Merge pull request #19 from pietro1991-dot/devin/1781688049-validazione-esterna

* PaPP v2 Modello: validazione esterna multi-simbolo (no pollution) Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * PaPP v2 Modello: modello mean-reversion (rev/speed/disc) pooled 4 FX + LOSO + doc Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: Pietro Giacobazzi <giacobazzipietro@gmail.com> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
PaPP v2 Modello: modello mean-reversion (rev/speed/disc) pooled 4 FX + LOSO + doc
2026-06-17 11:57:13 +02:00 · 2026-06-17 09:28:15 +00:00 · 2026-06-17 09:21:43 +00:00 · 2026-06-17 11:15:06 +02:00 · 2026-06-17 07:48:33 +00:00 · 2026-06-17 07:48:26 +00:00
42 changed files with 2105 additions and 31 deletions
@@ -0,0 +1,3 @@
+data/*.csv
+scripts/__pycache__/
+*.pyc
@@ -0,0 +1,129 @@
+# PaPP v2 — Analisi dei pattern di incrocio
+
+Questa cartella contiene l'analisi statistica di **cosa succede dopo che due linee
+si incrociano** (le 9 linee del sistema: prezzo, Mediana, 7 MA), gli script per
+riprodurla e i risultati.
+
+Risultati di riferimento: **EURUSD D1, dal 1999** (l'euro reale esiste dal 1999;
+i dati pre-1999 forniti dal broker sono sintetici e vengono esclusi).
+
+---
+
+## 1. Da dove vengono i dati
+
+I dati sono generati in MetaTrader dallo script `PaPP v2/PaPP_CrossExport.mq5`,
+ancorato a **D1** esattamente come l'indicatore. Produce due file:
+
+| file | contenuto |
+|---|---|
+| `PaPP_crosses_<SYM>_D1.csv` | un record per **ogni incrocio** tra le 9 linee |
+| `PaPP_bars_<SYM>_D1.csv` | un record per **ogni giorno D1** (la *baseline*) |
+
+Per ogni record sono salvati:
+- **contesto** al momento dell'evento: distanza dalla Mediana, ampiezza del
+  cluster, trend (sopra/sotto MA365), e le metriche **velocita' / accelerazione /
+  volatilita'** calcolate come **mediana delle 7 scale** (no ATR di MetaTrader);
+- **esiti futuri** a 1/3/5/10/20 giorni: rendimento, max favorevole/avverso,
+  ritorno alla Mediana, e la **traiettoria completa** `cret_1 … cret_20`
+  (rendimento cumulato giorno per giorno, **in percentuale**).
+
+Le 36 coppie sono tutte le combinazioni delle 9 linee; ogni coppia ha 2 direzioni
+(`dir=+1` la 1a linea passa sopra la 2a, `dir=-1` sotto) → 72 casi.
+
+---
+
+## 2. Le 3 correzioni metodologiche (perche' l'analisi e' "onesta")
+
+Una media grezza dei rendimenti dopo un incrocio e' fuorviante. Abbiamo corretto
+i tre problemi tipici:
+
+### 2.1 Bias di periodo → confronto con una baseline nello stesso regime
+Non confrontiamo il rendimento post-incrocio con **zero**, ma con quello di un
+**giorno qualunque nello stesso regime di mercato**. Il regime e' definito da:
+`trend (sopra/sotto MA365) × tercile del cluster × tercile della velocita'`.
+
+`extra-rendimento = rendimento dopo l'incrocio − rendimento medio della baseline
+nello stesso regime`
+
+Se l'extra e' ~0, l'incrocio non aggiunge nulla oltre al contesto.
+(Su EURUSD il drift di fondo della baseline e' risultato ~0, quindi non c'era un
+bias rialzista che gonfiava i numeri.)
+
+### 2.2 "Movimenti piccoli" → effetto in unita' di volatilita'
+L'extra-rendimento e' espresso anche come **frazione della deviazione standard**
+del movimento tipico a quell'orizzonte (`eff = extra / sd_baseline_h`), cosi' un
+0.3% pesa diversamente a 5 o a 20 giorni.
+
+### 2.3 Finestre sovrapposte + tanti test → bootstrap a blocchi + multi-test
+- Gli eventi vicini condividono il futuro (autocorrelazione) → la significativita'
+  e' calcolata con **block bootstrap** (blocchi temporali di 20 giorni), non con il
+  t-test classico.
+- Testiamo 72 casi × 5 orizzonti → alcuni "vincono" per fortuna. Applichiamo la
+  correzione **Benjamini-Hochberg** (`q-value`): consideriamo robusti solo i casi
+  con `q < 0.10`.
+
+---
+
+## 3. Verifiche di correttezza
+
+Lo script `full_table.py` esegue 4 controlli automatici:
+- **V1** la direzione registrata coincide col segno di (A−B) all'incrocio (~99.9%);
+- **V2** `cret_1` coincide esattamente con `ret_1` (differenza 0);
+- **V3** ricalcolo indipendente della media di un pattern (combacia col summary);
+- **V4** la baseline ha drift ~0 (atteso su FX).
+
+---
+
+## 4. Come riprodurre
+
+```bash
+# 1) genera i due CSV da MetaTrader (PaPP_CrossExport.mq5) e copiali in ./data
+# 2) dalla cartella scripts:
+cd scripts
+python excess_analysis.py EURUSD 1999     # summary + top per orizzonte
+python full_table.py      EURUSD 1999     # verifiche + tabella 72 casi
+python plot_trajectories.py EURUSD 1999   # grafico traiettorie extra-rendimento
+```
+Dipendenze: `pandas`, `numpy`, `matplotlib`. I risultati finiscono in `./results`.
+
+---
+
+## 5. Risultati principali (EURUSD, 1999+)
+
+**A) Mean-reversion (il segnale piu' robusto, vale per quasi tutte le coppie):**
+dopo un incrocio il prezzo torna a toccare la Mediana entro 20 giorni nel
+**77–94%** dei casi, in **2–4 giorni** mediani.
+
+**B) Edge direzionali significativi (q<0.10), legati alle scale lunghe:**
+- SALGONO: `MA365xMA7 +`, `MA365xMA182 ±`, `MA365xMA121 −`, `MA121xMA7 +`,
+  `MA121xMA3 +`, `PRICExMA121 −`;
+- SCENDONO: `MA182xMA30 +`, `MA365xMA121 +` (forte a 20g);
+- gli incroci tra MA cortissime e prezzo↔MA brevi sono **neutri** (rumore).
+
+**Lettura onesta:** gli edge direzionali sono **reali ma modesti** (~0.1–0.3 sigma,
+0.2–0.5% di extra, 55–59% di probabilita' di battere la baseline). Il tema
+ricorrente e' la **MA121 (semestrale)**. I casi con pochi campioni (n<40) vanno
+trattati con cautela anche se "significativi".
+
+Vedi `results/tabella_incroci_EURUSD_1999.md` per la tabella completa dei 72 casi.
+
+---
+
+## 6. Contenuto della cartella
+
+```
+Analisi/
+├── README.md                 questo documento
+├── scripts/
+│   ├── _common.py            utility (load, regime, bootstrap, BH)
+│   ├── excess_analysis.py    extra-rendimento + significativita'
+│   ├── full_table.py         verifiche + tabella 72 casi
+│   └── plot_trajectories.py  grafico traiettorie
+├── results/
+│   ├── summary_EURUSD_1999.csv
+│   ├── tabella_incroci_EURUSD_1999.csv
+│   ├── tabella_incroci_EURUSD_1999.md
+│   └── trajectories_EURUSD_1999.png
+└── data/
+    └── README.md             dove mettere i CSV di input (non versionati)
+```
@@ -0,0 +1,13 @@
+# Dati di input
+
+Gli script in `../scripts` leggono da questa cartella i due CSV prodotti dallo
+script MQL5 `PaPP v2/PaPP_CrossExport.mq5` (eseguito in MetaTrader):
+
+- `PaPP_crosses_<SYMBOL>_D1.csv` — un record per **incrocio** tra le 9 linee
+  (prezzo, Mediana, 7 MA), con contesto + esiti futuri.
+- `PaPP_bars_<SYMBOL>_D1.csv` — un record per **ogni giorno D1** (baseline),
+  con lo stesso regime e la traiettoria `cret_1..20`.
+
+I file dati **non sono versionati** (sono grandi e dipendono dal broker).
+Per riprodurre l'analisi: genera i due CSV da MetaTrader e copiali qui, poi
+lancia gli script (vedi `../README.md`).
@@ -0,0 +1,65 @@
+pair,dir,n,raw_1,exc_1,eff_1,pos_1,p_1,raw_3,exc_3,eff_3,pos_3,p_3,raw_5,exc_5,eff_5,pos_5,p_5,raw_10,exc_10,eff_10,pos_10,p_10,raw_20,exc_20,eff_20,pos_20,p_20,q_1,q_3,q_5,q_10,q_20
+MA121xMA14,-1,73,0.08883123287671232,0.0738440967816724,0.1268396325759725,0.5342465753424658,0.077,0.1377391780821918,0.10205717603308966,0.1030845124068534,0.4931506849315068,0.237,0.13806506849315067,0.09286285233037742,0.07319339008513785,0.547945205479452,0.375,0.12088643835616443,0.019819180009174625,0.011012627551783014,0.4520547945205479,0.923,-0.061453287671232926,-0.2486090503677838,-0.09775445144285876,0.410958904109589,0.264,0.4106666666666667,0.6067199999999999,0.7228235294117648,0.9527741935483871,0.6214193548387097
+MA121xMA14,1,73,0.08970109589041095,0.08841645476774412,0.1518701037073849,0.6164383561643836,0.183,0.171722602739726,0.1640382872092089,0.16568954296299623,0.5205479452054794,0.007,0.1471627397260274,0.13240461945271742,0.10435973823202067,0.547945205479452,0.138,0.16662917808219183,0.1383347923764789,0.07686642662260364,0.547945205479452,0.029,0.2644176712328766,0.2490256435298178,0.09791825817462992,0.547945205479452,0.074,0.732,0.07466666666666667,0.6308571428571429,0.2651428571428572,0.6214193548387097
+MA121xMA3,-1,117,0.05220358974358977,0.04398986786725697,0.07555998272746543,0.42735042735042733,0.304,0.04510350427350427,0.01416661259177849,0.014309217717397828,0.48717948717948717,0.871,0.06861871794871795,0.021877594054191637,0.01724365809953614,0.49572649572649574,0.917,0.2250457264957265,0.13531015620709289,0.07518577224650531,0.5213675213675214,0.218,0.09543794871794872,-0.053395235693741994,-0.020995301527366637,0.452991452991453,0.734,0.8202105263157895,0.9779649122807017,0.9406984126984127,0.6678260869565217,0.8936727272727273
+MA121xMA3,1,117,-0.03262435897435896,-0.03502834140056345,-0.06016705663188382,0.5384615384615384,0.393,0.1085807692307692,0.09438643424690306,0.09533655476621142,0.5042735042735043,0.15,0.16597222222222224,0.13826618338430888,0.10897975285129598,0.5042735042735043,0.164,0.2847652991452991,0.23515049270743255,0.13066255988423547,0.5897435897435898,0.003,0.22466495726495722,0.13930786769167774,0.05477662284509896,0.49572649572649574,0.375,0.8202105263157895,0.4896,0.6684444444444444,0.048,0.6666666666666666
+MA121xMA30,-1,52,-0.020661538461538457,-0.0237911422942284,-0.040865280756085726,0.4807692307692308,0.831,-0.07388230769230766,-0.07690927545575411,-0.07768346595588999,0.5576923076923077,0.721,-0.12157519230769233,-0.114888060239567,-0.09055339566054517,0.4423076923076923,0.707,-0.27518923076923074,-0.3105672292466324,-0.17256825074998694,0.4807692307692308,0.43,-0.3224990384615384,-0.42409334989842495,-0.16675584705606972,0.46153846153846156,0.296,0.9467936507936509,0.9228799999999999,0.8872156862745098,0.833939393939394,0.6214193548387097
+MA121xMA30,1,53,0.08432094339622644,0.08607884816227486,0.1478548719438829,0.6415094339622641,0.022,0.0901020754716981,0.08913430535697553,0.09003155646270568,0.5471698113207547,0.091,0.09538396226415095,0.08448989403948784,0.06659392445413015,0.5660377358490566,0.307,-0.029476415094339632,-0.0497229199320908,-0.027628791793896622,0.41509433962264153,0.696,-0.012036037735849067,-0.03067699468685477,-0.012062363711589094,0.5660377358490566,0.847,0.2773333333333333,0.416,0.7228235294117648,0.9474098360655738,0.9346206896551724
+MA121xMA7,-1,88,0.07495238636363637,0.06364985841309972,0.10932931685114719,0.48863636363636365,0.281,0.07764045454545455,0.043606296058068095,0.044045249356668474,0.4318181818181818,0.685,0.10674397727272728,0.06296209107771732,0.049625967512090224,0.45454545454545453,0.68,0.11821409090909088,0.025940150893838124,0.014413775963417735,0.48863636363636365,0.748,0.1481702272727273,-0.01654939020211934,-0.006507311614475473,0.45454545454545453,0.945,0.8202105263157895,0.9228799999999999,0.8844799999999999,0.9474098360655738,0.9782857142857142
+MA121xMA7,1,88,0.06656613636363636,0.06872677868019474,0.11804977968245185,0.5795454545454546,0.197,0.15830397727272727,0.15216329709975998,0.15369501584741296,0.5795454545454546,0.018,0.2576479545454546,0.239825884966136,0.18902789555062602,0.5454545454545454,0.001,0.3227229545454545,0.2991385847331414,0.16621786665788313,0.5681818181818182,0.001,0.19040772727272728,0.15980304007422197,0.06283543780182936,0.5227272727272727,0.389,0.7416470588235294,0.16457142857142856,0.010666666666666666,0.021333333333333333,0.6728648648648649
+MA14xMA3,-1,413,0.018732493946731234,0.019495711743007522,0.0334871577020072,0.4891041162227603,0.466,0.05811405339805826,0.05033597672560418,0.05084267289150997,0.5084745762711864,0.062,0.022634417475728145,0.004728052246124062,0.0037265942592662146,0.4963680387409201,0.297,-0.02661601941747573,-0.027830847621834614,-0.01546435115720282,0.47699757869249393,0.283,-0.004355085158150855,-0.022630394656332584,-0.008898396145645172,0.4745762711864407,0.3,0.8202105263157895,0.33066666666666666,0.7228235294117648,0.6966153846153845,0.6214193548387097
+MA14xMA3,1,412,-0.003732427184466025,-0.0042915657702153115,-0.007371484643913094,0.4878640776699029,0.878,-0.03452007281553398,-0.03988291933152033,-0.04028439206782132,0.4975728155339806,0.264,-0.04675264563106798,-0.0575933632259271,-0.04539440039934409,0.46359223300970875,0.3,0.009159538834951474,0.011765943826390329,0.006537806160257662,0.5218446601941747,0.868,-0.05554092457420925,-0.06562692404933614,-0.025804868933107607,0.470873786407767,0.25,0.9467936507936509,0.6352592592592593,0.7228235294117648,0.9474098360655738,0.6214193548387097
+MA14xMA7,-1,383,0.003936057441253264,0.0020882087632935874,0.003586849102660063,0.4908616187989556,0.932,0.017638219895287948,0.01082872489342116,0.010937729898232244,0.5013054830287206,0.268,0.023900732984293183,0.011324957744819978,0.00892619631115032,0.4804177545691906,0.26,-0.054068979057591615,-0.06435243929014356,-0.035757758172790935,0.4699738903394256,0.151,0.05511498687664045,0.016967571614375454,0.006671742855004413,0.4830287206266319,0.248,0.9467936507936509,0.6352592592592593,0.7228235294117648,0.6678260869565217,0.6214193548387097
+MA14xMA7,1,382,-0.0006903926701570699,0.0018220445243756229,0.003129667340805309,0.4869109947643979,0.931,-0.022581282722513082,-0.025758127076624282,-0.02601741566263479,0.4581151832460733,0.551,0.010029188481675414,-0.0001709152586449735,-0.0001347133636709491,0.4790575916230366,0.99,0.020934383202099727,0.024244274020344084,0.013471453406539668,0.5,0.224,0.0999728083989501,0.09411047957551737,0.03700476025438057,0.4973821989528796,0.134,0.9467936507936509,0.9144888888888889,0.99,0.6678260869565217,0.6214193548387097
+MA182xMA121,-1,30,-0.07841333333333335,-0.07979096882524894,-0.13705438362389624,0.4,0.381,-0.13186333333333336,-0.13923038014068193,-0.14063191249157805,0.5,0.211,-0.20915666666666669,-0.2250881162338893,-0.17741176241736653,0.43333333333333335,0.0,-0.12362599999999999,-0.17644799079844736,-0.0980442179759313,0.5,0.417,0.41436733333333337,0.33319840545603613,0.13101545297246694,0.4666666666666667,0.204,0.8202105263157895,0.5973333333333334,0.0,0.833939393939394,0.6214193548387097
+MA182xMA121,1,31,0.005469354838709664,0.005930804715525939,0.01018715271474295,0.5483870967741935,0.883,-0.17420967741935484,-0.1661471549215242,-0.16781963913363782,0.5483870967741935,0.153,-0.3184922580645161,-0.31420679972467563,-0.24765404338251065,0.3548387096774194,0.046,-0.34026225806451604,-0.33899465157276687,-0.1883640916571304,0.3548387096774194,0.021,-0.46702466666666675,-0.4624251636271663,-0.18182812788542654,0.3870967741935484,0.0,0.9467936507936509,0.4896,0.32711111111111113,0.224,0.0
+MA182xMA14,-1,46,0.15412304347826086,0.14217416973434086,0.2442080035756289,0.5,0.0,0.2857415217391305,0.2571233697039764,0.2597116462025928,0.5869565217391305,0.0,0.2071847826086957,0.171448060576255,0.13513331178384638,0.5217391304347826,0.325,-0.09928499999999998,-0.20905151224177224,-0.11616052946640151,0.41304347826086957,0.427,0.14800260869565224,-0.07458470946041838,-0.029327119622323313,0.43478260869565216,0.804,0.0,0.0,0.7228235294117648,0.833939393939394,0.9083508771929825
+MA182xMA14,1,47,0.02657595744680852,0.027371215978263932,0.0470146583024122,0.5106382978723404,0.691,0.01741063829787233,0.004927755680655171,0.004977359861845885,0.5531914893617021,0.998,0.0006495744680851034,-0.022737164244711856,-0.01792116104803993,0.44680851063829785,0.884,-0.022737234042553203,-0.05318987605447526,-0.029555223487665976,0.425531914893617,0.689,-0.048247872340425546,-0.06350047154634395,-0.024968736066497244,0.425531914893617,0.762,0.9422978723404255,0.999,0.9406984126984127,0.9474098360655738,0.8936727272727273
