def plot_biomarker_predictions(args, diagnoses, values_observed, values_model):
# Setup plot
fig, ax = plt.subplots()
pt.setup_axes(plt, ax)
ax.set_title('{0} estimation based on {1} with {2} visits'.format(
args.predict_biomarker, args.method, len(args.visits)))
ax.set_xlabel('Observed {0}'.format(args.predict_biomarker))
ax.set_ylabel('Predicted {0}'.format(args.predict_biomarker))
# Draw plot
plt.scatter(values_observed,
values_model,
s=15.0,
c=diagnoses,
edgecolor='none',
vmin=0.0,
vmax=1.0,
cmap=pt.progression_cmap,
alpha=0.5)
# Show or save the plot
plt.tight_layout()
if args.plot_file is not None:
plt.savefig(args.plot_file, transparent=True)
else:
plt.show()
plt.close(fig)
def plot_dpi_dpr_distribution(args, dpis, dprs, diagnoses):
print log.INFO, 'Plotting estimate distributions...'
diagnoses = np.array(diagnoses)
diagnoses[(0.25 <= diagnoses) & (diagnoses <= 0.75)] = 0.5
# Setup plot
fig, ax = plt.subplots()
pt.setup_axes(plt, ax)
biomarkers_str = args.method if args.biomarkers is None else ', '.join(args.biomarkers)
ax.set_title('DP estimation using {0} at {1}'.format(biomarkers_str, ', '.join(args.visits)))
ax.set_xlabel('DP')
ax.set_ylabel('DPR')
plt.scatter(dpis, dprs, c=diagnoses, edgecolor='none', s=25.0,
vmin=0.0, vmax=1.0, cmap=pt.progression_cmap,
alpha=0.5)
# Plot legend
# noinspection PyUnresolvedReferences
rects = [mpl.patches.Rectangle((0, 0), 1, 1, fc=pt.color_cn + (0.5,), linewidth=0),
mpl.patches.Rectangle((0, 0), 1, 1, fc=pt.color_mci + (0.5,), linewidth=0),
mpl.patches.Rectangle((0, 0), 1, 1, fc=pt.color_ad + (0.5,), linewidth=0)]
labels = ['CN', 'MCI', 'AD']
legend = ax.legend(rects, labels, fontsize=10, ncol=len(rects), loc='upper center', framealpha=0.9)
legend.get_frame().set_edgecolor((0.6, 0.6, 0.6))
# Draw or save the plot
plt.tight_layout()
if args.plot_file is not None:
plt.savefig(args.plot_file, transparent=True)
else:
plt.show()
plt.close(fig)
def plot_error_bars(args, biomarkers, errors):
print log.INFO, 'Plotting error bars...'
fig, ax = plt.subplots(figsize=(8, 5))
pt.setup_axes(plt, ax)
ax.set_title('Influence of the number of training samples')
ax.set_xlabel('Number of samples')
ax.set_ylabel('Mean area between PDFs')
color = {
'longitudinal': (0.0, 0.0, 0.0),
'triangular': (0.0, 0.0, 0.5),
'uniform': (0.0, 0.5, 0.0)
}
sample_numbers = range(args.sample_numbers_range[0],
args.sample_numbers_range[1],
args.sample_numbers_range[2])
for biomarker in biomarkers:
for sampling in ['longitudinal', 'triangular', 'uniform']:
curve_median = []
curve_err_1 = []
curve_err_2 = []
for experiment in sample_numbers:
errors_experiment = errors[biomarker][sampling][experiment]
median = np.median(errors_experiment)
curve_median.append(median)
curve_err_1.append(median -
np.percentile(errors_experiment, 25))
curve_err_2.append(
np.percentile(errors_experiment, 75) - median)
plt.errorbar(sample_numbers,
curve_median,
yerr=[curve_err_1, curve_err_2],
linestyle='-',
color=color[sampling],
label='{0} sampling'.format(sampling))
legend = plt.legend(fontsize=10,
ncol=3,
loc='upper center',
framealpha=0.9)
legend.get_frame().set_edgecolor((0.6, 0.6, 0.6))
# Show or save plot
plt.tight_layout()
if args.plot_file is not None:
plt.savefig(args.plot_file, transparent=True)
else:
plt.show()
plt.close(fig)
def main():
parser = argparse.ArgumentParser(description='Estimate model curves for biomarkers using VGAM.')
parser.add_argument('-m', '--method', choices=DataHandler.get_method_choices(), default='all', help='the method to collect data for')
parser.add_argument('-b', '--biomarkers', nargs='+', default=None, help='name of the biomarker to be plotted')
parser.add_argument('-e', '--extrapolator', type=str, choices=['lin', 'sqrt', 'exp'], default='exp', help='the type of extrapolator')
parser.add_argument('--plot_threshold', type=float, default=0.3, help='the threshold above which praphs are plotted')
parser.add_argument('--recompute_errors', action='store_true', help='recompute the matrix containing the fitting errors')
parser.add_argument('--search_range', nargs=3, default=(1000, 5000, 10), help='the range in which the offset is sought')
args = parser.parse_args()
# Get the data files and biomarkers
data_handler_joint = DataHandler.get_data_handler(method=args.method,
biomarkers=args.biomarkers,
phase='joint')
biomarkers, offsets, errors, descriminativeness, overlap = get_fitting_data(args, data_handler_joint)
# Plot single biomarker fits
fig, ax = plt.subplots()
pt.setup_axes(plt, ax, xgrid=False)
ax.set_title('Optimal offset between CN/MCI and MCI/AD models')
ax.set_xlabel('Offset (days)')
ax.set_ylabel('Fitting error')
for i, biomarker in enumerate(biomarkers):
if descriminativeness[i] > args.plot_threshold:
print log.RESULT, 'Min error for {0} at {1}'.format(biomarker, offsets[np.argmin(errors[i, :])])
ax.plot(offsets, errors[i, :], label=biomarker, linestyle='--')
# Get optimal offset
mean_errors = np.mean(errors, 0)
weighted_mean_errors = np.dot(errors.T, descriminativeness) / np.sum(descriminativeness)
# Plot joint fit
ax.plot(offsets, mean_errors, label='Mean', linewidth=2, color='g')
ax.plot(offsets, weighted_mean_errors, label='Weighted mean', linewidth=2, color='r')
# Get and lot optimal offset
optimal_offset = offsets[np.argmin(mean_errors)]
optimal_offset_weighted = offsets[np.argmin(weighted_mean_errors)]
print log.RESULT, 'Optimal threshold: {0}'.format(optimal_offset)
print log.RESULT, 'Optimal threshold (weighted): {0}'.format(optimal_offset_weighted)
ax.axvline(optimal_offset, linestyle=':', color='g')
ax.axvline(optimal_offset_weighted, linestyle=':', color='r')
# Plot overlap
ax.axvline(overlap, color='0.15', linestyle=':')
ax.legend()
plt.show()
plt.close(fig)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('-b', '--biomarkers', nargs=2, default=['D1', 'D2'], help='name of the biomarker to be plotted')
parser.add_argument('--plot_file', type=str, default=None, help='filename of the output file')
args = parser.parse_args()
# Collect data for test
data_handler = DataHandler.get_data_handler(biomarkers=args.biomarkers)
biomarkers = data_handler.get_biomarker_names()
measurements = data_handler.get_measurements_as_dict(biomarkers=biomarkers,
select_complete=True)
# Collect biomarker values
biomarkers_1 = []
biomarkers_2 = []
diagnoses = []
for rid in measurements:
for visit in measurements[rid]:
biomarkers_1.append(measurements[rid][visit][biomarkers[0]])
biomarkers_2.append(measurements[rid][visit][biomarkers[1]])
diagnoses.append(measurements[rid][visit]['DX.scan'])
diagnoses = np.array(diagnoses)
diagnoses[(0.25 <= diagnoses) & (diagnoses <= 0.75)] = 0.5
# Setup plot
fig, ax = plt.subplots()
pt.setup_axes(plt, ax)
ax.scatter(biomarkers_1, biomarkers_2, s=15.0, c=diagnoses, edgecolor='none',
vmin=0.0, vmax=1.0, cmap=pt.progression_cmap, alpha=0.25)
ax.set_xlabel(biomarkers[0])
ax.set_ylabel(biomarkers[1])
# Plot legend
rects = [mpl.patches.Rectangle((0, 0), 1, 1, fc=pt.color_cn + (0.25,), linewidth=0),
mpl.patches.Rectangle((0, 0), 1, 1, fc=pt.color_mci + (0.25,), linewidth=0),
mpl.patches.Rectangle((0, 0), 1, 1, fc=pt.color_ad + (0.25,), linewidth=0)]
labels = ['CN', 'MCI', 'AD']
legend = ax.legend(rects, labels, fontsize=10, ncol=len(rects), loc='upper center', framealpha=0.9)
legend.get_frame().set_edgecolor((0.6, 0.6, 0.6))
# Draw or save the plot
plt.tight_layout()
if args.plot_file is not None:
plt.savefig(args.plot_file, transparent=True)
else:
plt.show()
plt.close(fig)
def plot_error_bars(args, biomarkers, errors):
print log.INFO, 'Plotting error bars...'
fig, ax = plt.subplots(figsize=(8, 5))
pt.setup_axes(plt, ax)
ax.set_title('Influence of the number of training samples')
ax.set_xlabel('Number of samples')
ax.set_ylabel('Mean area between PDFs')
color = {'longitudinal': (0.0, 0.0, 0.0), 'triangular': (0.0, 0.0, 0.5), 'uniform': (0.0, 0.5, 0.0)}
sample_numbers = range(args.sample_numbers_range[0],
args.sample_numbers_range[1],
args.sample_numbers_range[2])
for biomarker in biomarkers:
for sampling in ['longitudinal', 'triangular', 'uniform']:
curve_median = []
curve_err_1 = []
curve_err_2 = []
for experiment in sample_numbers:
errors_experiment = errors[biomarker][sampling][experiment]
median = np.median(errors_experiment)
curve_median.append(median)
curve_err_1.append(median - np.percentile(errors_experiment, 25))
curve_err_2.append(np.percentile(errors_experiment, 75) - median)
plt.errorbar(sample_numbers, curve_median, yerr=[curve_err_1, curve_err_2],
linestyle='-', color=color[sampling],
label='{0} sampling'.format(sampling))
legend = plt.legend(fontsize=10, ncol=3, loc='upper center', framealpha=0.9)
legend.get_frame().set_edgecolor((0.6, 0.6, 0.6))
# Show or save plot
plt.tight_layout()
if args.plot_file is not None:
plt.savefig(args.plot_file, transparent=True)
else:
plt.show()
plt.close(fig)
def plot_biomarker_predictions(args, diagnoses, values_observed, values_model):
# Setup plot
fig, ax = plt.subplots()
pt.setup_axes(plt, ax)
ax.set_title('{0} estimation based on {1} with {2} visits'.format(args.predict_biomarker,
args.method,
len(args.visits)))
ax.set_xlabel('Observed {0}'.format(args.predict_biomarker))
ax.set_ylabel('Predicted {0}'.format(args.predict_biomarker))
# Draw plot
plt.scatter(values_observed, values_model, s=15.0,
c=diagnoses, edgecolor='none', vmin=0.0, vmax=1.0,
cmap=pt.progression_cmap, alpha=0.5)
# Show or save the plot
plt.tight_layout()
if args.plot_file is not None:
plt.savefig(args.plot_file, transparent=True)
else:
plt.show()
plt.close(fig)
def plot_dpi_dpr_distribution(args, dpis, dprs, diagnoses):
print log.INFO, 'Plotting estimate distributions...'
