Skip to content

update parse_log_file #821

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

Open
klaricch wants to merge 4 commits into
base: main
Choose a base branch
from
Open

update parse_log_file #821

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
08e67f5
update parse_log_file
klaricch Mar 3, 2026
68a8226
small edit
klaricch Mar 16, 2026
b225566
small edit
klaricch Mar 16, 2026
6408033
swtitch from frac to sum for struct missingness
klaricch Apr 9, 2026
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: 4 additions & 0 deletions gnomad/assessment/parse_validity_logs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,6 +32,10 @@ def parse_log_file(log_file):
"compare_subset_freqs": "subset freqs",
"check_globals_for_retired_terms": "globals check",
"summarize_variant_filters": "variant summary",
"validate_config_fields_in_ht": "general info",
"log_field_validation_results": "general info",
"check_fields_not_in_requirements": "general info",
"load_gnomad_data": "load gnomAD data",
}

with hl.hadoop_open(log_file, "r") as f:
Expand Down
8 changes: 3 additions & 5 deletions gnomad/assessment/validity_checks.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1449,7 +1449,7 @@ def check_missingness_of_struct(
struct_expr: hl.expr.StructExpression, prefix: str = ""
) -> Dict[str, Any]:
"""
Recursively check the fraction of missing values of all fields within a StructExpression.
Recursively check the number of missing values of all fields within a StructExpression.

Either a standalone or nested struct can be provided. If the struct contains an array (or set) of values, the array
will be considered missing if it is NA, an empty array, or only has missing elements.
Expand All @@ -1468,11 +1468,9 @@ def check_missingness_of_struct(
elif isinstance(struct_expr, (hl.expr.ArrayExpression, hl.expr.SetExpression)):
# Count array/set as missing if it is NA, an empty array/set, or only has missing
# elements.
return hl.agg.fraction(
hl.or_else(struct_expr.all(lambda x: hl.is_missing(x)), True)
)
return hl.agg.sum(hl.or_else(struct_expr.all(lambda x: hl.is_missing(x)), True))
else:
return hl.agg.fraction(hl.is_missing(struct_expr))
return hl.agg.sum(hl.is_missing(struct_expr))


def flatten_missingness_struct(
Expand Down
Loading