Adriano Dal Pastro
d5dd6f4b72
- altlib.causality_ok(target_fn, tf): online-consistency guard (ricalcola il target su un prefisso, la coda deve combaciare col full). eval_weights shifta la posizione ma non vede una feature non-causale (finestra centrata/shift(-k)/stat full-sample) -> questa sì. - intra_score integra DUE gate prima/dopo lo scoring: causality (leak -> LEAK, squalificato) e day_boundary_robust (ARTIFACT-RISK -> fuori dagli slot). Effetto sul leaderboard intraday: open_drive + weekly_seasonality + overnight -> CAL-ARTIFACT (da soli, niente skeptic); prevday_range_breakout resta (ROBUST). earns_slot 10 -> 8. - +2 test (causal-ok / leak), suite intera verde. Il lab intraday ora auto-becca leak e artefatti-calendario che ieri richiedevano 3 scettici. Chiude la 3a lezione harness dell'onda intraday. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
84 lines
3.5 KiB
Python
84 lines
3.5 KiB
Python
"""Locks the two harness-realism gates codified from the 2026-06-21 intraday wave:
|
|
* day_boundary_robust — a calendar/session/hour signal whose marginal uplift INVERTS when
|
|
the UTC day boundary is shifted is a labeling ARTIFACT (this killed open_drive). A price
|
|
signal that ignores the calendar is INVARIANT; a genuine calendar effect is ROBUST.
|
|
* eval_weights_smallcap — at ~$600 a sub-min_order rebalance can't execute; the modeled
|
|
proportional fee on thousands of sub-dollar moves is a fiction. The realistic evaluator
|
|
skips them.
|
|
"""
|
|
import sys
|
|
from pathlib import Path
|
|
|
|
import numpy as np
|
|
import pandas as pd
|
|
|
|
ROOT = Path(__file__).resolve().parents[1]
|
|
sys.path.insert(0, str(ROOT / "scripts" / "research" / "alt"))
|
|
import altlib as al # noqa: E402
|
|
|
|
|
|
# --- LESSON 1: day-boundary robustness -------------------------------------------------
|
|
def test_day_boundary_invariant_for_price_signal():
|
|
"""A signal that never reads the calendar is INVARIANT to the day-boundary shift."""
|
|
def mom(df):
|
|
c = df["close"].values
|
|
return np.tanh(3 * (c / al.sma(c, 200) - 1))
|
|
r = al.day_boundary_robust(mom, offsets=(0, 6, 12, 18))
|
|
assert r["verdict"] == "INVARIANT"
|
|
assert r["spread"] == 0.0
|
|
assert r["calendar_sensitive"] is False
|
|
|
|
|
|
def test_day_boundary_flags_calendar_artifact():
|
|
"""A pure hour-of-day bias is calendar-sensitive: its uplift swings with the boundary
|
|
(the open_drive failure mode). It must be flagged, never INVARIANT."""
|
|
def hourbias(df):
|
|
h = pd.to_datetime(df["datetime"], utc=True).dt.hour.values
|
|
return np.where(h < 8, 1.0, 0.0)
|
|
r = al.day_boundary_robust(hourbias, offsets=(0, 6, 12, 18))
|
|
assert r["calendar_sensitive"] is True
|
|
assert r["spread"] > 0.05
|
|
assert r["verdict"] != "INVARIANT"
|
|
|
|
|
|
# --- LESSON 2: small-capital fill realism ----------------------------------------------
|
|
def test_smallcap_skips_subdollar_rebalances():
|
|
"""Thousands of sub-min_order wiggles (a vol-target overlay's fiction) do NOT execute."""
|
|
df = al.get("BTC", "1h")
|
|
rng = np.random.default_rng(0)
|
|
micro = 0.5 + 0.001 * rng.standard_normal(len(df)) # tiny drift around 0.5
|
|
r = al.eval_weights_smallcap(df, micro, capital=600.0, min_order=5.0)
|
|
modeled_turn = al.eval_weights(df, micro)["turnover_per_year"]
|
|
assert r["executed_turnover_per_year"] < modeled_turn * 0.2
|
|
assert r["n_executed_trades"] < len(df) * 0.05
|
|
|
|
|
|
def test_smallcap_keeps_real_trades():
|
|
"""A low-turnover signal with genuine large moves executes them, ~no Sharpe haircut."""
|
|
df = al.get("BTC", "1h")
|
|
step = np.zeros(len(df)); step[: len(df) // 2] = 0.5; step[len(df) // 2:] = -0.5
|
|
r = al.eval_weights_smallcap(df, step, capital=600.0, min_order=5.0)
|
|
assert r["n_executed_trades"] >= 2
|
|
assert abs(r["sharpe_haircut"]) < 0.2
|
|
|
|
|
|
# --- LESSON 3: look-ahead (online-consistency) guard -----------------------------------
|
|
def test_causality_passes_causal_signal():
|
|
"""A causal signal recomputed on a prefix matches the full run on its tail."""
|
|
def mom(df):
|
|
c = df["close"].values
|
|
return np.tanh(3 * (c / al.sma(c, 200) - 1))
|
|
r = al.causality_ok(mom, tf="1h")
|
|
assert r["ok"] is True
|
|
assert r["max_tail_diff"] == 0.0
|
|
|
|
|
|
def test_causality_flags_lookahead():
|
|
"""A signal that reads tomorrow's move (future peek) is disqualified."""
|
|
def leaky(df):
|
|
c = df["close"].values
|
|
f = np.zeros(len(c)); f[:-1] = np.sign(c[1:] - c[:-1]) # uses close[i+1]
|
|
return f
|
|
r = al.causality_ok(leaky, tf="1h")
|
|
assert r["ok"] is False
|