forked from animatedread/Warrior_EA
8f2164698b
Step 3 of the swing-pivot plan, whole-hog. The swing label is now the ONE target and the era verdict is precision + recall per class against the label's own base rate - no win rate, no break-even, no expectancy, no geometry anywhere in training. DELETED - Expert/Excursion/ (4), Expert/BarrierHorizon/ (4), GeometrySweep, FirstPassageLadder, Labeling/TripleBarrier.mqh (CLabelOverlap survives in Labeling/LabelOverlap.mqh), 3 test EAs. - TripleBarrierLabel + walk, fractal label, geometry derivation/scan/ adoption, exit-policy replay, excursion MI targets, the drift verdict (DIRECTION_INTELLIGENT), the recall floor, balanced-accuracy telemetry, the barrier defines, the .cfg geometry adopt (slots kept as zeros for the positional layout), the derived-geometry live-order override. - TRAINING_TARGET input/enum: direction models are always swing; META2 re-keys the meta head onto label agreement (descriptor loses its two geometry slots). REWORKED - Labels.mqh (1795 -> ~370 lines): AdvanceSwingLabelState with FINALITY-GATED CACHING - an unresolved bar (pivot pair uncommitted) is never cached, so it can never freeze as a false Neutral; training, calibration, OOS scoring and online learning all skip unresolved bars. - SDeployVerdict: significance-only; SOosTally chance = larger directional class share; pooled gate poolability = timeframe (record v2). - Purge/embargo/declustering gaps: the measured mean label resolution lag (LabelResolutionBars), not a barrier horizon. - Pool purge key + backfill DB rows: marked at the bar the label resolved on (m_labelResolveAge), not a fabricated barrier touch. - Online learning frontier: finality, not a horizon delay. - m_bestBalancedOos -> m_bestSelectionScore, m_erasSinceBestBalanced -> m_erasSinceBest, ensemble vote outcome arrays -> label arrays. STEP 4 folded in: Entry_Multiplier / SL_Mode / TP_Mode / tradingdirection are inputs again - trade management is the tester GA's search space. Fingerprints: every direction model re-keys (TGT:SWG1 now unconditional, CUT token gone); META1 -> META2. Full retrain, as planned. Compile-verified in _claude_stage: Warrior_EA + both surviving test EAs, 0 errors, 0 warnings each. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
66 lines
4.3 KiB
MQL5
66 lines
4.3 KiB
MQL5
//+------------------------------------------------------------------+
|
|
//| Warrior_EA |
|
|
//| AnimateDread |
|
|
//| |
|
|
//| A READ-ONLY VIEW of one model's training data. |
|
|
//+------------------------------------------------------------------+
|
|
#ifndef WARRIOR_TRAINING_ITRAININGDATA_MQH
|
|
#define WARRIOR_TRAINING_ITRAININGDATA_MQH
|
|
//+------------------------------------------------------------------+
|
|
//| WHAT A TRAINING-SIDE COLLABORATOR IS ALLOWED TO SEE. |
|
|
//| |
|
|
//| Everything that analyses a model's data - baselines, geometry |
|
|
//| scans, redundancy reports - needs the same handful of things: a |
|
|
//| feature row, a label, an outcome, an excursion, and the shape |
|
|
//| they all share. Before this, each one reached straight into |
|
|
//| CExpertSignalAIBase's members, which is why a 951-line diagnostic |
|
|
//| could not be moved, tested or replaced without moving the signal |
|
|
//| class with it. |
|
|
//| |
|
|
//| Every accessor is BOUNDS-CHECKED and returns false rather than |
|
|
//| reading past a cache. The caller asks "is there a label at r?" |
|
|
//| and never "how long is the label array?", so a short cache is a |
|
|
//| missing row here instead of an out-of-range read at each of the |
|
|
//| thirty-odd call sites that used to do the test themselves. |
|
|
//| |
|
|
//| MQL5 has interfaces, but a class may implement one only if it |
|
|
//| inherits nothing else, and CExpertSignalAIBase is already a |
|
|
//| CExpertSignalCustom. So this is an abstract class and the signal |
|
|
//| exposes itself through a small ADAPTER that does inherit it - see |
|
|
//| CAIBaseTrainingData. Collaborators depend on this and never on |
|
|
//| the signal. |
|
|
//+------------------------------------------------------------------+
|
|
class CTrainingDataView
|
|
{
|
|
public:
|
|
~CTrainingDataView(void) { }
|
|
//--- SHAPE: the geometry every row shares.
|
|
virtual int HistoryBars(void) = 0; // bars per feature window
|
|
virtual int FeaturesPerBar(void) = 0; // columns per bar
|
|
virtual int LabelResolutionBars(void) = 0; // mean label resolution lag; also the declustering gap
|
|
virtual int PurgeBars(void) = 0; // purge width between fitted and held-out spans
|
|
virtual int CalibrationHiIndex(const int totalIter, const int oosCutoff) = 0;
|
|
//--- ROWS: false means "this bar has nothing to say", never a partial answer.
|
|
virtual bool HasLabel(const int bar) = 0;
|
|
virtual bool IsBuyLabel(const int bar) = 0;
|
|
virtual bool IsSellLabel(const int bar) = 0;
|
|
virtual bool RowFeatures(const int bar, const int width, double &x[]) = 0;
|
|
//--- THE MODEL'S OWN CALL on a bar, as the chart drew it: which way and how strongly.
|
|
//--- False = it said nothing (never scored, or scored Neutral). Direction rather than a raw
|
|
//--- double on purpose - turning one into the other needs the head's output width, which is the
|
|
//--- model's business and not a reader's.
|
|
virtual bool DirectionalCall(const int bar, bool &isBuy, double &magnitude) = 0;
|
|
//--- IDENTITY, for log lines and for the once-per-chart guards.
|
|
virtual string Id(void) = 0;
|
|
virtual bool IsEnsembleMember(void) = 0;
|
|
virtual int EnsembleIndex(void) = 0;
|
|
//--- The net's own gate on this chart, for the row every baseline is read against. False when
|
|
//--- the gate has not scored yet, which is NOT the same as a gate that scored zero.
|
|
virtual bool GateReference(double &precPct, int &calls, double &chancePct) = 0;
|
|
//--- POLICY the collaborator must not re-derive: overlapping labels are worth less than their
|
|
//--- count, and only the model knows its own overlap - see EffectiveSampleSize.
|
|
virtual double EffectiveSampleSize(const double rawN) = 0;
|
|
virtual bool Stopping(void) = 0;
|
|
};
|
|
#endif // WARRIOR_TRAINING_ITRAININGDATA_MQH
|
|
//+------------------------------------------------------------------+
|