+MA182xMA3,-1,85,-0.09941294117647062,-0.10679718080176766,-0.18344208627937292,0.4470588235294118,0.05,0.05273082352941179,0.02606567006587443,0.026328054466521728,0.49411764705882355,0.704,0.15997435294117648,0.11817045873361055,0.09314054291437561,0.5294117647058824,0.093,0.0777025882352941,-0.008570515770733375,-0.004762250409253931,0.5058823529411764,0.894,-0.1411765882352941,-0.29043387357038863,-0.11420020288600495,0.43529411764705883,0.232,0.35555555555555557,0.9228799999999999,0.496,0.9474098360655738,0.6214193548387097
+MA182xMA3,1,86,0.0698374418604651,0.0700915914742381,0.1203940747700236,0.5232558139534884,0.399,-0.005633953488372075,-0.014586499381746465,-0.014733331206447278,0.45348837209302323,0.852,0.04616872093023254,0.01856945567260769,0.01463622297405181,0.47674418604651164,0.885,0.15744883720930233,0.09773602792407764,0.054307517940716026,0.5465116279069767,0.561,-0.14362348837209307,-0.21674959256674572,-0.08522713670512076,0.4418604651162791,0.478,0.8202105263157895,0.9779649122807017,0.9406984126984127,0.9474098360655738,0.7438222222222223
+MA182xMA30,-1,35,0.000345142857142874,-0.00639372195911028,-0.010982290791425238,0.45714285714285713,0.886,-0.24531428571428568,-0.26509787608500746,-0.2677664262183302,0.34285714285714286,0.004,-0.3593151428571428,-0.3857562050012093,-0.30404842928973563,0.37142857142857144,0.013,-0.2841117142857143,-0.37521814952454474,-0.20849186139235856,0.42857142857142855,0.12,0.06680142857142857,-0.12502296447058353,-0.04915972001623338,0.45714285714285713,0.506,0.9467936507936509,0.0512,0.11885714285714286,0.64,0.7438222222222223
+MA182xMA30,1,36,-0.048224722222222224,-0.04621714866274137,-0.07938571139170819,0.5,0.373,-0.1100925,-0.11774658475991877,-0.11893185515551644,0.5555555555555556,0.169,-0.18590361111111106,-0.20336353989805037,-0.16028871105419773,0.4166666666666667,0.021,-0.32208666666666663,-0.33650870997062715,-0.18698276564025307,0.3888888888888889,0.0,0.30108914285714294,0.29981266194992334,0.11788799426722685,0.5555555555555556,0.0,0.8202105263157895,0.5150476190476191,0.168,0.0,0.0
+MA182xMA7,-1,66,-0.04358954545454546,-0.05050061533379705,-0.08674328447320295,0.5303030303030303,0.129,0.13645151515151513,0.10235803550251647,0.10338840041271781,0.5606060606060606,0.28,0.17344772727272728,0.12187603155843105,0.09606123111692019,0.6212121212121212,0.074,0.12494348484848483,0.010132061312829493,0.005629931082838358,0.4696969696969697,0.957,0.05132227272727275,-0.15314031847959297,-0.06021561887876152,0.42424242424242425,0.557,0.5897142857142857,0.64,0.4305454545454545,0.965,0.7749565217391305
+MA182xMA7,1,67,0.0076192537313432805,0.007690816049038089,0.01321026763660675,0.5223880597014925,0.927,-0.023750447761194032,-0.03375519602686864,-0.03409498536878306,0.43283582089552236,0.618,0.034717462686567155,0.008729420900812945,0.00688042519884507,0.44776119402985076,0.926,0.06607283582089549,0.023456423448585822,0.013033680254006787,0.5074626865671642,0.865,-0.26800970149253733,-0.31012847852817405,-0.12194423031052547,0.417910447761194,0.143,0.9467936507936509,0.9144888888888889,0.9406984126984127,0.9474098360655738,0.6214193548387097
+MA30xMA14,-1,186,0.0577908064516129,0.05259839919140563,0.0903465804077389,0.543010752688172,0.17,-0.0017063978494623539,-0.010112015633565624,-0.010213806040435803,0.45161290322580644,0.893,-0.06830774193548388,-0.08005346012548165,-0.06309718027811081,0.478494623655914,0.35,-0.012653118279569909,-0.025284888363596887,-0.014049676026344394,0.5161290322580645,0.857,-0.02853736559139785,-0.05713421272326213,-0.022465487942291914,0.5053763440860215,0.736,0.7253333333333334,0.9853793103448276,0.7228235294117648,0.9474098360655738,0.8936727272727273
+MA30xMA14,1,186,0.028153548387096782,0.03170731760067301,0.054462640748789,0.5268817204301075,0.374,0.016020537634408603,0.011875477638208995,0.01199501955194561,0.5,0.847,-0.0370360752688172,-0.051548816287307384,-0.04063016076138508,0.478494623655914,0.499,-0.015004569892473113,-0.02383805484556744,-0.013245735668765603,0.5161290322580645,0.877,-0.13373016129032259,-0.14118492834996732,-0.05551469346121136,0.45698924731182794,0.358,0.8202105263157895,0.9779649122807017,0.8661333333333333,0.9474098360655738,0.6582857142857143
+MA30xMA3,-1,259,-0.0686582945736434,-0.07045313085314982,-0.12101507934562955,0.444015444015444,0.0,-0.09360682170542636,-0.10294030448543791,-0.10397653067976174,0.4247104247104247,0.002,-0.02850724806201553,-0.04647059528236293,-0.036627567672481515,0.47104247104247104,0.179,-0.11155980620155038,-0.11046364200140908,-0.06137968103684801,0.4555984555984556,0.093,-0.12523593023255816,-0.1360730749117463,-0.05350468446125606,0.47104247104247104,0.193,0.0,0.032,0.6684444444444444,0.6109090909090908,0.6214193548387097
+MA30xMA3,1,258,0.003845116279069767,0.005820412909908539,0.009997536256906005,0.5271317829457365,0.915,-0.04823112403100775,-0.04900228621850522,-0.04949555707888578,0.49224806201550386,0.314,-0.02961368217054264,-0.03685357516921869,-0.029047547385211904,0.4496124031007752,0.566,-0.02533209302325577,-0.012891433059302676,-0.007163189941517431,0.5,0.892,0.033963837209302274,0.042444573151777756,0.01668944054546775,0.46511627906976744,0.768,0.9467936507936509,0.648258064516129,0.8661333333333333,0.9474098360655738,0.8936727272727273
+MA30xMA7,-1,217,-0.05117294930875576,-0.056314638355585346,-0.09672984502457939,0.4608294930875576,0.069,-0.06452811059907836,-0.0717807121141479,-0.07250327704643271,0.4470046082949309,0.11,-0.013609953917050683,-0.023106382430078936,-0.0182121744079565,0.5069124423963134,0.737,-0.12043755760368663,-0.11133827885959051,-0.061865677428109146,0.4838709677419355,0.24,-0.052397834101382504,-0.04586767788325113,-0.018035424228529984,0.4976958525345622,0.809,0.4014545454545455,0.46305882352941174,0.8899622641509434,0.6678260869565217,0.9083508771929825
+MA30xMA7,1,217,0.003779170506912438,0.009125723884904737,0.015674962725502214,0.5207373271889401,0.807,-0.0005046543778801771,-4.6403900819300904e-05,-4.687101559798865e-05,0.47465437788018433,0.999,0.02160400921658988,0.011743430538667134,0.009256031564660542,0.48847926267281105,0.885,0.0010320737327188937,0.010928539345289034,0.00607249812751899,0.5207373271889401,0.903,0.05348820276497695,0.060377308008461784,0.02374069091705335,0.47465437788018433,0.725,0.9467936507936509,0.999,0.9406984126984127,0.9474098360655738,0.8936727272727273
+MA365xMA3,-1,52,-0.04855076923076924,-0.055414123714596746,-0.09518305995752137,0.46153846153846156,0.286,-0.09403961538461539,-0.12269999145316907,-0.12393512424029882,0.4423076923076923,0.461,-0.0693607692307692,-0.1221366700679434,-0.09626666327433527,0.46153846153846156,0.305,-0.07728211538461537,-0.20408719617845544,-0.1134020821527723,0.4423076923076923,0.105,-0.12928634615384618,-0.3965028394292718,-0.1559071059826835,0.5192307692307693,0.014,0.8202105263157895,0.867764705882353,0.7228235294117648,0.6109090909090908,0.17066666666666666
+MA365xMA3,1,53,0.0277454716981132,0.03944546541478535,0.06775420863758708,0.5283018867924528,0.453,-0.11042018867924527,-0.09593619605608099,-0.09690191691569978,0.4339622641509434,0.388,0.05649377358490564,0.05409192357361935,0.0426346075230801,0.4716981132075472,0.605,0.13301754716981135,0.08737104766439538,0.04854816426772733,0.4716981132075472,0.358,-0.11447471698113201,-0.14433877731913455,-0.05675480429168384,0.41509433962264153,0.635,0.8202105263157895,0.7524848484848485,0.8661333333333333,0.8182857142857143,0.8646808510638297
+MA365xMA7,-1,45,-0.08103666666666666,-0.08923106924932349,-0.1532693408304292,0.4444444444444444,0.026,-0.08737622222222222,-0.11088535951052053,-0.11200156287387926,0.4666666666666667,0.293,0.06799755555555557,0.028631136728832742,0.022566719700993443,0.5777777777777777,0.725,0.11502799999999996,0.013962899947202765,0.007758555933705275,0.5111111111111111,0.892,0.005609333333333373,-0.23899853974037966,-0.09397554559418657,0.5111111111111111,0.357,0.2773333333333333,0.6466206896551724,0.8899622641509434,0.9474098360655738,0.6582857142857143
+MA365xMA7,1,46,0.0038217391304347843,0.008635565491361663,0.014833033400740497,0.6086956521739131,0.899,0.20962499999999995,0.22640806887844978,0.22868715647927684,0.5652173913043478,0.123,0.3370608695652174,0.3490665574814269,0.27513008771814923,0.5869565217391305,0.0,0.3500547826086956,0.3806829912027037,0.21152842829387347,0.5217391304347826,0.0,0.055503913043478265,0.1384013091555915,0.05442015902262408,0.45652173913043476,0.44,0.9467936507936509,0.46305882352941174,0.0,0.0,0.7220512820512821
+MA7xMA3,-1,783,-0.011259987228607916,-0.00975812807678263,-0.01676122308798532,0.4955300127713921,0.641,0.017358071519795654,0.01560250403940561,0.015759563254097973,0.5146871008939975,0.631,-0.0046635294117647105,-0.01147923416737819,-0.009047795143125342,0.4942528735632184,0.318,0.03795154731457801,0.029777241916376193,0.016545874985372265,0.49680715197956576,0.187,0.04697303457106272,0.03581190524176629,0.014081438897150272,0.48531289910600256,0.231,0.9323636363636364,0.9144888888888889,0.7228235294117648,0.6678260869565217,0.6214193548387097
+MA7xMA3,1,783,0.00861537675606641,0.00646313831490142,0.011101525035556403,0.49808429118773945,0.722,0.01716249042145593,0.013723166107400172,0.013861307375396486,0.5095785440613027,0.707,0.016700791826309083,0.013356612675784767,0.01052752244047766,0.4827586206896552,0.799,0.07514809706257983,0.06249071427303802,0.03472328125660524,0.5159642401021711,0.469,0.06313083120204603,0.028391969974839334,0.011163879376742887,0.48659003831417624,0.236,0.9467936507936509,0.9228799999999999,0.9406984126984127,0.8462222222222222,0.6214193548387097
+MEDxMA121,-1,84,0.13476738095238097,0.1342521365628516,0.23060058171634015,0.6428571428571429,0.0,0.2586453571428571,0.2501091238058481,0.25262679292313406,0.5952380952380952,0.0,0.3434838095238096,0.3255167069312205,0.256568377039313,0.5833333333333334,0.0,0.3004757142857143,0.2635298831974455,0.14643171165885227,0.5714285714285714,0.096,0.3823957142857143,0.33092119114937013,0.13012003973213382,0.5476190476190477,0.012,0.0,0.0,0.0,0.6109090909090908,0.17066666666666666
+MEDxMA121,1,91,0.08019505494505494,0.07113435068349859,0.12218518876196342,0.4945054945054945,0.04,-0.021887032967032947,-0.05134812811197136,-0.051865012879751,0.4725274725274725,0.548,0.03865461538461538,0.0007329198464039522,0.0005776786613029268,0.4725274725274725,0.921,0.11142747252747255,0.023207607627741874,0.012895424485469585,0.5164835164835165,0.883,0.0024489010989010673,-0.15220237822472207,-0.05984681559116825,0.5054945054945055,0.512,0.344,0.9144888888888889,0.9406984126984127,0.9474098360655738,0.7438222222222223
+MEDxMA14,-1,185,0.032015297297297296,0.02576974210266877,0.04426385807851503,0.5027027027027027,0.487,0.05068994594594595,0.033539059114855246,0.03387667276153632,0.5027027027027027,0.643,-0.015857783783783795,-0.04359209068399024,-0.034358764758901025,0.4594594594594595,0.566,-0.029033783783783792,-0.08171127707936293,-0.04540328413380422,0.5027027027027027,0.374,0.08017043243243241,-0.052804933089093314,-0.02076319128352251,0.4972972972972973,0.761,0.8202105263157895,0.9144888888888889,0.8661333333333333,0.8253793103448276,0.8936727272727273
+MEDxMA14,1,182,0.015483516483516483,0.01999690520857099,0.034348041615443144,0.46153846153846156,0.525,0.1268462087912088,0.13251803922698374,0.13385200325743654,0.5054945054945055,0.029,0.17036961538461537,0.17188403061779176,0.1354769381588161,0.532967032967033,0.059,0.14587467032967033,0.1614950869059967,0.08973556134589228,0.5274725274725275,0.132,0.18018712707182324,0.2308097174336803,0.09075565544388747,0.5384615384615384,0.011,0.8320000000000001,0.18560000000000001,0.3776,0.6498461538461539,0.17066666666666666
+MEDxMA182,-1,58,-0.022809137931034486,-0.02034156879114435,-0.03494005917786492,0.4827586206896552,0.614,0.007036206896551722,0.0022230272623963124,0.002245404883013482,0.46551724137931033,0.976,-0.01394482758620689,-0.02929424853310631,-0.02308937649800395,0.43103448275862066,0.815,0.028821551724137955,-0.010465656017253815,-0.005815294666567431,0.4827586206896552,0.866,-0.048383620689655175,-0.07670426764079707,-0.03016054160321107,0.41379310344827586,0.706,0.913860465116279,0.999,0.9406984126984127,0.9474098360655738,0.8936727272727273
+MEDxMA182,1,60,-0.05141766666666667,-0.06026824424805813,-0.10352082684448174,0.43333333333333335,0.235,0.04781166666666667,0.021414182490574342,0.021629743702848616,0.4666666666666667,0.829,0.0006648333333333163,-0.033655107046627795,-0.026526553046821413,0.5166666666666667,0.668,-0.03795049999999997,-0.13075443319485391,-0.0726543617270161,0.45,0.579,0.17888899999999996,-0.015228210882883987,-0.005987816610498588,0.45,0.994,0.791578947368421,0.9779649122807017,0.8844799999999999,0.9474098360655738,0.994
+MEDxMA3,-1,278,0.0016162230215827325,-0.0013541581255577132,-0.0023259939058275247,0.4784172661870504,0.98,0.05901579136690648,0.02813674104933946,0.028419973435759655,0.5323741007194245,0.533,0.03532474820143886,-0.020805920013216492,-0.01639897743168258,0.4892086330935252,0.656,0.11916438848920864,0.041241944307270115,0.02291629481931619,0.4748201438848921,0.61,0.0010353237410072069,-0.1184472277241612,-0.0465741040158174,0.44244604316546765,0.36,0.98,0.9144888888888889,0.8844799999999999,0.9474098360655738,0.6582857142857143
+MEDxMA3,1,274,0.009557919708029194,0.008903575935155169,0.01529338632939503,0.5255474452554745,0.86,0.03554923357664233,0.0316743286442259,0.03199317138704499,0.4927007299270073,0.617,0.04520335766423357,0.04004414771615872,0.031562318525261424,0.4708029197080292,0.598,0.05428197080291972,0.0728305922625407,0.040468686726284606,0.5218978102189781,0.476,-0.03939229927007301,0.006092626048882876,0.0023956542063691354,0.4708029197080292,0.963,0.9467936507936509,0.9144888888888889,0.8661333333333333,0.8462222222222222,0.9782857142857142
+MEDxMA30,-1,142,0.09557457746478873,0.09776959269544033,0.16793568822782315,0.5704225352112676,0.0,0.0356945070422535,0.02280826220621985,0.02303785661885766,0.5422535211267606,0.755,0.06607436619718313,0.03764384568598137,0.029670429159297504,0.4647887323943662,0.596,-0.01828098591549294,-0.04765629320824421,-0.026480460208646955,0.4788732394366197,0.694,0.12349077464788734,0.04999247118411797,0.01965731573185583,0.4859154929577465,0.734,0.0,0.9292307692307692,0.8661333333333333,0.9474098360655738,0.8936727272727273
+MEDxMA30,1,151,-0.045856,-0.0465670003137284,-0.07998664033256168,0.48344370860927155,0.069,-0.10282526666666669,-0.09594826670609755,-0.0969141090722904,0.45695364238410596,0.028,-0.02792053333333333,-0.016624814962354777,-0.013103480413284912,0.48344370860927155,0.344,-0.1730158,-0.12058887270215377,-0.06700581665555486,0.48344370860927155,0.093,-0.26233259999999997,-0.17042491921170735,-0.06701201933351998,0.47019867549668876,0.193,0.4014545454545455,0.18560000000000001,0.7228235294117648,0.6109090909090908,0.6214193548387097
+MEDxMA365,-1,37,-0.052988108108108105,-0.044443665841789014,-0.07633945692868081,0.4594594594594595,0.662,-0.08400891891891892,-0.06157995647948478,-0.06219983772297179,0.4864864864864865,0.624,-0.1621889189189189,-0.14576280294546232,-0.1148884987716481,0.43243243243243246,0.176,0.024111081081081055,0.04505525828960639,0.025035182008697174,0.5135135135135135,0.761,-0.05749944444444447,0.018377259173368816,0.0072260397876034365,0.40540540540540543,0.016,0.9415111111111112,0.9144888888888889,0.6684444444444444,0.9474098360655738,0.17066666666666666
