def create_time_plot(config_path,
info_path,
out_dir,
iteration_index = 249):
if not os.path.exists(out_dir):
os.mkdir(out_dir)
cfg = MsBayesConfig(config_path)
dmc = DMCSimulationResults(info_path)
sum_path = (dmc.get_result_path_prefix(1, 1, 1) +
'{0}-posterior-summary.txt'.format(iteration_index))
labels = []
for t in cfg.taxa:
l = t.strip().split('.')
labels.append(r'\textit{{{0} {1}}}'.format(l[0], l[1]))
pg = plotting.get_marginal_divergence_time_plot(
config_path = config_path,
posterior_summary_path = sum_path,
labels = labels,
horizontal = True,
label_size = 12.0,
measure_tick_label_size = 12.0,
measure_axis_label = 'Divergence time ($4N_C$ generations)',
measure_axis_label_size = 16.0,
label_axis_label = 'Taxon pair',
label_axis_label_size = 16.0)
pg.savefig(os.path.join(out_dir, 'negros-panay-marginal-times.pdf'))
def main_cli():
_LOG.info('Parsing and writing results...')
for info_path in POWER_INFO_PATHS:
power_results = DMCSimulationResults(info_path)
power_results.write_result_summaries(
prior_indices = [power_results.combined_prior_index],
include_tau_exclusion_info = True)
def parse_sim_results(info_path):
_LOG.info('Parsing and writing results...')
info_path = expand_path(info_path)
sim_results = DMCSimulationResults(info_path)
sim_results.write_result_summaries(
prior_indices = [sim_results.combined_prior_index],
include_tau_exclusion_info = True)
def main_cli():
info_path = os.path.join(project_util.RESULT_DIR, 'dpp',
'pymsbayes-results', 'pymsbayes-info.txt')
_LOG.info('Parsing and writing results...')
results = DMCSimulationResults(info_path)
prior_indices = results.prior_index_to_config.keys()
results.write_result_summaries(
prior_indices = prior_indices,
include_tau_exclusion_info = False)
def main_cli():
bin_dir = os.path.abspath(os.path.dirname(__file__))
project_dir = os.path.abspath(os.path.dirname(bin_dir))
result_dir = os.path.abspath(os.path.join(project_dir, 'results'))
info_path = os.path.join(result_dir, 'no-sort', 'pymsbayes-results',
'pymsbayes-info.txt')
_LOG.info('Parsing and writing results...')
results = DMCSimulationResults(info_path)
prior_indices = results.prior_index_to_config.keys()
results.write_result_summaries(
prior_indices = prior_indices,
include_tau_exclusion_info = False)
def parse_results(info_path):
dmc_sim = DMCSimulationResults(info_path)
psi_results = {}
omega_results = {}
observed_configs = {}
tau_results = {}
for k, v in dmc_sim.observed_index_to_config.iteritems():
observed_configs[k] = MsBayesConfig(v)
prior_index = '{0}-combined'.format(''.join(
sorted([str(i) for i in dmc_sim.prior_index_to_config.iterkeys()])))
for observed_index, cfg in observed_configs.iteritems():
result_path = dmc_sim.get_result_summary_path(observed_index,
prior_index)
psi, omega, tau = PowerResult.parse_result_summary(result_path)
psi_results[cfg] = psi
omega_results[cfg] = omega
tau_results[cfg] = tau
return psi_results, omega_results, tau_results
def create_plots(dpp_info_path, old_info_path, out_dir):
# matplotlib.rc('text',**{'usetex': True})
# old = ([1] * 992) + ([2] * 8)
if not os.path.exists(out_dir):
os.mkdir(out_dir)
dmc_sim = DMCSimulationResults(dpp_info_path)
dmc_sim_old = DMCSimulationResults(old_info_path)
psi_path = dmc_sim.get_result_path_prefix(1, 1, 1) + '99-psi-results.txt'
