def plot_rocs(title, rocs, num_pssms):
"""
Plot roc graphs.
"""
import pylab as P
for bg_type, rocs_for_bg in rocs.iteritems():
for dataset, rocs_for_dataset in rocs_for_bg.iteritems():
tag = '%s-%s-%s' % (title, bg_type, dataset)
fig = P.figure()
for p in num_pssms:
plot_roc_points(rocs_for_dataset[p][::-1], label='%d PSSMs' % (p+1))
P.legend(loc='lower right')
P.title(tag)
plot_random_classifier()
label_plot()
P.savefig(os.path.join(options.output_dir, 'roc-%s.png' % tag))
P.close(fig)
def plot_rocs(title, rocs, num_pssms):
"""
Plot roc graphs.
"""
import pylab as P
for bg_type, rocs_for_bg in rocs.iteritems():
for dataset, rocs_for_dataset in rocs_for_bg.iteritems():
tag = '%s-%s-%s' % (title, bg_type, dataset)
fig = P.figure()
for p in num_pssms:
plot_roc_points(rocs_for_dataset[p][::-1],
label='%d PSSMs' % (p + 1))
P.legend(loc='lower right')
P.title(tag)
plot_random_classifier()
label_plot()
P.savefig(os.path.join(options.output_dir, 'roc-%s.png' % tag))
P.close(fig)
for method in methods
)
aucs[bg]['AUC50'] = dict(
(method, auc50s[method][0])
for method in methods
)
# ROC curves
P.figure()
for method in methods:
rocs = [roc for roc, t in roc_thresholds[method]]
auc = aucs[bg]['AUC'][method]
auc50 = aucs[bg]['AUC50'][method]
R.plot_roc_points(rocs, label=method, marker=markers[method], color=colors[method])
R.plot_random_classifier(label='Random')
R.label_plot()
P.legend(loc='lower right')
P.title('%s - %s' % (fragment_name(fragment), bg))
P.savefig(os.path.join(options.results_dir, 'ROC-%s-%s.png' % (fragment, bg)))
P.savefig(os.path.join(options.results_dir, 'ROC-%s-%s.eps' % (fragment, bg)))
P.close()
# precision-recall curves
P.figure()
for method in methods:
rocs = [roc for roc, t in roc_thresholds[method]]
R.plot_precision_versus_recall(rocs, label=method, marker=markers[method], color=colors[method])
R.label_precision_versus_recall()
P.legend(loc='lower left')
logging.basicConfig(level=logging.INFO)
R.seed(1)
param_settings = (
(True, False, True, 'Cumulative Bayesian', 'blue', '-.'),
(False, False, True, 'Non-cumulative Bayesian', 'blue', '-'),
(False, False, False, 'BiFa', 'cyan', '-'),
(True, True, True, 'Cumulative p-values', 'red', '-.'),
(False, True, True, 'Non-cumulative p-values', 'red', '-'),
)
try:
test_cases
except NameError:
test_cases = list(dataset.generate_test_cases(ignore_chip_data=False))
logging.info('Have %d test cases', len(test_cases))
#P.close('all')
P.figure(figsize=(16, 12))
for param_setting in param_settings:
plot_param_setting_rocs(test_cases, *param_setting)
roc.plot_random_classifier()
P.xlim(0, 0.2)
P.ylim(0, 0.4)
P.xlim(0, 1)
P.ylim(0, 1)
P.legend(loc='lower right')
P.show()
pickle_file)
freqs, gaps = pwm
roc = run_pwm_forward_backward(tag, freqs, gaps, positive_seqs,
negative_seqs)
cPickle.dump(roc, open(pickle_file, 'wb'))
return roc
def do_pwm(tag, pwm, color, marker):
roc_points = calc_or_unpickle_roc(tag, pwm, positive_seqs,
negative_seqs)
roc.plot_roc_points(roc_points,
label=tag,
color=color,
marker=marker)
P.figure()
do_pwm('GLAM2-Sp1-i4', glam2_sp1_i4(), 'magenta', 's')
do_pwm('GLAM2-Sp1-i7', glam2_sp1_i7(), 'cyan', '^')
do_pwm('Gapped-Sp1', gapped_sp1(), 'blue', 'o')
do_pwm('TRANSFAC-Sp1', transfac_sp1(), 'red', 'v')
do_pwm('MEME-Sp1', meme_sp1(), 'green', 'd')
roc.plot_random_classifier(label='Random')
