def absolute_structure_analysis(xs, fo2, fc, scale, nu=None, log=None,
outlier_cutoff_factor=None):
if log is None:
log = sys.stdout
hooft_analysis = absolute_structure.hooft_analysis(
fo2, fc, scale_factor=scale, outlier_cutoff_factor=outlier_cutoff_factor)
print >> log, "Gaussian analysis:"
hooft_analysis.show(out=log)
NPP = absolute_structure.bijvoet_differences_probability_plot(
hooft_analysis)
print >> log, "Probability plot:"
NPP.show(out=log)
print >> log
if nu is None:
nu = absolute_structure.maximise_students_t_correlation_coefficient(
NPP.y, min_nu=1, max_nu=200)
distribution = distributions.students_t_distribution(nu)
observed_deviations = NPP.y
expected_deviations = distribution.quantiles(observed_deviations.size())
fit = flex.linear_regression(
expected_deviations[5:-5], observed_deviations[5:-5])
t_analysis = absolute_structure.students_t_hooft_analysis(
fo2, fc, nu, scale_factor=scale, probability_plot_slope=fit.slope(),
outlier_cutoff_factor=outlier_cutoff_factor)
tPP = absolute_structure.bijvoet_differences_probability_plot(
t_analysis, use_students_t_distribution=True, students_t_nu=nu)
print >> log, "Student's t analysis:"
print >> log, "nu: %.2f" %nu
t_analysis.show(out=log)
print >> log, "Probability plot:"
tPP.show(out=log)
print >> log
if xs is not None:
flack = absolute_structure.flack_analysis(xs, fo2.as_xray_observations())
flack.show(out=log)
def absolute_structure_analysis(xs,
fo2,
fc,
scale,
nu=None,
log=None,
outlier_cutoff_factor=None):
if log is None:
log = sys.stdout
hooft_analysis = absolute_structure.hooft_analysis(
fo2,
fc,
scale_factor=scale,
outlier_cutoff_factor=outlier_cutoff_factor)
print >> log, "Gaussian analysis:"
hooft_analysis.show(out=log)
NPP = absolute_structure.bijvoet_differences_probability_plot(
hooft_analysis)
print >> log, "Probability plot:"
NPP.show(out=log)
print >> log
if nu is None:
nu = absolute_structure.maximise_students_t_correlation_coefficient(
NPP.y, min_nu=1, max_nu=200)
distribution = distributions.students_t_distribution(nu)
observed_deviations = NPP.y
expected_deviations = distribution.quantiles(observed_deviations.size())
fit = flex.linear_regression(expected_deviations[5:-5],
observed_deviations[5:-5])
t_analysis = absolute_structure.students_t_hooft_analysis(
fo2,
fc,
nu,
scale_factor=scale,
probability_plot_slope=fit.slope(),
outlier_cutoff_factor=outlier_cutoff_factor)
tPP = absolute_structure.bijvoet_differences_probability_plot(
t_analysis, use_students_t_distribution=True, students_t_nu=nu)
print >> log, "Student's t analysis:"
print >> log, "nu: %.2f" % nu
t_analysis.show(out=log)
print >> log, "Probability plot:"
tPP.show(out=log)
print >> log
if xs is not None:
flack = absolute_structure.flack_analysis(xs,
fo2.as_xray_observations())
flack.show(out=log)
def exercise(self, debug=False):
if debug:
distribution = distributions.normal_distribution()
observed_deviations = (
self.fo2.data() - self.scale_factor*self.fc.as_intensity_array().data())
observed_deviations = observed_deviations.select(
flex.sort_permutation(observed_deviations))
expected_deviations = distribution.quantiles(observed_deviations.size())
csv_utils.writer(
open('delta_F_npp.csv', 'wb'), (expected_deviations, observed_deviations))
# first with the correct absolute structure
gaussian = absolute_structure.hooft_analysis(self.fo2, self.fc)
analyses = [gaussian]
NPP = absolute_structure.bijvoet_differences_probability_plot(gaussian)
if self.use_students_t_errors:
nu_calc = absolute_structure.maximise_students_t_correlation_coefficient(
