forked from mnbvc188199/Warrior_EA
0c38bfc9ab
Three compile errors, all the same cause. Inside a CExpertBase subclass a bare Period() no longer reaches the builtin ENUM_TIMEFRAMES Period(); MQL5's method- hiding rules resolve it to the inherited bool CExpertBase::Period(ENUM_TIMEFRAMES) setter, which takes an argument - hence 'wrong parameters count, 0 passed, but 1 requires'. Switched to the _Period predefined variable, which is what the rest of this codebase already uses (100 occurrences; ::Period() appears nowhere). AutoTune.mqh line 82 builds its own per-symbol/timeframe filename exactly this way, so the pool file naming now matches the convention it should have followed from the start. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
263 lines
14 KiB
MQL5
263 lines
14 KiB
MQL5
//+------------------------------------------------------------------+
|
|
//| PooledGate.mqh |
|
|
//| Cross-instrument certification for the deploy decision |
|
|
//+------------------------------------------------------------------+
|
|
//| WHY THIS EXISTS. |
|
|
//| |
|
|
//| Measured 2026-08-17 on SP500 H4: the OOS window is 4,738 bars and |
|
|
//| the mean triple-barrier label lifespan is 75.6 bars, so the |
|
|
//| holdout carries ~63 INDEPENDENT observations (see |
|
|
//| EffectiveSampleSize). Certifying a 3pp edge at 2 sigma needs |
|
|
//| ~1,036. The deploy gate was therefore unreachable by arithmetic - |
|
|
//| not because the models were short, but because the window cannot |
|
|
//| resolve the question either way. Sixteen times short. |
|
|
//| |
|
|
//| Training on more data is one answer; it is not the answer to |
|
|
//| THIS problem. The bottleneck is CERTIFICATION, and certification |
|
|
//| pools cleanly across instruments in a way training does not: each |
|
|
//| symbol keeps its own model, its own derived geometry and its own |
|
|
//| chance rate, and only the EVIDENCE is combined. |
|
|
//| |
|
|
//| WHAT IS POOLED, and what must not be. |
|
|
//| |
|
|
//| Not win rates. Symbols have different geometries and therefore |
|
|
//| different break-evens and different always-long drifts; averaging |
|
|
//| raw win rates across them is meaningless. What pools is the |
|
|
//| EXCESS OVER EACH SYMBOL'S OWN CHANCE RATE, combined by inverse- |
|
|
//| variance weighting - the standard fixed-effects meta-analysis. A |
|
|
//| symbol with a tighter estimate carries more weight, and each |
|
|
//| symbol is compared only against itself. |
|
|
//| |
|
|
//| excess_i = p_i - c_i var_i = c_i(1-c_i)/n_eff_i |
|
|
//| w_i = (1/var_i) / SUM(1/var_j) |
|
|
//| pooled = SUM(w_i * excess_i) |
|
|
//| |
|
|
//| THE CORRELATION PROBLEM, handled honestly rather than assumed |
|
|
//| away. SP500 and NAS100 are ~0.9 correlated; pooling them as |
|
|
//| independent inflates the evidence. Nothing here can measure that |
|
|
//| correlation without sharing return series, so instead of guessing |
|
|
//| it this file BRACKETS it and reports both ends: |
|
|
//| |
|
|
//| SE_INDEP = sqrt(1 / SUM(1/var_i)) all independent |
|
|
//| SE_CORR = SUM(w_i * sqrt(var_i)) all perfectly correlated|
|
|
//| |
|
|
//| The truth is between them, always. THE GATE USES SE_CORR - the |
|
|
//| pessimistic end - so a pass cannot be an artifact of correlated |
|
|
//| instruments, which on a funded account is the only safe default. |
|
|
//| The ratio SE_CORR/SE_INDEP is logged as the "diversification |
|
|
//| credit" the pool would earn if its members were independent, so |
|
|
//| the cost of that conservatism is visible rather than hidden. |
|
|
//| |
|
|
//| ONE FILE PER INSTRUMENT, never a shared append target. Each chart |
|
|
//| writes only its own record and reads everyone else's, so there is |
|
|
//| no concurrent-write path to get wrong. Every FileOpen carries |
|
|
//| FILE_SHARE_READ|FILE_SHARE_WRITE - the omission that produced the |
|
|
//| tester's 0-trade optimizer-cache corruption. |
|
|
//+------------------------------------------------------------------+
|
|
#property strict
|
|
|
|
//--- Records older than this are ignored. A chart that was stopped days ago is not evidence about the
|
|
//--- model running now, and a stale pool silently certifying a dead configuration is the failure mode
|
|
//--- this guards. Long enough to survive an overnight run, short enough that yesterday cannot vote.
