chore: comment out debug step in similarity cache workflow

The debug step was helpful for diagnosing numpy array issues but is no longer needed for normal operation. Commented out rather than removed so it's available if needed for future troubleshooting.
This commit is contained in:
matt 2025-10-19 08:37:07 -07:00
parent 33791c93e8
commit b2ccbbd664

View file

@ -89,44 +89,45 @@ jobs:
exit 1
fi
- name: Debug - Inspect Parquet file after tagging
if: steps.check_cache.outputs.needs_build == 'true'
run: |
python -c "
import pandas as pd
from pathlib import Path
from code.path_util import get_processed_cards_path
parquet_path = Path(get_processed_cards_path())
print(f'Reading Parquet file: {parquet_path}')
print(f'File exists: {parquet_path.exists()}')
if not parquet_path.exists():
raise FileNotFoundError(f'Parquet file not found: {parquet_path}')
df = pd.read_parquet(parquet_path)
print(f'Loaded {len(df)} rows from Parquet file')
print(f'Columns: {list(df.columns)}')
print('')
# Show first 5 rows completely
print('First 5 complete rows:')
print('=' * 100)
for idx, row in df.head(5).iterrows():
print(f'Row {idx}:')
for col in df.columns:
value = row[col]
if isinstance(value, (list, tuple)) or hasattr(value, '__array__'):
# For array-like, show type and length
try:
length = len(value)
print(f' {col}: {type(value).__name__}[{length}] = {value}')
except:
print(f' {col}: {type(value).__name__} = {value}')
else:
print(f' {col}: {value}')
print('-' * 100)
"
# Debug step - uncomment if needed to inspect Parquet file contents
# - name: Debug - Inspect Parquet file after tagging
# if: steps.check_cache.outputs.needs_build == 'true'
# run: |
# python -c "
# import pandas as pd
# from pathlib import Path
# from code.path_util import get_processed_cards_path
#
# parquet_path = Path(get_processed_cards_path())
# print(f'Reading Parquet file: {parquet_path}')
# print(f'File exists: {parquet_path.exists()}')
#
# if not parquet_path.exists():
# raise FileNotFoundError(f'Parquet file not found: {parquet_path}')
#
# df = pd.read_parquet(parquet_path)
# print(f'Loaded {len(df)} rows from Parquet file')
# print(f'Columns: {list(df.columns)}')
# print('')
#
# # Show first 5 rows completely
# print('First 5 complete rows:')
# print('=' * 100)
# for idx, row in df.head(5).iterrows():
# print(f'Row {idx}:')
# for col in df.columns:
# value = row[col]
# if isinstance(value, (list, tuple)) or hasattr(value, '__array__'):
# # For array-like, show type and length
# try:
# length = len(value)
# print(f' {col}: {type(value).__name__}[{length}] = {value}')
# except:
# print(f' {col}: {type(value).__name__} = {value}')
# else:
# print(f' {col}: {value}')
# print('-' * 100)
# "
- name: Generate theme catalog
if: steps.check_cache.outputs.needs_build == 'true'