psi_path_old = dmc_sim_old.get_result_path_prefix(1, 1, 1) + '99-psi-results.txt'
psis = []
for d in spreadsheet_iter([psi_path]):
n = int(round(10000 * float(d['estimated_prob'])))
psis.extend([int(d['num_of_div_events'])] * n)
psis_old = []
for d in spreadsheet_iter([psi_path_old]):
n = int(round(10000 * float(d['estimated_prob'])))
psis_old.extend([int(d['num_of_div_events'])] * n)
bins = range(1, dmc_sim.num_taxon_pairs + 2)
hd = HistData(x = psis,
normed = True,
bins = bins,
histtype = 'bar',
align = 'mid',
orientation = 'vertical',
zorder = 0)
# hd_old= HistData(x = old,
hd_old= HistData(x = psis_old,
normed = True,
bins = bins,
histtype = 'bar',
align = 'mid',
orientation = 'vertical',
zorder = 0)
tick_labels = []
for x in bins[0:-1]:
if x % 2:
tick_labels.append(str(x))
else:
tick_labels.append('')
xticks_obj = Ticks(ticks = bins,
labels = tick_labels,
horizontalalignment = 'left')
hist = ScatterPlot(hist_data_list = [hd],
x_label = 'Number of divergence events',
y_label = 'Posterior probability',
xticks_obj = xticks_obj)
hist_old = ScatterPlot(hist_data_list = [hd_old],
x_label = 'Number of divergence events',
y_label = 'Posterior probability',
xticks_obj = xticks_obj)
hist.set_xlim(left = bins[0], right = bins[-1])
hist_old.set_xlim(left = bins[0], right = bins[-1])
hist.set_ylim(bottom = 0.0, top = 0.1)
pg = PlotGrid(subplots = [hist],
num_columns = 1,
height = 4.0,
width = 6.5,
label_schema = None,
auto_height = False)
pg.auto_adjust_margins = False
pg.margin_top = 1
pg.reset_figure()
pg.savefig(os.path.join(out_dir, 'philippines-dpp-psi-posterior.pdf'))
# hist.set_ylim(bottom = 0.0, top = 1.0)
hist.set_ylim(bottom = 0.0, top = 0.5)
hist.set_ylabel('')
# hist_old.set_ylim(bottom = 0.0, top = 1.0)
hist_old.set_ylim(bottom = 0.0, top = 0.5)
pg = PlotGrid(subplots = [hist_old, hist],
num_columns = 2,
height = 3.5,
width = 8.0,
share_x = True,
share_y = True,
label_schema = None,
auto_height = False,
# column_labels = [r'\texttt{msBayes}', r'\texttt{dpp-msbayes}'],
column_labels = [r'msBayes', r'dpp-msbayes'],
column_label_size = 18.0)
pg.auto_adjust_margins = False
pg.margin_top = 0.92
pg.padding_between_horizontal = 1.0
pg.reset_figure()
pg.savefig(os.path.join(out_dir, 'philippines-dpp-psi-posterior-old-vs-dpp.pdf'))
pg.label_schema = 'uppercase'
pg.reset_figure()
pg.savefig(os.path.join(out_dir, 'philippines-dpp-psi-posterior-old-vs-dpp-labels.pdf'))
prior_psis = get_dpp_psi_values(dmc_sim.num_taxon_pairs, 1.5, 18.099702, num_sims = 100000)
prior_hd = HistData(x = prior_psis,
normed = True,
bins = bins,
histtype = 'bar',
align = 'mid',
orientation = 'vertical',
zorder = 0)
prior_hist = ScatterPlot(hist_data_list = [prior_hd],
x_label = 'Number of divergence events',
y_label = 'Probability',
xticks_obj = xticks_obj)
prior_hist.set_xlim(left = bins[0], right = bins[-1])
prior_hist.set_ylim(bottom = 0.0, top = 0.12)
hist.set_ylim(bottom = 0.0, top = 0.12)
pg = PlotGrid(subplots = [prior_hist, hist],
num_columns = 2,
height = 3.5,
width = 8.0,
share_x = True,
share_y = True,
label_schema = None,
auto_height = False,
# column_labels = [r'\texttt{msBayes}', r'\texttt{dpp-msbayes}'],
column_labels = [r'Prior', r'Posterior'],
column_label_size = 18.0)
pg.auto_adjust_margins = False
pg.margin_top = 0.92
pg.padding_between_horizontal = 1.0
pg.reset_figure()
