dennisthiessen
099846513b
Two changes so the cross-sectional signal results can actually be trusted. (a) History depth — the binding constraint. Ingestion defaulted to 365 days, so long-lookback factors (12-month momentum, 52-week high) were only computable on a handful of weeks at the tail, and every IC reflected a single market regime. - New `settings.ohlcv_history_days` (default 1825 ≈ 5y); new tickers backfill this far instead of 1 year. - New manual "data_backfill" job (Admin → Jobs) re-fetches the full window for every ticker, ignoring incremental resume — run once to deepen existing 1-year histories. Idempotent (upsert); resumes after rate limits. (b) Factor-IC honesty. The IC was averaged over weekly rebalances whose 30-day forward windows overlap, inflating the t-stat ~sqrt(6)x. - IC now measured on NON-OVERLAPPING windows (weeks thinned to ~HORIZON apart). - Each signal carries a `reliable` flag (>= 12 independent windows); BacktestPanel greys out and de-stars thin signals so a lucky 9-week IC of 0.3 can't masquerade as an edge. 332 backend tests pass; frontend build clean. No migration (config + job + an added JSON field on the cached backtest report). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
115 lines
3.6 KiB
Python
115 lines
3.6 KiB
Python
"""Unit tests for app.scheduler module."""
|
|
|
|
import pytest
|
|
|
|
from app.scheduler import (
|
|
_is_job_enabled,
|
|
_parse_frequency,
|
|
_resume_tickers,
|
|
_last_successful,
|
|
configure_scheduler,
|
|
scheduler,
|
|
)
|
|
|
|
|
|
class TestParseFrequency:
|
|
def test_hourly(self):
|
|
assert _parse_frequency("hourly") == {"hours": 1}
|
|
|
|
def test_daily(self):
|
|
assert _parse_frequency("daily") == {"hours": 24}
|
|
|
|
def test_case_insensitive(self):
|
|
assert _parse_frequency("Hourly") == {"hours": 1}
|
|
assert _parse_frequency("DAILY") == {"hours": 24}
|
|
|
|
def test_weekly_maps_to_one_week(self):
|
|
assert _parse_frequency("weekly") == {"weeks": 1}
|
|
|
|
def test_unknown_defaults_to_daily(self):
|
|
assert _parse_frequency("monthly") == {"hours": 24}
|
|
assert _parse_frequency("") == {"hours": 24}
|
|
|
|
|
|
class TestResumeTickers:
|
|
def test_no_previous_returns_full_list(self):
|
|
symbols = ["AAPL", "GOOG", "MSFT"]
|
|
_last_successful["test_job"] = None
|
|
result = _resume_tickers(symbols, "test_job")
|
|
assert result == ["AAPL", "GOOG", "MSFT"]
|
|
|
|
def test_resume_after_first(self):
|
|
symbols = ["AAPL", "GOOG", "MSFT"]
|
|
_last_successful["test_job"] = "AAPL"
|
|
result = _resume_tickers(symbols, "test_job")
|
|
# Should start from GOOG, then wrap around
|
|
assert result == ["GOOG", "MSFT", "AAPL"]
|
|
|
|
def test_resume_after_middle(self):
|
|
symbols = ["AAPL", "GOOG", "MSFT", "TSLA"]
|
|
_last_successful["test_job"] = "GOOG"
|
|
result = _resume_tickers(symbols, "test_job")
|
|
assert result == ["MSFT", "TSLA", "AAPL", "GOOG"]
|
|
|
|
def test_resume_after_last(self):
|
|
symbols = ["AAPL", "GOOG", "MSFT"]
|
|
_last_successful["test_job"] = "MSFT"
|
|
result = _resume_tickers(symbols, "test_job")
|
|
# All already processed, wraps to full list
|
|
assert result == ["AAPL", "GOOG", "MSFT"]
|
|
|
|
def test_unknown_last_returns_full_list(self):
|
|
symbols = ["AAPL", "GOOG", "MSFT"]
|
|
_last_successful["test_job"] = "NVDA"
|
|
result = _resume_tickers(symbols, "test_job")
|
|
assert result == ["AAPL", "GOOG", "MSFT"]
|
|
|
|
def test_empty_list(self):
|
|
_last_successful["test_job"] = "AAPL"
|
|
result = _resume_tickers([], "test_job")
|
|
assert result == []
|
|
|
|
|
|
class TestConfigureScheduler:
|
|
def test_configure_adds_all_jobs(self):
|
|
# Remove any existing jobs first
|
|
scheduler.remove_all_jobs()
|
|
configure_scheduler()
|
|
jobs = scheduler.get_jobs()
|
|
job_ids = {j.id for j in jobs}
|
|
assert job_ids == {
|
|
"data_collector",
|
|
"data_backfill",
|
|
"sentiment_collector",
|
|
"fundamental_collector",
|
|
"rr_scanner",
|
|
"ticker_universe_sync",
|
|
"outcome_evaluator",
|
|
"alerts",
|
|
"market_regime",
|
|
"backtest",
|
|
"daily_pipeline",
|
|
"intraday_pipeline",
|
|
}
|
|
|
|
def test_configure_is_idempotent(self):
|
|
scheduler.remove_all_jobs()
|
|
configure_scheduler()
|
|
configure_scheduler() # Should replace, not duplicate
|
|
job_ids = [j.id for j in scheduler.get_jobs()]
|
|
# Each ID should appear exactly once
|
|
assert sorted(job_ids) == sorted([
|
|
"alerts",
|
|
"backtest",
|
|
"daily_pipeline",
|
|
"intraday_pipeline",
|
|
"data_collector",
|
|
"data_backfill",
|
|
"fundamental_collector",
|
|
"market_regime",
|
|
"outcome_evaluator",
|
|
"rr_scanner",
|
|
"sentiment_collector",
|
|
"ticker_universe_sync",
|
|
])
|