def model_based_outliers(self,
f_model,
level=.01,
return_data=False,
plot_out=None):
assert self.r_free_flags is not None
if (self.r_free_flags.data().count(True) == 0):
self.r_free_flags = self.r_free_flags.array(
data=~self.r_free_flags.data())
sigmaa_estimator = sigmaa_estimation.sigmaa_estimator(
miller_obs=self.miller_obs,
miller_calc=f_model,
r_free_flags=self.r_free_flags,
kernel_width_free_reflections=200,
n_sampling_points=20,
n_chebyshev_terms=13)
sigmaa_estimator.show(out=self.out)
sigmaa = sigmaa_estimator.sigmaa()
obs_norm = abs(sigmaa_estimator.normalized_obs)
calc_norm = sigmaa_estimator.normalized_calc
f_model_outlier_object = scaling.likelihood_ratio_outlier_test(
f_obs=obs_norm.data(),
sigma_obs=None,
f_calc=calc_norm.data(),
# the data is prenormalized, all epsies are unity
epsilon=flex.double(calc_norm.data().size(), 1.0),
centric=obs_norm.centric_flags().data(),
alpha=sigmaa.data(),
beta=1.0 - sigmaa.data() * sigmaa.data())
modes = f_model_outlier_object.posterior_mode()
lik = f_model_outlier_object.log_likelihood()
p_lik = f_model_outlier_object.posterior_mode_log_likelihood()
s_der = f_model_outlier_object.posterior_mode_snd_der()
ll_gain = f_model_outlier_object.standardized_likelihood()
# The smallest vallue should be 0.
# sometimes, due to numerical issues, it comes out
# a wee bit negative. please repair that
eps = 1.0e-10
zeros = flex.bool(ll_gain < eps)
p_values = ll_gain
p_values = p_values.set_selected(zeros, eps)
p_values = erf(flex.sqrt(p_values / 2.0))
p_values = 1.0 - flex.pow(p_values, float(p_values.size()))
# select on p-values
flags = flex.bool(p_values > level)
flags = self.miller_obs.customized_copy(data=flags)
ll_gain = self.miller_obs.customized_copy(data=ll_gain)
p_values = self.miller_obs.customized_copy(data=p_values)
log_message = """
Model based outlier rejection.
------------------------------
Calculated amplitudes and estimated values of alpha and beta
are used to compute the log-likelihood of the observed amplitude.
The method is inspired by Read, Acta Cryst. (1999). D55, 1759-1764.
Outliers are rejected on the basis of the assumption that a scaled
log likelihood differnce 2(log[P(Fobs)]-log[P(Fmode)])/Q\" is distributed
according to a Chi-square distribution (Q\" is equal to the second
derivative of the log likelihood function of the mode of the
distribution).
The outlier threshold of the p-value relates to the p-value of the
extreme value distribution of the chi-square distribution.
"""
flags.map_to_asu()
ll_gain.map_to_asu()
p_values.map_to_asu()
assert flags.indices().all_eq(self.miller_obs.indices())
assert ll_gain.indices().all_eq(self.miller_obs.indices())
assert p_values.indices().all_eq(self.miller_obs.indices())
log_message = self.make_log_model(log_message, flags, ll_gain,
p_values, obs_norm, calc_norm,
sigmaa, plot_out)
tmp_log = StringIO()
print >> tmp_log, log_message
# histogram of log likelihood gain values
print >> tmp_log
print >> tmp_log, "The histoghram of scaled (LL-gain) values is shown below."
print >> tmp_log, " Note: scaled (LL-gain) is approximately Chi-square distributed."