pg.savefig(os.path.join(out_dir, 'philippines-dpp-psi-posterior-prior.pdf'))
pg.label_schema = 'uppercase'
pg.reset_figure()
pg.savefig(os.path.join(out_dir, 'philippines-dpp-psi-posterior-prior-lablels.pdf'))
prior_psis_old = []
for i in range(22):
prior_psis_old.extend([i + 1] * 100)
prior_hd_old = HistData(x = prior_psis_old,
normed = True,
bins = bins,
histtype = 'bar',
align = 'mid',
orientation = 'vertical',
zorder = 0)
prior_hist_old = ScatterPlot(hist_data_list = [prior_hd_old],
x_label = 'Number of divergence events',
y_label = 'Prior probability',
xticks_obj = xticks_obj)
prior_hist.set_xlim(left = bins[0], right = bins[-1])
prior_hist.set_ylim(bottom = 0.0, top = 0.5)
hist.set_ylim(bottom = 0.0, top = 0.5)
prior_hist.set_ylim(bottom = 0.0, top = 0.5)
for h in [hist_old, hist, prior_hist_old, prior_hist]:
h.set_ylabel(ylabel = '')
h.set_xlabel(xlabel = '')
h.set_title_text('')
h.set_extra_y_label('')
pg = PlotGrid(subplots = [hist_old, hist, prior_hist_old, prior_hist],
num_columns = 2,
height = 6.0,
width = 8.0,
share_x = True,
share_y = False,
label_schema = None,
auto_height = False,
title = r'Number of divergence events',
title_top = False,
title_size = 16.0,
y_title = 'Probability',
y_title_size = 16.0,
column_labels = [r'msBayes', r'dpp-msbayes'],
row_labels = ['Posterior', 'Prior'],
column_label_offset = 0.07,
column_label_size = 22.0,
row_label_offset = 0.04,
row_label_size = 20.0)
pg.auto_adjust_margins = False
pg.margin_top = 0.94
pg.margin_bottom = 0.045
pg.margin_right = 0.95
pg.margin_left = 0.045
pg.padding_between_vertical = 0.5
pg.padding_between_horizontal = 1.0
pg.reset_figure()
pg.set_shared_x_limits()
pg.set_shared_y_limits(by_row = True)
pg.reset_figure()
pg.savefig(os.path.join(out_dir, 'philippines-dpp-psi-posterior-old-vs-dpp-with-prior.pdf'))
def get_histograms(config_path,
info_path,
num_samples = 10000,
num_div_values = None,
div_model_values = None,
ordered_div_model_values = None,
iteration_index = 99,
y_limits = [0.45, 0.45, 0.05, 0.05],
xtick_label_size = 8.0):
cfg = MsBayesConfig(config_path)
dmc = DMCSimulationResults(info_path)
npairs = dmc.num_taxon_pairs
psi_path = (dmc.get_result_path_prefix(1, 1, 1) +
'{0}-psi-results.txt'.format(iteration_index))
sum_path = (dmc.get_result_path_prefix(1, 1, 1) +
'{0}-posterior-summary.txt'.format(iteration_index))
psis = get_values_psi_path(psi_path)
omega, omega_hpd = get_omega_from_summary_path(sum_path)
(num_div_prior_psis, div_model_prior_psis, ordered_div_model_prior_psis) = (
num_div_values, div_model_values, ordered_div_model_values)
if ((not num_div_values) or (not div_model_values) or
(not ordered_div_model_values)):
if cfg.div_model_prior == 'dpp':
num_div_prior_psis, div_model_prior_psis, ordered_div_model_prior_psis = get_dpp_prior_values(
config_path = config_path,
num_samples = num_samples)
elif cfg.div_model_prior == 'uniform':
num_div_prior_psis, div_model_prior_psis, ordered_div_model_prior_psis = get_uniform_prior_values(
npairs = npairs,
num_samples = num_samples)
elif cfg.div_model_prior == 'psi':
num_div_prior_psis, div_model_prior_psis, ordered_div_model_prior_psis = get_psi_uniform_prior_values(
npairs = npairs,
num_samples = num_samples)
# Extra bin for zero values
bins = range(0, npairs + 2)
hds = []
for p in [psis, num_div_prior_psis, div_model_prior_psis, ordered_div_model_prior_psis]:
