Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Remove unused code and fix invalid total terms percentage #324

Merged
merged 1 commit into from
May 24, 2024
Merged

Remove unused code and fix invalid total terms percentage #324

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
30 changes: 4 additions & 26 deletions src/ccf_tools.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,7 +56,6 @@ def no_parent(log_dict, cell_type, row_number):
ct_invalid_terms = set()
ct_temp_terms = set()
ct_out_ct = set()
unique_terms = set()
as_valid_terms = set()
ct_valid_terms = set()
rt = []
Expand All @@ -73,10 +72,6 @@ def no_parent(log_dict, cell_type, row_number):
for current, next in zip(anatomical_structures, anatomical_structures[1:]):
log_dict, terms_set = is_valid_id(log_dict, current, row["rowNumber"], terms_set)
log_dict, terms_set = is_valid_id(log_dict, next, row["rowNumber"], terms_set)
if current['id'] != '':
unique_terms.add(current['id'])
if next['id'] != '':
unique_terms.add(next['id'])
if check_id(current['id']) and check_id(next['id']):
d = {}
d['s'] = next['id']
Expand All @@ -96,29 +91,25 @@ def no_parent(log_dict, cell_type, row_number):
else:
as_temp_terms.add(current['rdfs_label'])
as_invalid_terms.add(current['rdfs_label'])
unique_terms.add(current['rdfs_label'])
elif not check_id(current['id']) and current['name'] != '':
if current['id'] != '':
as_out_ub.add(current['id'])
else:
as_temp_terms.add(current['name'])
as_invalid_terms.add(current['name'])
unique_terms.add(current['name'])

if not check_id(next['id']) and next['rdfs_label'] != '':
if next['id'] != '':
as_out_ub.add(next['id'])
else:
as_temp_terms.add(next['rdfs_label'])
as_invalid_terms.add(next['rdfs_label'])
unique_terms.add(next['rdfs_label'])
elif not check_id(next['id']) and next['name'] != '':
if next['id'] != '':
as_out_ub.add(next['id'])
else:
as_temp_terms.add(next['name'])
as_invalid_terms.add(next['name'])
unique_terms.add(next['name'])

# CT-CT RELATIONSHIP
cell_types = row['cell_types']
Expand All @@ -127,10 +118,6 @@ def no_parent(log_dict, cell_type, row_number):
for current, next in zip(cell_types, cell_types[1:]):
log_dict, terms_set = is_valid_id(log_dict, current, row["rowNumber"], terms_set)
log_dict, terms_set = is_valid_id(log_dict, next, row["rowNumber"], terms_set)
if current['id'] != '':
unique_terms.add(current['id'])
if next['id'] != '':
unique_terms.add(next['id'])
if check_id(current['id']) and check_id(next['id']):
d = {}
d['row_number'] = row['rowNumber']
Expand All @@ -150,29 +137,25 @@ def no_parent(log_dict, cell_type, row_number):
else:
ct_temp_terms.add(current['rdfs_label'])
ct_invalid_terms.add(current['rdfs_label'])
unique_terms.add(current['rdfs_label'])
elif not check_id(current['id']) and current['name'] != '':
if current['id'] != '':
ct_out_ct.add(current['id'])
else:
ct_temp_terms.add(current['name'])
ct_invalid_terms.add(current['name'])
unique_terms.add(current['name'])

if not check_id(next['id']) and next['rdfs_label'] != '':
if next['id'] != '':
ct_out_ct.add(next['id'])
else:
ct_temp_terms.add(next['rdfs_label'])
ct_invalid_terms.add(next['rdfs_label'])
unique_terms.add(next['rdfs_label'])
elif not check_id(next['id']) and next['name'] != '':
if next['id'] != '':
ct_out_ct.add(next['id'])
else:
ct_temp_terms.add(next['name'])
ct_invalid_terms.add(next['name'])
unique_terms.add(next['name'])

if not check_id(current['id']) and (check_id(next['id']) or not check_id(next['id'])):
log_dict = no_parent(log_dict, next, row['rowNumber'])
Expand All @@ -199,8 +182,6 @@ def no_parent(log_dict, cell_type, row_number):
dl.append(d)
as_valid_terms.add(last_as['id'])
ct_valid_terms.add(last_ct['id'])
unique_terms.add(last_as['id'])
unique_terms.add(last_ct['id'])
else:
if check_id(last_as['id']):
as_valid_terms.add(last_as['id'])
Expand All @@ -212,29 +193,25 @@ def no_parent(log_dict, cell_type, row_number):
else:
as_temp_terms.add(last_as['rdfs_label'])
as_invalid_terms.add(last_as['rdfs_label'])
unique_terms.add(last_as['rdfs_label'])
elif not check_id(last_as['id']) and last_as['name'] != '':
if last_as['id'] != '':
as_out_ub.add(last_as['id'])
else:
as_temp_terms.add(last_as['name'])
as_invalid_terms.add(last_as['name'])
unique_terms.add(last_as['name'])

if not check_id(last_ct['id']) and last_ct['rdfs_label'] != '':
if last_ct['id'] != '':
ct_out_ct.add(last_ct['id'])
else:
ct_temp_terms.add(last_ct['rdfs_label'])
ct_invalid_terms.add(last_ct['rdfs_label'])
unique_terms.add(last_ct['rdfs_label'])
elif not check_id(last_ct['id']) and last_ct['name'] != '':
if last_ct['id'] != '':
ct_out_ct.add(last_ct['id'])
else:
ct_temp_terms.add(last_ct['name'])
ct_invalid_terms.add(last_ct['name'])
unique_terms.add(last_ct['name'])

# NEW CL TERMS REPORT
for cl in cell_types:
Expand Down Expand Up @@ -267,16 +244,17 @@ def no_parent(log_dict, cell_type, row_number):
rut.append(r)



total_terms = len(as_valid_terms) + len(as_invalid_terms) + len(ct_valid_terms) + len(ct_invalid_terms)
as_invalid_term_percent = 0
ct_invalid_terms_percent = 0
invalid_terms_percent = 0
if len(as_valid_terms) + len(ct_invalid_terms) > 0:
as_invalid_term_percent = round((len(as_invalid_terms)*100)/(len(as_valid_terms)+len(as_invalid_terms)), 2)
if len(ct_valid_terms) + len(ct_invalid_terms) > 0:
ct_invalid_terms_percent = round((len(ct_invalid_terms)*100)/(len(ct_valid_terms)+len(ct_invalid_terms)), 2)
if len(unique_terms) > 0:
invalid_terms_percent = round((len(as_invalid_terms)+len(ct_invalid_terms))*100/len(unique_terms), 2)
if total_terms > 0:
print(total_terms)
invalid_terms_percent = round(((len(as_invalid_terms)+len(ct_invalid_terms))/total_terms)*100, 2)

report_terms = {
'Table': '',
Expand Down
Loading