Adriano/PythagorasGoal
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(live): SWAP fade 1h -> 15m su PORT06 (scelta utente, gate fade15m_port06_gate)

Browse Source 
FADE specs tf=15m (sid invariati -> pesi/alloc intatti; DIP01 resta 1h);
builder canonico allineato (combine_portfolio.FADE_TF) -> parita' delle due
facce; regression-lock aggiornato al nuovo baseline (FULL Sh 7.34->8.13
DD 3.46->2.47, OOS Sh 10.07->10.86 DD 1.48->2.09). Runner invariato (fetch
15m gia' esistente dal blend pairs). Suite 126 passed.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
This commit is contained in:
Adriano Dal Pastro
2026-06-12 20:47:44 +00:00
parent 82a1c60e08
commit f78380596a
4 changed files with 55 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/portfolio/test_backtest_parity_cap.py
+6 -3
View File
@@ -12,6 +12,9 @@ def test_port06_cap_backtest_numbers_locked():
# flat-skip, mezza size) -> FULL 6.47->7.20, OOS 8.82->9.66, DD 4.1%->3.7%.
# Aggiornato 2026-06-09 (2): + XS01 (reversione cross-sectional 8 asset, PAPER) ->
# FULL 7.20->7.34, OOS 9.66->10.07, FULL DD 3.68->3.46 (OOS DD +0.17pp).
assert r.full["sharpe"] == pytest.approx(7.34, abs=0.15)
assert r.oos["sharpe"] == pytest.approx(10.07, abs=0.25)
assert r.full["dd"] == pytest.approx(3.46, abs=0.5)
# Aggiornato 2026-06-12: SWAP fade 1h->15m (combine_portfolio.FADE_TF, scelta utente,
# gate fade15m_port06_gate.py) -> FULL 7.34->8.13 DD 3.46->2.47, OOS 10.07->10.86.
# Nuovo baseline atteso, non una regressione.
assert r.full["sharpe"] == pytest.approx(8.13, abs=0.15)
assert r.oos["sharpe"] == pytest.approx(10.86, abs=0.25)
assert r.full["dd"] == pytest.approx(2.47, abs=0.5)