+MEDxMA365,1,33,0.04310818181818182,0.033538262652949624,0.057607596240413346,0.3939393939393939,0.467,-0.24473333333333333,-0.2613341902535032,-0.2639648540616853,0.45454545454545453,0.024,-0.2011839393939394,-0.22845028730182979,-0.1800617854603076,0.48484848484848486,0.0,0.007929090909090924,-0.07648707759406145,-0.04250043128312073,0.48484848484848486,0.391,-0.023826363636363684,-0.2655400486147341,-0.10441181344783067,0.48484848484848486,0.25,0.8202105263157895,0.18560000000000001,0.0,0.833939393939394,0.6214193548387097
+MEDxMA7,-1,240,0.032916,0.028922037628442143,0.049678454826067274,0.5,0.273,0.07765416666666666,0.05252018029204549,0.05304886326827398,0.4875,0.309,0.10422920833333332,0.061008686719023736,0.048086317548386735,0.49166666666666664,0.36,0.071882375,-0.026142383843300174,-0.014526147724009906,0.4666666666666667,0.803,0.08066995833333333,-0.0952759562795003,-0.03746303213023842,0.45,0.523,0.8202105263157895,0.648258064516129,0.7228235294117648,0.9474098360655738,0.7438222222222223
+MEDxMA7,1,228,-0.017271403508771918,-0.014612735942202441,-0.025099827049393664,0.4780701754385965,0.692,-0.02944258771929824,-0.025152482353638195,-0.025405674348721083,0.4517543859649123,0.621,-0.04444464912280701,-0.0425041334698064,-0.03350124988858029,0.4824561403508772,0.578,0.06615530701754384,0.09176395309153222,0.05098910437306316,0.5087719298245614,0.459,-0.16573013157894737,-0.10527782017970046,-0.04139582024685679,0.4605263157894737,0.407,0.9422978723404255,0.9144888888888889,0.8661333333333333,0.8462222222222222,0.6854736842105262
+PRICExMA121,-1,192,-0.0011136458333333293,-0.004321236691526296,-0.0074224494321805026,0.5052083333333334,0.902,-0.010871927083333344,-0.029809491337830406,-0.03010956210134849,0.4895833333333333,0.583,0.09514203125000002,0.05954765934694924,0.046934753239454445,0.4739583333333333,0.384,0.3310727604166667,0.26758402338724646,0.1486844151477113,0.5572916666666666,0.006,0.32460203125,0.22753344857801383,0.08946740843803147,0.5208333333333334,0.184,0.9467936507936509,0.9144888888888889,0.7228235294117648,0.07680000000000001,0.6214193548387097
+PRICExMA121,1,192,-0.01707552083333333,-0.02508815448381743,-0.043093116923686614,0.4375,0.506,0.05637640624999999,0.02523433133294733,0.025488347242985227,0.546875,0.638,0.05928677083333333,0.011224987205133263,0.008847400726859207,0.53125,0.879,0.24070796875,0.1627908530956468,0.09045556037885953,0.5833333333333334,0.205,0.268875625,0.14933833036295596,0.05872065615642983,0.5104166666666666,0.475,0.8303589743589743,0.9144888888888889,0.9406984126984127,0.6678260869565217,0.7438222222222223
+PRICExMA14,-1,622,-0.0007665755627009639,-0.0018991178433711558,-0.0032620537046294576,0.49356913183279744,0.912,-0.0019257395498392205,-0.006407874566158778,-0.006472378042310187,0.4967845659163987,0.863,0.01326204180064309,0.006098477075160193,0.004806746726876642,0.477491961414791,0.908,0.054067636655948534,0.048405319518770785,0.02689666046418209,0.5209003215434084,0.567,0.0538585990338164,0.025635383517887092,0.010079974359787401,0.47266881028938906,0.266,0.9467936507936509,0.9779649122807017,0.9406984126984127,0.9474098360655738,0.6214193548387097
+PRICExMA14,1,623,-0.014676420545746376,-0.012730073428247585,-0.021866038135425148,0.47030497592295345,0.545,0.0014275884244372957,-0.0017997899895379008,-0.0018179071841660246,0.5104333868378812,0.353,0.01065803858520899,0.0017789860443975937,0.0014021755334454116,0.4799357945425361,0.313,0.018954067524115756,0.018142742565829078,0.010081106612527126,0.5008025682182986,0.216,0.009328470209339785,-0.0016065739848631821,-0.000631713762472983,0.478330658105939,0.301,0.8320000000000001,0.706,0.7228235294117648,0.6678260869565217,0.6214193548387097
+PRICExMA182,-1,140,-0.03597321428571429,-0.03340255555820349,-0.05737449652377054,0.4714285714285714,0.467,-0.14893500000000004,-0.15623978620456583,-0.15781254004350195,0.4,0.084,-0.0647025714285714,-0.08853573897542956,-0.06978281106690429,0.40714285714285714,0.504,-0.020481785714285727,-0.07441844204291212,-0.041350983482826315,0.45714285714285713,0.723,-0.12365392857142858,-0.18888427375986003,-0.0742703394758254,0.4142857142857143,0.512,0.8202105263157895,0.4135384615384616,0.8661333333333333,0.9474098360655738,0.7438222222222223
+PRICExMA182,1,139,-0.0896921582733813,-0.09121777580897454,-0.1566818428589591,0.37410071942446044,0.043,-0.20890776978417264,-0.22287974738094982,-0.22512331790053275,0.4316546762589928,0.0,-0.17689208633093526,-0.20531272749844615,-0.16182503741941978,0.4316546762589928,0.0,-0.037221366906474825,-0.0959753157129084,-0.05332916930073661,0.5035971223021583,0.601,-0.2234721582733813,-0.3121830074348682,-0.12275208242190383,0.41007194244604317,0.269,0.344,0.0,0.0,0.9474098360655738,0.6214193548387097
+PRICExMA3,-1,1365,0.009650820512820511,0.007866696390052672,0.013512371647677317,0.5194139194139195,0.546,0.004900637362637359,0.0005338891034665343,0.0005392633820510158,0.49523809523809526,0.967,-0.014673824175824178,-0.021474615265459643,-0.016926035035635823,0.4908424908424908,0.523,0.0031851612903225817,-0.01312927468962779,-0.007295347845621781,0.4981684981684982,0.312,0.023199125642909633,-0.01370675673718383,-0.005389572438822788,0.46886446886446886,0.3,0.8320000000000001,0.999,0.8661333333333333,0.7395555555555555,0.6214193548387097
+PRICExMA3,1,1365,-0.02202981684981685,-0.02273581944468149,-0.039052586602871024,0.4783882783882784,0.209,-0.03701229304029305,-0.041212891349244836,-0.04162775195970622,0.49523809523809526,0.138,-0.02945506598240469,-0.037629510780640175,-0.029659130558273072,0.5003663003663004,0.132,-0.03193128393250184,-0.047784958430012396,-0.02655195368948444,0.47985347985347987,0.178,-0.030928433823529382,-0.061740428492180005,-0.02427667741850723,0.4776556776556777,0.203,0.7431111111111111,0.4896,0.6308571428571429,0.6678260869565217,0.6214193548387097
+PRICExMA30,-1,427,0.017202927400468377,0.016748936289171738,0.0287691097534581,0.5292740046838408,0.482,0.02481250585480094,0.01723528755002068,0.017408782824930823,0.5128805620608899,0.739,0.04980238875878221,0.03435935517273575,0.027081633000940863,0.5058548009367682,0.609,-0.0037466042154566874,-0.0024782808638988425,-0.0013770692889511526,0.49882903981264637,0.965,-0.000713957845433267,-0.007468103997197523,-0.0029364997311411936,0.4707259953161593,0.96,0.8202105263157895,0.9273725490196079,0.8661333333333333,0.965,0.9782857142857142
+PRICExMA30,1,428,-0.0248903738317757,-0.023387683566524868,-0.04017227266184648,0.4602803738317757,0.48,-0.0617211475409836,-0.0655309759513266,-0.06619062927331552,0.4766355140186916,0.049,-0.013615925058548018,-0.024266764130097773,-0.019126773392219566,0.4696261682242991,0.29,-0.07462002341920372,-0.06491943693220595,-0.03607281327859661,0.4696261682242991,0.222,-0.054220702576112424,-0.048489250722391825,-0.019066241145406414,0.4929906542056075,0.286,0.8202105263157895,0.2850909090909091,0.7228235294117648,0.6678260869565217,0.6214193548387097
+PRICExMA365,-1,91,0.04233637362637362,0.051379225589190385,0.08825244508086891,0.5494505494505495,0.352,-0.03783879120879119,-0.01651874682732147,-0.01668502920083335,0.4725274725274725,0.916,-0.08764582417582417,-0.07071979625208016,-0.05574049799164656,0.45054945054945056,0.691,0.050201208791208776,0.05812351032993255,0.03229662231078432,0.5054945054945055,0.636,-0.037380659340659296,0.009720292990034775,0.0038220728798851783,0.46153846153846156,0.934,0.8202105263157895,0.9936271186440678,0.8844799999999999,0.9474098360655738,0.9782857142857142
+PRICExMA365,1,90,0.02415055555555556,0.01823703590189069,0.03132517064850537,0.5333333333333333,0.766,-0.09987566666666665,-0.12869613106931163,-0.12999162269223585,0.5111111111111111,0.119,-0.03710444444444445,-0.09106985104869357,-0.07178016790920748,0.5,0.285,-0.020465666666666653,-0.15015651256242515,-0.0834352251989804,0.5,0.272,-0.25178677777777786,-0.4833343703655808,-0.19004974343721462,0.4444444444444444,0.131,0.9467936507936509,0.46305882352941174,0.7228235294117648,0.6966153846153845,0.6214193548387097
+PRICExMA7,-1,943,0.0040334994697773085,0.0022016087035053853,0.0037816325366443436,0.5174973488865323,0.931,0.006369278897136809,0.0036908801335600087,0.003728033575971337,0.503711558854719,0.954,-0.021293319194061505,-0.024543468508016503,-0.019344868475054382,0.4867444326617179,0.551,-0.020223319194061496,-0.032993771526510784,-0.018333155921783178,0.5026511134676565,0.682,-0.011021698513800412,-0.04781024414862614,-0.018799252011075365,0.46659597030752914,0.275,0.9467936507936509,0.999,0.8661333333333333,0.9474098360655738,0.6214193548387097
+PRICExMA7,1,943,-0.030620678685047715,-0.03060022548503894,-0.052561024190461304,0.46447507953340406,0.111,-0.0391947613997879,-0.04300707032128343,-0.043439991644285206,0.4941675503711559,0.219,-0.027821029723991513,-0.03550596058707976,-0.027985373681522555,0.49204665959703076,0.188,-0.03401875796178344,-0.04477221200020043,-0.024877905907279303,0.4782608695652174,0.233,-0.04745296493092454,-0.06773696556330241,-0.026634548908210244,0.47720042417815484,0.247,0.5464615384615384,0.5973333333333334,0.6684444444444444,0.6678260869565217,0.6214193548387097
+PRICExMED,-1,641,0.021020873634945397,0.020767861465922702,0.035672288409384675,0.5241809672386896,0.383,0.029750327613104526,0.017480843427518426,0.01765681053728184,0.5085803432137286,0.698,0.049702854914196556,0.029052419946197283,0.02289877009672308,0.49453978159126366,0.646,0.038525850234009354,0.019713901742313477,0.010954129150653281,0.5101404056162246,0.82,-0.0002629017160686441,-0.02220791100080794,-0.008732273239305728,0.4711388455538221,0.897,0.8202105263157895,0.9228799999999999,0.8844799999999999,0.9474098360655738,0.9730169491525424
+PRICExMED,1,641,-0.017737067082683303,-0.018597079812694105,-0.031943606506588146,0.46801872074882994,0.371,-0.012760781249999995,-0.025778301267431636,-0.02603779293254773,0.5070202808112324,0.224,0.016005624999999975,-0.006679395257350678,-0.005264619493538456,0.49297971918876754,0.363,-0.019372687500000024,-0.034250126998993366,-0.019031256190547588,0.4711388455538221,0.279,-0.028446968750000003,-0.040138517270669895,-0.015782686638798674,0.4914196567862715,0.346,0.8202105263157895,0.5973333333333334,0.7228235294117648,0.6966153846153845,0.6582857142857143
@@ -0,0 +1,73 @@
+pair,dir,n,raw_1,exc_1,eff_1,pos_1,p_1,raw_3,exc_3,eff_3,pos_3,p_3,raw_5,exc_5,eff_5,pos_5,p_5,raw_10,exc_10,eff_10,pos_10,p_10,raw_20,exc_20,eff_20,pos_20,p_20,rev10,rev20,btr_med,q10,dopo_10g
+MA182xMA30,1,36,-0.048224722222222224,-0.04621714866274137,-0.07938571139170819,50.0,0.373,-0.1100925,-0.11774658475991877,-0.11893185515551644,55.55555555555556,0.169,-0.18590361111111106,-0.20336353989805037,-0.16028871105419773,41.66666666666667,0.021,-0.32208666666666663,-0.33650870997062715,-0.18698276564025307,38.88888888888889,0.0,0.30108914285714294,0.29981266194992334,0.11788799426722685,55.55555555555556,0.0,63.888888888888886,85.71428571428571,4.0,0.0,SCENDE (extra -)
+MA365xMA121,1,15,-0.06725866666666667,-0.058566438960441905,-0.10059769057760735,46.666666666666664,0.0,-0.018635333333333337,0.028778700115319186,0.02906839464310546,53.333333333333336,0.0,0.13790733333333333,0.208849745178588,0.1646128724719079,60.0,0.0,-0.2540478571428571,-0.13029592304024354,-0.07239958824198307,53.333333333333336,0.0,-1.1132885714285716,-0.9020608936587976,-0.3546953246360883,40.0,0.0,42.857142857142854,71.42857142857143,5.0,0.0,SCENDE (extra -)
+MA365xMA7,1,46,0.0038217391304347843,0.008635565491361663,0.014833033400740497,60.86956521739131,0.899,0.20962499999999995,0.22640806887844978,0.22868715647927684,56.52173913043478,0.123,0.3370608695652174,0.3490665574814269,0.27513008771814923,58.69565217391305,0.0,0.3500547826086956,0.3806829912027037,0.21152842829387347,52.17391304347826,0.0,0.055503913043478265,0.1384013091555915,0.05442015902262408,45.65217391304348,0.44,63.04347826086957,80.43478260869566,4.0,0.0,SALE (extra +)
+MA365xMA182,-1,16,0.11833625,0.09693051199759066,0.16649442627114283,50.0,0.0,0.202560625,0.16364152085364525,0.1652887826451773,50.0,0.0,0.18938187499999998,0.13167340689274035,0.1037834052334698,56.25,0.0,0.601891875,0.4523359166858753,0.2513427385214686,68.75,0.0,0.5659212499999999,0.21605763977409165,0.08495505704603279,56.25,0.0,56.25,68.75,4.0,0.0,SALE (extra +)
+MA365xMA121,-1,14,0.17198357142857143,0.1629340707798868,0.27986661862668516,71.42857142857143,0.0,0.4065378571428571,0.3874812569771546,0.39138175280623044,85.71428571428571,0.0,0.5851271428571427,0.5604673261957672,0.4417536464449268,71.42857142857143,0.0,0.5330257142857142,0.478114598100192,0.26566679315241315,78.57142857142857,0.0,1.191782142857143,1.0296555048052016,0.4048662303260845,78.57142857142857,0.0,50.0,71.42857142857143,3.0,0.0,SALE (extra +)
+MA365xMA182,1,16,0.17777875000000004,0.1885936498878568,0.32394125326852685,50.0,0.0,0.391371875,0.4316317402153096,0.4359766672849197,62.5,0.0,0.23858875,0.2984378579545668,0.2352251519878852,68.75,0.0,0.473659375,0.5563856908686655,0.30915852148482825,56.25,0.0,0.42106437500000005,0.6221694442657866,0.24464046115270321,62.5,0.0,75.0,81.25,4.0,0.0,SALE (extra +)
+MA121xMA7,1,88,0.06656613636363636,0.06872677868019474,0.11804977968245185,57.95454545454546,0.197,0.15830397727272727,0.15216329709975998,0.15369501584741296,57.95454545454546,0.018,0.2576479545454546,0.239825884966136,0.18902789555062602,54.54545454545454,0.001,0.3227229545454545,0.2991385847331414,0.16621786665788313,56.81818181818182,0.001,0.19040772727272728,0.15980304007422197,0.06283543780182936,52.27272727272727,0.389,72.72727272727273,86.36363636363636,3.0,0.010285714285714287,SALE (extra +)
+MA121xMA3,1,117,-0.03262435897435896,-0.03502834140056345,-0.06016705663188382,53.84615384615385,0.393,0.1085807692307692,0.09438643424690306,0.09533655476621142,50.427350427350426,0.15,0.16597222222222224,0.13826618338430888,0.10897975285129598,50.427350427350426,0.164,0.2847652991452991,0.23515049270743255,0.13066255988423547,58.97435897435898,0.003,0.22466495726495722,0.13930786769167774,0.05477662284509896,49.572649572649574,0.375,75.21367521367522,87.17948717948718,4.0,0.027,SALE (extra +)
+PRICExMA121,-1,192,-0.0011136458333333293,-0.004321236691526296,-0.0074224494321805026,50.520833333333336,0.902,-0.010871927083333344,-0.029809491337830406,-0.03010956210134849,48.95833333333333,0.583,0.09514203125000002,0.05954765934694924,0.046934753239454445,47.39583333333333,0.384,0.3310727604166667,0.26758402338724646,0.1486844151477113,55.729166666666664,0.006,0.32460203125,0.22753344857801383,0.08946740843803147,52.083333333333336,0.184,80.20833333333334,92.1875,3.0,0.048,SALE (extra +)
+MA182xMA121,1,31,0.005469354838709664,0.005930804715525939,0.01018715271474295,54.83870967741935,0.883,-0.17420967741935484,-0.1661471549215242,-0.16781963913363782,54.83870967741935,0.153,-0.3184922580645161,-0.31420679972467563,-0.24765404338251065,35.483870967741936,0.046,-0.34026225806451604,-0.33899465157276687,-0.1883640916571304,35.483870967741936,0.021,-0.46702466666666675,-0.4624251636271663,-0.18182812788542654,38.70967741935484,0.0,54.83870967741935,76.66666666666667,2.5,0.1512,neutro
+MA121xMA14,1,73,0.08970109589041095,0.08841645476774412,0.1518701037073849,61.64383561643836,0.183,0.171722602739726,0.1640382872092089,0.16568954296299623,52.054794520547944,0.007,0.1471627397260274,0.13240461945271742,0.10435973823202067,54.794520547945204,0.138,0.16662917808219183,0.1383347923764789,0.07686642662260364,54.794520547945204,0.029,0.2644176712328766,0.2490256435298178,0.09791825817462992,54.794520547945204,0.074,71.23287671232876,83.56164383561644,3.0,0.18981818181818183,neutro