hds.append(HistData(x = p,
normed = True,
bins = bins,
histtype = 'bar',
align = 'mid',
orientation = 'vertical',
zorder = 0))
tick_labels = []
for x in bins[0:-1]:
if x % 2:
tick_labels.append(str(x))
else:
tick_labels.append('')
xticks_obj = Ticks(ticks = bins,
labels = tick_labels,
horizontalalignment = 'left',
size = xtick_label_size)
hists = []
for i, hd in enumerate(hds):
right_text = ''
if i == 0:
right_text = r'$D_T = {0:.2f} ({1:.2f}-{2:.2f})$'.format(omega,
omega_hpd[0],
omega_hpd[1])
hist = ScatterPlot(hist_data_list = [hd],
right_text = right_text,
xticks_obj = xticks_obj)
# cut off extra zero-valued bin
hist.set_xlim(left = bins[1], right = bins[-1])
top = y_limits[i]
hist.set_ylim(bottom = 0.0, top = top)
hist.right_text_size = 10.0
hist.plot_label_size = 12.0
yticks = [i for i in hist.ax.get_yticks()]
ytick_labels = [i for i in yticks]
if len(ytick_labels) > 5:
for i in range(1, len(ytick_labels), 2):
ytick_labels[i] = ''
yticks_obj = Ticks(ticks = yticks,
labels = ytick_labels,
size = 10.0)
hist.yticks_obj = yticks_obj
hists.append(hist)
return hists
def summarize_sim_results(info_path):
info_path = expand_path(info_path)
sim_results = DMCSimulationResults(info_path)
out_dir = os.path.dirname(info_path)
summary_path = os.path.join(out_dir, 'results-summary.txt')
result_path = sim_results.get_result_summary_path(observed_index = 1,
prior_index = sim_results.combined_prior_index)
d = get_dict_from_spreadsheets([result_path])
num_excluded = [int(x) for x in d['num_excluded']]
num_excluded_glm = [int(x) for x in d['num_excluded_glm']]
bf_num_excluded = [int(x) for x in d['bf_num_excluded']]
bf_num_excluded_glm = [int(x) for x in d['bf_num_excluded_glm']]
prob_of_exclusion = [float(x) for x in d['prob_of_exclusion']]
prob_of_exclusion_glm = [float(x) for x in d['prob_of_exclusion_glm']]
prior_prob_of_exclusion = [float(x) for x in d['prior_prob_of_exclusion']]
bf_of_exclusion = [float(x) for x in d['bf_of_exclusion']]
bf_of_exclusion_glm = [float(x) for x in d['bf_of_exclusion_glm']]
num_sims = sim_results.num_sim_reps
assert len(num_excluded) == num_sims
assert len(num_excluded_glm) == num_sims
assert len(prob_of_exclusion) == num_sims
assert len(prob_of_exclusion_glm) == num_sims
summary_stream, close = process_file_arg(summary_path, 'w')
summary_stream.write('Proportion of simulations excluding truth: {0}'
'\n'.format(
len([1 for x in bf_num_excluded if x > 0]) / float(num_sims)))
summary_stream.write('Proportion of simulations excluding truth with GLM-'
'adjustment: {0}\n'.format(
len([1 for x in bf_num_excluded_glm if x > 0]) / float(num_sims)))
summary_stream.write('Average number of tau parameters excluded: {0}'
'\n'.format(
sum(bf_num_excluded) / float(num_sims)))
summary_stream.write('Average number of tau parameters excluded with GLM: '
'{0}\n'.format(sum(bf_num_excluded_glm) / float(num_sims)))
summary_stream.write('Mode number of tau parameters excluded: {0}\n'.format(
mode_list(bf_num_excluded)))
summary_stream.write('Mode number of tau parameters excluded with GLM: '
'{0}\n'.format(mode_list(bf_num_excluded_glm)))
summary_stream.write('Max number of tau parameters excluded: {0}\n'.format(
max(bf_num_excluded)))
summary_stream.write('Max number of tau parameters excluded with GLM: '
'{0}\n'.format(max(bf_num_excluded_glm)))
