Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
4 changes: 2 additions & 2 deletions src/data_validation/validate_dataset.py
Original file line number Diff line number Diff line change
Expand Up @@ -14,8 +14,8 @@ def validate_dataset_entry(row):
expectedNumberOfFiles=handle_nan(row['expected number of files']),
dataCollectionStartYear=handle_nan(row['data collection start year']),
dataCollectionEndYear=handle_nan(row['data collection end year']),
dataCategory=row['data category'],
dataType=handle_nan(row['data type']),
dataCategory=row['data category'].split('|') if handle_nan(row['data category']) else [],
dataType=row['data type'].split('|') if handle_nan(row['data type']) else [],
experimentalStrategy=row['experimental strategy'].split('|') if handle_nan(row['experimental strategy']) else [],
experimentalPlatform=row['experimental platform'].split('|') if handle_nan(row['experimental platform']) else [],
publication=row['publication'].split('|') if handle_nan(row['publication']) else [],
Expand Down
1 change: 1 addition & 0 deletions src/data_validation/validate_study.py
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,7 @@ def validate_study_entry(row):
publication = str(row['publication']).split('|') if handle_nan(row['publication']) else [],
expectedNumberOfParticipants = handle_nan(row['expected number of participants']),
guidType = row['guid type'],
guidMapped = bool(row['guids mapped?']),
acknowledgments = row['acknowledgments'].split('|') if handle_nan(row['acknowledgments']) else [],
citationStatement = row['citation statement'].split('|') if handle_nan(row['citation statement']) else []
)
Expand Down
4 changes: 2 additions & 2 deletions src/data_validation/validation.py
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,7 @@

def validate_study(file_path, output_path='.'):
string_columns = ['study code', 'program', 'research domain', 'participant lifespan stage',
'clinical data source type', 'data category', 'guid type']
'study design', 'clinical data source type', 'data category', 'guid type']
return validate_data(file_path, string_columns, validate_study_entry, output_path)


Expand All @@ -36,7 +36,7 @@ def validate_datafile(file_path, output_path='.'):


def validate_dataset(file_path, output_path='.'):
string_columns = ['study code', 'data category', 'data access']
string_columns = ['study code', 'data category']
return validate_data(file_path, string_columns, validate_dataset_entry, output_path)


Expand Down
Loading