|
|
#define POOL_MAX_AGE_HOURS 12
|
|
//--- Minimum distinct instruments before the pooled statistic is allowed to gate anything. Below this
|
|
//--- the pool is not a pool - it is one symbol with extra steps, and SE_CORR would equal SE_INDEP.
|
|
#define POOL_MIN_INSTRUMENTS 3
|
|
//--- Ceiling on peers read, sizing the fixed arrays. Well above the 24-instrument catalog.
|
|
#define POOL_MAX_RECORDS 64
|
|
//--- Bumped whenever the record layout changes. A reader that finds a different version SKIPS the
|
|
//--- record rather than misreading its columns - the stale-enum trap in a different costume.
|
|
#define POOL_RECORD_VERSION 1
|
|
#define POOL_DIR "Warrior_EA\\Pool"
|
|
|
|
//+------------------------------------------------------------------+
|
|
//| One instrument's contribution to the pooled certificate. |
|
|
//+------------------------------------------------------------------+
|
|
struct SPoolRecord
|
|
{
|
|
string symbol;
|
|
int timeframe;
|
|
double targetRR; // ratio must match: it fixes the structural break-even
|
|
double chancePct; // this symbol's own zero-skill rate
|
|
double winPct; // what the model actually collected
|
|
double effN; // INDEPENDENT calls, already deflated by label lifespan
|
|
double lifespanBars;
|
|
long eraCount;
|
|
datetime stamp;
|
|
};
|
|
|
|
//+------------------------------------------------------------------+
|
|
//| Publish this instance's evidence. Called once per era, after the |
|
|
//| local gate has computed its own numbers. |
|
|
//| |
|
|
//| Writes ONLY this instrument's file. The filename carries symbol |
|
|
//| and timeframe so two charts can never collide, and a chart that |
|
|
//| restarts overwrites its own record rather than accumulating a |
|
|
//| history that would let one instrument vote many times. |
|
|
//+------------------------------------------------------------------+
|
|
void CExpertSignalAIBase::PublishPoolRecord(double chancePct, double winPct, double effN)
|
|
{
|
|
//--- Nothing measurable to contribute. Writing a placeholder would let a symbol with no evidence
|
|
//--- dilute the pool's weighting, which is the opposite of what inverse-variance weighting is for.
|
|
if(chancePct <= 0.0 || chancePct >= 100.0 || winPct < 0.0 || effN < 2.0)
|
|
return;
|
|
//--- _Period, not Period(): inside a CExpertBase subclass the bare call resolves to the inherited
|
|
//--- SETTER bool CExpertBase::Period(ENUM_TIMEFRAMES) rather than the builtin. Same predefined
|
|
//--- variable AutoTune.mqh uses to build its own per-symbol/timeframe filename.
|
|
string fn = StringFormat("%s\\%s_%d.csv", POOL_DIR, m_symbol.Name(), (int)_Period);
|
|
int h = FileOpen(fn, FILE_COMMON | FILE_WRITE | FILE_CSV | FILE_ANSI |
|
|
FILE_SHARE_READ | FILE_SHARE_WRITE, ',');
|
|
if(h == INVALID_HANDLE)
|
|
{
|
|
//--- One-shot: a pool that cannot be written is a silent loss of the whole mechanism, and a
|
|
//--- mechanism that declines to act must announce it (the third quiet no-op this codebase has
|
|
//--- been bitten by).