diagnoses = np.array(diagnoses)
diagnoses[(0.25 <= diagnoses) & (diagnoses <= 0.75)] = 0.5
# Setup plot
fig, ax = plt.subplots()
pt.setup_axes(plt, ax)
biomarkers_str = args.method if args.biomarkers is None else ', '.join(
args.biomarkers)
ax.set_title('DP estimation using {0} at {1}'.format(
biomarkers_str, ', '.join(args.visits)))
ax.set_xlabel('DP')
ax.set_ylabel('DPR')
plt.scatter(dpis,
dprs,
c=diagnoses,
edgecolor='none',
s=25.0,
vmin=0.0,
vmax=1.0,
cmap=pt.progression_cmap,
alpha=0.5)
# Plot legend
# noinspection PyUnresolvedReferences
rects = [
mpl.patches.Rectangle((0, 0),
1,
1,
fc=pt.color_cn + (0.5, ),
linewidth=0),
mpl.patches.Rectangle((0, 0),
1,
1,
fc=pt.color_mci + (0.5, ),
linewidth=0),
mpl.patches.Rectangle((0, 0),
1,
1,
fc=pt.color_ad + (0.5, ),
linewidth=0)
]
labels = ['CN', 'MCI', 'AD']
legend = ax.legend(rects,
labels,
fontsize=10,
ncol=len(rects),
loc='upper center',
framealpha=0.9)
legend.get_frame().set_edgecolor((0.6, 0.6, 0.6))
# Draw or save the plot
plt.tight_layout()
if args.plot_file is not None:
plt.savefig(args.plot_file, transparent=True)
else:
plt.show()
plt.close(fig)
def plot_errors_sampling(args, biomarkers, errors, num_samples):
print log.INFO, 'Plotting error bars...'
fig, ax = plt.subplots(figsize=(8, 5))
pt.setup_axes(plt, ax, xgrid=False)
ax.set_title('Influence of the sampling strategy on DP estimation')
ax.set_ylabel('Mean progress estimation error')
plt.tick_params(labelbottom='off')
samplings = ['longitudinal', 'triangular', 'uniform']
biomarker_strings = {'synth_hipp': '$\mathcal{M}^{HV}$',
'synth_mmse': '$\mathcal{M}^{MMSE}$',
'synth_cdrsb': '$\mathcal{M}^{CDR-SB}$'}
# Collect data
data = []
medians = []
for biomarker in biomarkers:
for sampling in samplings:
data.append(errors[biomarker][sampling][num_samples])
medians.append(np.median(errors[biomarker][sampling][num_samples]))
# Set limits
max_data = np.max(data)
ax.set_ylim(0, 1.15 * max_data)
# Draw boxplot
boxplot = plt.boxplot(data, patch_artist=True)
# Set boxplot colours
colours = [(0.0, 0.0, 0.0), (0.0, 0.0, 0.5), (0.0, 0.5, 0.0)] * len(biomarkers)
for i in range(len(data)):
pt.set_boxplot_color(boxplot, i, colours[i])
# Write median errors as text
upper_labels = [str(np.round(m, 3)) for m in medians]
for i in np.arange(len(upper_labels)):
ax.text(i + 1, 1.02 * max_data, upper_labels[i],
horizontalalignment='center', size=10, color=colours[i])
# Write category labels
for i, biomarker in enumerate(biomarkers):
plt.text((i + 0.5) * len(samplings) + 0.5, -74,
biomarker_strings[biomarker],
horizontalalignment='center')
# Plot legend
legend = ax.legend([mpl.patches.Rectangle((0, 0), 1, 1, fc=(0.0, 0.0, 0.0, 0.2), ec=(0.0, 0.0, 0.0, 1.0), linewidth=1),
mpl.patches.Rectangle((0, 0), 1, 1, fc=(0.0, 0.0, 0.5, 0.2), ec=(0.0, 0.0, 0.5, 1.0), linewidth=1),
mpl.patches.Rectangle((0, 0), 1, 1, fc=(0.0, 0.5, 0.0, 0.2), ec=(0.0, 0.5, 0.0, 1.0), linewidth=1)],
['{0} sampling'.format(s) for s in samplings], fontsize=10, ncol=3, loc='upper center', framealpha=0.9)
legend.get_frame().set_edgecolor((0.6, 0.6, 0.6))
# Draw horizontal lines
for x in range(3, len(data), 3):
plt.axvline(x + 0.5, color='k', alpha=0.4)
# Show or save plot
plt.tight_layout()
if args.plot_file is not None:
plt.savefig(args.plot_file, transparent=True)
else:
plt.show()
plt.close(fig)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('-m', '--method', choices=DataHandler.get_method_choices(), default='all', help='the method to collect data for')
parser.add_argument('-b', '--biomarkers', nargs='+', default=None, help='name of the biomarker to be plotted')
parser.add_argument('-p', '--phase', default=None, choices=DataHandler.get_phase_choices(), help='the phase for which the model is to be trained')
parser.add_argument('--save_plots', action='store_true', default=False, help='save the plots with a default filename')
args = parser.parse_args()
# Collect data for test
data_handler = DataHandler.get_data_handler(method=args.method,
biomarkers=args.biomarkers,
phase=args.phase)
biomarkers = data_handler.get_biomarker_names()
measurements = data_handler.get_measurements_as_dict(visits=['bl', 'm12'],
biomarkers=biomarkers,
select_training_set=True,
select_complete=True)
# Setup plotting folder
eval_folder = DataHandler.make_dir(data_handler.get_eval_folder(), 'quants')
# Process all biomarkers
for biomarker in biomarkers:
print log.INFO, 'Generating quantile correlation plot for {0}...'.format(biomarker)
model_file = data_handler.get_model_file(biomarker)
pm = ProgressionModel(biomarker, model_file)
q_file = os.path.join(eval_folder, '{0}.p'.format(biomarker))
if os.path.isfile(q_file):
(q_bl, q_m12) = pickle.load(open(q_file, 'rb'))
else:
q_bl = []
q_m12 = []
for rid in measurements:
val_bl = measurements[rid]['bl'][biomarker]
val_m12 = measurements[rid]['m12'][biomarker]
p_bl = measurements[rid]['bl']['progress']
p_m12 = measurements[rid]['m12']['progress']
q_bl.append(pm.approximate_quantile(p_bl, val_bl))
q_m12.append(pm.approximate_quantile(p_m12, val_m12))
pickle.dump((q_bl, q_m12), open(q_file, 'wb'))
# Setup plot
fig, axs = plt.subplots(1, 2)
plt.suptitle('Correlation between bl and m12 quantiles')
# Plot 1
ax = axs[0]
pt.setup_axes(plt, ax, yspine=True)
ax.set_xlabel('Quantile bl')
ax.set_ylabel('Quantile m12')
ax.scatter(q_bl, q_m12, edgecolor='none', s=25.0, alpha=0.5)
# Plot 2
q_bl = np.array(q_bl)
q_m12 = np.array(q_m12)
errors = q_bl - q_m12
loc, scale = norm.fit(errors, floc=0.0)
ax = axs[1]
pt.setup_axes(plt, ax)
ax.set_xlabel('Difference bl to m12')
ax.set_ylabel('Probability')
ax.set_xlim(-1.05, 1.05)
ax.hist(errors, bins=15, normed=True, histtype='stepfilled', alpha=0.3)
x = np.linspace(-1.0, 1.0, 100)
ax.plot(x, norm.pdf(x, loc=loc, scale=scale), color='k')
# Draw or save the plot
plt.tight_layout()
if args.save_plots:
plot_file = os.path.join(eval_folder, '{0}.pdf'.format(biomarker))
plt.savefig(plot_file, transparent=True)
else:
plt.show()
plt.close(fig)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('-b',
'--biomarkers',
nargs=2,
default=['D1', 'D2'],
help='name of the biomarker to be plotted')
parser.add_argument('--plot_file',
type=str,
default=None,
help='filename of the output file')
args = parser.parse_args()
# Collect data for test
data_handler = DataHandler.get_data_handler(biomarkers=args.biomarkers)
biomarkers = data_handler.get_biomarker_names()
measurements = data_handler.get_measurements_as_dict(biomarkers=biomarkers,
select_complete=True)
# Collect biomarker values
biomarkers_1 = []
biomarkers_2 = []
diagnoses = []
for rid in measurements:
for visit in measurements[rid]:
biomarkers_1.append(measurements[rid][visit][biomarkers[0]])
biomarkers_2.append(measurements[rid][visit][biomarkers[1]])
diagnoses.append(measurements[rid][visit]['DX.scan'])
diagnoses = np.array(diagnoses)
diagnoses[(0.25 <= diagnoses) & (diagnoses <= 0.75)] = 0.5
# Setup plot
fig, ax = plt.subplots()
pt.setup_axes(plt, ax)
ax.scatter(biomarkers_1,
biomarkers_2,
s=15.0,
c=diagnoses,
edgecolor='none',
vmin=0.0,
vmax=1.0,
cmap=pt.progression_cmap,
alpha=0.25)
ax.set_xlabel(biomarkers[0])
ax.set_ylabel(biomarkers[1])
# Plot legend
rects = [
mpl.patches.Rectangle((0, 0),
1,
1,
fc=pt.color_cn + (0.25, ),
linewidth=0),
mpl.patches.Rectangle((0, 0),
1,
1,
fc=pt.color_mci + (0.25, ),
linewidth=0),
mpl.patches.Rectangle((0, 0),
1,
1,
fc=pt.color_ad + (0.25, ),
linewidth=0)
]
labels = ['CN', 'MCI', 'AD']
legend = ax.legend(rects,
labels,
fontsize=10,
ncol=len(rects),
loc='upper center',
framealpha=0.9)
legend.get_frame().set_edgecolor((0.6, 0.6, 0.6))
# Draw or save the plot
plt.tight_layout()
if args.plot_file is not None:
plt.savefig(args.plot_file, transparent=True)
else:
plt.show()
plt.close(fig)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('-m',
'--method',
choices=DataHandler.get_method_choices(),
default='all',
help='the method to collect data for')
parser.add_argument('-b',
'--biomarkers',
nargs='+',
default=None,
help='name of the biomarker to be plotted')
parser.add_argument('-p',
'--phase',
default=None,
choices=DataHandler.get_phase_choices(),
help='the phase for which the model is to be trained')
parser.add_argument('--save_plots',
action='store_true',
default=False,
help='save the plots with a default filename')
args = parser.parse_args()
# Collect data for test
data_handler = DataHandler.get_data_handler(method=args.method,
biomarkers=args.biomarkers,
phase=args.phase)
biomarkers = data_handler.get_biomarker_names()
measurements = data_handler.get_measurements_as_dict(
visits=['bl', 'm12'],
biomarkers=biomarkers,
select_training_set=True,
select_complete=True)
# Setup plotting folder
eval_folder = DataHandler.make_dir(data_handler.get_eval_folder(),
'quants')
# Process all biomarkers
for biomarker in biomarkers:
print log.INFO, 'Generating quantile correlation plot for {0}...'.format(
biomarker)
model_file = data_handler.get_model_file(biomarker)
pm = ProgressionModel(biomarker, model_file)
q_file = os.path.join(eval_folder, '{0}.p'.format(biomarker))
if os.path.isfile(q_file):
(q_bl, q_m12) = pickle.load(open(q_file, 'rb'))
else:
q_bl = []
q_m12 = []
for rid in measurements:
val_bl = measurements[rid]['bl'][biomarker]
val_m12 = measurements[rid]['m12'][biomarker]
