CalvinBackup/OpenAirframes
1
0
Fork 0
mirror of https://github.com/PlaneQuery/OpenAirframes.git synced 2026-08-16 20:50:20 +02:00
Code Issues Packages Projects Releases Wiki Activity

use date of file instead of min timestamp

Browse Source
This commit is contained in:
ggman12
2026-02-15 16:44:09 -05:00
parent 405855c566
commit 1a553d5f44
1 changed files with 7 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/adsb/combine_chunks_to_csv.py
+7 -6
View File
@@ -102,16 +102,17 @@ def download_and_merge_base_release(compressed_df: pl.DataFrame) -> tuple[pl.Dat
if base_path and os.path.exists(str(base_path)): if base_path and os.path.exists(str(base_path)):
print(f"Loading base release from {base_path}") print(f"Loading base release from {base_path}")
# Extract start date from filename (e.g., openairframes_adsb_2025-05-01_2026-02-14.csv.gz)
import re
filename = os.path.basename(str(base_path))
match = re.search(r'openairframes_adsb_(\d{4}-\d{2}-\d{2})_', filename)
earliest_date = match.group(1) if match else None
print(f"Start date from base filename: {earliest_date}")
# Read CSV with schema matching the new data # Read CSV with schema matching the new data
base_df = pl.read_csv(base_path, schema=compressed_df.schema) base_df = pl.read_csv(base_path, schema=compressed_df.schema)
print(f"Base release has {len(base_df)} records") print(f"Base release has {len(base_df)} records")
# Extract earliest date from base release
earliest_timestamp = base_df['time'].min()
earliest_dt = datetime.fromisoformat(str(earliest_timestamp).replace('Z', '+00:00'))
earliest_date = earliest_dt.strftime('%Y-%m-%d')
print(f"Earliest date in base release: {earliest_date}")
# Ensure columns match # Ensure columns match
base_cols = set(base_df.columns) base_cols = set(base_df.columns)
new_cols = set(compressed_df.columns) new_cols = set(compressed_df.columns)