gahusb
91de16675b
ChronosPipeline (legacy T5) does not support amazon/chronos-2 or chronos-bolt-* (input_patch_size). Switch to BaseChronosPipeline which auto-detects variant and returns the appropriate sub-pipeline (ChronosBoltPipeline / Chronos2Pipeline / ChronosPipeline). Also handle the dtype kwarg deprecation: try newer `dtype=` first, fall back to `torch_dtype=` for older versions. Test mock_pipeline fixture updated to patch BaseChronosPipeline. 45/45 tests pass. Verified amazon/chronos-bolt-base loads on CUDA. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
85 lines
3.1 KiB
Python
85 lines
3.1 KiB
Python
"""Tests for ChronosPredictor (model mock)."""
|
|
from unittest.mock import MagicMock, patch
|
|
|
|
import numpy as np
|
|
import pytest
|
|
|
|
|
|
@pytest.fixture
|
|
def mock_pipeline():
|
|
"""Mock BaseChronosPipeline.from_pretrained returning a mock pipeline object."""
|
|
with patch("chronos.BaseChronosPipeline") as cls:
|
|
cls.__name__ = "BaseChronosPipeline"
|
|
instance = MagicMock()
|
|
cls.from_pretrained.return_value = instance
|
|
yield instance
|
|
|
|
|
|
@pytest.fixture
|
|
def mock_torch_cpu():
|
|
with patch("torch.cuda.is_available", return_value=False):
|
|
yield
|
|
|
|
|
|
def _daily_ohlcv(close_seq):
|
|
return [{"datetime": f"2026-05-{i+1:02d}", "open": c, "high": c, "low": c,
|
|
"close": c, "volume": 1000} for i, c in enumerate(close_seq)]
|
|
|
|
|
|
def test_predict_batch_returns_prediction_dict(mock_pipeline, mock_torch_cpu):
|
|
"""mock pipeline → dict[ticker, ChronosPrediction]. last_close=100, samples=102 → ~+2% return."""
|
|
import torch
|
|
samples = np.full((100,), 102.0)
|
|
mock_pipeline.predict.return_value = torch.tensor(samples.reshape(1, 100, 1))
|
|
|
|
from signal_v2.chronos_predictor import ChronosPredictor, ChronosPrediction
|
|
predictor = ChronosPredictor(model_name="mock-model")
|
|
daily = {"005930": _daily_ohlcv([100] * 60)}
|
|
result = predictor.predict_batch(daily)
|
|
assert "005930" in result
|
|
pred = result["005930"]
|
|
assert isinstance(pred, ChronosPrediction)
|
|
assert abs(pred.median - 0.02) < 0.001
|
|
|
|
|
|
def test_conf_high_when_distribution_narrow(mock_pipeline, mock_torch_cpu):
|
|
"""좁은 distribution → conf ≈ 1."""
|
|
import torch
|
|
np.random.seed(42)
|
|
samples = np.random.normal(102.0, 0.1, 100)
|
|
mock_pipeline.predict.return_value = torch.tensor(samples.reshape(1, 100, 1))
|
|
|
|
from signal_v2.chronos_predictor import ChronosPredictor
|
|
predictor = ChronosPredictor(model_name="mock-model")
|
|
daily = {"005930": _daily_ohlcv([100] * 60)}
|
|
result = predictor.predict_batch(daily)
|
|
assert result["005930"].conf > 0.8
|
|
|
|
|
|
def test_conf_low_when_distribution_wide(mock_pipeline, mock_torch_cpu):
|
|
"""넓은 distribution → conf ≈ 0."""
|
|
import torch
|
|
np.random.seed(42)
|
|
samples = np.random.normal(100.0, 30.0, 100)
|
|
mock_pipeline.predict.return_value = torch.tensor(samples.reshape(1, 100, 1))
|
|
|
|
from signal_v2.chronos_predictor import ChronosPredictor
|
|
predictor = ChronosPredictor(model_name="mock-model")
|
|
daily = {"005930": _daily_ohlcv([100] * 60)}
|
|
result = predictor.predict_batch(daily)
|
|
assert result["005930"].conf < 0.3
|
|
|
|
|
|
def test_return_computed_from_price_relative_to_last_close(mock_pipeline, mock_torch_cpu):
|
|
"""price 예측 → last_close 대비 return 변환. last_close=100, samples=110 → return ~+10%."""
|
|
import torch
|
|
samples = np.full((100,), 110.0)
|
|
mock_pipeline.predict.return_value = torch.tensor(samples.reshape(1, 100, 1))
|
|
|
|
from signal_v2.chronos_predictor import ChronosPredictor
|
|
predictor = ChronosPredictor(model_name="mock-model")
|
|
# last close in the seq = 100
|
|
daily = {"005930": _daily_ohlcv(list(range(41, 101)))} # last = 100
|
|
result = predictor.predict_batch(daily)
|
|
assert abs(result["005930"].median - 0.10) < 0.001
|