+MA365xMA30,-1,21,0.046082857142857155,0.031842647608960044,0.054695092756136064,38.095238095238095,0.372,-0.02703523809523809,-0.037881073440558855,-0.03826239503043005,42.857142857142854,0.418,-0.022549999999999997,-0.03278555411434502,-0.02584118182059828,42.857142857142854,0.608,-0.08356952380952382,-0.14177247861337977,-0.07877659435655403,38.095238095238095,0.06,0.5890909523809524,0.3392334579854691,0.133388468953063,52.38095238095239,0.003,66.66666666666666,80.95238095238095,6.0,0.36000000000000004,neutro
+MEDxMA30,1,151,-0.045856,-0.0465670003137284,-0.07998664033256168,48.34437086092716,0.069,-0.10282526666666669,-0.09594826670609755,-0.0969141090722904,45.6953642384106,0.028,-0.02792053333333333,-0.016624814962354777,-0.013103480413284912,48.34437086092716,0.344,-0.1730158,-0.12058887270215377,-0.06700581665555486,48.34437086092716,0.093,-0.26233259999999997,-0.17042491921170735,-0.06701201933351998,47.019867549668874,0.193,82.0,92.0,3.0,0.4608,neutro
+MA30xMA3,-1,259,-0.0686582945736434,-0.07045313085314982,-0.12101507934562955,44.4015444015444,0.0,-0.09360682170542636,-0.10294030448543791,-0.10397653067976174,42.471042471042466,0.002,-0.02850724806201553,-0.04647059528236293,-0.036627567672481515,47.10424710424711,0.179,-0.11155980620155038,-0.11046364200140908,-0.06137968103684801,45.559845559845556,0.093,-0.12523593023255816,-0.1360730749117463,-0.05350468446125606,47.10424710424711,0.193,77.13178294573643,89.92248062015504,3.0,0.4608,neutro
+MEDxMA121,-1,84,0.13476738095238097,0.1342521365628516,0.23060058171634015,64.28571428571429,0.0,0.2586453571428571,0.2501091238058481,0.25262679292313406,59.523809523809526,0.0,0.3434838095238096,0.3255167069312205,0.256568377039313,58.333333333333336,0.0,0.3004757142857143,0.2635298831974455,0.14643171165885227,57.14285714285714,0.096,0.3823957142857143,0.33092119114937013,0.13012003973213382,54.761904761904766,0.012,75.0,86.90476190476191,3.0,0.4608,neutro
+MA365xMA3,-1,52,-0.04855076923076924,-0.055414123714596746,-0.09518305995752137,46.15384615384615,0.286,-0.09403961538461539,-0.12269999145316907,-0.12393512424029882,44.230769230769226,0.461,-0.0693607692307692,-0.1221366700679434,-0.09626666327433527,46.15384615384615,0.305,-0.07728211538461537,-0.20408719617845544,-0.1134020821527723,44.230769230769226,0.105,-0.12928634615384618,-0.3965028394292718,-0.1559071059826835,51.92307692307693,0.014,61.53846153846154,84.61538461538461,5.0,0.4725,neutro
+MA182xMA30,-1,35,0.000345142857142874,-0.00639372195911028,-0.010982290791425238,45.714285714285715,0.886,-0.24531428571428568,-0.26509787608500746,-0.2677664262183302,34.285714285714285,0.004,-0.3593151428571428,-0.3857562050012093,-0.30404842928973563,37.142857142857146,0.013,-0.2841117142857143,-0.37521814952454474,-0.20849186139235856,42.857142857142854,0.12,0.06680142857142857,-0.12502296447058353,-0.04915972001623338,45.714285714285715,0.506,74.28571428571429,88.57142857142857,4.0,0.5082352941176471,neutro
+MEDxMA14,1,182,0.015483516483516483,0.01999690520857099,0.034348041615443144,46.15384615384615,0.525,0.1268462087912088,0.13251803922698374,0.13385200325743654,50.54945054945055,0.029,0.17036961538461537,0.17188403061779176,0.1354769381588161,53.2967032967033,0.059,0.14587467032967033,0.1614950869059967,0.08973556134589228,52.74725274725275,0.132,0.18018712707182324,0.2308097174336803,0.09075565544388747,53.84615384615385,0.011,68.13186813186813,83.42541436464089,3.5,0.528,neutro
+MA14xMA7,-1,383,0.003936057441253264,0.0020882087632935874,0.003586849102660063,49.08616187989556,0.932,0.017638219895287948,0.01082872489342116,0.010937729898232244,50.13054830287206,0.268,0.023900732984293183,0.011324957744819978,0.00892619631115032,48.04177545691906,0.26,-0.054068979057591615,-0.06435243929014356,-0.035757758172790935,46.99738903394256,0.151,0.05511498687664045,0.016967571614375454,0.006671742855004413,48.30287206266319,0.248,76.70157068062828,89.76377952755905,3.0,0.5722105263157895,neutro
+MA365xMA14,1,28,0.026667142857142865,0.03498123966244576,0.06008615148960548,46.42857142857143,0.298,0.1704282142857143,0.18737662697316468,0.1892628130500779,57.14285714285714,0.0,0.0984778571428571,0.11082274884109121,0.08734916581471197,42.857142857142854,0.222,-0.2500064285714286,-0.21573985268097465,-0.11987693963888939,42.857142857142854,0.202,0.1012014814814815,0.21951720363596228,0.08631537666049734,57.14285714285714,0.021,53.57142857142857,81.48148148148148,7.0,0.5958620689655173,neutro
+MA30xMA7,-1,217,-0.05117294930875576,-0.056314638355585346,-0.09672984502457939,46.08294930875576,0.069,-0.06452811059907836,-0.0717807121141479,-0.07250327704643271,44.70046082949309,0.11,-0.013609953917050683,-0.023106382430078936,-0.0182121744079565,50.69124423963134,0.737,-0.12043755760368663,-0.11133827885959051,-0.061865677428109146,48.38709677419355,0.24,-0.052397834101382504,-0.04586767788325113,-0.018035424228529984,49.76958525345622,0.809,78.3410138248848,88.47926267281106,3.0,0.5958620689655173,neutro
+PRICExMA30,1,428,-0.0248903738317757,-0.023387683566524868,-0.04017227266184648,46.02803738317757,0.48,-0.0617211475409836,-0.0655309759513266,-0.06619062927331552,47.66355140186916,0.049,-0.013615925058548018,-0.024266764130097773,-0.019126773392219566,46.96261682242991,0.29,-0.07462002341920372,-0.06491943693220595,-0.03607281327859661,46.96261682242991,0.222,-0.054220702576112424,-0.048489250722391825,-0.019066241145406414,49.29906542056075,0.286,80.56206088992974,90.86651053864169,2.0,0.5958620689655173,neutro
+PRICExMA3,1,1365,-0.02202981684981685,-0.02273581944468149,-0.039052586602871024,47.83882783882784,0.209,-0.03701229304029305,-0.041212891349244836,-0.04162775195970622,49.523809523809526,0.138,-0.02945506598240469,-0.037629510780640175,-0.029659130558273072,50.03663003663004,0.132,-0.03193128393250184,-0.047784958430012396,-0.02655195368948444,47.985347985347985,0.178,-0.030928433823529382,-0.061740428492180005,-0.02427667741850723,47.765567765567766,0.203,69.4057226705796,84.92647058823529,4.0,0.5958620689655173,neutro
+PRICExMA7,1,943,-0.030620678685047715,-0.03060022548503894,-0.052561024190461304,46.447507953340406,0.111,-0.0391947613997879,-0.04300707032128343,-0.043439991644285206,49.41675503711559,0.219,-0.027821029723991513,-0.03550596058707976,-0.027985373681522555,49.20466595970308,0.188,-0.03401875796178344,-0.04477221200020043,-0.024877905907279303,47.82608695652174,0.233,-0.04745296493092454,-0.06773696556330241,-0.026634548908210244,47.720042417815485,0.247,71.44373673036092,86.07863974495218,3.0,0.5958620689655173,neutro
+PRICExMA14,1,623,-0.014676420545746376,-0.012730073428247585,-0.021866038135425148,47.03049759229535,0.545,0.0014275884244372957,-0.0017997899895379008,-0.0018179071841660246,51.04333868378812,0.353,0.01065803858520899,0.0017789860443975937,0.0014021755334454116,47.99357945425361,0.313,0.018954067524115756,0.018142742565829078,0.010081106612527126,50.08025682182986,0.216,0.009328470209339785,-0.0016065739848631821,-0.000631713762472983,47.8330658105939,0.301,76.52733118971061,90.01610305958133,3.0,0.5958620689655173,neutro
+MA14xMA7,1,382,-0.0006903926701570699,0.0018220445243756229,0.003129667340805309,48.69109947643979,0.931,-0.022581282722513082,-0.025758127076624282,-0.02601741566263479,45.811518324607334,0.551,0.010029188481675414,-0.0001709152586449735,-0.0001347133636709491,47.90575916230366,0.99,0.020934383202099727,0.024244274020344084,0.013471453406539668,50.0,0.224,0.0999728083989501,0.09411047957551737,0.03700476025438057,49.73821989528796,0.134,74.2782152230971,88.9763779527559,3.0,0.5958620689655173,neutro
+MA7xMA3,-1,783,-0.011259987228607916,-0.00975812807678263,-0.01676122308798532,49.55300127713921,0.641,0.017358071519795654,0.01560250403940561,0.015759563254097973,51.46871008939975,0.631,-0.0046635294117647105,-0.01147923416737819,-0.009047795143125342,49.42528735632184,0.318,0.03795154731457801,0.029777241916376193,0.016545874985372265,49.68071519795657,0.187,0.04697303457106272,0.03581190524176629,0.014081438897150272,48.53128991060026,0.231,72.63427109974424,86.68373879641486,3.0,0.5958620689655173,neutro
+MA121xMA3,-1,117,0.05220358974358977,0.04398986786725697,0.07555998272746543,42.73504273504273,0.304,0.04510350427350427,0.01416661259177849,0.014309217717397828,48.717948717948715,0.871,0.06861871794871795,0.021877594054191637,0.01724365809953614,49.572649572649574,0.917,0.2250457264957265,0.13531015620709289,0.07518577224650531,52.13675213675214,0.218,0.09543794871794872,-0.053395235693741994,-0.020995301527366637,45.2991452991453,0.734,74.35897435897436,91.45299145299145,4.0,0.5958620689655173,neutro
+PRICExMA121,1,192,-0.01707552083333333,-0.02508815448381743,-0.043093116923686614,43.75,0.506,0.05637640624999999,0.02523433133294733,0.025488347242985227,54.6875,0.638,0.05928677083333333,0.011224987205133263,0.008847400726859207,53.125,0.879,0.24070796875,0.1627908530956468,0.09045556037885953,58.333333333333336,0.205,0.268875625,0.14933833036295596,0.05872065615642983,51.041666666666664,0.475,78.64583333333334,92.1875,3.0,0.5958620689655173,neutro
+PRICExMA365,1,90,0.02415055555555556,0.01823703590189069,0.03132517064850537,53.333333333333336,0.766,-0.09987566666666665,-0.12869613106931163,-0.12999162269223585,51.11111111111111,0.119,-0.03710444444444445,-0.09106985104869357,-0.07178016790920748,50.0,0.285,-0.020465666666666653,-0.15015651256242515,-0.0834352251989804,50.0,0.272,-0.25178677777777786,-0.4833343703655808,-0.19004974343721462,44.44444444444444,0.131,66.66666666666666,85.55555555555556,3.0,0.6367499999999999,neutro
+PRICExMED,1,641,-0.017737067082683303,-0.018597079812694105,-0.031943606506588146,46.80187207488299,0.371,-0.012760781249999995,-0.025778301267431636,-0.02603779293254773,50.70202808112324,0.224,0.016005624999999975,-0.006679395257350678,-0.005264619493538456,49.297971918876755,0.363,-0.019372687500000024,-0.034250126998993366,-0.019031256190547588,47.113884555382214,0.279,-0.028446968750000003,-0.040138517270669895,-0.015782686638798674,49.141965678627145,0.346,86.5625,94.21875,2.0,0.6367499999999999,neutro
+MA14xMA3,-1,413,0.018732493946731234,0.019495711743007522,0.0334871577020072,48.91041162227603,0.466,0.05811405339805826,0.05033597672560418,0.05084267289150997,50.847457627118644,0.062,0.022634417475728145,0.004728052246124062,0.0037265942592662146,49.63680387409201,0.297,-0.02661601941747573,-0.027830847621834614,-0.01546435115720282,47.699757869249396,0.283,-0.004355085158150855,-0.022630394656332584,-0.008898396145645172,47.45762711864407,0.3,77.42718446601941,90.2676399026764,4.0,0.6367499999999999,neutro
+PRICExMA3,-1,1365,0.009650820512820511,0.007866696390052672,0.013512371647677317,51.94139194139195,0.546,0.004900637362637359,0.0005338891034665343,0.0005392633820510158,49.523809523809526,0.967,-0.014673824175824178,-0.021474615265459643,-0.016926035035635823,49.08424908424908,0.523,0.0031851612903225817,-0.01312927468962779,-0.007295347845621781,49.81684981684982,0.312,0.023199125642909633,-0.01370675673718383,-0.005389572438822788,46.88644688644688,0.3,69.72140762463343,85.15797207935341,4.0,0.6807272727272727,neutro
+MA365xMA3,1,53,0.0277454716981132,0.03944546541478535,0.06775420863758708,52.83018867924528,0.453,-0.11042018867924527,-0.09593619605608099,-0.09690191691569978,43.39622641509434,0.388,0.05649377358490564,0.05409192357361935,0.0426346075230801,47.16981132075472,0.605,0.13301754716981135,0.08737104766439538,0.04854816426772733,47.16981132075472,0.358,-0.11447471698113201,-0.14433877731913455,-0.05675480429168384,41.509433962264154,0.635,60.37735849056604,77.35849056603774,4.0,0.7581176470588236,neutro
+MEDxMA14,-1,185,0.032015297297297296,0.02576974210266877,0.04426385807851503,50.27027027027027,0.487,0.05068994594594595,0.033539059114855246,0.03387667276153632,50.27027027027027,0.643,-0.015857783783783795,-0.04359209068399024,-0.034358764758901025,45.94594594594595,0.566,-0.029033783783783792,-0.08171127707936293,-0.04540328413380422,50.27027027027027,0.374,0.08017043243243241,-0.052804933089093314,-0.02076319128352251,49.72972972972973,0.761,69.1891891891892,83.24324324324324,4.0,0.7693714285714286,neutro
+MEDxMA365,1,33,0.04310818181818182,0.033538262652949624,0.057607596240413346,39.39393939393939,0.467,-0.24473333333333333,-0.2613341902535032,-0.2639648540616853,45.45454545454545,0.024,-0.2011839393939394,-0.22845028730182979,-0.1800617854603076,48.484848484848484,0.0,0.007929090909090924,-0.07648707759406145,-0.04250043128312073,48.484848484848484,0.391,-0.023826363636363684,-0.2655400486147341,-0.10441181344783067,48.484848484848484,0.25,75.75757575757575,87.87878787878788,6.0,0.782,neutro
+MA121xMA30,-1,52,-0.020661538461538457,-0.0237911422942284,-0.040865280756085726,48.07692307692308,0.831,-0.07388230769230766,-0.07690927545575411,-0.07768346595588999,55.769230769230774,0.721,-0.12157519230769233,-0.114888060239567,-0.09055339566054517,44.230769230769226,0.707,-0.27518923076923074,-0.3105672292466324,-0.17256825074998694,48.07692307692308,0.43,-0.3224990384615384,-0.42409334989842495,-0.16675584705606972,46.15384615384615,0.296,63.46153846153846,86.53846153846155,5.0,0.7938461538461539,neutro
+MA182xMA14,-1,46,0.15412304347826086,0.14217416973434086,0.2442080035756289,50.0,0.0,0.2857415217391305,0.2571233697039764,0.2597116462025928,58.69565217391305,0.0,0.2071847826086957,0.171448060576255,0.13513331178384638,52.17391304347826,0.325,-0.09928499999999998,-0.20905151224177224,-0.11616052946640151,41.30434782608695,0.427,0.14800260869565224,-0.07458470946041838,-0.029327119622323313,43.47826086956522,0.804,63.04347826086957,86.95652173913044,5.0,0.7938461538461539,neutro
+MA182xMA121,-1,30,-0.07841333333333335,-0.07979096882524894,-0.13705438362389624,40.0,0.381,-0.13186333333333336,-0.13923038014068193,-0.14063191249157805,50.0,0.211,-0.20915666666666669,-0.2250881162338893,-0.17741176241736653,43.333333333333336,0.0,-0.12362599999999999,-0.17644799079844736,-0.0980442179759313,50.0,0.417,0.41436733333333337,0.33319840545603613,0.13101545297246694,46.666666666666664,0.204,70.0,83.33333333333334,3.0,0.7938461538461539,neutro
+MA7xMA3,1,783,0.00861537675606641,0.00646313831490142,0.011101525035556403,49.808429118773944,0.722,0.01716249042145593,0.013723166107400172,0.013861307375396486,50.95785440613027,0.707,0.016700791826309083,0.013356612675784767,0.01052752244047766,48.275862068965516,0.799,0.07514809706257983,0.06249071427303802,0.03472328125660524,51.59642401021711,0.469,0.06313083120204603,0.028391969974839334,0.011163879376742887,48.65900383141762,0.236,71.13665389527458,85.93350383631714,4.0,0.816,neutro
+MEDxMA3,1,274,0.009557919708029194,0.008903575935155169,0.01529338632939503,52.55474452554745,0.86,0.03554923357664233,0.0316743286442259,0.03199317138704499,49.27007299270073,0.617,0.04520335766423357,0.04004414771615872,0.031562318525261424,47.08029197080292,0.598,0.05428197080291972,0.0728305922625407,0.040468686726284606,52.18978102189781,0.476,-0.03939229927007301,0.006092626048882876,0.0023956542063691354,47.08029197080292,0.963,77.00729927007299,87.95620437956204,4.0,0.816,neutro
+MEDxMA7,1,228,-0.017271403508771918,-0.014612735942202441,-0.025099827049393664,47.80701754385965,0.692,-0.02944258771929824,-0.025152482353638195,-0.025405674348721083,45.17543859649123,0.621,-0.04444464912280701,-0.0425041334698064,-0.03350124988858029,48.24561403508772,0.578,0.06615530701754384,0.09176395309153222,0.05098910437306316,50.877192982456144,0.459,-0.16573013157894737,-0.10527782017970046,-0.04139582024685679,46.05263157894737,0.407,74.12280701754386,85.96491228070175,4.0,0.816,neutro