|
|
if(!m_poolWriteWarned)
|
|
{
|
|
m_poolWriteWarned = true;
|
|
Print(ID + StringFormat(": WARNING - cannot write the pooled-gate record %s (error %d). This "
|
|
"instrument will not contribute to cross-instrument certification and "
|
|
"the pool will be short one member.", fn, GetLastError()));
|
|
}
|
|
return;
|
|
}
|
|
FileWrite(h, POOL_RECORD_VERSION, m_symbol.Name(), (int)_Period, BARRIER_TARGET_RR,
|
|
chancePct, winPct, effN, MeanLabelLifespan(), (long)m_eraCount, (long)TimeCurrent());
|
|
FileClose(h);
|
|
}
|
|
|
|
//+------------------------------------------------------------------+
|
|
//| Read every peer's record and combine. Returns the number of |
|
|
//| instruments that qualified; the pooled figures come back through |
|
|
//| the out-params. |
|
|
//| |
|
|
//| INCLUDES THIS INSTRUMENT: its own file was just written, so the |
|
|
//| directory scan picks it up like any other and there is no special |
|
|
//| case to get wrong. |
|
|
//+------------------------------------------------------------------+
|
|
int CExpertSignalAIBase::ReadPooledEvidence(double &pooledExcessPp, double &seIndep, double &seCorr,
|
|
string &detail)
|
|
{
|
|
pooledExcessPp = 0.0;
|
|
seIndep = 0.0;
|
|
seCorr = 0.0;
|
|
detail = "";
|
|
SPoolRecord rec[POOL_MAX_RECORDS];
|
|
int count = 0;
|
|
string found;
|
|
long searchHandle = FileFindFirst(POOL_DIR + "\\*.csv", found, FILE_COMMON);
|
|
if(searchHandle == INVALID_HANDLE)
|
|
return 0;
|
|
do
|
|
{
|
|
if(count >= POOL_MAX_RECORDS)
|
|
break;
|
|
int h = FileOpen(POOL_DIR + "\\" + found, FILE_COMMON | FILE_READ | FILE_CSV | FILE_ANSI |
|
|
FILE_SHARE_READ | FILE_SHARE_WRITE, ',');
|
|
if(h == INVALID_HANDLE)
|
|
continue;
|
|
int ver = (int)FileReadNumber(h);
|
|
//--- Version mismatch: SKIP, never reinterpret. Reading v2 columns as v1 would produce a
|
|
//--- plausible-looking record built from the wrong fields, which is worse than one fewer member.
|
|
if(ver != POOL_RECORD_VERSION)
|
|
{
|
|
FileClose(h);
|
|
continue;
|
|
}
|
|
SPoolRecord r;
|
|
r.symbol = FileReadString(h);
|
|
r.timeframe = (int)FileReadNumber(h);
|
|
r.targetRR = FileReadNumber(h);
|
|
r.chancePct = FileReadNumber(h);
|
|
r.winPct = FileReadNumber(h);
|
|
r.effN = FileReadNumber(h);
|
|
r.lifespanBars = FileReadNumber(h);
|
|
r.eraCount = (long)FileReadNumber(h);
|
|
r.stamp = (datetime)(long)FileReadNumber(h);
|
|
FileClose(h);
|
|
//--- POOLABILITY. Symbol deliberately does NOT have to match - that is the entire point - but
|
|
//--- everything that changes what the numbers MEAN does.
|
|
if(r.timeframe != (int)_Period)
|
|
continue; // different bar semantics
|
|
if(MathAbs(r.targetRR - BARRIER_TARGET_RR) > 0.01)
|
|
continue; // different structural break-even
|
|
if(r.effN < 2.0 || r.chancePct <= 0.0 || r.chancePct >= 100.0)
|
|
continue; // no usable estimate
|
|
if((TimeCurrent() - r.stamp) > POOL_MAX_AGE_HOURS * 3600)
|
|
continue; // stale: a stopped chart is not evidence about now
|
|
rec[count++] = r;
|
|
}
|
|
while(FileFindNext(searchHandle, found));
|
|
FileFindClose(searchHandle);
|
|
if(count <= 0)
|
|
return 0;
|
|
//--- FIXED-EFFECTS COMBINATION. Each symbol is scored against ITS OWN chance rate, so symbols with
|
|
//--- different geometries and different drifts are directly comparable in this one currency.
