Skip to content

Fix process_live.py when no trades.csv file exists #17

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
dafalcon wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix process_live.py when no trades.csv file exists #17

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
34 changes: 21 additions & 13 deletions update_utils/process_live.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -108,19 +108,21 @@ def process_live():
print("🔄 Processing Live Trades")
print("=" * 60)

last_processed = {}
last_processed = None

if os.path.exists(processed_file):
print(f"✓ Found existing processed file: {processed_file}")
result = subprocess.run(['tail', '-n', '1', processed_file], capture_output=True, text=True)
last_line = result.stdout.strip()
splitted = last_line.split(',')

last_processed['timestamp'] = pd.to_datetime(splitted[0])
last_processed['transactionHash'] = splitted[-1]
last_processed['maker'] = splitted[2]
last_processed['taker'] = splitted[3]

last_processed = {
'timestamp': pd.to_datetime(splitted[0]),
'transactionHash': splitted[-1],
'maker': splitted[2],
'taker': splitted[3],
}

print(f"📍 Resuming from: {last_processed['timestamp']}")
print(f" Last hash: {last_processed['transactionHash'][:16]}...")
else:
Expand All @@ -142,13 +144,19 @@ def process_live():

df = df.with_row_index()

same_timestamp = df.filter(pl.col('timestamp') == last_processed['timestamp'])
same_timestamp = same_timestamp.filter(
(pl.col("transactionHash") == last_processed['transactionHash']) & (pl.col("maker") == last_processed['maker']) & (pl.col("taker") == last_processed['taker'])
)

df_process = df.filter(pl.col('index') > same_timestamp.row(0)[0])
df_process = df_process.drop('index')
if last_processed is None:
df_process = df.drop('index')
else:
same_timestamp = df.filter(pl.col('timestamp') == last_processed['timestamp'])
same_timestamp = same_timestamp.filter(
(pl.col("transactionHash") == last_processed['transactionHash']) & (pl.col("maker") == last_processed['maker']) & (pl.col("taker") == last_processed['taker'])
)

if same_timestamp.is_empty():
print("⚠ Last processed row not found in source data; processing all rows")
df_process = df.drop('index')
else:
df_process = df.filter(pl.col('index') > same_timestamp.row(0)[0]).drop('index')

print(f"⚙️ Processing {len(df_process):,} new rows...")

Expand Down