Skip to content
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

Normalization 2 #29

Closed
wants to merge 3 commits into from
Closed

Normalization 2 #29

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
6448b2c
fix normalization increasing state bug
geeli123 Nov 14, 2024
29e23ca
fix normalization increasing state bug
geeli123 Nov 14, 2024
788cafc
add better logging
geeli123 Nov 20, 2024
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
38 changes: 26 additions & 12 deletions src/normalize/normalize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -110,17 +110,19 @@ def parse_files(s3, s3_fs, source_prefix, destination_prefix, start_date, state_
str(cur_processing.day),
)
LOGGER.info(f"Processing date: {date_partition}")
max_timestamp = cur_processing.timestamp()
max_epoch_timestamp = cur_processing.timestamp()

trip_updates_pa, vehicles_pa, alerts_pa = None, None, None
for page in paginator.paginate(Bucket=source_bucket, Prefix=date_partition, PaginationConfig={'PageSize': 10}):
trip_updates_pa = None
vehicles_pa = None
alerts_pa = None

for page in paginator.paginate(Bucket=source_bucket, Prefix=date_partition, PaginationConfig={'PageSize': 60}):
for obj in page.get("Contents", []):
key = obj["Key"]
if key.endswith(".binpb"):
# Check if this file is newer than the last processed file
file_write_time = float(key.split("/")[-1].removesuffix(".binpb"))
if file_write_time > cur_processing.timestamp():
file_write_epoch_time = float(key.split("/")[-1].removesuffix(".binpb"))
if file_write_epoch_time > cur_processing.timestamp():
LOGGER.info(f"Processing file: {key}")
# Download the file
response = s3.get_object(Bucket=source_bucket, Key=key)
Expand Down Expand Up @@ -150,32 +152,44 @@ def parse_files(s3, s3_fs, source_prefix, destination_prefix, start_date, state_
else cur_alerts_pa
)

max_timestamp = max(max_timestamp, file_write_time)
max_epoch_timestamp = max(max_epoch_timestamp, file_write_epoch_time)

if trip_updates_pa:
s3_uri = f"{destination_prefix}/trip-updates"
LOGGER.info(f"Writing {trip_updates_pa.num_rows} entries to {s3_uri}")
time_range = pa.compute.min_max(trip_updates_pa['time'])
LOGGER.info(
f"Writing {trip_updates_pa.num_rows} entries to {s3_uri}. "
f"Min timestamp {time_range['min']}, max timestamp {time_range['max']}"
)
write_data(s3_fs, trip_updates_pa, s3_uri)
if vehicles_pa:
s3_uri = f"{destination_prefix}/vehicles"
LOGGER.info(f"Writing {vehicles_pa.num_rows} entries to {s3_uri}")
time_range = pa.compute.min_max(vehicles_pa['time'])
LOGGER.info(
f"Writing {vehicles_pa.num_rows} entries to {s3_uri}. "
f"Min timestamp {time_range['min']}, max timestamp {time_range['max']}"
)
write_data(s3_fs, vehicles_pa, s3_uri)
if alerts_pa:
s3_uri = f"{destination_prefix}/alerts"
LOGGER.info(f"Writing {alerts_pa.num_rows} entries to {s3_uri}")
time_range = pa.compute.min_max(alerts_pa['time'])
LOGGER.info(
f"Writing {alerts_pa.num_rows} entries to {s3_uri}. "
f"Min timestamp {time_range['min']}, max timestamp {time_range['max']}"
)
write_data(s3_fs, alerts_pa, s3_uri)

# Update the last processed timestamp
if max_timestamp == last_processed:
if max_epoch_timestamp == last_processed:
LOGGER.warning(
f"No data found in partition: {date_partition} "
f"- is this expected?"
)
LOGGER.info(
f"Updating last processed timestamp to "
f"maximum file timestamp: {dt.datetime.utcfromtimestamp(max_timestamp).isoformat()}"
f"maximum file timestamp: {dt.datetime.utcfromtimestamp(max_epoch_timestamp).isoformat()}"
)
update_last_processed_timestamp(s3, state_bucket, state_key, max_timestamp)
update_last_processed_timestamp(s3, state_bucket, state_key, max_epoch_timestamp)
cur_processing = (cur_processing + dt.timedelta(days=1)).replace(hour=0, minute=0, second=0, microsecond=0)


Expand Down
Loading