roc.label_plot()
P.legend(loc='lower right')
P.savefig('ROC.eps')
P.savefig('ROC.png')
P.xlim(0., .2)
P.ylim(0., .5)
P.savefig('ROC-zoom.eps')
P.savefig('ROC-zoom.png')
methods = []
datasets_to_ignore = set(('T99004',))
show_title = False
sys.argv.pop(0) # remove script name
while sys.argv:
method = sys.argv.pop(0)
methods.append(method)
file_glob = sys.argv.pop(0)
logging.info('Method: %s; glob: %s', method, file_glob)
load_stat_files(glob(file_glob), overall_stats[method])
styles = [ '-', '--' ]
for bg in bg_types:
for dataset in datasets:
P.figure()
for style, method in zip(styles, methods):
stats = overall_stats[method]
rocs = list(stats[bg][0][dataset].iteritems())
rocs.sort()
rocs = [r[1] for r in rocs]
plot_roc_points(rocs, linestyle=style, color='k', label=method)
label_plot()
P.legend(loc='lower right')
if show_title:
P.title('%s - %s' % (dataset, bg))
plot_random_classifier(label='random')
P.savefig('ROC-%s-%s.png' % (bg, dataset))
P.savefig('ROC-%s-%s.eps' % (bg, dataset))
P.clf()
R.seed(1)
param_settings = (
(True, False, True, 'Cumulative Bayesian', 'blue', '-.'),
(False, False, True, 'Non-cumulative Bayesian', 'blue', '-'),
(False, False, False, 'BiFa', 'cyan', '-'),
(True, True, True, 'Cumulative p-values', 'red', '-.'),
(False, True, True, 'Non-cumulative p-values', 'red', '-'),
)
try: test_cases
except NameError:
test_cases = list(dataset.generate_test_cases(ignore_chip_data=False))
logging.info('Have %d test cases', len(test_cases))
#P.close('all')
P.figure(figsize=(16,12))
for param_setting in param_settings:
plot_param_setting_rocs(test_cases, *param_setting)
roc.plot_random_classifier()
P.xlim(0, 0.2)
P.ylim(0, 0.4)
P.xlim(0, 1)
P.ylim(0, 1)
P.legend(loc='lower right')
P.show()
methods = []
datasets_to_ignore = set(('T99004', ))
show_title = False
sys.argv.pop(0) # remove script name
while sys.argv:
method = sys.argv.pop(0)
methods.append(method)
file_glob = sys.argv.pop(0)
logging.info('Method: %s; glob: %s', method, file_glob)
load_stat_files(glob(file_glob), overall_stats[method])
styles = ['-', '--']
for bg in bg_types:
for dataset in datasets:
P.figure()
for style, method in zip(styles, methods):
stats = overall_stats[method]
rocs = list(stats[bg][0][dataset].iteritems())
rocs.sort()
rocs = [r[1] for r in rocs]
plot_roc_points(rocs, linestyle=style, color='k', label=method)
label_plot()
P.legend(loc='lower right')
if show_title:
P.title('%s - %s' % (dataset, bg))
plot_random_classifier(label='random')
P.savefig('ROC-%s-%s.png' % (bg, dataset))
P.savefig('ROC-%s-%s.eps' % (bg, dataset))
P.clf()
return method
for bg in backgrounds:
# ROC curves
P.figure()
for method in methods:
rocs = R.picked_rocs_from_thresholds(scores[(method, )],
scores[(method, bg)],
num_points=options.num_points)
auc = R.area_under_curve(rocs)
R.plot_roc_points(rocs,
label='%.2f %s' % (auc, name(method)),
marker=markers[method])
R.plot_random_classifier(label='0.50 Random')
R.label_plot()
P.legend(loc='lower right')
P.title('Full Sp1 - %s' % bg)
P.savefig('ROC-Sp1-%s.png' % bg)
P.savefig('ROC-Sp1-%s.eps' % bg)
# precision-recall curves
P.figure()
for method in methods:
rocs = R.picked_rocs_from_thresholds(scores[(method, )],
scores[(method, bg)],
num_points=options.num_points)
R.plot_precision_versus_recall(rocs,
label=name(method),
marker=markers[method])
