From 13d91d566ba87755b995488d229b6198189e9b1e Mon Sep 17 00:00:00 2001
From: Erick Ahmed <engineering@erickahmed.com>
Date: Mon, 13 Jul 2026 20:06:45 +0200
Subject: [PATCH] Move to subfolder

- Makes python recognize it as a submodule
---
 stat/utils/extractor.py | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)
 create mode 100644 stat/utils/extractor.py

diff --git a/stat/utils/extractor.py b/stat/utils/extractor.py
new file mode 100644
index 0000000..a5dd172
--- /dev/null
+++ b/stat/utils/extractor.py
@@ -0,0 +1,23 @@
+import json
+from pathlib import Path
+import pandas as pd
+
+def extract_id(row: pd.Series) -> str:
+    """Extracts PGN from metadata or falls back to CAN ID."""
+    meta = row.get('j1939_metadata')
+    if pd.isna(meta):
+        return f"ID: {row['ID']}"
+    if isinstance(meta, str):
+        try:
+            meta = json.loads(meta)
+        except json.JSONDecodeError:
+            return f"ID: {row['ID']}"
+    if isinstance(meta, dict) and 'PGN' in meta:
+        return f"PGN: {meta['PGN']}"
+    return f"ID: {row['ID']}"
+
+def load_data(file_path: Path) -> pd.DataFrame:
+    """Loads Parquet file and adds an Identifier column."""
+    df = pd.read_parquet(file_path)
+    df['Identifier'] = df.apply(extract_id, axis=1)
+    return df