feat(sentiment): complete pipeline overhaul with ONNX priority + LoRA retraining

- 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
This commit is contained in:
Codex
2026-09-27 04:34:49 +02:00
parent 2ea14bd465
commit c32db97d57
178 changed files with 64849 additions and 42 deletions

View File

@@ -0,0 +1,101 @@
# Asset alias mappings - maps common aliases to canonical tickers
aliases:
# Major crypto
"BTC": "BTC"
"BITCOIN": "BTC"
"XBT": "BTC"
"ETH": "ETH"
"ETHEREUM": "ETH"
"ETHER": "ETH"
"SOL": "SOL"
"SOLANA": "SOL"
"BNB": "BNB"
"BINANCE": "BNB"
"ADA": "ADA"
"CARDANO": "ADA"
"XRP": "XRP"
"RIPPLE": "XRP"
"DOGE": "DOGE"
"DOGECOIN": "DOGE"
"MATIC": "MATIC"
"POLYGON": "MATIC"
"AVAX": "AVAX"
"AVALANCHE": "AVAX"
"DOT": "DOT"
"POLKADOT": "DOT"
"LINK": "LINK"
"CHAINLINK": "LINK"
"UNI": "UNI"
"UNISWAP": "UNI"
"AAVE": "AAVE"
"ARB": "ARB"
"ARBITRUM": "ARB"
"OP": "OP"
"OPTIMISM": "OP"
# People aliases
"VITALIK": "ETH"
"VITALIK BUTERIN": "ETH"
"CZ": "BNB"
"CHANGPENG ZHAO": "BNB"
"ELON": "DOGE"
"ELON MUSK": "DOGE"
"SAYLOR": "BTC"
"MICHAEL SAYLOR": "BTC"
"SBF": "SOL" # Historical
# Stablecoins
"USDT": "USDT"
"TETHER": "USDT"
"USDC": "USDC"
"CIRCLE": "USDC"
"DAI": "DAI"
"MAKER": "MKR"
# Meme/Other
"SHIB": "SHIB"
"SHIBA": "SHIB"
"PEPE": "PEPE"
"WIF": "WIF"
"BONK": "BONK"
# Trade assets from DOLPHIN-NAUTILUS log
"ZIL": "ZIL"
"ZILLIQA": "ZIL"
"ONG": "ONG"
"ONTOLOGY": "ONG"
"ONTOLOGY GAS": "ONG"
"ONE": "ONE"
"HARMONY": "ONE"
"STX": "STX"
"STACKS": "STX"
"ALGO": "ALGO"
"ALGORAND": "ALGO"
"DASH": "DASH"
"LTC": "LTC"
"LITECOIN": "LTC"
"FET": "FET"
"FETCH": "FET"
"FETCH.AI": "FET"
"XTZ": "XTZ"
"TEZOS": "XTZ"
"ENJ": "ENJ"
"ENJIN": "ENJ"
"XLM": "XLM"
"STELLAR": "XLM"
"ETC": "ETC"
"ETHEREUM CLASSIC": "ETC"
"TRX": "TRX"
"TRON": "TRX"