+MEDxMA182,1,60,-0.05141766666666667,-0.06026824424805813,-0.10352082684448174,43.333333333333336,0.235,0.04781166666666667,0.021414182490574342,0.021629743702848616,46.666666666666664,0.829,0.0006648333333333163,-0.033655107046627795,-0.026526553046821413,51.66666666666667,0.668,-0.03795049999999997,-0.13075443319485391,-0.0726543617270161,45.0,0.579,0.17888899999999996,-0.015228210882883987,-0.005987816610498588,45.0,0.994,65.0,86.66666666666667,4.0,0.9263999999999999,neutro
+PRICExMA14,-1,622,-0.0007665755627009639,-0.0018991178433711558,-0.0032620537046294576,49.356913183279744,0.912,-0.0019257395498392205,-0.006407874566158778,-0.006472378042310187,49.67845659163987,0.863,0.01326204180064309,0.006098477075160193,0.004806746726876642,47.7491961414791,0.908,0.054067636655948534,0.048405319518770785,0.02689666046418209,52.09003215434084,0.567,0.0538585990338164,0.025635383517887092,0.010079974359787401,47.266881028938904,0.266,76.84887459807074,90.33816425120773,4.0,0.9263999999999999,neutro
+MA182xMA3,1,86,0.0698374418604651,0.0700915914742381,0.1203940747700236,52.32558139534884,0.399,-0.005633953488372075,-0.014586499381746465,-0.014733331206447278,45.348837209302324,0.852,0.04616872093023254,0.01856945567260769,0.01463622297405181,47.674418604651166,0.885,0.15744883720930233,0.09773602792407764,0.054307517940716026,54.65116279069767,0.561,-0.14362348837209307,-0.21674959256674572,-0.08522713670512076,44.18604651162791,0.478,79.06976744186046,90.69767441860465,4.5,0.9263999999999999,neutro
+PRICExMA182,1,139,-0.0896921582733813,-0.09121777580897454,-0.1566818428589591,37.410071942446045,0.043,-0.20890776978417264,-0.22287974738094982,-0.22512331790053275,43.16546762589928,0.0,-0.17689208633093526,-0.20531272749844615,-0.16182503741941978,43.16546762589928,0.0,-0.037221366906474825,-0.0959753157129084,-0.05332916930073661,50.35971223021583,0.601,-0.2234721582733813,-0.3121830074348682,-0.12275208242190383,41.007194244604314,0.269,74.82014388489209,87.76978417266187,3.0,0.9279999999999999,neutro
+MA365xMA14,-1,27,0.0902722222222222,0.07865735022168166,0.13510720336948964,48.148148148148145,0.26,0.04923888888888893,0.04209174007923389,0.04251544742936071,55.55555555555556,0.667,0.02028925925925927,0.014956636694835468,0.01178864224493211,55.55555555555556,0.823,0.00419037037037034,-0.0592687614602882,-0.0329329868902486,51.85185185185185,0.635,0.3909422222222223,0.13360208025451417,0.05253307571701034,51.85185185185185,0.437,59.25925925925925,88.88888888888889,7.5,0.9279999999999999,neutro
+MA182xMA14,1,47,0.02657595744680852,0.027371215978263932,0.0470146583024122,51.06382978723404,0.691,0.01741063829787233,0.004927755680655171,0.004977359861845885,55.319148936170215,0.998,0.0006495744680851034,-0.022737164244711856,-0.01792116104803993,44.680851063829785,0.884,-0.022737234042553203,-0.05318987605447526,-0.029555223487665976,42.5531914893617,0.689,-0.048247872340425546,-0.06350047154634395,-0.024968736066497244,42.5531914893617,0.762,74.46808510638297,85.1063829787234,5.0,0.9279999999999999,neutro
+MA121xMA30,1,53,0.08432094339622644,0.08607884816227486,0.1478548719438829,64.15094339622641,0.022,0.0901020754716981,0.08913430535697553,0.09003155646270568,54.71698113207547,0.091,0.09538396226415095,0.08448989403948784,0.06659392445413015,56.60377358490566,0.307,-0.029476415094339632,-0.0497229199320908,-0.027628791793896622,41.509433962264154,0.696,-0.012036037735849067,-0.03067699468685477,-0.012062363711589094,56.60377358490566,0.847,62.264150943396224,81.13207547169812,3.0,0.9279999999999999,neutro
+MEDxMA30,-1,142,0.09557457746478873,0.09776959269544033,0.16793568822782315,57.04225352112676,0.0,0.0356945070422535,0.02280826220621985,0.02303785661885766,54.22535211267606,0.755,0.06607436619718313,0.03764384568598137,0.029670429159297504,46.478873239436616,0.596,-0.01828098591549294,-0.04765629320824421,-0.026480460208646955,47.88732394366197,0.694,0.12349077464788734,0.04999247118411797,0.01965731573185583,48.59154929577465,0.734,85.2112676056338,93.66197183098592,2.0,0.9279999999999999,neutro
+PRICExMA7,-1,943,0.0040334994697773085,0.0022016087035053853,0.0037816325366443436,51.74973488865323,0.931,0.006369278897136809,0.0036908801335600087,0.003728033575971337,50.37115588547189,0.954,-0.021293319194061505,-0.024543468508016503,-0.019344868475054382,48.67444326617179,0.551,-0.020223319194061496,-0.032993771526510784,-0.018333155921783178,50.26511134676564,0.682,-0.011021698513800412,-0.04781024414862614,-0.018799252011075365,46.65959703075291,0.275,72.1102863202545,86.51804670912952,4.0,0.9279999999999999,neutro
+MEDxMA3,-1,278,0.0016162230215827325,-0.0013541581255577132,-0.0023259939058275247,47.84172661870504,0.98,0.05901579136690648,0.02813674104933946,0.028419973435759655,53.23741007194245,0.533,0.03532474820143886,-0.020805920013216492,-0.01639897743168258,48.92086330935252,0.656,0.11916438848920864,0.041241944307270115,0.02291629481931619,47.482014388489205,0.61,0.0010353237410072069,-0.1184472277241612,-0.0465741040158174,44.24460431654676,0.36,77.6978417266187,91.00719424460432,3.0,0.9279999999999999,neutro
+MA365xMA30,1,22,0.07007000000000001,0.0787243826923708,0.13522234289077065,50.0,0.246,-0.028239545454545458,-0.015094491472952283,-0.015246436889594057,50.0,0.776,-0.23031318181818178,-0.2243817259801987,-0.17685499406389435,45.45454545454545,0.05,0.03273272727272725,0.05564617297318344,0.030920077286350045,59.09090909090909,0.667,0.43400904761904746,0.5400784830084224,0.21236184187372262,54.54545454545454,0.0,63.63636363636363,90.47619047619048,8.0,0.9279999999999999,neutro
+PRICExMA365,-1,91,0.04233637362637362,0.051379225589190385,0.08825244508086891,54.94505494505495,0.352,-0.03783879120879119,-0.01651874682732147,-0.01668502920083335,47.25274725274725,0.916,-0.08764582417582417,-0.07071979625208016,-0.05574049799164656,45.05494505494506,0.691,0.050201208791208776,0.05812351032993255,0.03229662231078432,50.54945054945055,0.636,-0.037380659340659296,0.009720292990034775,0.0038220728798851783,46.15384615384615,0.934,68.13186813186813,85.71428571428571,4.5,0.9279999999999999,neutro
+PRICExMA182,-1,140,-0.03597321428571429,-0.03340255555820349,-0.05737449652377054,47.14285714285714,0.467,-0.14893500000000004,-0.15623978620456583,-0.15781254004350195,40.0,0.084,-0.0647025714285714,-0.08853573897542956,-0.06978281106690429,40.714285714285715,0.504,-0.020481785714285727,-0.07441844204291212,-0.041350983482826315,45.714285714285715,0.723,-0.12365392857142858,-0.18888427375986003,-0.0742703394758254,41.42857142857143,0.512,77.85714285714286,87.85714285714286,4.0,0.9422608695652175,neutro
+MEDxMA7,-1,240,0.032916,0.028922037628442143,0.049678454826067274,50.0,0.273,0.07765416666666666,0.05252018029204549,0.05304886326827398,48.75,0.309,0.10422920833333332,0.061008686719023736,0.048086317548386735,49.166666666666664,0.36,0.071882375,-0.026142383843300174,-0.014526147724009906,46.666666666666664,0.803,0.08066995833333333,-0.0952759562795003,-0.03746303213023842,45.0,0.523,75.83333333333333,87.5,4.0,0.9422608695652175,neutro
+MA30xMA14,-1,186,0.0577908064516129,0.05259839919140563,0.0903465804077389,54.3010752688172,0.17,-0.0017063978494623539,-0.010112015633565624,-0.010213806040435803,45.16129032258064,0.893,-0.06830774193548388,-0.08005346012548165,-0.06309718027811081,47.8494623655914,0.35,-0.012653118279569909,-0.025284888363596887,-0.014049676026344394,51.61290322580645,0.857,-0.02853736559139785,-0.05713421272326213,-0.022465487942291914,50.53763440860215,0.736,72.58064516129032,85.48387096774194,4.0,0.9422608695652175,neutro
+MA30xMA14,1,186,0.028153548387096782,0.03170731760067301,0.054462640748789,52.68817204301075,0.374,0.016020537634408603,0.011875477638208995,0.01199501955194561,50.0,0.847,-0.0370360752688172,-0.051548816287307384,-0.04063016076138508,47.8494623655914,0.499,-0.015004569892473113,-0.02383805484556744,-0.013245735668765603,51.61290322580645,0.877,-0.13373016129032259,-0.14118492834996732,-0.05551469346121136,45.69892473118279,0.358,72.58064516129032,87.09677419354838,3.0,0.9422608695652175,neutro
+MA30xMA3,1,258,0.003845116279069767,0.005820412909908539,0.009997536256906005,52.71317829457365,0.915,-0.04823112403100775,-0.04900228621850522,-0.04949555707888578,49.224806201550386,0.314,-0.02961368217054264,-0.03685357516921869,-0.029047547385211904,44.96124031007752,0.566,-0.02533209302325577,-0.012891433059302676,-0.007163189941517431,50.0,0.892,0.033963837209302274,0.042444573151777756,0.01668944054546775,46.51162790697674,0.768,78.29457364341084,89.92248062015504,3.0,0.9422608695652175,neutro
+MEDxMA182,-1,58,-0.022809137931034486,-0.02034156879114435,-0.03494005917786492,48.275862068965516,0.614,0.007036206896551722,0.0022230272623963124,0.002245404883013482,46.55172413793103,0.976,-0.01394482758620689,-0.02929424853310631,-0.02308937649800395,43.103448275862064,0.815,0.028821551724137955,-0.010465656017253815,-0.005815294666567431,48.275862068965516,0.866,-0.048383620689655175,-0.07670426764079707,-0.03016054160321107,41.37931034482759,0.706,77.58620689655173,89.65517241379311,5.0,0.9422608695652175,neutro
+MA182xMA3,-1,85,-0.09941294117647062,-0.10679718080176766,-0.18344208627937292,44.70588235294118,0.05,0.05273082352941179,0.02606567006587443,0.026328054466521728,49.411764705882355,0.704,0.15997435294117648,0.11817045873361055,0.09314054291437561,52.94117647058824,0.093,0.0777025882352941,-0.008570515770733375,-0.004762250409253931,50.588235294117645,0.894,-0.1411765882352941,-0.29043387357038863,-0.11420020288600495,43.529411764705884,0.232,68.23529411764706,90.58823529411765,5.0,0.9422608695652175,neutro
+MA30xMA7,1,217,0.003779170506912438,0.009125723884904737,0.015674962725502214,52.07373271889401,0.807,-0.0005046543778801771,-4.6403900819300904e-05,-4.687101559798865e-05,47.465437788018434,0.999,0.02160400921658988,0.011743430538667134,0.009256031564660542,48.8479262672811,0.885,0.0010320737327188937,0.010928539345289034,0.00607249812751899,52.07373271889401,0.903,0.05348820276497695,0.060377308008461784,0.02374069091705335,47.465437788018434,0.725,76.49769585253456,88.0184331797235,3.0,0.9422608695652175,neutro
+MA14xMA3,1,412,-0.003732427184466025,-0.0042915657702153115,-0.007371484643913094,48.786407766990294,0.878,-0.03452007281553398,-0.03988291933152033,-0.04028439206782132,49.75728155339806,0.264,-0.04675264563106798,-0.0575933632259271,-0.04539440039934409,46.359223300970875,0.3,0.009159538834951474,0.011765943826390329,0.006537806160257662,52.18446601941748,0.868,-0.05554092457420925,-0.06562692404933614,-0.025804868933107607,47.0873786407767,0.25,75.48543689320388,90.2676399026764,4.0,0.9422608695652175,neutro
+MA365xMA7,-1,45,-0.08103666666666666,-0.08923106924932349,-0.1532693408304292,44.44444444444444,0.026,-0.08737622222222222,-0.11088535951052053,-0.11200156287387926,46.666666666666664,0.293,0.06799755555555557,0.028631136728832742,0.022566719700993443,57.77777777777777,0.725,0.11502799999999996,0.013962899947202765,0.007758555933705275,51.11111111111111,0.892,0.005609333333333373,-0.23899853974037966,-0.09397554559418657,51.11111111111111,0.357,57.77777777777777,84.44444444444444,6.0,0.9422608695652175,neutro
+PRICExMED,-1,641,0.021020873634945397,0.020767861465922702,0.035672288409384675,52.418096723868956,0.383,0.029750327613104526,0.017480843427518426,0.01765681053728184,50.858034321372855,0.698,0.049702854914196556,0.029052419946197283,0.02289877009672308,49.453978159126365,0.646,0.038525850234009354,0.019713901742313477,0.010954129150653281,51.014040561622465,0.82,-0.0002629017160686441,-0.02220791100080794,-0.008732273239305728,47.113884555382214,0.897,87.3634945397816,94.38377535101404,2.0,0.9422608695652175,neutro
+MEDxMA121,1,91,0.08019505494505494,0.07113435068349859,0.12218518876196342,49.45054945054945,0.04,-0.021887032967032947,-0.05134812811197136,-0.051865012879751,47.25274725274725,0.548,0.03865461538461538,0.0007329198464039522,0.0005776786613029268,47.25274725274725,0.921,0.11142747252747255,0.023207607627741874,0.012895424485469585,51.64835164835166,0.883,0.0024489010989010673,-0.15220237822472207,-0.05984681559116825,50.54945054945055,0.512,72.52747252747253,87.91208791208791,3.5,0.9422608695652175,neutro
+MA182xMA7,1,67,0.0076192537313432805,0.007690816049038089,0.01321026763660675,52.23880597014925,0.927,-0.023750447761194032,-0.03375519602686864,-0.03409498536878306,43.28358208955223,0.618,0.034717462686567155,0.008729420900812945,0.00688042519884507,44.776119402985074,0.926,0.06607283582089549,0.023456423448585822,0.013033680254006787,50.74626865671642,0.865,-0.26800970149253733,-0.31012847852817405,-0.12194423031052547,41.7910447761194,0.143,79.1044776119403,88.05970149253731,5.0,0.9422608695652175,neutro
+MA121xMA7,-1,88,0.07495238636363637,0.06364985841309972,0.10932931685114719,48.86363636363637,0.281,0.07764045454545455,0.043606296058068095,0.044045249356668474,43.18181818181818,0.685,0.10674397727272728,0.06296209107771732,0.049625967512090224,45.45454545454545,0.68,0.11821409090909088,0.025940150893838124,0.014413775963417735,48.86363636363637,0.748,0.1481702272727273,-0.01654939020211934,-0.006507311614475473,45.45454545454545,0.945,73.86363636363636,89.77272727272727,4.0,0.9422608695652175,neutro
+MEDxMA365,-1,37,-0.052988108108108105,-0.044443665841789014,-0.07633945692868081,45.94594594594595,0.662,-0.08400891891891892,-0.06157995647948478,-0.06219983772297179,48.64864864864865,0.624,-0.1621889189189189,-0.14576280294546232,-0.1148884987716481,43.24324324324324,0.176,0.024111081081081055,0.04505525828960639,0.025035182008697174,51.35135135135135,0.761,-0.05749944444444447,0.018377259173368816,0.0072260397876034365,40.54054054054054,0.016,67.56756756756756,88.88888888888889,8.0,0.9422608695652175,neutro
+MA121xMA14,-1,73,0.08883123287671232,0.0738440967816724,0.1268396325759725,53.42465753424658,0.077,0.1377391780821918,0.10205717603308966,0.1030845124068534,49.31506849315068,0.237,0.13806506849315067,0.09286285233037742,0.07319339008513785,54.794520547945204,0.375,0.12088643835616443,0.019819180009174625,0.011012627551783014,45.20547945205479,0.923,-0.061453287671232926,-0.2486090503677838,-0.09775445144285876,41.0958904109589,0.264,65.75342465753424,86.3013698630137,5.0,0.9493714285714286,neutro
+PRICExMA30,-1,427,0.017202927400468377,0.016748936289171738,0.0287691097534581,52.92740046838408,0.482,0.02481250585480094,0.01723528755002068,0.017408782824930823,51.288056206088996,0.739,0.04980238875878221,0.03435935517273575,0.027081633000940863,50.585480093676814,0.609,-0.0037466042154566874,-0.0024782808638988425,-0.0013770692889511526,49.88290398126464,0.965,-0.000713957845433267,-0.007468103997197523,-0.0029364997311411936,47.07259953161593,0.96,81.49882903981265,90.63231850117096,3.0,0.9650000000000001,neutro
+MA182xMA7,-1,66,-0.04358954545454546,-0.05050061533379705,-0.08674328447320295,53.03030303030303,0.129,0.13645151515151513,0.10235803550251647,0.10338840041271781,56.060606060606055,0.28,0.17344772727272728,0.12187603155843105,0.09606123111692019,62.121212121212125,0.074,0.12494348484848483,0.010132061312829493,0.005629931082838358,46.96969696969697,0.957,0.05132227272727275,-0.15314031847959297,-0.06021561887876152,42.42424242424242,0.557,66.66666666666666,89.39393939393939,6.0,0.9650000000000001,neutro
@@ -0,0 +1,79 @@
+# EURUSD (D1, 1999+) — cosa succede dopo ogni incrocio (36 coppie x 2 dir)
+
+extra5/10/20 = extra-rendimento % vs baseline stesso regime; pos10 = % che batte il baseline;
+q10 = significativita' (BH, <0.10 robusto); rev10/20 = % ritorno alla Mediana; btr = giorni mediani.
