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
93 lines
3.0 KiB
Python
93 lines
3.0 KiB
Python
"""Tests for payload schemas"""
|
|
|
|
import pytest
|
|
from datetime import datetime
|
|
from sentiment_engine.schemas.payload import NormalizedPayload, SourceType, AssetMention, EngagementMetrics
|
|
|
|
|
|
class TestNormalizedPayload:
|
|
"""Tests for NormalizedPayload schema"""
|
|
|
|
def test_valid_payload(self):
|
|
payload = NormalizedPayload(
|
|
source_id="test_source",
|
|
source_type=SourceType.NEWS,
|
|
source_credibility_base=0.8,
|
|
ingest_ts=datetime.now().timestamp(),
|
|
publish_ts=datetime.now().timestamp(),
|
|
asset_mentions=[AssetMention(asset_id="BTC", mention_span=(0, 3), confidence=0.9, source_text="BTC", mention_type="ticker")],
|
|
raw_text="BTC surges to new highs",
|
|
title="BTC Surges",
|
|
url="https://test.com",
|
|
author="Test Author",
|
|
content_length=100,
|
|
language="en"
|
|
)
|
|
assert payload.source_id == "test_source"
|
|
assert payload.has_assets is True
|
|
assert payload.get_assets() == ["BTC"]
|
|
|
|
def test_empty_text_raises(self):
|
|
with pytest.raises(ValueError, match="raw_text cannot be empty"):
|
|
NormalizedPayload(
|
|
source_id="test",
|
|
source_type=SourceType.NEWS,
|
|
source_credibility_base=0.5,
|
|
ingest_ts=1234567890.0,
|
|
raw_text="",
|
|
content_length=0,
|
|
language="en"
|
|
)
|
|
|
|
def test_whitespace_text_raises(self):
|
|
with pytest.raises(ValueError, match="raw_text cannot be empty"):
|
|
NormalizedPayload(
|
|
source_id="test",
|
|
source_type=SourceType.NEWS,
|
|
source_credibility_base=0.5,
|
|
ingest_ts=1234567890.0,
|
|
raw_text=" ",
|
|
content_length=0,
|
|
language="en"
|
|
)
|
|
|
|
|
|
class TestAssetMention:
|
|
"""Tests for AssetMention schema"""
|
|
|
|
def test_valid_mention(self):
|
|
mention = AssetMention(
|
|
asset_id="BTC",
|
|
mention_span=(0, 3),
|
|
confidence=0.9,
|
|
source_text="BTC",
|
|
mention_type="ticker"
|
|
)
|
|
assert mention.asset_id == "BTC"
|
|
assert mention.confidence == 0.9
|
|
|
|
|
|
class TestEngagementMetrics:
|
|
"""Tests for EngagementMetrics"""
|
|
|
|
def test_total_engagement(self):
|
|
metrics = EngagementMetrics(retweets=10, likes=50, replies=5, upvotes=100, comments=20)
|
|
assert metrics.total_engagement() == 185
|
|
|
|
def test_default_zero(self):
|
|
metrics = EngagementMetrics()
|
|
assert metrics.total_engagement() == 0
|
|
|
|
|
|
class TestSourceType:
|
|
"""Tests for SourceType enum"""
|
|
|
|
def test_all_values(self):
|
|
assert SourceType.NEWS == "news"
|
|
assert SourceType.SOCIAL == "social"
|
|
assert SourceType.EXCHANGE_ANN == "exchange_ann"
|
|
assert SourceType.REGULATORY == "regulatory"
|
|
assert SourceType.CORPORATE == "corporate"
|
|
assert SourceType.FORUM == "forum"
|
|
assert SourceType.ON_CHAIN == "on_chain"
|