoff=cutoff, epsilon=1e-12)
# Optimize the model parameters using brute
composite_model_parameters, _ = tracts.optimize_brute_multifracs(
bins, pop.Ls, group_data, ninds, migration_fun,
group_ancestry_averages, startparams,
outofbounds_fun=migration_outofbounds_fun,
cutoff=cutoff)
# Construct the composite demographic model
composite_model = tracts.composite_demographic_model(
migration_fun, composite_model_parameters,
group_ancestry_averages)
## 1b. the fracs2 model.
nind = len(pop.indivs)
_, data = pop.get_global_tractlengths(npts=50, split_count=1)
data = [data[ancestry_label] for ancestry_label in ancestry_labels]
ancestry_averages = pop.get_mean_ancestry_proportions(ancestry_labels)
fracs2_model_parameters, _ = tracts.optimize_brute_fracs2(
bins, pop.Ls, data, nind,
migration_fun, ancestry_averages, startparams,
outofbounds_fun=migration_outofbounds_fun, cutoff=cutoff)
fracs2_model = tracts.demographic_model(
migration_fun(fracs2_model_parameters, ancestry_averages))
return {
'classical': {
'params': fracs2_model_parameters,
'model': fracs2_model,
'averages': ancestry_averages,
'theories': dict(
(
name,
fp.Theory(
bins,
nind * np.array(
fracs2_model.expectperbin(
pop.Ls, i, bins)),
migration_fun_name + ' classical',
name)
)
for i, name in enumerate(labels)),
},
'composite': {
'params': composite_model_parameters,
'model': composite_model,
'ninds': ninds,
'averages': group_ancestry_averages,
'groups': group_data,
'theories': dict(
(
name,
fp.Theory(
bins,
composite_model.expectperbin(
pop.Ls, i, bins, ninds),
migration_fun_name + ' composite',
name)
)
for i, name in enumerate(labels)),
},
'misc': {
'startparams': startparams,
'bins': bins,
'data': data,
'fun': migration_fun,
},
}
for frac, flat_tract in izip(bypopfrac, flattracts):
frac.append(flat_tract / flat_tracts_sum)
props = map(numpy.mean, bypopfrac)
Ls = pop.Ls
nind = pop.nind
cutoff = 2
def randomize(arr, scale=2):
# takes an array and multiplies every element by a factor between 0 and
# 2, uniformly. caps at 1.
return map(lambda i: min(i, 1), scale * numpy.random.random(arr.shape) * arr)
xopt = tracts.optimize_brute_fracs2(
bins, Ls, data, nind, func, props, slices, outofbounds_fun=bound, cutoff=cutoff)
print xopt
optmod = tracts.demographic_model(func(xopt[0], props))
optpars = xopt[0]
liks = xopt[1]
maxlik = optmod.loglik(bins, Ls, data, pop.nind, cutoff=cutoff)
expects = []
for popnum in range(len(data)):
expects.append(optmod.expectperbin(Ls, popnum, bins))
expects = nind * numpy.array(expects)
outf = outdir + "boot%d_%2.2f" % (bootnum, maxlik,)
fbins = open(outf + "_bins", 'w')
for frac, flat_tract in izip(bypopfrac, flattracts):
frac.append(flat_tract / flat_tracts_sum)
props = map(numpy.mean, bypopfrac)
Ls = pop.Ls
nind = pop.nind
cutoff = 2
def randomize(arr, scale=2):
# takes an array and multiplies every element by a factor between 0 and
# 2, uniformly. caps at 1.
return map(lambda i: min(i, 1), scale * numpy.random.random(arr.shape) * arr)
xopt = tracts.optimize_brute_fracs2(
bins, Ls, data, nind, func, props, slices, outofbounds_fun=bound, cutoff=cutoff)
print xopt
optmod = tracts.demographic_model(func(xopt[0], props))
optpars = xopt[0]
liks = xopt[1]
maxlik = optmod.loglik(bins, Ls, data, pop.nind, cutoff=cutoff)
expects = []
for popnum in range(len(data)):
expects.append(optmod.expectperbin(Ls, popnum, bins))
expects = nind * numpy.array(expects)
outf = outdir + "boot%d_%2.2f" % (bootnum, maxlik,)
fbins = open(outf + "_bins", 'w')
