def test_export_individuals(self):
test_individuals = Individual.objects.filter(individual_id='NA19675')
# test tsv with all columns
response = export_individuals(
'test_individuals_table',
test_individuals,
'tsv',
include_project_column=True,
include_case_review_columns=True,
include_phenotips_columns=True,
)
self.assertEqual(response.status_code, 200)
rows = [row.split('\t') for row in response.content.rstrip('\n').split('\n')]
HEADER = [
'project', 'family_id', 'individual_id', 'paternal_id', 'maternal_id', 'sex', 'affected_status', 'notes',
'case_review_status', 'case_review_status_last_modified_date', 'case_review_status_last_modified_by', 'case_review_discussion',
'phenotips_features_present', 'phenotips_features_absent', 'paternal_ancestry', 'maternal_ancestry', 'age_of_onset'
]
self.assertListEqual(rows[0], HEADER)
self.assertEqual(len(rows), 2)
# test Excel format
response = export_individuals('test_families_table', test_individuals, 'xls', include_project_column=True, include_case_review_columns=True, include_phenotips_columns=True)
self.assertEqual(response.status_code, 200)
wb = load_workbook(StringIO(response.content))
worksheet = wb.active
# test unknown format
self.assertRaisesRegexp(ValueError, '.*format.*',
lambda: export_individuals('test_families_table', test_individuals, file_format='unknown_format'))
def test_export_individuals(self):
test_individuals = Individual.objects.filter(individual_id='NA19675_1')
# test tsv with all columns
response = export_individuals(
'test_individuals_table',
test_individuals,
'tsv',
include_project_name=True,
include_case_review_status=True,
include_case_review_last_modified_date=True,
include_case_review_last_modified_by=True,
include_case_review_discussion=True,
include_hpo_terms_present=True,
include_hpo_terms_absent=True,
include_paternal_ancestry=True,
include_maternal_ancestry=True,
include_age_of_onset=True,
)
self.assertEqual(response.status_code, 200)
rows = [
row.split('\t')
for row in response.content.rstrip('\n').split('\n')
]
self.assertEqual(rows[0][0], 'Project')
self.assertEqual(rows[0][1], 'Family ID')
self.assertEqual(len(rows), 2)
# test Excel format
response = export_individuals(
'test_families_table',
test_individuals,
'xls',
include_project_name=True,
include_case_review_status=True,
include_case_review_last_modified_date=True,
include_case_review_last_modified_by=True,
include_case_review_discussion=True,
include_hpo_terms_present=True,
include_hpo_terms_absent=True,
include_paternal_ancestry=True,
include_maternal_ancestry=True,
include_age_of_onset=True)
self.assertEqual(response.status_code, 200)
wb = load_workbook(StringIO(response.content))
worksheet = wb.active
# test unknown format
self.assertRaisesRegexp(
ValueError, '.*format.*',
lambda: export_individuals('test_families_table',
test_individuals,
file_format='unknown_format'))
def test_export_individuals(self):
test_individuals = Individual.objects.filter(individual_id='NA19675_1')
# test tsv with all columns
response = export_individuals(
'test_individuals_table',
test_individuals,
'tsv',
include_project_name=True,
include_case_review_status=True,
include_case_review_last_modified_date=True,
include_case_review_last_modified_by=True,
include_case_review_discussion=True,
include_hpo_terms_present=True,
include_hpo_terms_absent=True,
include_paternal_ancestry=True,
include_maternal_ancestry=True,
include_age_of_onset=True,
)
self.assertEqual(response.status_code, 200)
rows = [row.split('\t') for row in response.content.rstrip('\n').split('\n')]
self.assertEqual(rows[0][0], 'Project')
self.assertEqual(rows[0][1], 'Family ID')
self.assertEqual(len(rows), 2)
# test Excel format
response = export_individuals(
'test_families_table',
test_individuals,
'xls',
include_project_name=True,
include_case_review_status=True,
include_case_review_last_modified_date=True,
include_case_review_last_modified_by=True,
include_case_review_discussion=True,
include_hpo_terms_present=True,
include_hpo_terms_absent=True,
include_paternal_ancestry=True,
include_maternal_ancestry=True,
include_age_of_onset=True)
self.assertEqual(response.status_code, 200)
wb = load_workbook(StringIO(response.content))
worksheet = wb.active
# test unknown format
self.assertRaisesRegexp(ValueError, '.*format.*',
lambda: export_individuals('test_families_table', test_individuals, file_format='unknown_format'))
def export_project_individuals_handler(request, project_guid):
"""Export project Individuals table.
