def get_godambe(func_ex, all_boot, p0, data, eps, log=True):
#assume that last element of p0 is theta, and the remaining elements are the demographic model parameters
#log dictates whether parameters are regular are logarithmic
#func_ex is dadi extrapolated function, all_boot is bootstrapped data, p0 is best_fit params for data/func_ex combination
J = numpy.zeros((len(p0), len(p0)))
func = lambda params: Inference.ll(params[-1]*func_ex(params[:-1], ns, grid_pts), data)
hess = -get_hess(func, p0, eps)
if log:
func = lambda params: Inference.ll(numpy.exp(params[-1])*func_ex(numpy.exp(params[:-1]), ns, grid_pts), data)
hess = -get_hess(func, numpy.log(p0), eps)
for ii, boot in enumerate(all_boot):
boot = Spectrum(boot)
if not log:
func = lambda params: Inference.ll(params[-1]*func_ex(params[:-1], ns, grid_pts), boot)
grad_temp = get_grad(func, p0, eps)
if log:
func = lambda params: Inference.ll(numpy.exp(params[-1])*func_ex(numpy.exp(params[:-1]), ns, grid_pts), boot)
grad_temp = get_grad(func, numpy.log(p0), eps)
J_temp = numpy.outer(grad_temp, grad_temp)
J = J + J_temp
J = J/len(all_boot)
J_inv = numpy.linalg.inv(J)
# G = H*J^-1*H
godambe = numpy.dot(numpy.dot(hess, J_inv), hess)
return godambe, hess
def _object_func(params,
data,
model_func,
sel_dist,
theta,
lower_bound=None,
upper_bound=None,
verbose=0,
multinom=False,
flush_delay=0,
func_args=[],
func_kwargs={},
fixed_params=None,
ll_scale=1,
output_stream=sys.stdout,
store_thetas=False):
"""
Objective function for optimization.
"""
global _counter
_counter += 1
# Deal with fixed parameters
params_up = Inference._project_params_up(params, fixed_params)
# Check our parameter bounds
if lower_bound is not None:
for pval, bound in zip(params_up, lower_bound):
if bound is not None and pval < bound:
return -_out_of_bounds_val / ll_scale
if upper_bound is not None:
for pval, bound in zip(params_up, upper_bound):
if bound is not None and pval > bound:
return -_out_of_bounds_val / ll_scale
ns = data.sample_sizes
all_args = [params_up, ns, sel_dist, theta] + list(func_args)
sfs = model_func(*all_args, **func_kwargs)
if multinom:
result = Inference.ll_multinom(sfs, data)
else:
result = Inference.ll(sfs, data)
if store_thetas:
global _theta_store
_theta_store[tuple(params)] = optimal_sfs_scaling(sfs, data)
# Bad result
if numpy.isnan(result):
result = _out_of_bounds_val
if (verbose > 0) and (_counter % verbose == 0):
param_str = 'array([%s])' % (', '.join(
['%- 12g' % v for v in params_up]))
output_stream.write('%-8i, %-12g, %s%s' %
(_counter, result, param_str, os.linesep))
Misc.delayed_flush(delay=flush_delay)
return -result / ll_scale
def func(params, data, theta_adjust=1):
key = (tuple(params), tuple(ns), tuple(grid_pts))
if key not in cache:
cache[key] = func_ex(params, ns, grid_pts)
# theta_adjust deals with bootstraps that need different thetas
fs = theta_adjust * cache[key]
return Inference.ll(fs, data)
def func(params, data):
key = (tuple(params), tuple(ns), tuple(grid_pts))
if key not in cache:
cache[key] = func_ex(params, ns, grid_pts)
fs = cache[key]
return Inference.ll(fs, data)
def _object_func(params,
data1,
data2,
cache1,
cache2,
model_func,
sel_dist,
scal_fac1,
scal_fac2,
theta1,
theta2,
lower_bound=None,
upper_bound=None,
verbose=0,
multinom=False,
flush_delay=0,
func_args=[],
func_kwargs={},
fixed_params1=None,
fixed_params2=None,
ll_scale=1,
output_stream=sys.stdout,
store_thetas=False):
"""
Objective function for optimization.
"""
global _counter
_counter += 1
# Scaling factors scales sel_dist differently for species 1 and species 2
sel_dist1 = copy_func(
sel_dist, defaults=scal_fac1) # scal_fac1 should be 2*Nea of pop 1
sel_dist2 = copy_func(
sel_dist, defaults=scal_fac2) # scal_fac2 should be 4*Nea of pop 2
# Deal with fixed parameters
params_up1 = Inference._project_params_up(params, fixed_params1)
params_up2 = Inference._project_params_up(params, fixed_params2)
# Check our parameter bounds
if lower_bound is not None:
for pval, bound in zip(params_up1, lower_bound):
if bound is not None and pval < bound:
return -_out_of_bounds_val / ll_scale
if upper_bound is not None:
for pval, bound in zip(params_up1, upper_bound):
if bound is not None and pval > bound:
return -_out_of_bounds_val / ll_scale
ns1 = data1.sample_sizes
ns2 = data2.sample_sizes
all_args1 = [params_up1, ns1, sel_dist1, theta1, cache1] + list(func_args)
all_args2 = [params_up2, ns2, sel_dist2, theta2, cache2] + list(func_args)
# Pass the pts argument via keyword, but don't alter the passed-in
# func_kwargs
#func_kwargs = func_kwargs.copy()
#func_kwargs['pts'] = pts
sfs1 = model_func(*all_args1, **func_kwargs)
sfs2 = model_func(*all_args2, **func_kwargs)
if multinom:
result = Inference.ll_multinom(sfs1, data1) + Inference.ll_multinom(
sfs2, data2)
else:
result = Inference.ll(sfs1, data1) + Inference.ll(sfs2, data2)
# Bad result
if numpy.isnan(result):
result = _out_of_bounds_val
if (verbose > 0) and (_counter % verbose == 0):
param_str = 'array([%s])' % (', '.join(
['%- 12g' % v for v in params_up1]))
output_stream.write('%-8i, %-12g, %s%s' %
(_counter, result, param_str, os.linesep))
Misc.delayed_flush(delay=flush_delay)
return -result / ll_scale