|
|
double sumInvVar = 0.0;
|
|
for(int i = 0; i < count; i++)
|
|
{
|
|
double c = rec[i].chancePct / 100.0;
|
|
double var = c * (1.0 - c) / rec[i].effN; // in fraction^2
|
|
if(var <= 0.0)
|
|
continue;
|
|
sumInvVar += 1.0 / var;
|
|
}
|
|
if(sumInvVar <= 0.0)
|
|
return 0;
|
|
double weighted = 0.0, sumWSd = 0.0;
|
|
for(int i = 0; i < count; i++)
|
|
{
|
|
double c = rec[i].chancePct / 100.0;
|
|
double var = c * (1.0 - c) / rec[i].effN;
|
|
if(var <= 0.0)
|
|
continue;
|
|
double w = (1.0 / var) / sumInvVar;
|
|
weighted += w * (rec[i].winPct - rec[i].chancePct); // percentage points
|
|
//--- Perfectly-correlated bound: the weighted sum of the individual standard deviations, which
|
|
//--- is what the pooled SE degenerates to when every member moves together.
|
|
sumWSd += w * MathSqrt(var) * 100.0;
|
|
detail += StringFormat("%s%s %.0f%%/%.0f%% n%.0f w%.2f", (detail == "" ? "" : " "),
|
|
rec[i].symbol, rec[i].winPct, rec[i].chancePct, rec[i].effN, w);
|
|
}
|
|
pooledExcessPp = weighted;
|
|
seIndep = 100.0 * MathSqrt(1.0 / sumInvVar);
|
|
seCorr = sumWSd;
|
|
return count;
|
|
}
|
|
|
|
//+------------------------------------------------------------------+
|
|
//| The cross-instrument verdict, as one log line and one boolean. |
|
|
//| |
|
|
//| Gates on the PESSIMISTIC bound. A pooled edge that clears SE_CORR |
|
|
//| cannot be explained by the members being correlated, because that |
|
|
//| bound already assumes they are perfectly correlated. |
|
|
//+------------------------------------------------------------------+
|
|
bool CExpertSignalAIBase::PooledGatePasses(string &report)
|
|
{
|
|
report = "";
|
|
double excess = 0.0, seIndep = 0.0, seCorr = 0.0;
|
|
string detail = "";
|
|
int members = ReadPooledEvidence(excess, seIndep, seCorr, detail);
|
|
if(members < POOL_MIN_INSTRUMENTS)
|
|
{
|
|
report = StringFormat(" | POOL %d/%d instruments - not enough to certify across symbols yet"
|
|
" (run more charts on this timeframe at the same %.1f:1 ratio; each one is"
|
|
" worth far more independent evidence than more bars of the same symbol)",
|
|
members, POOL_MIN_INSTRUMENTS, BARRIER_TARGET_RR);
|
|
return false;
|
|
}
|
|
double bar = EDGE_MIN_SIGMAS * seCorr;
|
|
bool pass = (excess > bar);
|
|
//--- The credit the pool WOULD earn if its members were independent. Printed because the gap between
|
|
//--- the two bounds is the whole cost of refusing to assume independence, and it is the number that
|
|
//--- says whether adding a genuinely uncorrelated instrument is worth more than another correlated one.
|
|
double credit = (seIndep > 0.0) ? seCorr / seIndep : 1.0;
|
|
report = StringFormat(" | POOLED CERTIFICATE across %d instruments: excess %+.2fpp vs a %.2fpp bar"
|
|
" (%.0f x SE %.2fpp, the ALL-CORRELATED bound; SE would be %.2fpp if the"
|
|
" instruments were independent, a %.1fx diversification credit this gate"
|
|
" deliberately declines to claim) -> %s [%s]",
|
|
members, excess, bar, EDGE_MIN_SIGMAS, seCorr, seIndep, credit,
|
|
(pass ? "PASSES" : "fails"), detail);
|
|
return pass;
|
|
}
|
|
//+------------------------------------------------------------------+
|