Args:
project_guid (string): GUID of the project for which to export individual data
"""
format = request.GET.get('file_format', 'tsv')
include_phenotypes = bool(request.GET.get('include_phenotypes'))
project = get_project_and_check_permissions(project_guid, request.user)
# get all individuals in this project
individuals = Individual.objects.filter(family__project=project).order_by(
'family__family_id', 'affected')
filename_prefix = "%s_individuals" % _slugify(project.name)
return export_individuals(
filename_prefix,
individuals,
format,
include_hpo_terms_present=include_phenotypes,
include_hpo_terms_absent=include_phenotypes,
)
def export_case_review_individuals_handler(request, project_guid):
"""Export case review Individuals table.
Args:
project_guid (string): GUID of the project for which to export case review individual data
"""
format = request.GET.get('file_format', 'tsv')
project = get_project_and_check_permissions(project_guid, request.user)
individuals = Individual.objects.filter(
family__project=project,
case_review_status__regex="[\w].*").order_by('family__family_id',
'affected')
filename_prefix = "%s_case_review_individuals" % _slugify(project.name)
return export_individuals(
filename_prefix,
individuals,
format,
include_case_review_status=True,
include_case_review_discussion=True,
include_hpo_terms_present=True,
include_hpo_terms_absent=True,
)
def handle(self, *args, **options):
project_names = options.get('projects')
if options.get('project_category'):
project_names += [p.name for p in ProjectCategory.objects.get(name=options['project_category']).projects.all()]
if not len(project_names):
raise Exception('Error: No projects specified')
print('Exporting individuals from {} projects'.format(len(project_names)))
individuals = Individual.objects.filter(family__project__name__in=project_names).all()
print('Found {} individuals to export'.format(len(individuals)))
response = export_individuals(
'projects_individuals',
individuals,
'xls',
include_project_name=True,
include_project_created_date=True,
include_created_date=True,
include_analysis_status=True,
include_coded_phenotype=True,
include_hpo_terms_present=True,
include_hpo_terms_absent=True,
include_first_loaded_date=True,
)
print('Parsed individual data')
filename = re.search('filename="(?P<file_name>.*)"', response.get('Content-Disposition')).group('file_name')
with open(filename, 'w') as f:
f.write(response.content)
print('Wrote results to {}'.format(filename))
def handle(self, *args, **options):
project_names = options.get('projects')
if options.get('project_category'):
project_names += [
p.name for p in ProjectCategory.objects.get(
name=options['project_category']).projects.all()
]
if not len(project_names):
raise Exception('Error: No projects specified')
print('Exporting individuals from {} projects'.format(
len(project_names)))
individuals = Individual.objects.filter(
family__project__name__in=project_names).all()
print('Found {} individuals to export'.format(len(individuals)))
response = export_individuals(
'projects_individuals',
individuals,
'xls',
include_project_name=True,
include_project_created_date=True,
include_created_date=True,
include_analysis_status=True,
include_coded_phenotype=True,
include_hpo_terms_present=True,
include_hpo_terms_absent=True,
include_first_loaded_date=True,
)
print('Parsed individual data')
filename = re.search(
'filename="(?P<file_name>.*)"',
response.get('Content-Disposition')).group('file_name')
with open(filename, 'w') as f:
f.write(response.content)
print('Wrote results to {}'.format(filename))