Skip to content

modified download.py WorldBank_CommodityMarket #2076

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

Merged
niveditasing merged 4 commits into from
Jul 6, 2026
Merged

modified download.py WorldBank_CommodityMarket #2076

Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
b36c963
modified download.py
niveditasing Jun 24, 2026
66cc88d
Refactor exception logging in download.py to use logging.exception an…
niveditasing Jun 24, 2026
b56089d
Merge branch 'master' into commodity_marked_fix
niveditasing Jun 29, 2026
3fe9228
Merge branch 'master' into commodity_marked_fix
niveditasing Jul 6, 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
9 changes: 5 additions & 4 deletions statvar_imports/world_bank/commodity_market/download.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@ def download_file(url, filename):
raise

def clean_values(df):
return df.applymap(lambda x: pd.NA if isinstance(x, str) and ("..." in x or "…" in x or x.strip() in ["...", "..", "…"]) else x)
return df.map(lambda x: pd.NA if isinstance(x, str) and ("..." in x or "…" in x or x.strip() in ["...", "..", "…"]) else x)

def process_xlsx(file_path):
try:
Expand Down Expand Up @@ -70,7 +70,7 @@ def process_xlsx(file_path):

header_rows = header_rows.ffill(axis=0).infer_objects(copy=False)
header_rows = header_rows.fillna('').astype(str)
header_rows = header_rows.applymap(lambda x: ' '.join(x.split()))
header_rows = header_rows.map(lambda x: ' '.join(x.split()))
combined_header = header_rows.apply(lambda x: ' '.join(dict.fromkeys(x)).strip(), axis=0)
combined_header = combined_header.str.replace(' +', ' ', regex=True)
data_df.columns = combined_header.values
Expand All @@ -92,7 +92,7 @@ def process_xlsx(file_path):

header_rows = header_rows.ffill(axis=0).infer_objects(copy=False)
header_rows = header_rows.fillna('').astype(str)
header_rows = header_rows.applymap(lambda x: ' '.join(x.split()))
header_rows = header_rows.map(lambda x: ' '.join(x.split()))
combined_header = header_rows.apply(lambda x: ' '.join(dict.fromkeys(x)).strip(), axis=0)
combined_header = combined_header.str.replace(' +', ' ', regex=True)
data_df.columns = combined_header.values
Expand All @@ -114,7 +114,8 @@ def process_xlsx(file_path):
logging.info(f"Skipping unrecognized sheet: {sheet_name}")

except Exception as e:
logging.error(f"Failed to process {file_path}: {e}")
logging.exception(f"Failed to process {file_path}")
raise

def main():
logging.set_verbosity(logging.DEBUG)
Expand Down
Loading