p_bl = measurements[rid]['bl']['progress']
p_m12 = measurements[rid]['m12']['progress']
q_bl.append(pm.approximate_quantile(p_bl, val_bl))
q_m12.append(pm.approximate_quantile(p_m12, val_m12))
pickle.dump((q_bl, q_m12), open(q_file, 'wb'))
# Setup plot
fig, axs = plt.subplots(1, 2)
plt.suptitle('Correlation between bl and m12 quantiles')
# Plot 1
ax = axs[0]
pt.setup_axes(plt, ax, yspine=True)
ax.set_xlabel('Quantile bl')
ax.set_ylabel('Quantile m12')
ax.scatter(q_bl, q_m12, edgecolor='none', s=25.0, alpha=0.5)
# Plot 2
q_bl = np.array(q_bl)
q_m12 = np.array(q_m12)
errors = q_bl - q_m12
loc, scale = norm.fit(errors, floc=0.0)
ax = axs[1]
pt.setup_axes(plt, ax)
ax.set_xlabel('Difference bl to m12')
ax.set_ylabel('Probability')
ax.set_xlim(-1.05, 1.05)
ax.hist(errors, bins=15, normed=True, histtype='stepfilled', alpha=0.3)
x = np.linspace(-1.0, 1.0, 100)
ax.plot(x, norm.pdf(x, loc=loc, scale=scale), color='k')
# Draw or save the plot
plt.tight_layout()
if args.save_plots:
plot_file = os.path.join(eval_folder, '{0}.pdf'.format(biomarker))
plt.savefig(plot_file, transparent=True)
else:
plt.show()
plt.close(fig)
def plot_errors(args, values, methods):
fig, ax = plt.subplots()
pt.setup_axes(plt, ax, xgrid=False)
num_methods = len(methods)
for i in xrange(num_methods):
ax.axvline(i * 2 + 1.5, linestyle='-', color='k', alpha=0.4)
ax.set_axisbelow(True)
ax.set_title('Prediction of {0}'.format(args.predict_biomarker))
ax.set_ylabel('Prediction error')
ax.set_xticklabels([])
# Append plot for naive estimation
values_observed = np.array(values[values.keys()[0]]['observed'])
values_naive = np.array(values[values.keys()[0]]['naive'])
errors_naive = np.abs(values_observed - values_naive)
data = [errors_naive]
medians = [np.median(errors_naive)]
weights = ['normal']
for method in methods:
values_model1 = np.array(values[method]['model_dpi'])
values_model2 = np.array(values[method]['model_dpi_dpr'])
errors_model1 = np.abs(values_observed - values_model1)
errors_model2 = np.abs(values_observed - values_model2)
data.append(errors_model1)
data.append(errors_model2)
medians.append(np.median(errors_model1))
medians.append(np.median(errors_model2))
weights.append('bold' if stats.ttest_rel(errors_naive, errors_model1
)[1] < 0.01 else 'normal')
weights.append('bold' if stats.ttest_rel(errors_naive, errors_model2
)[1] < 0.01 else 'normal')
# Set colors
colors = [(0.0, 0.0, 0.0)]
for i in range(num_methods):
colors.append((0.0, 0.0, 0.5))
colors.append((0.0, 0.5, 0.0))
# Set limits
max_data = np.max(data)
ax.set_ylim(-0.01 * max_data, 1.01 * max_data)
# Add labels to x axis
for i, method in enumerate(methods):
ax.text(i * 2 + 2.5,
-0.04 * max_data,
method,
horizontalalignment='center')
# Write median errors as text
pos = np.arange(1, 2 * num_methods + 2)
upper_labels = [str(np.round(m, 2)) for m in medians]
for i in range(2 * num_methods + 1):
ax.text(pos[i],
0.91 * max_data,
upper_labels[i],
weight=weights[i],
horizontalalignment='center',
size=10,
color=colors[i])
# Plot boxplots
boxplot = plt.boxplot(data, patch_artist=True)
for i in range(len(boxplot['boxes'])):
pt.set_boxplot_color(boxplot, i, colors[i])
# Plot legend
legend = ax.legend([
mpl.patches.Rectangle((0, 0),
1,
1,
fc=(0.0, 0.0, 0.0, 0.2),
ec=(0.0, 0.0, 0.0, 1.0),
linewidth=1),
mpl.patches.Rectangle((0, 0),
1,
1,
fc=(0.0, 0.0, 0.5, 0.2),
ec=(0.0, 0.0, 0.5, 1.0),
linewidth=1),
mpl.patches.Rectangle((0, 0),
1,
1,
fc=(0.0, 0.5, 0.0, 0.2),
ec=(0.0, 0.5, 0.0, 1.0),
linewidth=1)
], ['Naive', 'DPI', 'DPI + DPR'],
fontsize=10,
ncol=3,
loc='upper center',
framealpha=0.9)
legend.get_frame().set_edgecolor((0.6, 0.6, 0.6))
# Show or save plot
plt.tight_layout()
if args.plot_file is not None:
plt.savefig(args.plot_file, transparent=True)
else:
plt.show()
plt.close(fig)
def plot_biomarker(data_handler, biomarker, measurements, dpi, dpr):
"""
Plot the model of one biomarker with the fitted values
:param data_handler: the data handler
:param biomarker: the biomarker to plot
:param measurements: the measurements containing the biomarker samples of one subject
:param dpi: the estimated DPI
:param dpr: the estimated DPR
"""
model_file = data_handler.get_model_file(biomarker)
if not os.path.isfile(model_file):
print log.ERROR, 'Model file not found: {0}'.format(model_file)
return
print log.INFO, 'Generating plot for {0}...'.format(biomarker)
#
# Read model
#
pm = ProgressionModel(biomarker, model_file)
progress_extrapolate = 0.3 * (pm.max_progress - pm.min_progress)
min_progress_extrapolate = int(pm.min_progress - progress_extrapolate)
max_progress_extrapolate = int(pm.max_progress + progress_extrapolate)
progress_linspace_ex1 = np.linspace(min_progress_extrapolate,
pm.min_progress, 20)
progress_linspace_int = np.linspace(pm.min_progress, pm.max_progress, 60)
progress_linspace_ex2 = np.linspace(pm.max_progress,
max_progress_extrapolate, 20)
#
# Setup plot
#
biomarker_string = pt.get_biomarker_string(biomarker)
figure_width = 6
fig = plt.figure(figsize=(figure_width, 5))
ax1 = plt.subplot(1, 1, 1)
pt.setup_axes(plt, ax1, xgrid=False, ygrid=False)
ax1.set_title(
'Model for {0} with fitted sample values'.format(biomarker_string))
ax1.set_xlabel('Disease progress (days before/after conversion to MCI)')
ax1.set_ylabel(DataHandler.get_biomarker_unit(biomarker))
ax1.set_xlim(min_progress_extrapolate, max_progress_extrapolate)
#
# Plot the percentile curves of the fitted model
#
ax1.axvline(pm.min_progress, color='0.15', linestyle=':')
ax1.axvline(pm.max_progress, color='0.15', linestyle=':')
quantiles = [0.1, 0.25, 0.5, 0.75, 0.9]
grey_values = ['0.4', '0.2', '0', '0.2', '0.4']
for grey_value, quantile in zip(grey_values, quantiles):
curve_int = pm.get_quantile_curve(progress_linspace_int, quantile)
ax1.plot(progress_linspace_int, curve_int, color=grey_value)
curve_ex1 = pm.get_quantile_curve(progress_linspace_ex1, quantile)
curve_ex2 = pm.get_quantile_curve(progress_linspace_ex2, quantile)
ax1.plot(progress_linspace_ex1, curve_ex1, '--', color=grey_value)
ax1.plot(progress_linspace_ex2, curve_ex2, '--', color=grey_value)
label = 'q = {0}'.format(quantile * 100)
ax1.text(progress_linspace_int[-1] + 100,
curve_int[-1],
label,
fontsize=10)
#
# Plot points
#
progr_points = []
value_points = []
diagn_points = []
for visit in measurements[0]:
if biomarker in measurements[0][visit]:
progress = measurements[0][visit]['scantime'] * dpr + dpi
value = measurements[0][visit][biomarker]
progr_points.append(progress)
value_points.append(value)
diagn_points.append(1.0)
ax1.axvline(progress, color='b', linestyle='--')
ax1.text(progress + 150, value, visit, color='b', fontsize=10)
ax1.scatter(progr_points,
value_points,
s=25.0,
color='b',
edgecolor='none',
vmin=0.0,
vmax=1.0,
alpha=0.9)
#
# Draw or save the plot
#
plt.tight_layout()
plt.show()
plt.close(fig)
def evaluate_curves(biomarker_name, num_samples=200, show_plots=False, csig=0):
biomarker = 'synth_{0}'.format(biomarker_name)
print log.INFO, 'Evaluating {0} for {1} samples, csig={2}...'.format(biomarker, num_samples, csig)
donohue_model_path = '/Development/DiseaseProgressionModel/models/donohue/'
vgam_model_path = '/Development/DiseaseProgressionModel/models/synth/'
# Setup plot
if show_plots:
fig = plt.figure()
ax = plt.subplot(1, 1, 1)
pt.setup_axes(plt, ax, xgrid=False, ygrid=False)
ax.set_title('')
ax.set_xlabel('')
else:
fig = None
ax = None
# Initialise values
offset_donohue = 0 # 182.5
errors_donohue = []
errors_vgam_mean = []
errors_vgam_median = []
# Get real curve values
progress_linspace = np.linspace(-1500, 1500)
mean_curve = [SynthModel.get_mean_value(biomarker, p) for p in progress_linspace]
median_curve = [SynthModel.get_distributed_value(biomarker, p, cdf=0.5) for p in progress_linspace]
# Plot synthetic model curve
if show_plots:
progress_linspace_synth = np.linspace(-2500, 2500, 100)
quantiles = [0.1, 0.25, 0.5, 0.75, 0.9]
alphas = [0.4, 0.7, 1.0, 0.7, 0.4]
for quantile, alpha in zip(quantiles, alphas):
curve_synth = [SynthModel.get_distributed_value(biomarker, p, cdf=quantile)
for p in progress_linspace_synth]
ax.plot(progress_linspace_synth, curve_synth, color='b', alpha=alpha)
curve_synth = [SynthModel.get_mean_value(biomarker, p) for p in progress_linspace_synth]
ax.plot(progress_linspace_synth, curve_synth, '--', color='b')
# Get values for mean calculation
end_values = [SynthModel.get_distributed_value(biomarker, progress_linspace[0], cdf=0.001),
SynthModel.get_distributed_value(biomarker, progress_linspace[-1], cdf=0.001),
SynthModel.get_distributed_value(biomarker, progress_linspace[0], cdf=0.999),
SynthModel.get_distributed_value(biomarker, progress_linspace[-1], cdf=0.999)]
values = np.linspace(min(end_values), max(end_values), 100)
for run in range(100):
# Get Donohue model
donohue_file = os.path.join(donohue_model_path,
'population_value-{0}_csig{1}_run{2}.csv'.format(biomarker_name, csig, run))
r = mlab.csv2rec(donohue_file)
progrs = r[r.dtype.names[0]] - offset_donohue
vals = r[r.dtype.names[1]]
curve_donohue = []
progr_donohue = []
for p in progress_linspace:
if progrs[0] < p < progrs[-1]:
i = 1
while p > progrs[i]:
i += 1
progr_donohue.append(float(progrs[i]))
curve_donohue.append(float(vals[i]))
else:
print log.WARNING, 'Model scope too small... skipping!'
