Skip to content

⚡ Bolt: Optimize results filtering in fix_encoding.py #113

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

⚡ Bolt: Optimize results filtering in fix_encoding.py #113

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
32 changes: 21 additions & 11 deletions training/scripts/fix_encoding.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,9 +30,7 @@
S3DatasetLoader, # noqa: E402
)

logging.getLogger("ai.training.utils.s3_dataset_loader").setLevel(
logging.ERROR
)
logging.getLogger("ai.training.utils.s3_dataset_loader").setLevel(logging.ERROR)

DEFAULT_S3_BUCKET = "pixel-data"
MAX_RETRIES = 3
Expand Down Expand Up @@ -887,10 +885,16 @@ def print_results(results: list[dict[str, Any]], output: OutputHandler) -> None:
output.header("📊 ENCODING FIX RESULTS")
output.separator()

successful = [r for r in results if r.get("success")]
failed = [r for r in results if not r.get("success")]
skipped = [r for r in successful if r.get("skipped")]
fixed = [r for r in successful if not r.get("skipped")]
successful, failed, skipped, fixed = [], [], [], []
for r in results:
if r.get("success"):
successful.append(r)
if r.get("skipped"):
skipped.append(r)
else:
fixed.append(r)
else:
failed.append(r)

output.info(f"\n✅ Fixed: {len(fixed)} files")
output.info(f"⏭️ Skipped (already UTF-8): {len(skipped)} files")
Expand Down Expand Up @@ -919,10 +923,16 @@ def save_results(
results: list[dict[str, Any]],
) -> Path:
"""Save encoding fix results to JSON file"""
successful = [r for r in results if r.get("success")]
failed = [r for r in results if not r.get("success")]
skipped = [r for r in successful if r.get("skipped")]
fixed = [r for r in successful if not r.get("skipped")]
successful, failed, skipped, fixed = [], [], [], []
for r in results:
if r.get("success"):
successful.append(r)
if r.get("skipped"):
skipped.append(r)
else:
fixed.append(r)
else:
failed.append(r)

results_path = project_root / "ai/training_ready/data/encoding_fix_results.json"
with open(results_path, "w") as f:
Expand Down