def main_cli():
taus = []
unique_taus = []
f = open('tau.txt', 'rU')
f.next()
for l in f:
l = l.strip().split()
taus.extend([float(t) for t in l])
unique_taus.extend([float(t) for t in set(l)])
hd_t = HistData(x = taus,
bins=10,
zorder = 0)
plot_t = ScatterPlot(
hist_data_list = [hd_t],
x_label = r'Divergence time ($\tau$)',
y_label = r'Density')
plot_t.savefig('tau_prior.pdf')
hd_t = HistData(x = unique_taus,
bins=10,
zorder = 0)
plot_t = ScatterPlot(
hist_data_list = [hd_t],
x_label = r'Divergence time ($\tau$)',
y_label = r'Density')
plot_t.savefig('unique_tau_prior.pdf')
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