continue
# Get VGAM model
if csig == 0:
vgam_model_file = os.path.join(vgam_model_path,
'{0}_model_{1}_longitudinal_{2}.csv'.format(biomarker,
num_samples, run))
else:
vgam_model_file = os.path.join(vgam_model_path,
'{0}_model_{1}_longitudinal_csig{2}.0_{3}.csv'.format(biomarker,
num_samples,
csig, run))
pm = ProgressionModel(biomarker, vgam_model_file)
curve_vgam_median = pm.get_quantile_curve(progress_linspace, 0.5)
curve_vgam_mean = [np.sum(pm.get_density_distribution(values, p) * values /
np.sum(pm.get_density_distribution(values, p))) for p in progress_linspace]
# Calculate errors
errors_donohue.append(np.mean(np.abs(np.array(curve_donohue) - np.array(mean_curve))))
errors_vgam_mean.append(np.mean(np.abs(np.array(curve_vgam_mean) - np.array(mean_curve))))
errors_vgam_median.append(np.mean(np.abs(np.array(curve_vgam_median) - np.array(median_curve))))
if show_plots:
ax.plot(progr_donohue, curve_donohue, '--', color='g', alpha=0.2, linewidth=2)
# ax.plot(progress_linspace, curve_vgam_median, '-', color='r', alpha=0.2, linewidth=2)
ax.plot(progress_linspace, curve_vgam_mean, '--', color='r', alpha=0.2, linewidth=2)
print log.RESULT, 'Donohue (mean):', np.mean(errors_donohue), np.var(errors_donohue)
print log.RESULT, 'VGAM (mean):', np.mean(errors_vgam_mean), np.var(errors_vgam_mean)
print log.RESULT, 'VGAM (median):', np.mean(errors_vgam_median), np.var(errors_vgam_median)
# Draw or save the plot
if show_plots:
plt.tight_layout()
plt.show()
plt.close(fig)
def plot_model(args, data_handler, biomarker):
model_file = data_handler.get_model_file(biomarker)
if not os.path.isfile(model_file):
print log.ERROR, 'Model file not found: {0}'.format(model_file)
return
print log.INFO, 'Generating plot for {0}...'.format(biomarker)
plot_synth_model = args.plot_synth_model and biomarker in SynthModel.get_biomarker_names()
#
# Read model
#
pm = ProgressionModel(biomarker, model_file, extrapolator=args.extrapolator)
progress_extrapolate = 0.3 * (pm.max_progress - pm.min_progress)
min_progress_extrapolate = int(pm.min_progress - progress_extrapolate)
max_progress_extrapolate = int(pm.max_progress + progress_extrapolate)
progress_linspace_ex1 = np.linspace(min_progress_extrapolate, pm.min_progress, 20)
progress_linspace_int = np.linspace(pm.min_progress, pm.max_progress, 60)
progress_linspace_ex2 = np.linspace(pm.max_progress, max_progress_extrapolate, 20)
# Calc min and max val in interval between 1% and 99% percentie
min_val, max_val = pm.get_value_range([0.1, 0.9])
# progress_linspace = np.linspace(min_progress_extrapolate, max_progress_extrapolate, 100)
# min_val = float('inf')
# max_val = float('-inf')
# for quantile in [0.1, 0.9]:
# curve = pm.get_quantile_curve(progress_linspace, quantile)
# min_val = min(min_val, np.min(curve))
# max_val = max(max_val, np.max(curve))
#
# Setup plot
#
biomarker_string = pt.get_biomarker_string(biomarker)
figure_width = 6 if args.no_densities or args.only_densities else 12
fig = plt.figure(figsize=(figure_width, 5))
if args.only_densities:
ax1 = None
ax2 = plt.subplot(1, 1, 1)
pt.setup_axes(plt, ax2, xgrid=False, ygrid=False)
elif args.no_densities:
ax1 = plt.subplot(1, 1, 1)
ax2 = None
pt.setup_axes(plt, ax1, xgrid=False, ygrid=False)
else:
ax1 = plt.subplot(1, 2, 1)
ax2 = plt.subplot(1, 2, 2)
pt.setup_axes(plt, ax1, xgrid=False, ygrid=False)
pt.setup_axes(plt, ax2)
if not args.only_densities:
if args.no_model and not args.plot_synth_model:
ax1.set_title('Aligned samples for {0}'.format(biomarker_string))
else:
ax1.set_title('Quantile curves for {0}'.format(biomarker_string))
if args.phase == 'mciad':
ax1.set_xlabel('Disease progress (days before/after conversion to AD)')
else:
ax1.set_xlabel('Disease progress (days before/after conversion to MCI)')
ax1.set_ylabel(DataHandler.get_biomarker_unit(biomarker))
if args.xlim is not None:
ax1.set_xlim(args.xlim[0], args.xlim[1])
else:
ax1.set_xlim(min_progress_extrapolate, max_progress_extrapolate)
if args.ylim is not None:
ax1.set_ylim(args.ylim[0], args.ylim[1])
#
# Plot the percentile curves of the fitted model
#
if not args.no_model and not args.only_densities:
ax1.axvline(pm.min_progress, color='0.15', linestyle=':')
ax1.axvline(pm.max_progress, color='0.15', linestyle=':')
quantiles = [0.1, 0.25, 0.5, 0.75, 0.9]
grey_values = ['0.4', '0.2', '0', '0.2', '0.4']
for grey_value, quantile in zip(grey_values, quantiles):
curve_int = pm.get_quantile_curve(progress_linspace_int, quantile)
ax1.plot(progress_linspace_int, curve_int, color=grey_value)
if not args.no_extrapolation:
curve_ex1 = pm.get_quantile_curve(progress_linspace_ex1, quantile)
curve_ex2 = pm.get_quantile_curve(progress_linspace_ex2, quantile)
ax1.plot(progress_linspace_ex1, curve_ex1, '--', color=grey_value)
ax1.plot(progress_linspace_ex2, curve_ex2, '--', color=grey_value)
if args.plot_quantile_label:
label = '$q={0}\%$'.format(quantile * 100)
ax1.text(progress_linspace_int[-1] + 10, curve_int[-1], label, fontsize=10)
if args.plot_donohue:
print 'Plotting Donohue'
donohue_file = os.path.join(data_handler._conf.models_folder,
'donohue', 'population_{0}.csv'.format(biomarker.replace(' ', '.')))