NPP.y, min_nu=1, max_nu=200)
t_analysis = absolute_structure.students_t_hooft_analysis(
self.fo2, self.fc, nu_calc, probability_plot_slope=NPP.fit.slope())
analyses.append(gaussian)
tPP = absolute_structure.bijvoet_differences_probability_plot(
t_analysis, use_students_t_distribution=True, students_t_nu=nu_calc)
if tPP.distribution.degrees_of_freedom() < 100:
assert tPP.correlation.coefficient() > NPP.correlation.coefficient()
else:
assert approx_equal(NPP.correlation.coefficient(), 1, 0.005)
for analysis in analyses:
assert approx_equal(analysis.hooft_y, 0, 1e-2)
assert approx_equal(analysis.p2_true, 1)
assert approx_equal(analysis.p2_false, 0)
assert approx_equal(analysis.p3_true, 1)
assert approx_equal(analysis.p3_false, 0)
assert approx_equal(analysis.p3_racemic_twin, 0)
if debug:
csv_utils.writer(open('npp.csv', 'wb'), (NPP.x,NPP.y))
if self.use_students_t_errors:
csv_utils.writer(open('tpp.csv', 'wb'), (tPP.x,tPP.y))
assert approx_equal(NPP.fit.y_intercept(), 0)
# and now with the wrong absolute structure
gaussian = absolute_structure.hooft_analysis(self.fo2, self.fc_i)
analyses = [gaussian]
NPP = absolute_structure.bijvoet_differences_probability_plot(gaussian)
if self.use_students_t_errors:
nu_calc = absolute_structure.maximise_students_t_correlation_coefficient(
NPP.y, min_nu=1, max_nu=200)
t_analysis = absolute_structure.students_t_hooft_analysis(
self.fo2, self.fc_i, nu_calc, probability_plot_slope=NPP.fit.slope())
analyses.append(gaussian)
tPP = absolute_structure.bijvoet_differences_probability_plot(
t_analysis, use_students_t_distribution=True)
if tPP.distribution.degrees_of_freedom() < 100:
assert tPP.correlation.coefficient() > NPP.correlation.coefficient()
else:
assert approx_equal(NPP.correlation.coefficient(), 1, 0.002)
assert approx_equal(NPP.fit.y_intercept(), 0)
for analysis in analyses:
assert approx_equal(analysis.hooft_y, 1, 1e-2)
assert approx_equal(analysis.p2_true, 0)
assert approx_equal(analysis.p2_false, 1)
assert approx_equal(analysis.p3_true, 0)
assert approx_equal(analysis.p3_false, 1)
assert approx_equal(analysis.p3_racemic_twin, 0)
# test for the case of a racemic twin
gaussian = absolute_structure.hooft_analysis(self.fo2_twin, self.fc)
analyses = [gaussian]
NPP = absolute_structure.bijvoet_differences_probability_plot(gaussian)
if self.use_students_t_errors:
nu_calc = absolute_structure.maximise_students_t_correlation_coefficient(
NPP.y, min_nu=1, max_nu=200)
t_analysis = absolute_structure.students_t_hooft_analysis(
self.fo2_twin, self.fc, nu_calc, probability_plot_slope=NPP.fit.slope())
tPP = absolute_structure.bijvoet_differences_probability_plot(
t_analysis, use_students_t_distribution=True)
if tPP.distribution.degrees_of_freedom() < 100:
assert tPP.correlation.coefficient() > NPP.correlation.coefficient()
else:
assert approx_equal(NPP.correlation.coefficient(), 1, 0.002)
assert approx_equal(NPP.fit.y_intercept(), 0)
for analysis in analyses:
assert approx_equal(analysis.hooft_y, 0.5, 1e-2)
assert approx_equal(analysis.p3_true, 0)
assert approx_equal(analysis.p3_false, 0)
assert approx_equal(analysis.p3_racemic_twin, 1)
def exercise(self, debug=False):
if debug:
distribution = distributions.normal_distribution()
observed_deviations = (
self.fo2.data() - self.scale_factor*self.fc.as_intensity_array().data())
observed_deviations = observed_deviations.select(
flex.sort_permutation(observed_deviations))
expected_deviations = distribution.quantiles(observed_deviations.size())
