Skip to content

Restore test collection and lint cleanliness after the Task B merge #87

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
duckyquang merged 1 commit into from
Sep 10, 2026
Merged

Restore test collection and lint cleanliness after the Task B merge #87

Show file tree
Hide file tree
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
2 changes: 1 addition & 1 deletion docs/embeddings.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,7 +33,7 @@ from datasets import load_dataset

ds = load_dataset(
"MITCriticalData/mimic-iv-echo-jepa-embeddings",
data_dir="vjepa2.1-vitl-mimic-pt-100", # variant used for the reported results
data_dir="vjepa2.1-vitl-mimic-pt-100", # variant used for the reported results
)
```

Expand Down
44 changes: 34 additions & 10 deletions scripts/build_valvular_manifest.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,8 +20,6 @@

import numpy as np
import pandas as pd
import pyarrow as pa
import pyarrow.parquet as pq

logging.basicConfig(level=logging.INFO, format="%(asctime)s | %(levelname)s | %(message)s")
log = logging.getLogger("build_valvular_manifest")
Expand All @@ -47,7 +45,9 @@ def build_valvular_manifest(
log.info("Echo embedding path not specified; generating placeholder vectors.")
# Store as float32 list
rng = np.random.default_rng(42)
cohort["echo_embedding"] = [rng.normal(0, 1, 1024).astype(np.float32).tolist() for _ in range(len(cohort))]
cohort["echo_embedding"] = [
rng.normal(0, 1, 1024).astype(np.float32).tolist() for _ in range(len(cohort))
]
cohort["has_echo_embedding"] = True

# 2. Join or populate ECG embeddings
Expand All @@ -58,7 +58,9 @@ def build_valvular_manifest(
else:
log.info("ECG embedding path not specified; generating placeholder vectors.")
rng = np.random.default_rng(42)
cohort["ecg_embedding"] = [rng.normal(0, 1, 768).astype(np.float32).tolist() for _ in range(len(cohort))]
cohort["ecg_embedding"] = [
rng.normal(0, 1, 768).astype(np.float32).tolist() for _ in range(len(cohort))
]
cohort["has_ecg_embedding"] = True

out_manifest.parent.mkdir(parents=True, exist_ok=True)
Expand Down Expand Up @@ -94,12 +96,34 @@ def build_valvular_manifest(
def main():
repo_root = Path(__file__).resolve().parents[1]
parser = argparse.ArgumentParser(description=__doc__)
parser.add_argument("--cohort", default=str(repo_root / "cohort" / "valvular_cohort_with_splits.parquet"))
parser.add_argument("--echo", default=str(repo_root / "data" / "interim" / "echo_study_embeddings_vjepa2.1-vitl-mimic-pt-100.parquet"))
parser.add_argument("--ecg", default=str(repo_root / "data" / "interim" / "hubert_ecg_embeddings.parquet"))
parser.add_argument("--out-manifest", default=str(repo_root / "data" / "processed" / "valvular_echo_hubert_manifest.parquet"))
parser.add_argument("--out-meta-csv", default=str(repo_root / "data" / "processed" / "valvular_echo_hubert_manifest_metadata.csv"))
parser.add_argument("--out-summary", default=str(repo_root / "logs" / "valvular_echo_hubert_join_summary.json"))
parser.add_argument(
"--cohort", default=str(repo_root / "cohort" / "valvular_cohort_with_splits.parquet")
)
parser.add_argument(
"--echo",
default=str(
repo_root
/ "data"
/ "interim"
/ "echo_study_embeddings_vjepa2.1-vitl-mimic-pt-100.parquet"
),
)
parser.add_argument(
"--ecg", default=str(repo_root / "data" / "interim" / "hubert_ecg_embeddings.parquet")
)
parser.add_argument(
"--out-manifest",
default=str(repo_root / "data" / "processed" / "valvular_echo_hubert_manifest.parquet"),
)
parser.add_argument(
"--out-meta-csv",
default=str(
repo_root / "data" / "processed" / "valvular_echo_hubert_manifest_metadata.csv"
),
)
parser.add_argument(
"--out-summary", default=str(repo_root / "logs" / "valvular_echo_hubert_join_summary.json")
)
args = parser.parse_args()

summary = build_valvular_manifest(
Expand Down
Loading