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

Include year_letter_clade & more in metadata #373

Open
wants to merge 1 commit into
base: master
Choose a base branch
from
Open

Include year_letter_clade & more in metadata #373

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
14 changes: 11 additions & 3 deletions bin/join-metadata-and-clades
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,8 +14,11 @@ rate_per_day = 0.0007 * 29903 / 365
reference_day = datetime(2020,1,1).toordinal()

column_map = {
"clade": "Nextstrain_clade",
"clade_legacy": "Nextstrain_clade",
"Nextclade_pango": "Nextclade_pango",
"clade_nextstrain": "year_letter_clade",
"clade_who": "who_variant",
"clade_display_name": "clade_display_name",
"immune_escape": "immune_escape",
"ace2_binding": "ace2_binding",
"totalMissing": "missing_data",
Expand Down Expand Up @@ -53,9 +56,9 @@ def reorder_columns(result: pd.DataFrame):
Moves the new clade column after a specified column
"""
columns = list(result.columns)
columns.remove(column_map['clade'])
columns.remove(column_map['clade_legacy'])
insert_at = columns.index(INSERT_BEFORE_THIS_COLUMN)
columns.insert(insert_at, column_map['clade'])
columns.insert(insert_at, column_map['clade_legacy'])
return result[columns]


Expand Down Expand Up @@ -107,6 +110,11 @@ def main():
# Remove immune_escape and ace2_binding when clade <21L and not recombinant
clades.loc[clades.Nextstrain_clade < "21L",["immune_escape","ace2_binding"]] = float('nan')

# Calculate `clade_display_name` column, we can make this more sophisticated later
clades["clade_display_name"] = clades.apply(
lambda x: f"{x.year_letter_clade}" + (f" ({x.who_variant})" if x.who_variant.istitle() else ""),
axis=1
)

clades = clades[list(column_map.values())]

Expand Down