csv_utils.writer(
open('delta_F_npp.csv', 'wb'), (expected_deviations, observed_deviations))
# first with the correct absolute structure
gaussian = absolute_structure.hooft_analysis(self.fo2, self.fc)
analyses = [gaussian]
NPP = absolute_structure.bijvoet_differences_probability_plot(gaussian)
if self.use_students_t_errors:
nu_calc = absolute_structure.maximise_students_t_correlation_coefficient(
NPP.y, min_nu=1, max_nu=200)
t_analysis = absolute_structure.students_t_hooft_analysis(
self.fo2, self.fc, nu_calc, probability_plot_slope=NPP.fit.slope())
analyses.append(gaussian)
tPP = absolute_structure.bijvoet_differences_probability_plot(
t_analysis, use_students_t_distribution=True, students_t_nu=nu_calc)
if tPP.distribution.degrees_of_freedom() < 100:
assert tPP.correlation.coefficient() > NPP.correlation.coefficient()
else:
assert approx_equal(NPP.correlation.coefficient(), 1, 0.005)
for analysis in analyses:
assert approx_equal(analysis.hooft_y, 0, 1e-2)
assert approx_equal(analysis.p2_true, 1)
assert approx_equal(analysis.p2_false, 0)
assert approx_equal(analysis.p3_true, 1)
assert approx_equal(analysis.p3_false, 0)
assert approx_equal(analysis.p3_racemic_twin, 0)
if debug:
csv_utils.writer(open('npp.csv', 'wb'), (NPP.x,NPP.y))
if self.use_students_t_errors:
csv_utils.writer(open('tpp.csv', 'wb'), (tPP.x,tPP.y))
assert approx_equal(NPP.fit.y_intercept(), 0)
# and now with the wrong absolute structure
gaussian = absolute_structure.hooft_analysis(self.fo2, self.fc_i)
analyses = [gaussian]
NPP = absolute_structure.bijvoet_differences_probability_plot(gaussian)
if self.use_students_t_errors:
nu_calc = absolute_structure.maximise_students_t_correlation_coefficient(
NPP.y, min_nu=1, max_nu=200)
t_analysis = absolute_structure.students_t_hooft_analysis(
self.fo2, self.fc_i, nu_calc, probability_plot_slope=NPP.fit.slope())
analyses.append(gaussian)
tPP = absolute_structure.bijvoet_differences_probability_plot(
t_analysis, use_students_t_distribution=True)
if tPP.distribution.degrees_of_freedom() < 100:
assert tPP.correlation.coefficient() > NPP.correlation.coefficient()
else:
assert approx_equal(NPP.correlation.coefficient(), 1, 0.002)
assert approx_equal(NPP.fit.y_intercept(), 0)
for analysis in analyses:
assert approx_equal(analysis.hooft_y, 1, 1e-2)
assert approx_equal(analysis.p2_true, 0)
assert approx_equal(analysis.p2_false, 1)
assert approx_equal(analysis.p3_true, 0)
assert approx_equal(analysis.p3_false, 1)
assert approx_equal(analysis.p3_racemic_twin, 0)
# test for the case of a racemic twin
gaussian = absolute_structure.hooft_analysis(self.fo2_twin, self.fc)
analyses = [gaussian]
NPP = absolute_structure.bijvoet_differences_probability_plot(gaussian)
if self.use_students_t_errors:
nu_calc = absolute_structure.maximise_students_t_correlation_coefficient(
NPP.y, min_nu=1, max_nu=200)
t_analysis = absolute_structure.students_t_hooft_analysis(
self.fo2_twin, self.fc, nu_calc, probability_plot_slope=NPP.fit.slope())
tPP = absolute_structure.bijvoet_differences_probability_plot(
t_analysis, use_students_t_distribution=True)
if tPP.distribution.degrees_of_freedom() < 100:
assert tPP.correlation.coefficient() > NPP.correlation.coefficient()
else:
assert approx_equal(NPP.correlation.coefficient(), 1, 0.002)
assert approx_equal(NPP.fit.y_intercept(), 0)
for analysis in analyses:
assert approx_equal(analysis.hooft_y, 0.5, 1e-2)
assert approx_equal(analysis.p3_true, 0)
assert approx_equal(analysis.p3_false, 0)
assert approx_equal(analysis.p3_racemic_twin, 1)