if not os.path.isfile(donohue_file):
print log.ERROR, 'Donohue model file not found: {0}'.format(donohue_file)
return
r = mlab.csv2rec(donohue_file)
if args.method == 'joint':
offset = 2200
else:
offset = 300
progrs = r[r.dtype.names[0]] * 30.44 + offset
vals = r[r.dtype.names[1]]
curve_donohue = []
progr_donohue = []
for p in progress_linspace_int:
if progrs[0] < p < progrs[-1]:
i = 1
while p > progrs[i]:
i += 1
# TODO linear interpolation
progr_donohue.append(progrs[i])
curve_donohue.append(vals[i])
ax1.plot(progr_donohue, curve_donohue, '--', color='b', linewidth=2)
#
# Plot synthetic model curve
#
if plot_synth_model:
progress_linspace_synth = np.linspace(-2500, 2500, 100)
quantiles = [0.1, 0.25, 0.5, 0.75, 0.9]
alphas = [0.4, 0.7, 1.0, 0.7, 0.4]
for quantile, alpha in zip(quantiles, alphas):
curve_synth = [SynthModel.get_distributed_value(biomarker, p, cdf=quantile) for p in progress_linspace_synth]
ax1.plot(progress_linspace_synth, curve_synth, color='b', alpha=alpha)
#
# Plot predictor function
#
if args.plot_eta is not None and not args.only_densities:
# Get second axis of plot 1
ax1b = ax1.twinx()
# Plot all progresses
# ax1b.scatter(pm.all_progresses, pm.all_mus, facecolor='b', marker='o', edgecolor='none', alpha=0.2)
ax1b.text(pm.progresses[-1], pm.sigmas[-1], '$\mu$', color='b', fontsize=11)
# Plot binned progresses
ax1b.scatter(pm.progresses, pm.sigmas, color='b', marker='x')
# Plot interpolated model
mus = [pm.get_eta(pm.sigmas, p) for p in progress_linspace_int]
ax1b.plot(progress_linspace_int, mus, color='b')
if not args.no_extrapolation:
mus = [pm.get_eta(pm.sigmas, p) for p in progress_linspace_ex1]
ax1b.plot(progress_linspace_ex1, mus, '--', color='b')
mus = [pm.get_eta(pm.sigmas, p) for p in progress_linspace_ex2]
ax1b.plot(progress_linspace_ex2, mus, '--', color='b')
if args.xlim is not None:
ax1b.set_xlim(args.xlim[0], args.xlim[1])
else:
ax1b.set_xlim(min_progress_extrapolate, max_progress_extrapolate)
#
# Plot errors
#
if args.plot_errors and not args.only_densities:
eval_file = model_file.replace('.csv', '_eval_cover.csv')
if not os.path.isfile(eval_file):
print log.ERROR, 'Evaluation file not found: {0}'.format(eval_file)
else:
m = mlab.csv2rec(eval_file)
progresses = m['progress']
errors = m['error']
# Get second axis of plot 1
ax1b = ax1.twinx()
# ax1b.set_ylim(0, max(150, 1.2 * np.max(errors)))
ax1b.plot(progresses, errors, color='g', marker='x')
ax1b.text(progresses[-1], errors[-1], 'Discr.', color='g', fontsize=11)
ax1b.axhline(np.mean(errors), color='g', linestyle='--', alpha=0.5)
median_curve = pm.get_quantile_curve(progresses, 0.5)
min_value = np.min(median_curve)
max_value = np.max(median_curve)
rect = mpl.patches.Rectangle((progresses[0], min_value), progresses[-1] - progresses[0],
max_value - min_value,
fc=(0.0, 0.5, 0.0, 0.1), ec=(0.0, 0.5, 0.0, 0.8),
linewidth=1)
ax1.add_patch(rect)
#
# Plot points
#
if not args.no_points and not args.only_densities:
samples_file = data_handler.get_samples_file(biomarker)
if not os.path.isfile(samples_file):
print log.ERROR, 'Samples file not found: {0}'.format(samples_file)
else:
m = mlab.csv2rec(samples_file)
progr_points = m['progress']
value_points = m['value']
# diagn_points = [0.5 if p < 0 else 1.0 for p in progr_points]
diagn_points = m['diagnosis']
diagn_points[(0.25 <= diagn_points) & (diagn_points <= 0.75)] = 0.5
print log.INFO, 'Plotting {0} sample points...'.format(len(progr_points))
ax1.scatter(progr_points, value_points, s=15.0, c=diagn_points, edgecolor='none',
vmin=0.0, vmax=1.0, cmap=pt.progression_cmap, alpha=args.points_alpha)
if args.phase == 'cnmci':
rects = [mpl.patches.Rectangle((0, 0), 1, 1, fc=pt.color_cn + (args.points_alpha,), linewidth=0),
mpl.patches.Rectangle((0, 0), 1, 1, fc=pt.color_mci + (args.points_alpha,), linewidth=0)]
labels = ['CN', 'MCI']
elif args.phase == 'mciad':
rects = [mpl.patches.Rectangle((0, 0), 1, 1, fc=pt.color_mci + (args.points_alpha,), linewidth=0),
mpl.patches.Rectangle((0, 0), 1, 1, fc=pt.color_ad + (args.points_alpha,), linewidth=0)]
labels = ['MCI', 'AD']
else:
rects = [mpl.patches.Rectangle((0, 0), 1, 1, fc=pt.color_cn + (args.points_alpha,), linewidth=0),
mpl.patches.Rectangle((0, 0), 1, 1, fc=pt.color_mci + (args.points_alpha,), linewidth=0),
mpl.patches.Rectangle((0, 0), 1, 1, fc=pt.color_ad + (args.points_alpha,), linewidth=0)]
labels = ['CN', 'MCI', 'AD']
legend = ax1.legend(rects, labels, fontsize=10, ncol=len(rects), loc='upper center', framealpha=0.9)
legend.get_frame().set_edgecolor((0.6, 0.6, 0.6))
#
# Plot PDFs
#
progr_samples = [-2000, -1000, 0, 1000, 2000, 3000, 4000] if args.phase == 'joint' else \
[-2000, -1500, -1000, -500, 0, 500, 1000, 1500, 2000]
if args.phase == 'cnmci':
vmin = -2000
vmax = 6000
elif args.phase == 'mciad':
vmin = -6000
vmax = 2000
elif args.phase == 'joint':
vmin = -2000
vmax = 4000
sample_cmap = cmx.ScalarMappable(
norm=colors.Normalize(vmin=vmin, vmax=vmax),
cmap=plt.get_cmap(pt.progression_cmap))
if not args.no_sample_lines and not args.only_densities:
for progr in progr_samples:
if not args.no_extrapolation or pm.min_progress < progr < pm.max_progress:
# sample_color = sample_cmap.to_rgba(progr_samples.index(progr))
sample_color = sample_cmap.to_rgba(progr)
linestyle = '--' if progr < pm.min_progress or progr > pm.max_progress else '-'
ax1.axvline(progr, color=sample_color, linestyle=linestyle, alpha=0.3)
if not args.no_densities:
ax2.set_title('Probability density function for {0}'.format(biomarker_string))
ax2.set_xlabel(DataHandler.get_biomarker_unit(biomarker))
ax2.set_ylabel('Probability')
if args.ylim is None:
values = np.linspace(min_val, max_val, 250)
ax2.set_xlim(min_val, max_val)
else:
values = np.linspace(args.ylim[0], args.ylim[1], 250)
ax2.set_xlim(args.ylim[0], args.ylim[1])
for progr in progr_samples:
if not args.no_extrapolation or pm.min_progress < progr < pm.max_progress:
# sample_color = sample_cmap.to_rgba(progr_samples.index(progr))
sample_color = sample_cmap.to_rgba(progr)
linestyle = '--' if progr < pm.min_progress or progr > pm.max_progress else '-'
probs = pm.get_density_distribution(values, progr)
ax2.plot(values, probs, label=str(progr), color=sample_color, linestyle=linestyle)
if plot_synth_model:
probs = [SynthModel.get_probability(biomarker, progr, v) for v in values]
ax2.plot(values, probs, color='b', linestyle='--')
legend = ax2.legend(fontsize=10, loc='best', framealpha=0.9)
legend.get_frame().set_edgecolor((0.6, 0.6, 0.6))
#
# Draw or save the plot
#
plt.tight_layout()
if args.save_plots or args.plot_file is not None:
if args.plot_file is not None:
plot_filename = args.plot_file
else:
plot_filename = model_file.replace('.csv', '.pdf')
plt.savefig(plot_filename, transparent=True)
else:
plt.show()
plt.close(fig)
def plot_predictions(biomarker, model, visits, rid_measurements, dpi, dpr,
value_model, value_naive, mean_quantile, change,
intercept, rid):
next_visit = get_predicted_visit(visits)
scantime_first_visit = rid_measurements[visits[0]]['scantime']
scantime_next_visit = rid_measurements[next_visit]['scantime']
progress_first_visit = ModelFitter.scantime_to_progress(
scantime_first_visit, scantime_first_visit, dpi, dpr)
progress_next_visit = ModelFitter.scantime_to_progress(
scantime_next_visit, scantime_first_visit, dpi, dpr)
total_scantime = scantime_next_visit - scantime_first_visit
progress_linspace = np.linspace(
progress_first_visit - total_scantime * 0.05,
progress_next_visit + total_scantime * 0.05, 100)
fig, ax = plt.subplots()
pt.setup_axes(plt, ax, xgrid=False, ygrid=False)
ax.set_title('{0} predictions for RID {1} (DPI={2}, DPR={3})'.format(
pt.get_biomarker_string(biomarker), rid, dpi, dpr))
ax.set_xlabel('Disease progress (days before/after conversion to AD)')
ax.set_ylabel(DataHandler.get_biomarker_unit(biomarker))
ax.set_xlim(progress_first_visit - total_scantime * 0.1,
progress_next_visit + total_scantime * 0.1)
color_mapper = cm.ScalarMappable(cmap=plt.get_cmap(pt.progression_cmap),
norm=colors.Normalize(vmin=0.0, vmax=1.0))
# Plot the percentile curves of the fitted model
quantiles = [0.1, 0.25, 0.5, 0.75, 0.9]
grey_values = ['0.8', '0.6', '0.4', '0.62', '0.84']
for grey_value, quantile in zip(grey_values, quantiles):
curve = model.get_quantile_curve(progress_linspace, quantile)
ax.plot(progress_linspace, curve, zorder=1, color=grey_value)
# Collect points
progr_points = []
value_points = []
diagn_points = []
for visit in visits + [next_visit]:
value_points.append(rid_measurements[visit][biomarker])
progr_points.append(
ModelFitter.scantime_to_progress(
rid_measurements[visit]['scantime'], scantime_first_visit, dpi,