print >> tmp_log
print >> tmp_log, " scaled(LL-gain) Frequency"
histo = flex.histogram(ll_gain.data(), 15)
histo.show(f=tmp_log, format_cutoffs='%7.3f')
print >> self.out, tmp_log.getvalue()
if not return_data:
return flags
else:
assert flags.indices().all_eq(self.miller_obs.indices())
return self.miller_obs.select(flags.data())
def calc_sigmaa(obs, model, flag):
from mmtbx.scaling.sigmaa_estimation import sigmaa_estimator
se = sigmaa_estimator(obs, model, flag, kernel_width_free_reflections=100)
return se
def model_based_outliers(self, f_model, level=0.01, return_data=False, plot_out=None):
assert self.r_free_flags is not None
if self.r_free_flags.data().count(True) == 0:
self.r_free_flags = self.r_free_flags.array(data=~self.r_free_flags.data())
sigmaa_estimator = sigmaa_estimation.sigmaa_estimator(
miller_obs=self.miller_obs,
miller_calc=f_model,
r_free_flags=self.r_free_flags,
kernel_width_free_reflections=200,
n_sampling_points=20,
n_chebyshev_terms=13,
)
sigmaa_estimator.show(out=self.out)
sigmaa = sigmaa_estimator.sigmaa()
obs_norm = abs(sigmaa_estimator.normalized_obs)
calc_norm = sigmaa_estimator.normalized_calc
f_model_outlier_object = scaling.likelihood_ratio_outlier_test(
f_obs=obs_norm.data(),
sigma_obs=None,
f_calc=calc_norm.data(),
# the data is prenormalized, all epsies are unity
epsilon=flex.double(calc_norm.data().size(), 1.0),
centric=obs_norm.centric_flags().data(),
alpha=sigmaa.data(),
beta=1.0 - sigmaa.data() * sigmaa.data(),
)
modes = f_model_outlier_object.posterior_mode()
lik = f_model_outlier_object.log_likelihood()
p_lik = f_model_outlier_object.posterior_mode_log_likelihood()
s_der = f_model_outlier_object.posterior_mode_snd_der()
ll_gain = f_model_outlier_object.standardized_likelihood()
# The smallest vallue should be 0.
# sometimes, due to numerical issues, it comes out
# a wee bit negative. please repair that
eps = 1.0e-10
zeros = flex.bool(ll_gain < eps)
p_values = ll_gain
p_values = p_values.set_selected(zeros, eps)
p_values = erf(flex.sqrt(p_values / 2.0))
p_values = 1.0 - flex.pow(p_values, float(p_values.size()))
# select on p-values
flags = flex.bool(p_values > level)
flags = self.miller_obs.customized_copy(data=flags)
ll_gain = self.miller_obs.customized_copy(data=ll_gain)
p_values = self.miller_obs.customized_copy(data=p_values)
log_message = """
Model based outlier rejection.
------------------------------
Calculated amplitudes and estimated values of alpha and beta
are used to compute the log-likelihood of the observed amplitude.
The method is inspired by Read, Acta Cryst. (1999). D55, 1759-1764.
Outliers are rejected on the basis of the assumption that a scaled
log likelihood differnce 2(log[P(Fobs)]-log[P(Fmode)])/Q\" is distributed
according to a Chi-square distribution (Q\" is equal to the second
derivative of the log likelihood function of the mode of the
distribution).
The outlier threshold of the p-value relates to the p-value of the
extreme value distribution of the chi-square distribution.
"""
flags.map_to_asu()
ll_gain.map_to_asu()
p_values.map_to_asu()
assert flags.indices().all_eq(self.miller_obs.indices())
assert ll_gain.indices().all_eq(self.miller_obs.indices())
assert p_values.indices().all_eq(self.miller_obs.indices())
log_message = self.make_log_model(log_message, flags, ll_gain, p_values, obs_norm, calc_norm, sigmaa, plot_out)
tmp_log = StringIO()
print >> tmp_log, log_message
# histogram of log likelihood gain values
print >> tmp_log
print >> tmp_log, "The histoghram of scaled (LL-gain) values is shown below."
print >> tmp_log, " Note: scaled (LL-gain) is approximately Chi-square distributed."
print >> tmp_log
print >> tmp_log, " scaled(LL-gain) Frequency"
histo = flex.histogram(ll_gain.data(), 15)
histo.show(f=tmp_log, format_cutoffs="%7.3f")
print >>self.out, tmp_log.getvalue()
if not return_data:
return flags
else:
assert flags.indices().all_eq(self.miller_obs.indices())
return self.miller_obs.select(flags.data())
