print('Pearson Correlation between feature corr and blosum',
pearsonr(corr_scores, blos_scores)[0])
if __name__ == "__main__":
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('exp_name', help='Name of experiment')
args = parser.parse_args()
min_total = 100
filetype = 'pdf'
cache_path = get_cache_path() / f'{args.exp_name}.pickle'
args, feature_to_weighted_sums, weight_totals = pickle.load(
open(cache_path, "rb"))
print(args)
print(weight_totals)
report_dir = get_reports_path(
) / 'attention_analysis/blosum' / args.exp_name
report_dir.mkdir(parents=True, exist_ok=True)
create_figures(feature_to_weighted_sums, weight_totals, min_total,
report_dir, filetype)
with open(report_dir / 'args.json', 'w') as f:
json.dump(vars(args), f)
print('Saving', fname)
plt.savefig(fname, format=filetype)
plt.close()
if __name__ == "__main__":
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('exp_name', help='Name of experiment')
parser.add_argument('--min_total', type=int, default=100)
args = parser.parse_args()
use_bonferroni = True
if use_bonferroni:
print('Using bonferroni')
min_total = args.min_total
filetype = 'pdf'
print(args.exp_name)
cache_path = get_cache_path() / f'{args.exp_name}.pickle'
report_dir = get_reports_path() / 'attention_analysis' / f'{args.exp_name}_topheads'
pathlib.Path(report_dir).mkdir(parents=True, exist_ok=True)
cache_args, feature_to_weighted_sum, weight_total = pickle.load(open(cache_path, "rb"))
with open(report_dir / 'args.json', 'w') as f:
json.dump(vars(cache_args), f)
for feature_name, weighted_sum in feature_to_weighted_sum.items():
create_figure(feature_name, weighted_sum, weight_total, report_dir, min_total=min_total, filetype=filetype,
use_bonferroni=use_bonferroni, max_seq_len=cache_args.max_seq_len)
'1': 'Strand',
'2': 'Turn/Bend'
}
if __name__ == "__main__":
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('exp_names', nargs='+', help='Names of experiments')
args = parser.parse_args()
min_total = 100
filetype = 'pdf'
report_dir = get_reports_path() / 'attention_analysis/edge_features_combined'
pathlib.Path(report_dir).mkdir(parents=True, exist_ok=True)
feature_data = []
include_features = [contact_map_pattern, secondary_to_pattern, binding_site_pattern]
for exp in args.exp_names:
cache_path = get_cache_path() / f'{exp}.pickle'
args, feature_to_weighted_sum, weight_total = pickle.load(open(cache_path, "rb"))
with open(report_dir / f'args_{exp}.json', 'w') as f:
json.dump(vars(args), f)
for feature, weighted_sum in feature_to_weighted_sum.items():
for p in include_features:
m = p.match(feature)
desc = None
if m:
if p == contact_map_pattern:
'precision:', results['precision'], 'recall:',
results['recall'], 'precision at k:',
results['precision_at_k'])
scores[num_layers - 1] = results['precision_at_k']
except FileNotFoundError:
print('Skipping', fname)
continue
feature_scores.append(scores)
# Probing contact map results
features.append('Contact Map')
scores = [0] * 12
for num_layers in list(range(1, 13)):
fname = data_path / 'probing' / f'contact_map_{num_layers}/results.json'
try:
with open(fname) as infile:
results = json.load(infile)
print('contact maps', num_layers, 'f1:', results['f1'],
'precision:', results['precision'], 'recall:',
results['recall'], 'precision at k:',
results['precision_at_k'])
scores[num_layers - 1] = results['precision_at_k']
except FileNotFoundError:
print('Skipping', fname)
continue
feature_scores.append(scores)
report_dir = get_reports_path() / 'probing'
pathlib.Path(report_dir).mkdir(parents=True, exist_ok=True)
report(features, feature_scores, report_dir)