+
+| coppia | dir | n | extra5 | extra10 | extra20 | pos10 | q10 | rev10 | rev20 | btr | dopo 10g |
+|---|---|---|---|---|---|---|---|---|---|---|---|
+| MA182xMA30 | +1 | 36 | -0.203 | -0.337 | +0.300 | 39% | 0.000 | 64% | 86% | 4 | SCENDE (extra -) |
+| MA365xMA121 | +1 | 15 | +0.209 | -0.130 | -0.902 | 53% | 0.000 | 43% | 71% | 5 | SCENDE (extra -) |
+| MA365xMA7 | +1 | 46 | +0.349 | +0.381 | +0.138 | 52% | 0.000 | 63% | 80% | 4 | SALE (extra +) |
+| MA365xMA182 | -1 | 16 | +0.132 | +0.452 | +0.216 | 69% | 0.000 | 56% | 69% | 4 | SALE (extra +) |
+| MA365xMA121 | -1 | 14 | +0.560 | +0.478 | +1.030 | 79% | 0.000 | 50% | 71% | 3 | SALE (extra +) |
+| MA365xMA182 | +1 | 16 | +0.298 | +0.556 | +0.622 | 56% | 0.000 | 75% | 81% | 4 | SALE (extra +) |
+| MA121xMA7 | +1 | 88 | +0.240 | +0.299 | +0.160 | 57% | 0.010 | 73% | 86% | 3 | SALE (extra +) |
+| MA121xMA3 | +1 | 117 | +0.138 | +0.235 | +0.139 | 59% | 0.027 | 75% | 87% | 4 | SALE (extra +) |
+| PRICExMA121 | -1 | 192 | +0.060 | +0.268 | +0.228 | 56% | 0.048 | 80% | 92% | 3 | SALE (extra +) |
+| MA182xMA121 | +1 | 31 | -0.314 | -0.339 | -0.462 | 35% | 0.151 | 55% | 77% | 2 | neutro |
+| MA121xMA14 | +1 | 73 | +0.132 | +0.138 | +0.249 | 55% | 0.190 | 71% | 84% | 3 | neutro |
+| MA365xMA30 | -1 | 21 | -0.033 | -0.142 | +0.339 | 38% | 0.360 | 67% | 81% | 6 | neutro |
+| MEDxMA30 | +1 | 151 | -0.017 | -0.121 | -0.170 | 48% | 0.461 | 82% | 92% | 3 | neutro |
+| MA30xMA3 | -1 | 259 | -0.046 | -0.110 | -0.136 | 46% | 0.461 | 77% | 90% | 3 | neutro |
+| MEDxMA121 | -1 | 84 | +0.326 | +0.264 | +0.331 | 57% | 0.461 | 75% | 87% | 3 | neutro |
+| MA365xMA3 | -1 | 52 | -0.122 | -0.204 | -0.397 | 44% | 0.472 | 62% | 85% | 5 | neutro |
+| MA182xMA30 | -1 | 35 | -0.386 | -0.375 | -0.125 | 43% | 0.508 | 74% | 89% | 4 | neutro |
+| MEDxMA14 | +1 | 182 | +0.172 | +0.161 | +0.231 | 53% | 0.528 | 68% | 83% | 4 | neutro |
+| MA14xMA7 | -1 | 383 | +0.011 | -0.064 | +0.017 | 47% | 0.572 | 77% | 90% | 3 | neutro |
+| MA365xMA14 | +1 | 28 | +0.111 | -0.216 | +0.220 | 43% | 0.596 | 54% | 81% | 7 | neutro |
+| MA30xMA7 | -1 | 217 | -0.023 | -0.111 | -0.046 | 48% | 0.596 | 78% | 88% | 3 | neutro |
+| PRICExMA30 | +1 | 428 | -0.024 | -0.065 | -0.048 | 47% | 0.596 | 81% | 91% | 2 | neutro |
+| PRICExMA3 | +1 | 1365 | -0.038 | -0.048 | -0.062 | 48% | 0.596 | 69% | 85% | 4 | neutro |
+| PRICExMA7 | +1 | 943 | -0.036 | -0.045 | -0.068 | 48% | 0.596 | 71% | 86% | 3 | neutro |
+| PRICExMA14 | +1 | 623 | +0.002 | +0.018 | -0.002 | 50% | 0.596 | 77% | 90% | 3 | neutro |
+| MA14xMA7 | +1 | 382 | -0.000 | +0.024 | +0.094 | 50% | 0.596 | 74% | 89% | 3 | neutro |
+| MA7xMA3 | -1 | 783 | -0.011 | +0.030 | +0.036 | 50% | 0.596 | 73% | 87% | 3 | neutro |
+| MA121xMA3 | -1 | 117 | +0.022 | +0.135 | -0.053 | 52% | 0.596 | 74% | 91% | 4 | neutro |
+| PRICExMA121 | +1 | 192 | +0.011 | +0.163 | +0.149 | 58% | 0.596 | 79% | 92% | 3 | neutro |
+| PRICExMA365 | +1 | 90 | -0.091 | -0.150 | -0.483 | 50% | 0.637 | 67% | 86% | 3 | neutro |
+| PRICExMED | +1 | 641 | -0.007 | -0.034 | -0.040 | 47% | 0.637 | 87% | 94% | 2 | neutro |
+| MA14xMA3 | -1 | 413 | +0.005 | -0.028 | -0.023 | 48% | 0.637 | 77% | 90% | 4 | neutro |
+| PRICExMA3 | -1 | 1365 | -0.021 | -0.013 | -0.014 | 50% | 0.681 | 70% | 85% | 4 | neutro |
+| MA365xMA3 | +1 | 53 | +0.054 | +0.087 | -0.144 | 47% | 0.758 | 60% | 77% | 4 | neutro |
+| MEDxMA14 | -1 | 185 | -0.044 | -0.082 | -0.053 | 50% | 0.769 | 69% | 83% | 4 | neutro |
+| MEDxMA365 | +1 | 33 | -0.228 | -0.076 | -0.266 | 48% | 0.782 | 76% | 88% | 6 | neutro |
+| MA121xMA30 | -1 | 52 | -0.115 | -0.311 | -0.424 | 48% | 0.794 | 63% | 87% | 5 | neutro |
+| MA182xMA14 | -1 | 46 | +0.171 | -0.209 | -0.075 | 41% | 0.794 | 63% | 87% | 5 | neutro |
+| MA182xMA121 | -1 | 30 | -0.225 | -0.176 | +0.333 | 50% | 0.794 | 70% | 83% | 3 | neutro |
+| MA7xMA3 | +1 | 783 | +0.013 | +0.062 | +0.028 | 52% | 0.816 | 71% | 86% | 4 | neutro |
+| MEDxMA3 | +1 | 274 | +0.040 | +0.073 | +0.006 | 52% | 0.816 | 77% | 88% | 4 | neutro |
+| MEDxMA7 | +1 | 228 | -0.043 | +0.092 | -0.105 | 51% | 0.816 | 74% | 86% | 4 | neutro |
+| MEDxMA182 | +1 | 60 | -0.034 | -0.131 | -0.015 | 45% | 0.926 | 65% | 87% | 4 | neutro |
+| PRICExMA14 | -1 | 622 | +0.006 | +0.048 | +0.026 | 52% | 0.926 | 77% | 90% | 4 | neutro |
+| MA182xMA3 | +1 | 86 | +0.019 | +0.098 | -0.217 | 55% | 0.926 | 79% | 91% | 4 | neutro |
+| PRICExMA182 | +1 | 139 | -0.205 | -0.096 | -0.312 | 50% | 0.928 | 75% | 88% | 3 | neutro |
+| MA365xMA14 | -1 | 27 | +0.015 | -0.059 | +0.134 | 52% | 0.928 | 59% | 89% | 8 | neutro |
+| MA182xMA14 | +1 | 47 | -0.023 | -0.053 | -0.064 | 43% | 0.928 | 74% | 85% | 5 | neutro |
+| MA121xMA30 | +1 | 53 | +0.084 | -0.050 | -0.031 | 42% | 0.928 | 62% | 81% | 3 | neutro |
+| MEDxMA30 | -1 | 142 | +0.038 | -0.048 | +0.050 | 48% | 0.928 | 85% | 94% | 2 | neutro |
+| PRICExMA7 | -1 | 943 | -0.025 | -0.033 | -0.048 | 50% | 0.928 | 72% | 87% | 4 | neutro |
+| MEDxMA3 | -1 | 278 | -0.021 | +0.041 | -0.118 | 47% | 0.928 | 78% | 91% | 3 | neutro |
+| MA365xMA30 | +1 | 22 | -0.224 | +0.056 | +0.540 | 59% | 0.928 | 64% | 90% | 8 | neutro |
+| PRICExMA365 | -1 | 91 | -0.071 | +0.058 | +0.010 | 51% | 0.928 | 68% | 86% | 4 | neutro |
+| PRICExMA182 | -1 | 140 | -0.089 | -0.074 | -0.189 | 46% | 0.942 | 78% | 88% | 4 | neutro |
+| MEDxMA7 | -1 | 240 | +0.061 | -0.026 | -0.095 | 47% | 0.942 | 76% | 88% | 4 | neutro |
+| MA30xMA14 | -1 | 186 | -0.080 | -0.025 | -0.057 | 52% | 0.942 | 73% | 85% | 4 | neutro |
+| MA30xMA14 | +1 | 186 | -0.052 | -0.024 | -0.141 | 52% | 0.942 | 73% | 87% | 3 | neutro |
+| MA30xMA3 | +1 | 258 | -0.037 | -0.013 | +0.042 | 50% | 0.942 | 78% | 90% | 3 | neutro |
+| MEDxMA182 | -1 | 58 | -0.029 | -0.010 | -0.077 | 48% | 0.942 | 78% | 90% | 5 | neutro |
+| MA182xMA3 | -1 | 85 | +0.118 | -0.009 | -0.290 | 51% | 0.942 | 68% | 91% | 5 | neutro |
+| MA30xMA7 | +1 | 217 | +0.012 | +0.011 | +0.060 | 52% | 0.942 | 76% | 88% | 3 | neutro |
+| MA14xMA3 | +1 | 412 | -0.058 | +0.012 | -0.066 | 52% | 0.942 | 75% | 90% | 4 | neutro |
+| MA365xMA7 | -1 | 45 | +0.029 | +0.014 | -0.239 | 51% | 0.942 | 58% | 84% | 6 | neutro |
+| PRICExMED | -1 | 641 | +0.029 | +0.020 | -0.022 | 51% | 0.942 | 87% | 94% | 2 | neutro |
+| MEDxMA121 | +1 | 91 | +0.001 | +0.023 | -0.152 | 52% | 0.942 | 73% | 88% | 4 | neutro |
+| MA182xMA7 | +1 | 67 | +0.009 | +0.023 | -0.310 | 51% | 0.942 | 79% | 88% | 5 | neutro |
+| MA121xMA7 | -1 | 88 | +0.063 | +0.026 | -0.017 | 49% | 0.942 | 74% | 90% | 4 | neutro |
+| MEDxMA365 | -1 | 37 | -0.146 | +0.045 | +0.018 | 51% | 0.942 | 68% | 89% | 8 | neutro |
+| MA121xMA14 | -1 | 73 | +0.093 | +0.020 | -0.249 | 45% | 0.949 | 66% | 86% | 5 | neutro |
+| PRICExMA30 | -1 | 427 | +0.034 | -0.002 | -0.007 | 50% | 0.965 | 81% | 91% | 3 | neutro |
+| MA182xMA7 | -1 | 66 | +0.122 | +0.010 | -0.153 | 47% | 0.965 | 67% | 89% | 6 | neutro |
@@ -0,0 +1,82 @@
+"""Utility condivise per l'analisi PaPP v2.
+
+I dati di input sono i due CSV prodotti dallo script MQL5 `PaPP_CrossExport.mq5`:
+  - PaPP_crosses_<SYM>_D1.csv  (un record per incrocio)
+  - PaPP_bars_<SYM>_D1.csv     (un record per giorno D1 = baseline)
+
+Per default vengono cercati in ../data. Si possono passare percorsi diversi via argv.
+"""
+import os, sys, numpy as np, pandas as pd
+
+HERE = os.path.dirname(os.path.abspath(__file__))
+DATA = os.path.normpath(os.path.join(HERE, "..", "data"))
+HZ = [1, 3, 5, 10, 20]
+
+
+def load(path):
+    df = pd.read_csv(path)
+    df["time"] = pd.to_datetime(df["time"], format="%Y.%m.%d", errors="coerce")
+    if df["time"].isna().all():
+        df["time"] = pd.to_datetime(df["time"], errors="coerce")
+    return df.dropna(subset=["time"]).sort_values("time").reset_index(drop=True)
+
+
+def load_pair(sym="EURUSD", year_min=1999, data_dir=None):
+    d = data_dir or DATA
+    cr = load(os.path.join(d, f"PaPP_crosses_{sym}_D1.csv"))
+    ba = load(os.path.join(d, f"PaPP_bars_{sym}_D1.csv"))
+    if year_min:
+        cr = cr[cr.time.dt.year >= year_min].reset_index(drop=True)
+        ba = ba[ba.time.dt.year >= year_min].reset_index(drop=True)
+    return cr, ba
+
+
+def add_regime(df, edges):
+    """Regime = trend(sopra/sotto MA365) x tercile(cluster) x tercile(velocita')."""