dpr))
diagn_points.append(rid_measurements[visit]['DX.scan'])
# Collect lines
predict_diagnosis = rid_measurements[next_visit]['DX.scan']
predict_linspace = np.linspace(progress_first_visit, progress_next_visit,
50)
curve = [
model.get_value_at_quantile(p, mean_quantile) for p in predict_linspace
]
line = [
change *
ModelFitter.progress_to_scantime(p, scantime_first_visit, dpi, dpr) +
intercept for p in predict_linspace
]
# Plot model and linear prediction line
ax.plot(predict_linspace,
line,
zorder=1,
linestyle='--',
linewidth=2,
color='k',
label='naive prediction')
ax.plot(predict_linspace,
curve,
zorder=1,
linestyle='-',
linewidth=2,
color='k',
label='model-based prediction')
ax.scatter(progr_points,
value_points,
zorder=2,
s=50.0,
c=[color_mapper.to_rgba(d) for d in diagn_points],
edgecolor='none')
# Plot the predicted values
ax.scatter([progress_next_visit], [value_naive],
zorder=2,
s=50.0,
c='w',
edgecolor=color_mapper.to_rgba(predict_diagnosis))
ax.scatter([progress_next_visit], [value_model],
zorder=2,
s=50.0,
c='w',
edgecolor=color_mapper.to_rgba(predict_diagnosis))
plt.tight_layout()
plt.legend()
plot_filename = os.path.join(
'/Users/aschmiri/Desktop/temp',
'plot_predictions_{0}_{1}.pdf'.format(rid, biomarker))
plt.savefig(plot_filename, transparent=True)
# plt.show()
plt.close(fig)
def plot_biomarker(data_handler, biomarker, measurements, dpi, dpr):
"""
Plot the model of one biomarker with the fitted values
:param data_handler: the data handler
:param biomarker: the biomarker to plot
:param measurements: the measurements containing the biomarker samples of one subject
:param dpi: the estimated DPI
:param dpr: the estimated DPR
"""
model_file = data_handler.get_model_file(biomarker)
if not os.path.isfile(model_file):
print log.ERROR, 'Model file not found: {0}'.format(model_file)
return
print log.INFO, 'Generating plot for {0}...'.format(biomarker)
#
# Read model
#
pm = ProgressionModel(biomarker, model_file)
progress_extrapolate = 0.3 * (pm.max_progress - pm.min_progress)
min_progress_extrapolate = int(pm.min_progress - progress_extrapolate)
max_progress_extrapolate = int(pm.max_progress + progress_extrapolate)
progress_linspace_ex1 = np.linspace(min_progress_extrapolate, pm.min_progress, 20)
progress_linspace_int = np.linspace(pm.min_progress, pm.max_progress, 60)
progress_linspace_ex2 = np.linspace(pm.max_progress, max_progress_extrapolate, 20)
#
# Setup plot
#
biomarker_string = pt.get_biomarker_string(biomarker)
figure_width = 6
fig = plt.figure(figsize=(figure_width, 5))
ax1 = plt.subplot(1, 1, 1)
pt.setup_axes(plt, ax1, xgrid=False, ygrid=False)
ax1.set_title('Model for {0} with fitted sample values'.format(biomarker_string))
ax1.set_xlabel('Disease progress (days before/after conversion to MCI)')
ax1.set_ylabel(DataHandler.get_biomarker_unit(biomarker))
ax1.set_xlim(min_progress_extrapolate, max_progress_extrapolate)
#
# Plot the percentile curves of the fitted model
#
ax1.axvline(pm.min_progress, color='0.15', linestyle=':')
ax1.axvline(pm.max_progress, color='0.15', linestyle=':')
quantiles = [0.1, 0.25, 0.5, 0.75, 0.9]
grey_values = ['0.4', '0.2', '0', '0.2', '0.4']
for grey_value, quantile in zip(grey_values, quantiles):
curve_int = pm.get_quantile_curve(progress_linspace_int, quantile)
ax1.plot(progress_linspace_int, curve_int, color=grey_value)
curve_ex1 = pm.get_quantile_curve(progress_linspace_ex1, quantile)
curve_ex2 = pm.get_quantile_curve(progress_linspace_ex2, quantile)
ax1.plot(progress_linspace_ex1, curve_ex1, '--', color=grey_value)
ax1.plot(progress_linspace_ex2, curve_ex2, '--', color=grey_value)
label = 'q = {0}'.format(quantile * 100)
ax1.text(progress_linspace_int[-1] + 100, curve_int[-1], label, fontsize=10)
#
# Plot points
#
progr_points = []
value_points = []
diagn_points = []
for visit in measurements[0]:
if biomarker in measurements[0][visit]:
progress = measurements[0][visit]['scantime'] * dpr + dpi
value = measurements[0][visit][biomarker]
progr_points.append(progress)
value_points.append(value)
diagn_points.append(1.0)
ax1.axvline(progress, color='b', linestyle='--')
ax1.text(progress + 150, value, visit, color='b', fontsize=10)
ax1.scatter(progr_points, value_points, s=25.0, color='b', edgecolor='none',
vmin=0.0, vmax=1.0, alpha=0.9)
#
# Draw or save the plot
#
plt.tight_layout()
plt.show()
plt.close(fig)
def plot_model(args, data_handler, biomarker):
model_file = data_handler.get_model_file(biomarker)
if not os.path.isfile(model_file):
print log.ERROR, 'Model file not found: {0}'.format(model_file)
return
print log.INFO, 'Generating plot for {0}...'.format(biomarker)
plot_synth_model = args.plot_synth_model and biomarker in SynthModel.get_biomarker_names(
)
#
# Read model
#
pm = ProgressionModel(biomarker,
model_file,
extrapolator=args.extrapolator)
progress_extrapolate = 0.3 * (pm.max_progress - pm.min_progress)
min_progress_extrapolate = int(pm.min_progress - progress_extrapolate)
max_progress_extrapolate = int(pm.max_progress + progress_extrapolate)
progress_linspace_ex1 = np.linspace(min_progress_extrapolate,
pm.min_progress, 20)
progress_linspace_int = np.linspace(pm.min_progress, pm.max_progress, 60)
progress_linspace_ex2 = np.linspace(pm.max_progress,
max_progress_extrapolate, 20)
# Calc min and max val in interval between 1% and 99% percentie
min_val, max_val = pm.get_value_range([0.1, 0.9])
# progress_linspace = np.linspace(min_progress_extrapolate, max_progress_extrapolate, 100)
# min_val = float('inf')
# max_val = float('-inf')
# for quantile in [0.1, 0.9]:
# curve = pm.get_quantile_curve(progress_linspace, quantile)
# min_val = min(min_val, np.min(curve))
# max_val = max(max_val, np.max(curve))
#
# Setup plot
#
biomarker_string = pt.get_biomarker_string(biomarker)
figure_width = 6 if args.no_densities or args.only_densities else 12
fig = plt.figure(figsize=(figure_width, 5))
if args.only_densities:
ax1 = None
ax2 = plt.subplot(1, 1, 1)
pt.setup_axes(plt, ax2, xgrid=False, ygrid=False)
elif args.no_densities:
ax1 = plt.subplot(1, 1, 1)
ax2 = None
pt.setup_axes(plt, ax1, xgrid=False, ygrid=False)
else:
ax1 = plt.subplot(1, 2, 1)
ax2 = plt.subplot(1, 2, 2)
pt.setup_axes(plt, ax1, xgrid=False, ygrid=False)
pt.setup_axes(plt, ax2)
if not args.only_densities:
if args.no_model and not args.plot_synth_model:
ax1.set_title('Aligned samples for {0}'.format(biomarker_string))
else:
ax1.set_title('Quantile curves for {0}'.format(biomarker_string))
if args.phase == 'mciad':
ax1.set_xlabel(
'Disease progress (days before/after conversion to AD)')
else:
ax1.set_xlabel(
'Disease progress (days before/after conversion to MCI)')
ax1.set_ylabel(DataHandler.get_biomarker_unit(biomarker))
if args.xlim is not None:
ax1.set_xlim(args.xlim[0], args.xlim[1])
else:
ax1.set_xlim(min_progress_extrapolate, max_progress_extrapolate)
if args.ylim is not None:
ax1.set_ylim(args.ylim[0], args.ylim[1])
#
# Plot the percentile curves of the fitted model
#
if not args.no_model and not args.only_densities:
ax1.axvline(pm.min_progress, color='0.15', linestyle=':')
ax1.axvline(pm.max_progress, color='0.15', linestyle=':')
quantiles = [0.1, 0.25, 0.5, 0.75, 0.9]
grey_values = ['0.4', '0.2', '0', '0.2', '0.4']
for grey_value, quantile in zip(grey_values, quantiles):
curve_int = pm.get_quantile_curve(progress_linspace_int, quantile)
ax1.plot(progress_linspace_int, curve_int, color=grey_value)
if not args.no_extrapolation:
curve_ex1 = pm.get_quantile_curve(progress_linspace_ex1,
quantile)
curve_ex2 = pm.get_quantile_curve(progress_linspace_ex2,
quantile)
ax1.plot(progress_linspace_ex1,
curve_ex1,
'--',
color=grey_value)
ax1.plot(progress_linspace_ex2,
curve_ex2,
'--',
color=grey_value)
if args.plot_quantile_label:
label = '$q={0}\%$'.format(quantile * 100)
ax1.text(progress_linspace_int[-1] + 10,
curve_int[-1],
label,
fontsize=10)
if args.plot_donohue:
print 'Plotting Donohue'
donohue_file = os.path.join(
data_handler._conf.models_folder, 'donohue',
'population_{0}.csv'.format(biomarker.replace(' ', '.')))
if not os.path.isfile(donohue_file):
print log.ERROR, 'Donohue model file not found: {0}'.format(
donohue_file)
return
r = mlab.csv2rec(donohue_file)
if args.method == 'joint':
offset = 2200
else:
offset = 300
progrs = r[r.dtype.names[0]] * 30.44 + offset
vals = r[r.dtype.names[1]]
curve_donohue = []
progr_donohue = []
for p in progress_linspace_int:
if progrs[0] < p < progrs[-1]:
i = 1
while p > progrs[i]:
i += 1
# TODO linear interpolation
progr_donohue.append(progrs[i])
curve_donohue.append(vals[i])
ax1.plot(progr_donohue,
curve_donohue,
'--',
color='b',
linewidth=2)