summary_stream.write('Average probability of exclusion: {0}\n'.format(
sum(prob_of_exclusion) / float(num_sims)))
summary_stream.write('Average probability of exclusion with GLM: {0}\n'.format(
sum(prob_of_exclusion_glm) / float(num_sims)))
summary_stream.write('Median probability of exclusion: {0}\n'.format(
median(prob_of_exclusion)))
summary_stream.write('Median probability of exclusion with GLM: {0}\n'.format(
median(prob_of_exclusion_glm)))
summary_stream.write('Average Bayes factor of exclusion: {0}\n'.format(
sum(bf_of_exclusion) / float(num_sims)))
summary_stream.write('Average Bayes factor of exclusion with GLM: {0}\n'.format(
sum(bf_of_exclusion_glm) / float(num_sims)))
summary_stream.write('Median Bayes factor of exclusion: {0}\n'.format(
median(bf_of_exclusion)))
summary_stream.write('Median Bayes factor of exclusion with GLM: {0}\n'.format(
median(bf_of_exclusion_glm)))
summary_stream.write('Max Bayes factor of exclusion: {0}\n'.format(
max(bf_of_exclusion)))
summary_stream.write('Max Bayes factor of exclusion with GLM: {0}\n'.format(
max(bf_of_exclusion_glm)))
prob_of_bf_exclusion = (len([1 for x in bf_of_exclusion if x > 10.0]) /
float(num_sims))
prob_of_bf_exclusion_glm = (len([
1 for x in bf_of_exclusion_glm if x > 10.0]) /
float(num_sims))
summary_stream.write('Estimated probability Bayes factor of exclusion '
'> 10: {0}\n'.format(prob_of_bf_exclusion))
summary_stream.write('Estimated probability Bayes factor of exclusion '
'> 10 with GLM: {0}\n'.format(prob_of_bf_exclusion_glm))
summary_stream.close()
if plotting.MATPLOTLIB_AVAILABLE:
approx_prior_exclusion = 0.39184
prior_odds = approx_prior_exclusion / (1.0 - approx_prior_exclusion)
post_odds = prior_odds * 10
post = post_odds / (1.0 + post_odds)
observed_config1 = MsBayesConfig(sim_results.observed_index_to_config[1])
observed_config2 = MsBayesConfig(sim_results.observed_index_to_config[1])
cfg_to_num_ex = {observed_config1: bf_num_excluded,
observed_config2: bf_num_excluded_glm}
cfg_to_prob_exclusion = {observed_config1: prob_of_exclusion,
observed_config2: prob_of_exclusion_glm}
cfg_to_prob_of_bf_exclusion = {observed_config1: prob_of_bf_exclusion,
observed_config2: prob_of_bf_exclusion_glm}
ex_prob_plot = plotting.ProbabilityPowerPlotGrid(
observed_config_to_estimates = cfg_to_prob_exclusion,
variable = 'tau_exclusion',
div_model_prior = 'psi',
bayes_factor = 10,
bayes_factor_prob = post,
cfg_to_prob_of_bf_exclusion = cfg_to_prob_of_bf_exclusion,
height = 3.7,
margin_left = 0.03,
margin_bottom = 0.06,
margin_right = 1,
margin_top = 0.96,
padding_between_horizontal = 0.5,
padding_between_vertical = 1.0,
num_columns = 2)
fig = ex_prob_plot.create_grid()
fig.savefig(os.path.join(out_dir, 'prob_of_exclusion.pdf'))
ex_plot = plotting.PowerPlotGrid(
observed_config_to_estimates = cfg_to_num_ex,
variable = 'tau_exclusion',
num_columns = 2,
height = 3.7,
margin_left = 0.03,
margin_bottom = 0.06,
margin_right = 1,
margin_top = 0.95,
padding_between_horizontal = 0.5,
padding_between_vertical = 1.0)
fig = ex_plot.create_grid()
fig.savefig(os.path.join(out_dir, 'num_tau_excluded.pdf'))
def main_cli():
_LOG.info('Parsing and writing results...')
v_results = DMCSimulationResults(VALIDATION_INFO_PATH)
v_results.write_result_summaries(
prior_indices = [v_results.combined_prior_index],
include_tau_exclusion_info = True)