+    tr = (df["trend"] > 0).astype(int)
+    cl = np.digitize(df["cluster_pct"], edges["cl"])
+    ve = np.digitize(df["vel_med"], edges["ve"])
+    out = df.copy()
+    out["regime"] = tr.astype(str) + "_" + cl.astype(str) + "_" + ve.astype(str)
+    return out
+
+
+def regime_edges(ba):
+    return {
+        "cl": np.quantile(ba["cluster_pct"], [1/3, 2/3]),
+        "ve": np.quantile(ba["vel_med"], [1/3, 2/3]),
+    }
+
+
+def block_bootstrap_p(x, nb=2000, bs=20, seed=42):
+    """p-value bilaterale per media != 0 con block bootstrap (gestisce overlap)."""
+    rng = np.random.default_rng(seed)
+    x = np.asarray(x, float)
+    n = len(x)
+    if n < 10:
+        return np.nan
+    nblocks = int(np.ceil(n / bs))
+    idx = np.arange(n)
+    means = np.empty(nb)
+    for k in range(nb):
+        starts = rng.integers(0, n, size=nblocks)
+        pick = np.concatenate([
+            idx[s:s+bs] if s+bs <= n else np.concatenate([idx[s:], idx[:s+bs-n]])
+            for s in starts])[:n]
+        means[k] = x[pick].mean()
+    return 2 * min((means <= 0).mean(), (means >= 0).mean())
+
+
+def benjamini_hochberg(p):
+    """q-value BH per array di p (NaN ammessi)."""
+    p = np.asarray(p, float)
+    out = np.full_like(p, np.nan)
+    idx = np.where(~np.isnan(p))[0]
+    if len(idx) == 0:
+        return out
+    m = len(idx)
+    order = idx[np.argsort(p[idx])]
+    q = p[order] * m / np.arange(1, m + 1)
+    q = np.minimum.accumulate(q[::-1])[::-1]
+    out[order] = np.clip(q, 0, 1)
+    return out
@@ -0,0 +1,69 @@
+"""Fase 2 raffinata: extra-rendimento vs baseline + significativita'.
+
+Per ogni (coppia, direzione) calcola:
+  - rendimento medio grezzo a 1/3/5/10/20 g
+  - EXTRA-rendimento = evento - baseline nello stesso regime (toglie il bias di periodo)
+  - effetto in sigma del movimento tipico a h giorni
+  - quota di eventi che battono la baseline
+  - p-value (block bootstrap) e q-value (Benjamini-Hochberg)
+
+Uso:
+  python excess_analysis.py [SYMBOL] [YEAR_MIN]
+Output:
+  ../results/summary_<SYM>_<YEAR>.csv  + stampa dei top a 5/10/20 g
+"""
+import os, sys, numpy as np, pandas as pd
+from _common import load_pair, add_regime, regime_edges, block_bootstrap_p, benjamini_hochberg, HZ, HERE
+
+SYM = sys.argv[1] if len(sys.argv) > 1 else "EURUSD"
+YEAR = int(sys.argv[2]) if len(sys.argv) > 2 else 1999
+RESULTS = os.path.normpath(os.path.join(HERE, "..", "results"))
+
+cr, ba = load_pair(SYM, YEAR)
+print(f"[{SYM} {YEAR}+] incroci={len(cr)}  baseline={len(ba)}")
+
+edges = regime_edges(ba)
+cr = add_regime(cr, edges)
+ba = add_regime(ba, edges)
+
+base_mean = {h: ba.groupby("regime")[f"cret_{h}"].mean() for h in HZ}
+base_glob = {h: ba[f"cret_{h}"].mean() for h in HZ}
+base_sd   = {h: ba[f"cret_{h}"].std()  for h in HZ}
+
+rows = []
+for (pair, d), g in cr.groupby(["pair", "dir"]):
+    n = len(g)
+    if n < 30:
+        continue
+    rec = {"pair": pair, "dir": int(d), "n": n}
+    for h in HZ:
+        ev = g[f"cret_{h}"].values
+        bexp = g["regime"].map(base_mean[h]).fillna(base_glob[h]).values
+        exc = ev - bexp
+        rec[f"raw_{h}"] = np.nanmean(ev)
+        rec[f"exc_{h}"] = np.nanmean(exc)
+        rec[f"eff_{h}"] = np.nanmean(exc) / base_sd[h]
+        rec[f"pos_{h}"] = (exc > 0).mean()
+        rec[f"p_{h}"]   = block_bootstrap_p(exc)
+    rows.append(rec)
+
+res = pd.DataFrame(rows)
+for h in HZ:
+    res[f"q_{h}"] = benjamini_hochberg(res[f"p_{h}"].values)
+
+os.makedirs(RESULTS, exist_ok=True)
+outp = os.path.join(RESULTS, f"summary_{SYM}_{YEAR}.csv")
+res.to_csv(outp, index=False)
+
+print(f"vol giornaliera prezzo (sd cret_1) = {ba['cret_1'].std():.3f}%")
+print(f"baseline drift 5/10/20g = {base_glob[5]:.3f}% / {base_glob[10]:.3f}% / {base_glob[20]:.3f}%")
+for h in [5, 10, 20]:
+    sig = res[res[f"q_{h}"] < 0.10].copy()
+    sig["ae"] = sig[f"eff_{h}"].abs()
+    sig = sig.sort_values("ae", ascending=False).head(12)
+    print(f"\n=== TOP {h}g (q<0.10) ===")
+    for _, r in sig.iterrows():
+        print(f"  {r['pair']:13s} dir={int(r['dir']):+d} n={int(r['n']):5d} "
+              f"exc={r[f'exc_{h}']:+.3f}% eff={r[f'eff_{h}']:+.2f}sd "
+              f"pos={r[f'pos_{h}']*100:.0f}% q={r[f'q_{h}']:.3f}")
+print(f"\nsalvato: {outp}")
@@ -0,0 +1,83 @@
+"""Verifiche di correttezza + tabella completa 36 coppie x 2 direzioni.
+
+Verifiche:
+  V1 la direzione registrata coincide col segno di (A-B) all'incrocio
+  V2 cret_1 coincide con ret_1
+  V3 ricalcolo indipendente della media di un pattern
+  V4 baseline drift ~0
+
+Tabella: per ogni (coppia, dir) extra-rendimento 5/10/20g, quota che batte il baseline,
+q-value a 10g, tasso di ritorno alla Mediana (rev10/rev20), giorni mediani al ritorno,
+ed etichetta verbale "dopo 10g".
+
+Uso:
+  python full_table.py [SYMBOL] [YEAR_MIN]
+Output:
+  ../results/tabella_incroci_<SYM>_<YEAR>.csv (+ .md)
+"""
+import os, sys, numpy as np, pandas as pd
+from _common import load_pair, add_regime, regime_edges, block_bootstrap_p, benjamini_hochberg, HZ, HERE
+
+SYM = sys.argv[1] if len(sys.argv) > 1 else "EURUSD"
+YEAR = int(sys.argv[2]) if len(sys.argv) > 2 else 1999
+RESULTS = os.path.normpath(os.path.join(HERE, "..", "results"))
+
+cr, ba = load_pair(SYM, YEAR)
+
+# ---------------- VERIFICHE ----------------
+sub = cr[cr.pair == "PRICExMED"]
+chk = ((sub.price - sub.med) > 0).astype(int).replace(0, -1)
+print(f"[V1] PRICExMED dir vs segno(price-med): {(np.sign(sub.dir)==np.sign(chk)).mean()*100:.1f}% (atteso ~100%)")
+print(f"[V2] max|cret_1 - ret_1| = {(cr.cret_1-cr.ret_1).abs().max():.6f} (atteso 0)")
+g0 = cr[(cr.pair=='MA121xMA7') & (cr.dir==1)]
+print(f"[V3] MA121xMA7+ n={len(g0)} media cret_10 = {g0.cret_10.mean():.4f}%")
+print(f"[V4] baseline cret_10 medio={ba.cret_10.mean():.4f}% sd={ba.cret_10.std():.3f}% (drift ~0)")
+
+# ---------------- TABELLA ----------------
+edges = regime_edges(ba)
+cr = add_regime(cr, edges); ba = add_regime(ba, edges)
+bmean = {h: ba.groupby("regime")[f"cret_{h}"].mean() for h in HZ}
+bglob = {h: ba[f"cret_{h}"].mean() for h in HZ}
+bsd   = {h: ba[f"cret_{h}"].std()  for h in HZ}
+
+rows = []
+for (pair, d), g in cr.groupby(["pair", "dir"]):
+    rec = {"pair": pair, "dir": int(d), "n": len(g)}
+    for h in HZ:
+        ev = g[f"cret_{h}"].values
+        bexp = g["regime"].map(bmean[h]).fillna(bglob[h]).values
+        exc = ev - bexp
+        rec[f"raw_{h}"] = np.nanmean(ev)
+        rec[f"exc_{h}"] = np.nanmean(exc)
+        rec[f"eff_{h}"] = np.nanmean(exc) / bsd[h]
+        rec[f"pos_{h}"] = (exc > 0).mean() * 100
+        rec[f"p_{h}"] = block_bootstrap_p(exc)
+    rec["rev10"] = g["rev_10"].mean() * 100
+    rec["rev20"] = g["rev_20"].mean() * 100
+    rec["btr_med"] = g["bars_to_revert"].median()
+    rows.append(rec)
+res = pd.DataFrame(rows)
+res["q10"] = benjamini_hochberg(res["p_10"].values)
+
+def verb(r):
+    if r["q10"] < 0.10 and r["exc_10"] > 0: return "SALE (extra +)"
+    if r["q10"] < 0.10 and r["exc_10"] < 0: return "SCENDE (extra -)"
+    return "neutro"
+res["dopo_10g"] = res.apply(verb, axis=1)
+res = res.sort_values(["q10", "exc_10"]).reset_index(drop=True)
+
+os.makedirs(RESULTS, exist_ok=True)
+csvp = os.path.join(RESULTS, f"tabella_incroci_{SYM}_{YEAR}.csv")
+res.to_csv(csvp, index=False)
+
+md = [f"# {SYM} (D1, {YEAR}+) — cosa succede dopo ogni incrocio (36 coppie x 2 dir)", "",
+      "extra5/10/20 = extra-rendimento % vs baseline stesso regime; pos10 = % che batte il baseline;",
+      "q10 = significativita' (BH, <0.10 robusto); rev10/20 = % ritorno alla Mediana; btr = giorni mediani.", "",
+      "| coppia | dir | n | extra5 | extra10 | extra20 | pos10 | q10 | rev10 | rev20 | btr | dopo 10g |",
+      "|---|---|---|---|---|---|---|---|---|---|---|---|"]
+for _, x in res.iterrows():
+    md.append(f"| {x['pair']} | {int(x['dir']):+d} | {int(x['n'])} | {x['exc_5']:+.3f} | "
+              f"{x['exc_10']:+.3f} | {x['exc_20']:+.3f} | {x['pos_10']:.0f}% | {x['q10']:.3f} | "
+              f"{x['rev10']:.0f}% | {x['rev20']:.0f}% | {x['btr_med']:.0f} | {x['dopo_10g']} |")
+open(os.path.join(RESULTS, f"tabella_incroci_{SYM}_{YEAR}.md"), "w").write("\n".join(md))
+print(f"\nsalvato: {csvp} (+ .md)  righe={len(res)}")
@@ -0,0 +1,43 @@
+"""Grafico delle traiettorie di extra-rendimento (giorno per giorno) dopo l'incrocio.
+
+Disegna l'extra-rendimento cumulato (cret_1..20 - baseline stesso regime) per un
+insieme di pattern (default: i piu' consistenti legati alla MA121/MA365).
+
+Uso:
+  python plot_trajectories.py [SYMBOL] [YEAR_MIN]
+Output:
+  ../results/trajectories_<SYM>_<YEAR>.png
+"""
+import os, sys, numpy as np
+import matplotlib
+matplotlib.use("Agg")
+import matplotlib.pyplot as plt
+from _common import load_pair, add_regime, regime_edges, HERE
+
+SYM = sys.argv[1] if len(sys.argv) > 1 else "EURUSD"
+YEAR = int(sys.argv[2]) if len(sys.argv) > 2 else 1999
+RESULTS = os.path.normpath(os.path.join(HERE, "..", "results"))
+HZ = list(range(1, 21))
+
+cr, ba = load_pair(SYM, YEAR)
+edges = regime_edges(ba)
+cr = add_regime(cr, edges); ba = add_regime(ba, edges)
+bmean = {h: ba.groupby("regime")[f"cret_{h}"].mean() for h in HZ}
+bglob = {h: ba[f"cret_{h}"].mean() for h in HZ}
+
+sel = [("MA121xMA7", 1), ("MEDxMA121", -1), ("PRICExMA121", -1), ("MA121xMA3", 1), ("MA365xMA7", 1)]
+plt.figure(figsize=(11, 6))
+for pair, d in sel:
+    g = cr[(cr.pair == pair) & (cr.dir == d)]
+    if len(g) < 20:
+        continue
+    exc = [(g[f"cret_{h}"] - g["regime"].map(bmean[h]).fillna(bglob[h])).mean() for h in HZ]
+    plt.plot(HZ, exc, marker="o", ms=3, label=f"{pair} dir={d:+d} (n={len(g)})")
+plt.axhline(0, color="k", lw=.8)
+plt.title(f"{SYM} ({YEAR}+) - extra-rendimento medio vs baseline (stesso regime)")
+plt.xlabel("giorni dopo l'incrocio"); plt.ylabel("extra-rendimento cumulato (%)")
+plt.legend(); plt.grid(alpha=.3); plt.tight_layout()
+os.makedirs(RESULTS, exist_ok=True)
+outp = os.path.join(RESULTS, f"trajectories_{SYM}_{YEAR}.png")
+plt.savefig(outp, dpi=130)
+print("salvato:", outp)
@@ -0,0 +1,4 @@
+data/*.csv
+results/*.joblib
+src/__pycache__/
+*.pyc
@@ -0,0 +1,111 @@
+# PaPP v2 — Fase 3: modelli
+
+> **Modello principale → [`README_mean_reversion.md`](README_mean_reversion.md).**
+> La validazione esterna (sez. 5b) ha mostrato che l'edge **direzionale** non
+> generalizza fuori da EURUSD, mentre la **mean-reversion** sì. Il modeling è
+> quindi orientato sul **rientro alla Mediana**. Questo documento descrive il
+> primo modello (direzionale), tenuto come riferimento metodologico.
+
+---
+
+# Fase 3 (riferimento): classificatore extra-rendimento direzionale
+
+Architettura del modello che prova a prevedere, al momento di un incrocio, se
+l'**extra-rendimento a 10 giorni** (rispetto alla baseline dello stesso regime)
+sarà **positivo o no**. È lo scheletro modulare della Fase 3, già pronto per
+l'export ONNX della Fase 4.
+
+> Stato: **scaffolding funzionante end-to-end**. Il modello di riferimento è un
+> baseline volutamente semplice; i risultati attuali confermano che l'edge è
+> debole (vedi sotto) e indicano dove migliorare. L'obiettivo di questa cartella
+> è la **struttura**, non ancora un modello ottimizzato.
+
+---
+
+## 1. Idea e target
+
+- **Target** (binario): `1` se `extra-rendimento a 10g > 0`, altrimenti `0`, dove
+  `extra = cret_10(incrocio) − media cret_10 della baseline nello stesso regime`.
+- **Regime** = `trend (sopra/sotto MA365) × tercile(cluster) × tercile(velocità)`.
+- **Feature** (solo informazioni note all'incrocio, nessun esito futuro):
+  `dist_med_pct, cluster_pct, cluster_exp, slope_a, slope_b, vel_med, acc_med,
+  vol_med` (numeriche) + `pair, dir, trend, dow, month` (categoriche).
+
+### Niente leakage (punto chiave)
+Terzili del regime e medie di baseline sono stimati **solo sul training**
+(`labeling.RegimeBaseline.fit`) e applicati a validazione/OOS. Così la label di
+test non usa mai informazione futura.
+
+---
+
+## 2. Validazione
+
+- **Walk-forward espansivo**: train = tutti gli anni fino a T, test = anno T+1,
+  scorrendo T (configurabile `min_train_years`, `step_years`).
+- **Hold-out OOS**: tutti gli anni `>= oos_start_year` (default **2020**) sono
+  tenuti fuori dal training e usati solo alla fine.
+
+Metriche (`evaluate.py`): AUC, accuracy, Brier, e **precisione/lift sul decile a
+probabilità più alta** (uso pratico: si opera solo sui segnali più forti).
+
+---
+
+## 3. Struttura
+
+```
+Modello/
+├── config.yaml            tutti i parametri (target, regime, feature, split, modello)
+├── requirements.txt
+├── src/
+│   ├── data.py            caricamento CSV + etichetta di regime
+│   ├── labeling.py        RegimeBaseline: baseline per regime e target (fit su train)
+│   ├── features.py        ColumnTransformer (one-hot + impute), selezione X
+│   ├── splits.py          split OOS + walk-forward espansivo
+│   ├── model.py           factory modello (hist_gbdt | logistic)
+│   ├── evaluate.py        metriche
+│   └── train.py           pipeline end-to-end
+├── results/               metriche walk-forward + OOS (modello .joblib non versionato)
+└── data/                  i 2 CSV di input (non versionati)
+```
+
+## 4. Come eseguire
+
+```bash
+pip install -r requirements.txt
+# copia i 2 CSV in ./data (vedi data/README.md), poi:
+cd src
+python train.py            # usa ../config.yaml
+python selftest.py         # verifiche di correttezza (reproducibilita', anti-leakage, varianti)
+```
+
+## 5. Risultati attuali (EURUSD, hold-out 2020+)
+
+Con il baseline `hist_gbdt` e tutte le coppie:
+- walk-forward medio **AUC ≈ 0.51**, OOS 2020+ **AUC ≈ 0.52**, lift sul decile ≈ 1.0×.
+
+Lettura onesta: **vicino al caso**. È coerente con la Fase 2 (edge direzionali
+piccoli) e ci dà un riferimento pulito e senza leakage da cui partire.
