c32db97d57
- Added 30 new sources (5 RSS + 25 Telegram) for previously ZERO-coverage assets - Fixed model loading priority: ONNX > LoRA v2 > PyTorch > Mock - ONNX FinBERT (pre-trained on 1.2M financial docs) now PRIMARY - best for real-world text - LoRA v2 models trained on 518 carefully labeled samples (balanced Bearish/Bullish/Neutral) - Emotion LoRA v2 trained with weighted loss (greed/fear 2x, joy 1.5x) - 30 new sources: STX, FET, XTZ, ENJ, ETC, TRX, ONG, DASH, LTC, ZIL, NEAR, APT, SUI, ICP - Early stopping (patience=3) on both LoRA trainings - Human-in-the-loop verification CLI tool created - Disk-conscious: save_total_limit=1, adapters 6-8MB each Pipeline now correctly classifies: - BTC breaks 100k → +0.54 Bullish ✅ - Major hack → -0.23 Bearish ✅ - HODL → +0.91 Bullish ✅ - Rug pull → -0.30 Bearish ✅ - SEC sues → -0.30 Bearish ✅ - ETF approval → +0.32 Bullish ✅ - Whale accumulation → +0.31 Bullish ✅ Models: ONNX FinBERT (PRIORITY 1) + LoRA v2 adapters (6-8MB each) Training data: 518 carefully labeled samples (190 real + 328 synthetic) Early stopping (patience=3) on both FinBERT and DistilRoBERTa LoRA Emotion LoRA v2: weighted loss (greed/fear 2x, joy 1.5x) + early stopping
34 lines
1.4 KiB
Python
34 lines
1.4 KiB
Python
# Patch for labeling_pipeline.py - fix depeg pattern
|
|
import re
|
|
|
|
# Read the file
|
|
with open('/mnt/dolphinng5_predict/sentiment_engine/labeling_pipeline.py', 'r') as f:
|
|
content = f.read()
|
|
|
|
# Fix depeg pattern to match depegs, depegged, depegging
|
|
old_depeg = r'r"\b(hack|exploit|drain|stolen|rug|rugpull|scam|depeg|depegged)\b"'
|
|
new_depeg = r'r"\b(hack|exploit|drain|stolen|rug|rugpull|scam|depeg|depegged|depegs|depegging)\b"'
|
|
|
|
content = content.replace(old_depeg, new_depeg)
|
|
|
|
# Also add profit/arbitrage to bullish for completeness (but they're not necessarily bullish in context)
|
|
# Actually profit/arbitrage can be neutral or bullish depending on context, let's not add them
|
|
|
|
# Also add more regulatory keywords that are bearish
|
|
old_regulatory = r'r"\b(sec|lawsuit|enforcement|regulation|regulatory|cftc|ban|delist)\b"'
|
|
new_regulatory = r'r"\b(sec|lawsuit|enforcement|regulation|regulatory|cftc|ban|delist|crackdown|subpoena|investigation|charges|sues)\b"'
|
|
|
|
content = content.replace(old_regulatory, new_regulatory)
|
|
|
|
# Also add stablecoin/peg loss as bearish
|
|
old_bearish2 = r'r"\b(death.cross|breakdown|capitulation|liquidation)\b"'
|
|
new_bearish2 = r'r"\b(death.cross|breakdown|capitulation|liquidation|peg.loss|depeg|depegged|depegs)\b"'
|
|
|
|
content = content.replace(old_bearish2, new_bearish2)
|
|
|
|
# Write the patched file
|
|
with open('/mnt/dolphinng5_predict/sentiment_engine/labeling_pipeline.py', 'w') as f:
|
|
f.write(content)
|
|
|
|
print("Patch 2 applied successfully!")
|