#
# Plot synthetic model curve
#
if plot_synth_model:
progress_linspace_synth = np.linspace(-2500, 2500, 100)
quantiles = [0.1, 0.25, 0.5, 0.75, 0.9]
alphas = [0.4, 0.7, 1.0, 0.7, 0.4]
for quantile, alpha in zip(quantiles, alphas):
curve_synth = [
SynthModel.get_distributed_value(biomarker, p, cdf=quantile)
for p in progress_linspace_synth
]
ax1.plot(progress_linspace_synth,
curve_synth,
color='b',
alpha=alpha)
#
# Plot predictor function
#
if args.plot_eta is not None and not args.only_densities:
# Get second axis of plot 1
ax1b = ax1.twinx()
# Plot all progresses
# ax1b.scatter(pm.all_progresses, pm.all_mus, facecolor='b', marker='o', edgecolor='none', alpha=0.2)
ax1b.text(pm.progresses[-1],
pm.sigmas[-1],
'$\mu$',
color='b',
fontsize=11)
# Plot binned progresses
ax1b.scatter(pm.progresses, pm.sigmas, color='b', marker='x')
# Plot interpolated model
mus = [pm.get_eta(pm.sigmas, p) for p in progress_linspace_int]
ax1b.plot(progress_linspace_int, mus, color='b')
if not args.no_extrapolation:
mus = [pm.get_eta(pm.sigmas, p) for p in progress_linspace_ex1]
ax1b.plot(progress_linspace_ex1, mus, '--', color='b')
mus = [pm.get_eta(pm.sigmas, p) for p in progress_linspace_ex2]
ax1b.plot(progress_linspace_ex2, mus, '--', color='b')
if args.xlim is not None:
ax1b.set_xlim(args.xlim[0], args.xlim[1])
else:
ax1b.set_xlim(min_progress_extrapolate, max_progress_extrapolate)
#
# Plot errors
#
if args.plot_errors and not args.only_densities:
eval_file = model_file.replace('.csv', '_eval_cover.csv')
if not os.path.isfile(eval_file):
print log.ERROR, 'Evaluation file not found: {0}'.format(eval_file)
else:
m = mlab.csv2rec(eval_file)
progresses = m['progress']
errors = m['error']
# Get second axis of plot 1
ax1b = ax1.twinx()
# ax1b.set_ylim(0, max(150, 1.2 * np.max(errors)))
ax1b.plot(progresses, errors, color='g', marker='x')
ax1b.text(progresses[-1],
errors[-1],
'Discr.',
color='g',
fontsize=11)
ax1b.axhline(np.mean(errors), color='g', linestyle='--', alpha=0.5)
median_curve = pm.get_quantile_curve(progresses, 0.5)
min_value = np.min(median_curve)
max_value = np.max(median_curve)
rect = mpl.patches.Rectangle((progresses[0], min_value),
progresses[-1] - progresses[0],
max_value - min_value,
fc=(0.0, 0.5, 0.0, 0.1),
ec=(0.0, 0.5, 0.0, 0.8),
linewidth=1)
ax1.add_patch(rect)
#
# Plot points
#
if not args.no_points and not args.only_densities:
samples_file = data_handler.get_samples_file(biomarker)
if not os.path.isfile(samples_file):
print log.ERROR, 'Samples file not found: {0}'.format(samples_file)
else:
m = mlab.csv2rec(samples_file)
progr_points = m['progress']
value_points = m['value']
# diagn_points = [0.5 if p < 0 else 1.0 for p in progr_points]
diagn_points = m['diagnosis']
diagn_points[(0.25 <= diagn_points) & (diagn_points <= 0.75)] = 0.5
print log.INFO, 'Plotting {0} sample points...'.format(
len(progr_points))
ax1.scatter(progr_points,
value_points,
s=15.0,
c=diagn_points,
edgecolor='none',
vmin=0.0,
vmax=1.0,
cmap=pt.progression_cmap,
alpha=args.points_alpha)
if args.phase == 'cnmci':
rects = [
mpl.patches.Rectangle(
(0, 0),
1,
1,
fc=pt.color_cn + (args.points_alpha, ),
linewidth=0),
mpl.patches.Rectangle(
(0, 0),
1,
1,
fc=pt.color_mci + (args.points_alpha, ),
linewidth=0)
]
labels = ['CN', 'MCI']
elif args.phase == 'mciad':
rects = [
mpl.patches.Rectangle(
(0, 0),
1,
1,
fc=pt.color_mci + (args.points_alpha, ),
linewidth=0),
mpl.patches.Rectangle(
(0, 0),
1,
1,
fc=pt.color_ad + (args.points_alpha, ),
linewidth=0)
]
labels = ['MCI', 'AD']
else:
rects = [
mpl.patches.Rectangle(
(0, 0),
1,
1,
fc=pt.color_cn + (args.points_alpha, ),
linewidth=0),
mpl.patches.Rectangle(
(0, 0),
1,
1,
fc=pt.color_mci + (args.points_alpha, ),
linewidth=0),
mpl.patches.Rectangle(
(0, 0),
1,
1,
fc=pt.color_ad + (args.points_alpha, ),
linewidth=0)
]
labels = ['CN', 'MCI', 'AD']
legend = ax1.legend(rects,
labels,
fontsize=10,
ncol=len(rects),
loc='upper center',
framealpha=0.9)
legend.get_frame().set_edgecolor((0.6, 0.6, 0.6))
#
# Plot PDFs
#
progr_samples = [-2000, -1000, 0, 1000, 2000, 3000, 4000] if args.phase == 'joint' else \
[-2000, -1500, -1000, -500, 0, 500, 1000, 1500, 2000]
if args.phase == 'cnmci':
vmin = -2000
vmax = 6000
elif args.phase == 'mciad':
vmin = -6000
vmax = 2000
elif args.phase == 'joint':
vmin = -2000
vmax = 4000
sample_cmap = cmx.ScalarMappable(norm=colors.Normalize(vmin=vmin,
vmax=vmax),
cmap=plt.get_cmap(pt.progression_cmap))
if not args.no_sample_lines and not args.only_densities:
for progr in progr_samples:
if not args.no_extrapolation or pm.min_progress < progr < pm.max_progress:
# sample_color = sample_cmap.to_rgba(progr_samples.index(progr))
sample_color = sample_cmap.to_rgba(progr)
linestyle = '--' if progr < pm.min_progress or progr > pm.max_progress else '-'
ax1.axvline(progr,
color=sample_color,
linestyle=linestyle,
alpha=0.3)
if not args.no_densities:
ax2.set_title(
'Probability density function for {0}'.format(biomarker_string))
ax2.set_xlabel(DataHandler.get_biomarker_unit(biomarker))
ax2.set_ylabel('Probability')
if args.ylim is None:
values = np.linspace(min_val, max_val, 250)
ax2.set_xlim(min_val, max_val)
else:
values = np.linspace(args.ylim[0], args.ylim[1], 250)
ax2.set_xlim(args.ylim[0], args.ylim[1])
for progr in progr_samples:
if not args.no_extrapolation or pm.min_progress < progr < pm.max_progress:
# sample_color = sample_cmap.to_rgba(progr_samples.index(progr))
sample_color = sample_cmap.to_rgba(progr)
linestyle = '--' if progr < pm.min_progress or progr > pm.max_progress else '-'
probs = pm.get_density_distribution(values, progr)
ax2.plot(values,
probs,
label=str(progr),
color=sample_color,
linestyle=linestyle)
if plot_synth_model:
probs = [
SynthModel.get_probability(biomarker, progr, v)
for v in values
]
ax2.plot(values, probs, color='b', linestyle='--')
legend = ax2.legend(fontsize=10, loc='best', framealpha=0.9)
legend.get_frame().set_edgecolor((0.6, 0.6, 0.6))
#
# Draw or save the plot
#
plt.tight_layout()
if args.save_plots or args.plot_file is not None:
if args.plot_file is not None:
plot_filename = args.plot_file
else:
plot_filename = model_file.replace('.csv', '.pdf')
plt.savefig(plot_filename, transparent=True)
else:
plt.show()
plt.close(fig)
def plot_boxplots_noisy_data(args, biomarkers, errors, sigmas, noise_on_rate=True):
print log.INFO, 'Plotting error bars...'
fig, ax = plt.subplots(figsize=(8, 5))
pt.setup_axes(plt, ax, xgrid=False)
biomarker_strings = {'synth_hipp': '$\mathcal{M}^{HV}$',
'synth_mmse': '$\mathcal{M}^{MMSE}$',
'synth_cdrsb': '$\mathcal{M}^{CDR-SB}$'}
ylabels = {'area': 'Mean area between PDFs',
'peakdist': 'Distance between peaks',
'maxdist': 'Distance between progress maxima'}
if noise_on_rate:
ax.set_title('Influence of variations in progression rate')
else:
ax.set_title('Influence of variations in point of conversion')
ax.set_ylabel(ylabels[args.metric])
plt.tick_params(labelbottom='off')
# Collect data
data = []
medians = []
for biomarker in biomarkers:
for sigma in sigmas:
data.append(errors[biomarker][sigma])
medians.append(np.mean(errors[biomarker][sigma]))
# Set limits
max_data = np.max(data)
ax.set_ylim(0, 1.15 * max_data)
# Draw boxplot
boxplot = plt.boxplot(data, patch_artist=True)
# Set boxplot colours
colours = [(0.0, 0.0, 0.0), (0.0, 0.0, 0.5), (0.0, 0.5, 0.0)] * len(biomarkers)
for i in range(len(data)):
pt.set_boxplot_color(boxplot, i, colours[i])
# Write median errors as text
upper_labels = [str(np.round(m, 3)) for m in medians]
for i in np.arange(len(upper_labels)):
ax.text(i + 1, 1.02 * max_data, upper_labels[i],
horizontalalignment='center', size=10, color=colours[i])
# Write category labels
for i, biomarker in enumerate(biomarkers):
plt.text((i + 0.5) * len(sigmas) + 0.5, -0.07 * max_data,
biomarker_strings[biomarker],
horizontalalignment='center', size=15)
# Draw horizontal lines
for x in range(3, len(data), 3):
plt.axvline(x + 0.5, color='k', alpha=0.4)
# Plot legend
legend = ax.legend([mpl.patches.Rectangle((0, 0), 1, 1, fc=(0.0, 0.0, 0.0, 0.2), ec=(0.0, 0.0, 0.0, 1.0), linewidth=1),
mpl.patches.Rectangle((0, 0), 1, 1, fc=(0.0, 0.0, 0.5, 0.2), ec=(0.0, 0.0, 0.5, 1.0), linewidth=1),
mpl.patches.Rectangle((0, 0), 1, 1, fc=(0.0, 0.5, 0.0, 0.2), ec=(0.0, 0.5, 0.0, 1.0), linewidth=1)],
['$\sigma={0}$'.format(s) for s in sigmas], fontsize=10, ncol=3, loc='upper center', framealpha=0.9)
legend.get_frame().set_edgecolor((0.6, 0.6, 0.6))
# Show or save plot
plt.tight_layout()
if args.plot_file is not None:
plt.savefig(args.plot_file, transparent=True)
else:
plt.show()
plt.close(fig)
def plot_errors_data(args, errors, biomarker_sets, viscode_sets):
print log.INFO, 'Plotting results...'
num_viscode_sets = len(viscode_sets)
num_tests = len(biomarker_sets)
# Define figure and grid
fig, ax = plt.subplots(figsize=(8, 5))
pt.setup_axes(plt, ax, xgrid=False)
ax.set_title('DP estimation using different biomarker settings')
ax.set_ylabel('Mean progress estimation error')
plt.tick_params(labelbottom='off')
biomarker_strings = {'synth_hipp': '$\mathcal{M}^{HV}$',
'synth_mmse': '$\mathcal{M}^{MMSE}$',
'synth_cdrsb': '$\mathcal{M}^{CDR-SB}$'}
# Collect data
data = []
medians = []
for viscodes in viscode_sets:
viscodes_string = '_'.join([str(v) for v in viscodes])
for biomarkers in biomarker_sets:
biomarkers_string = '_'.join(biomarkers)
data.append(errors[biomarkers_string][viscodes_string])
medians.append(np.median(errors[biomarkers_string][viscodes_string]))
# Set limits
max_data = np.max(data)
ax.set_ylim(0, 1.15 * max_data)
# Draw boxplot
boxplot = plt.boxplot(data, patch_artist=True)
# Set boxplot colours
colours = [(0.0, 0.0, 0.0), (0.0, 0.0, 0.5), (0.0, 0.5, 0.0), (0.5, 0.0, 0.5)] * num_viscode_sets
for i in range(len(data)):
pt.set_boxplot_color(boxplot, i, colours[i])
# Write median errors as text
upper_labels = [str(np.round(s, 2)) for s in medians]
for i in range(len(data)):
ax.text(i + 1, 1.01 * max_data, upper_labels[i],
horizontalalignment='center', size=10, color=colours[i])
# Write category labels
for i in xrange(len(viscode_sets)):
ax.text(i * num_tests + 0.5 * (num_tests + 1), -70,
'{0} timepoint{1}'.format(len(viscode_sets[i]), '' if len(viscode_sets[i]) == 1 else 's'),
horizontalalignment='center')
# Plot legend
legend = ax.legend([mpl.patches.Rectangle((0, 0), 1, 1, fc=(0.0, 0.0, 0.0, 0.2), ec=(0.0, 0.0, 0.0, 1.0), linewidth=1),
mpl.patches.Rectangle((0, 0), 1, 1, fc=(0.0, 0.0, 0.5, 0.2), ec=(0.0, 0.0, 0.5, 1.0), linewidth=1),
mpl.patches.Rectangle((0, 0), 1, 1, fc=(0.0, 0.5, 0.0, 0.2), ec=(0.0, 0.5, 0.0, 1.0), linewidth=1),
mpl.patches.Rectangle((0, 0), 1, 1, fc=(0.5, 0.0, 0.5, 0.2), ec=(0.5, 0.0, 0.5, 1.0), linewidth=1)],
[biomarker_strings[b] for b in biomarker_sets[-1]] + ['All'], fontsize=10, ncol=4, loc='upper center', framealpha=0.9)
legend.get_frame().set_edgecolor((0.6, 0.6, 0.6))
# Draw horizontal lines
for i in xrange(1, len(viscode_sets)):
ax.axvline(i * num_tests + 0.5, linestyle='-', color='k', alpha=0.4)
# Show or save plot
plt.tight_layout()
if args.plot_file is not None:
plt.savefig(args.plot_file, transparent=True)
else:
plt.show()
plt.close(fig)
def plot_predictions(biomarker, model, visits, rid_measurements, dpi, dpr,
value_model, value_naive, mean_quantile, change, intercept, rid):
next_visit = get_predicted_visit(visits)
scantime_first_visit = rid_measurements[visits[0]]['scantime']
scantime_next_visit = rid_measurements[next_visit]['scantime']
progress_first_visit = ModelFitter.scantime_to_progress(scantime_first_visit, scantime_first_visit, dpi, dpr)
progress_next_visit = ModelFitter.scantime_to_progress(scantime_next_visit, scantime_first_visit, dpi, dpr)
total_scantime = scantime_next_visit - scantime_first_visit
progress_linspace = np.linspace(progress_first_visit - total_scantime * 0.05,
progress_next_visit + total_scantime * 0.05, 100)
fig, ax = plt.subplots()
pt.setup_axes(plt, ax, xgrid=False, ygrid=False)
ax.set_title('{0} predictions for RID {1} (DPI={2}, DPR={3})'.format(pt.get_biomarker_string(biomarker), rid, dpi, dpr))
ax.set_xlabel('Disease progress (days before/after conversion to AD)')
ax.set_ylabel(DataHandler.get_biomarker_unit(biomarker))
ax.set_xlim(progress_first_visit - total_scantime * 0.1, progress_next_visit + total_scantime * 0.1)
color_mapper = cm.ScalarMappable(cmap=plt.get_cmap(pt.progression_cmap),
norm=colors.Normalize(vmin=0.0, vmax=1.0))
# Plot the percentile curves of the fitted model
quantiles = [0.1, 0.25, 0.5, 0.75, 0.9]
grey_values = ['0.8', '0.6', '0.4', '0.62', '0.84']
for grey_value, quantile in zip(grey_values, quantiles):
curve = model.get_quantile_curve(progress_linspace, quantile)
ax.plot(progress_linspace, curve, zorder=1, color=grey_value)
# Collect points
progr_points = []
value_points = []
diagn_points = []
for visit in visits + [next_visit]:
value_points.append(rid_measurements[visit][biomarker])
progr_points.append(ModelFitter.scantime_to_progress(rid_measurements[visit]['scantime'],
scantime_first_visit, dpi, dpr))
diagn_points.append(rid_measurements[visit]['DX.scan'])
# Collect lines
predict_diagnosis = rid_measurements[next_visit]['DX.scan']
predict_linspace = np.linspace(progress_first_visit, progress_next_visit, 50)
curve = [model.get_value_at_quantile(p, mean_quantile) for p in predict_linspace]
line = [change * ModelFitter.progress_to_scantime(p, scantime_first_visit, dpi, dpr) + intercept for p in predict_linspace]
# Plot model and linear prediction line
ax.plot(predict_linspace, line, zorder=1, linestyle='--', linewidth=2, color='k',
label='naive prediction')
ax.plot(predict_linspace, curve, zorder=1, linestyle='-', linewidth=2, color='k',
label='model-based prediction')
ax.scatter(progr_points, value_points, zorder=2, s=50.0,
c=[color_mapper.to_rgba(d) for d in diagn_points], edgecolor='none')
# Plot the predicted values
ax.scatter([progress_next_visit], [value_naive], zorder=2, s=50.0, c='w',
edgecolor=color_mapper.to_rgba(predict_diagnosis))
ax.scatter([progress_next_visit], [value_model], zorder=2, s=50.0, c='w',
edgecolor=color_mapper.to_rgba(predict_diagnosis))
plt.tight_layout()
plt.legend()
plot_filename = os.path.join('/Users/aschmiri/Desktop/temp',
'plot_predictions_{0}_{1}.pdf'.format(rid, biomarker))
plt.savefig(plot_filename, transparent=True)
# plt.show()
plt.close(fig)
def plot_errors(args, values, methods):
fig, ax = plt.subplots()
pt.setup_axes(plt, ax, xgrid=False)
num_methods = len(methods)
for i in xrange(num_methods):
ax.axvline(i * 2 + 1.5, linestyle='-', color='k', alpha=0.4)
ax.set_axisbelow(True)
ax.set_title('Prediction of {0}'.format(args.predict_biomarker))
ax.set_ylabel('Prediction error')
ax.set_xticklabels([])
# Append plot for naive estimation
values_observed = np.array(values[values.keys()[0]]['observed'])
values_naive = np.array(values[values.keys()[0]]['naive'])
errors_naive = np.abs(values_observed - values_naive)
data = [errors_naive]
medians = [np.median(errors_naive)]
weights = ['normal']
for method in methods:
values_model1 = np.array(values[method]['model_dpi'])
values_model2 = np.array(values[method]['model_dpi_dpr'])
errors_model1 = np.abs(values_observed - values_model1)
errors_model2 = np.abs(values_observed - values_model2)
data.append(errors_model1)
data.append(errors_model2)
medians.append(np.median(errors_model1))
medians.append(np.median(errors_model2))
weights.append('bold' if stats.ttest_rel(errors_naive, errors_model1)[1] < 0.01 else 'normal')
weights.append('bold' if stats.ttest_rel(errors_naive, errors_model2)[1] < 0.01 else 'normal')
# Set colors
colors = [(0.0, 0.0, 0.0)]
for i in range(num_methods):
colors.append((0.0, 0.0, 0.5))
colors.append((0.0, 0.5, 0.0))
# Set limits
max_data = np.max(data)
ax.set_ylim(-0.01 * max_data, 1.01 * max_data)
# Add labels to x axis
for i, method in enumerate(methods):
ax.text(i * 2 + 2.5, -0.04 * max_data, method, horizontalalignment='center')
# Write median errors as text
pos = np.arange(1, 2 * num_methods + 2)
upper_labels = [str(np.round(m, 2)) for m in medians]
for i in range(2 * num_methods + 1):
ax.text(pos[i], 0.91 * max_data, upper_labels[i], weight=weights[i],
horizontalalignment='center', size=10, color=colors[i])
# Plot boxplots
boxplot = plt.boxplot(data, patch_artist=True)
for i in range(len(boxplot['boxes'])):
pt.set_boxplot_color(boxplot, i, colors[i])
# Plot legend
legend = ax.legend([mpl.patches.Rectangle((0, 0), 1, 1, fc=(0.0, 0.0, 0.0, 0.2), ec=(0.0, 0.0, 0.0, 1.0), linewidth=1),
mpl.patches.Rectangle((0, 0), 1, 1, fc=(0.0, 0.0, 0.5, 0.2), ec=(0.0, 0.0, 0.5, 1.0), linewidth=1),
mpl.patches.Rectangle((0, 0), 1, 1, fc=(0.0, 0.5, 0.0, 0.2), ec=(0.0, 0.5, 0.0, 1.0), linewidth=1)],
['Naive', 'DPI', 'DPI + DPR'], fontsize=10, ncol=3, loc='upper center', framealpha=0.9)
legend.get_frame().set_edgecolor((0.6, 0.6, 0.6))
# Show or save plot
plt.tight_layout()
if args.plot_file is not None:
plt.savefig(args.plot_file, transparent=True)
else:
plt.show()
plt.close(fig)
def plot_boxplots_noisy_data(args,
biomarkers,
errors,
sigmas,
noise_on_rate=True):
print log.INFO, 'Plotting error bars...'
fig, ax = plt.subplots(figsize=(8, 5))
pt.setup_axes(plt, ax, xgrid=False)
biomarker_strings = {
'synth_hipp': '$\mathcal{M}^{HV}$',
'synth_mmse': '$\mathcal{M}^{MMSE}$',
'synth_cdrsb': '$\mathcal{M}^{CDR-SB}$'
}
ylabels = {
'area': 'Mean area between PDFs',
'peakdist': 'Distance between peaks',
'maxdist': 'Distance between progress maxima'
}
if noise_on_rate:
ax.set_title('Influence of variations in progression rate')
else:
ax.set_title('Influence of variations in point of conversion')
ax.set_ylabel(ylabels[args.metric])
plt.tick_params(labelbottom='off')
# Collect data
data = []
medians = []
for biomarker in biomarkers:
for sigma in sigmas:
data.append(errors[biomarker][sigma])
medians.append(np.mean(errors[biomarker][sigma]))
# Set limits
max_data = np.max(data)
ax.set_ylim(0, 1.15 * max_data)
# Draw boxplot
boxplot = plt.boxplot(data, patch_artist=True)
# Set boxplot colours
colours = [(0.0, 0.0, 0.0), (0.0, 0.0, 0.5),
(0.0, 0.5, 0.0)] * len(biomarkers)
for i in range(len(data)):
pt.set_boxplot_color(boxplot, i, colours[i])
# Write median errors as text
upper_labels = [str(np.round(m, 3)) for m in medians]
for i in np.arange(len(upper_labels)):
ax.text(i + 1,
1.02 * max_data,
upper_labels[i],
horizontalalignment='center',
size=10,
color=colours[i])
# Write category labels
for i, biomarker in enumerate(biomarkers):
plt.text((i + 0.5) * len(sigmas) + 0.5,
-0.07 * max_data,
biomarker_strings[biomarker],
horizontalalignment='center',
size=15)
# Draw horizontal lines
for x in range(3, len(data), 3):
plt.axvline(x + 0.5, color='k', alpha=0.4)
# Plot legend
legend = ax.legend([
mpl.patches.Rectangle((0, 0),
1,
1,
fc=(0.0, 0.0, 0.0, 0.2),
ec=(0.0, 0.0, 0.0, 1.0),
linewidth=1),
mpl.patches.Rectangle((0, 0),
1,
1,
fc=(0.0, 0.0, 0.5, 0.2),
ec=(0.0, 0.0, 0.5, 1.0),
linewidth=1),
mpl.patches.Rectangle((0, 0),
1,
1,
fc=(0.0, 0.5, 0.0, 0.2),
ec=(0.0, 0.5, 0.0, 1.0),
linewidth=1)
], ['$\sigma={0}$'.format(s) for s in sigmas],
fontsize=10,
ncol=3,
loc='upper center',
framealpha=0.9)
legend.get_frame().set_edgecolor((0.6, 0.6, 0.6))
# Show or save plot
plt.tight_layout()
if args.plot_file is not None:
plt.savefig(args.plot_file, transparent=True)
else:
plt.show()
plt.close(fig)