+
+### 5b. Validazione esterna multi-simbolo (`src/external_validation.py`)
+Addestrando SOLO su EURUSD e testando su USDJPY/USDCHF/GBPUSD (mai visti):
+- i pattern direzionali "robusti" di EURUSD **non si replicano**: concordanza di
+  segno solo **38%**; il modello esterno ha **AUC ≈ 0.48–0.55** (caso) contro
+  AUC 0.91 in-sample (memorizzazione) → l'edge direzionale è **specifico di
+  EURUSD**, non generale.
+- al contrario la **mean-reversion è universale**: ritorno alla Mediana entro 20g
+  nell'**87–90%** dei casi su tutti i simboli, mediana **3 giorni**.
+
+Conclusione operativa: il bersaglio "su/giù" non regge fuori campione; il segnale
+generalizzabile e' la **mean-reversion**. Il modeling va orientato lì.
+
+## 6. Prossimi miglioramenti previsti
+
+- **Restringere ai pattern robusti** (q<0.10): in `config.yaml` valorizzare
+  `restrict_pairs` con gli incroci MA121/MA182/MA365 emersi in Fase 2.
+- **Target alternativi**: classificare solo le code (es. extra nel top/bottom 30%)
+  invece del semplice segno; oppure regressione sull'extra-rendimento.
+- **Feature aggiuntive**: percentile storico delle metriche (come nel pannello),
+  interazioni coppia×regime, stato di mean-reversion in corso.
+- **Calibrazione** delle probabilità e scelta soglia per massimizzare la
+  precisione sui segnali operativi.
+- **Fase 4**: export del `Pipeline` in **ONNX** (skl2onnx) e inferenza in MT5.
@@ -0,0 +1,123 @@
+# Fase 3 — Modello di MEAN-REVERSION (rientro alla Mediana)
+
+> Questo è il **modello principale** della Fase 3. Nasce dopo aver dimostrato
+> (vedi `README.md` sez. 5b, validazione esterna) che l'edge **direzionale**
+> "su/giù" **non generalizza** fuori da EURUSD, mentre la **mean-reversion** è
+> universale (rientro alla Mediana entro 20g nell'87–90% dei casi su tutti i
+> major FX). Quindi modelliamo ciò che è davvero robusto: il **rientro alla
+> Mediana**.
+
+---
+
+## 1. Idea
+
+Dopo un incrocio il prezzo tende a tornare sulla Mediana. Non vogliamo prevedere
+la direzione, ma **caratterizzare il rientro**. Tre target, costruiti da esiti
+già presenti nei CSV (nessuna baseline di regime: sono osservazioni dirette):
+
+| target | tipo | colonna | domanda |
+|---|---|---|---|
+| `rev`   | classificazione | `rev_10` | rientra alla Mediana **entro 10 giorni**? (sì/no) |
+| `speed` | regressione | `bars_to_revert` | in **quanti giorni** rientra (solo eventi rientrati) |
+| `disc`  | regressione | `disc_max_pct` | **quanto si allontana** (max %) prima di rientrare |
+
+Esclusione del banale (`drop_trivial`): gli eventi già praticamente sulla
+Mediana (`|dist_med_pct| < 0.05%`) rientrano per costruzione; vengono esclusi per
+studiare il rientro "vero".
+
+## 2. Feature (note al momento dell'incrocio)
+
+`abs_dist` (=|dist_med_pct|), `dist_med_pct`, `cluster_pct`, `cluster_exp`,
+`slope_a`, `slope_b`, `vel_med`, `acc_med`, `vol_med` (numeriche) +
+`pair`, `dir`, `trend`, `dow`, `month` (categoriche). Nessuna colonna di esito
+futuro è tra le feature.
+
+## 3. Pooling pulito + validazione (anti-inquinamento)
+
+I 4 major FX (EURUSD, USDJPY, USDCHF, GBPUSD) hanno mean-reversion omogenea →
+si possono **mettere in pool**. Le feature sono già in percentuale/relative,
+quindi confrontabili tra simboli. Due validazioni, entrambe oneste:
+
+1. **Walk-forward pooled**: train tutti i simboli fino all'anno T, test anno T+1
+   → generalizzazione **nel tempo**.
+2. **Leave-one-symbol-out (LOSO)**: train su 3 simboli, test sul 4° **mai visto**
+   → generalizzazione **tra strumenti** (la prova più severa anti-inquinamento).
+
+Ogni metrica è confrontata con una **baseline banale**:
+- classificazione → accuratezza della classe maggioritaria;
+- regressione → MAE ottenuto prevedendo sempre la mediana del train
+  (`skill_% = 1 − MAE/MAE_baseline`).
+
+## 4. Risultati (pool 4 major FX, ~39k incroci)
+
+**Walk-forward (nel tempo):**
+- `rev`   : **AUC ≈ 0.65** (la baseline è 0.5) → il modello sa **ordinare** quali
+  incroci rientreranno entro 10g e quali no.
+- `speed` : skill ≈ **+2%** → marginale (la mediana è ~3g e cambia poco).
+- `disc`  : skill ≈ **−3%** → non meglio della mediana.
+
+**Leave-one-symbol-out (su simbolo mai visto):**
+
+| target | EURUSD | USDJPY | USDCHF | GBPUSD |
+|---|---|---|---|---|
+| `rev` AUC | 0.677 | 0.687 | 0.682 | 0.688 |
+| `speed` skill | +1.3% | +4.8% | −2.9% | +2.8% |
+| `disc` skill | +2.0% | +5.8% | −1.1% | −0.1% |
+
+**Lettura:** il classificatore di rientro (`rev`) ha un edge **reale e
+generalizzabile** — AUC ~0.68 anche su un simbolo completamente fuori dal
+training. I due regressori (`speed`, `disc`) aggiungono poco: la velocità e
+l'ampiezza dell'allontanamento sono in pratica vicine alla mediana storica.
+
+## 5. Cosa guida il rientro (importanza, permutation su holdout 2018+)
+
+```
+abs_dist       +0.104   <- distanza dalla Mediana: di gran lunga il fattore #1
+dist_med_pct   +0.025   <- il segno della distanza (sopra/sotto)
+trend          +0.021
+cluster_exp    +0.017   <- cluster in espansione/contrazione
+vel_med        +0.010
+... (vol_med, cluster_pct ~0)
+pair           ~0       <- QUALI linee si incrociano e' irrilevante
+```
+
+Conferma economica: il rientro dipende da **quanto sei lontano dalla Mediana** e
+dal **regime**, non dallo specifico tipo di incrocio. È coerente con la Fase 2 e
+con la validazione esterna (il "pattern" di linee era rumore).
+
+## 6. Uso operativo
+
+Il modello `rev` non dice "compra/vendi": stima la **probabilità di rientro
+rapido**. Serve da **filtro**: tra i setup di mean-reversion (prezzo lontano
+dalla Mediana), privilegiare quelli con alta probabilità ed evitare il ~25% che
+tende a NON rientrare in fretta (i casi rischiosi, spesso inizio di trend).
+
+## 7. File e come eseguire
+
+```
+Modello/
+├── config_mr.yaml              parametri del modello di mean-reversion
+├── src/
+│   ├── mr_labeling.py          costruzione dei 3 target + maschere
+│   └── mr_train.py             pool + walk-forward + LOSO + modelli finali
+└── results/
+    ├── mr_wf_<task>.csv         metriche walk-forward per anno
+    ├── mr_loso_<task>.csv       metriche leave-one-symbol-out
+    ├── mr_summary.json          riepilogo medio
+    └── mr_model_<task>.joblib   modelli finali (non versionati)
+```
+
+```bash
+pip install -r requirements.txt
+# copia in ./data i CSV crosses+bars dei 4 simboli (vedi data/README.md), poi:
+cd src
+python mr_train.py            # usa ../config_mr.yaml
+```
+
+## 8. Prossimi passi
+
+- **Calibrazione** delle probabilità di `rev` e scelta soglia operativa
+  (precisione vs copertura) per l'EA.
+- Aggiungere altri major FX al pool per irrobustire ancora il LOSO.
+- **Fase 4**: export del modello `rev` in **ONNX** (skl2onnx) e inferenza in MT5
+  come filtro dei segnali di mean-reversion.
@@ -0,0 +1,53 @@
+# Configurazione Fase 3 — classificatore extra-rendimento positivo
+
+symbol: EURUSD
+year_min: 1999          # esclude i dati EURUSD sintetici pre-1999
+
+# --- target ---
+horizon: 10             # orizzonte (giorni D1) per l'extra-rendimento
+target: excess_positive # 1 se extra-rendimento a `horizon` > 0, altrimenti 0
+
+# --- definizione del regime per la baseline (terzili stimati SOLO sul train) ---
+regime:
+  use_trend: true       # sopra/sotto MA365
+  cluster_terciles: true
+  velocity_terciles: true
+
+# --- feature usate dal modello (note al momento dell'incrocio) ---
+features_numeric:
+  - dist_med_pct
+  - cluster_pct
+  - cluster_exp
+  - slope_a
+  - slope_b
+  - vel_med
+  - acc_med
+  - vol_med
+features_categorical:
+  - pair
+  - dir
+  - trend
+  - dow
+  - month
+
+# --- validazione ---
+oos_start_year: 2020    # hold-out finale mai usato in training
+walkforward:
+  scheme: expanding     # finestra espansiva
+  min_train_years: 8    # anni minimi nel primo fold
+  step_years: 1
+
+# --- modello di riferimento ---
+model:
+  kind: hist_gbdt       # hist_gbdt | logistic
+  hist_gbdt:
+    max_depth: 4
+    learning_rate: 0.05
+    max_iter: 400
+    l2_regularization: 1.0
+    early_stopping: true
+
+# opzionale: limita ai pattern robusti (q<0.10). Vuoto = usa tutti gli incroci.
+restrict_pairs: []
+
+seed: 42
@@ -0,0 +1,44 @@
+# Configurazione Fase 3 — modello di MEAN-REVERSION (rientro alla Mediana)
+
+# pooling pulito sui major FX (dinamica di mean-reversion omogenea)
+symbols: [EURUSD, USDJPY, USDCHF, GBPUSD]
+year_min: 1999
+
+horizon: 10            # orizzonte per il target di classificazione rev_N
+drop_trivial: true     # esclude gli eventi gia' praticamente sulla Mediana
+trivial_eps: 0.05      # soglia |dist_med_pct| (%) sotto cui l'evento e' "banale"
+
+# feature note al momento dell'incrocio
+features_numeric:
+  - abs_dist           # |dist_med_pct| (derivata): quanto e' lontano dalla Mediana
+  - dist_med_pct
+  - cluster_pct
+  - cluster_exp
+  - slope_a
+  - slope_b
+  - vel_med
+  - acc_med
+  - vol_med
+features_categorical:
+  - pair
+  - dir
+  - trend
+  - dow
+  - month
+
+# validazione
+oos_start_year: 2020
+walkforward:
+  min_train_years: 8
+  step_years: 1
+
+model:
+  kind: hist_gbdt
+  hist_gbdt:
+    max_depth: 4
+    learning_rate: 0.05
+    max_iter: 400
+    l2_regularization: 1.0
+    early_stopping: true
+
+seed: 42
@@ -0,0 +1,8 @@
+# Dati di input (non versionati)
+
+Copia qui i due CSV prodotti da `PaPP v2/PaPP_CrossExport.mq5`:
+
+- `PaPP_crosses_<SYMBOL>_D1.csv`
+- `PaPP_bars_<SYMBOL>_D1.csv`
+
+Sono gli stessi file usati in `PaPP v2/Analisi/`. Poi lancia `src/train.py`.
@@ -0,0 +1,8 @@
+pandas
+numpy
+scikit-learn
+pyyaml
+joblib
+# Fase 4 (export ONNX), opzionali finche' non si esporta:
+# skl2onnx
+# onnxruntime
@@ -0,0 +1,5 @@
+symbol,n,base_rate,auc,acc,brier,prec_top_decile,lift_top_decile
+EURUSD (in-sample),16895,0.4976028410772418,0.913591163259108,0.8320213080793134,0.15547236980731827,0.9875666074600356,1.9846482494394315
+USDJPY,7084,0.5172219085262564,0.4800203976097449,0.49110671936758893,0.28183992572414085,0.4646892655367232,0.8984330668837737
+USDCHF,7967,0.5049579515501443,0.47560023778083327,0.48449855654575125,0.2879368779869159,0.4296482412060301,0.8508594426270052
+GBPUSD,7239,0.5020030390937975,0.5483399577270303,0.5322558364414974,0.2593864013259506,0.5712309820193637,1.137903433912541
@@ -0,0 +1,5 @@
+n,mae,mae_baseline,skill_%,r2,test_symbol
+15898,0.7016688523942158,0.7156681469367216,1.956115359112609,0.056705406202969044,EURUSD
+6635,0.766700972158277,0.8138184204973624,5.789675823544238,0.09699286957940556,USDJPY
+7349,0.7110993410001212,0.703173893046673,-1.1270964453912402,0.13820883251935367,USDCHF
+6807,0.7712259995571173,0.7706658777728809,-0.07268023671362922,0.10481685322904755,GBPUSD
@@ -0,0 +1,5 @@
+n,base_rate,acc_baseline,auc,acc,test_symbol
+15887,0.7324227355699628,0.7324227355699628,0.6765454819075187,0.7357587965002832,EURUSD
+6619,0.7028252001812962,0.7028252001812962,0.6869979773747487,0.719292944553558,USDJPY
+7331,0.7603328331741918,0.7603328331741918,0.6816590320250597,0.7442368026190151,USDCHF
+6798,0.7374227714033539,0.7374227714033539,0.687844098341511,0.7375698734922036,GBPUSD
@@ -0,0 +1,5 @@
+n,mae,mae_baseline,skill_%,r2,test_symbol
+13909,3.610173858972498,3.65878208354303,1.3285356564187945,0.09908303164055288,EURUSD
+5729,3.615529034826519,3.7987432361668705,4.823021456044085,0.1281263482188003,USDJPY
+6570,3.627862458240022,3.5245053272450533,-2.9325287210094197,0.07345132592032444,USDCHF
+6090,3.638542831980693,3.744006568144499,2.8168683533072225,0.11825074333860008,GBPUSD
@@ -0,0 +1,51 @@
+{
+  "wf": {
+    "rev": {
+      "n": 1594.0,
+      "base_rate": 0.7183856164543461,
+      "acc_baseline": 0.7183856164543461,
+      "auc": 0.6478491068895667,
+      "acc": 0.7130101340748866,
+      "test_year": 2016.5
+    },
+    "speed": {
+      "n": 1406.55,
+      "mae": 3.6537111122909542,
+      "mae_baseline": 3.7337467740160712,
+      "skill_%": 1.7998203587207346,
+      "r2": 0.07833366023387726,
+      "test_year": 2016.5
+    },
+    "disc": {
+      "n": 1596.7,
+      "mae": 0.7847562209218487,
+      "mae_baseline": 0.7657217825432683,
+      "skill_%": -3.381481774117468,
+      "r2": -0.36203395606382444,
+      "test_year": 2016.5
+    }
+  },
+  "loso": {
+    "rev": {
+      "n": 9158.75,
+      "base_rate": 0.7332508850822013,
+      "acc_baseline": 0.7332508850822013,
+      "auc": 0.6832616474122095,
+      "acc": 0.734214604291265
+    },
+    "speed": {
+      "n": 8074.5,
+      "mae": 3.623027046004933,
+      "mae_baseline": 3.681509303774863,
+      "skill_%": 1.5089741861901707,
+      "r2": 0.10472786227956943
+    },
+    "disc": {
+      "n": 9172.25,
+      "mae": 0.7376737912774329,
+      "mae_baseline": 0.7508315845634095,
+      "skill_%": 1.6365036251379943,
+      "r2": 0.09918099038269396
+    }
+  }
+}
@@ -0,0 +1,21 @@
+n,mae,mae_baseline,skill_%,r2,test_year
+468,0.5210450337997958,0.4877705555555555,-6.82174802584008,-0.440278374819538,2007
+511,1.4979005200832076,1.46627927592955,-2.1565635327970734,-0.4428980601648529,2008
+590,0.5372706093503566,0.624245779661017,13.932840740691965,0.09814855360679986,2009
+548,0.8435515547481117,0.9210056204379563,8.40972779873087,-0.20129888622520697,2010
+649,0.6264895295465607,0.7349227426810478,14.754368974746313,-0.23270335993701874,2011
+563,0.8444189035765441,0.7120972291296623,-18.581967326092208,-0.6572098948790617,2012
+574,0.6570009471217217,0.5640415679442509,-16.480944749564785,-1.9530900867332583,2013
+1089,0.8585576108637076,0.8849660055096419,2.984114020371431,-0.0058690268732339845,2014
+2465,0.86287949087831,0.8346033630831645,-3.387971945223023,0.1741985535476418,2015
+2440,0.9893521953097881,0.9588108852459016,-3.1853320121677298,0.06164644338816894,2016
+2405,0.6483027913003414,0.606651659043659,-6.865741094707012,-0.3827607195275795,2017
+2208,0.716304832228868,0.6826646195652174,-4.927780303756735,-0.30219708772441267,2018
+2520,0.7276522650483845,0.693340365079365,-4.948781536048585,-0.9380918084727767,2019
+2351,1.0262956818683626,0.9582834198213527,-7.097301345325269,-0.054525480586665065,2020
+2378,0.5921425747388034,0.566631362489487,-4.502259129680586,-0.6404632411590949,2021
+2074,0.9417510265311481,1.0620946142719383,11.330778456426438,-0.41893129794772066,2022
+2185,0.6089553673717031,0.5467215652173913,-11.383088964044408,-0.23632995343602725,2023
+2317,0.7212702214350022,0.6373334527406128,-13.169992620574188,-0.24062608198432445,2024
+2335,0.7021795509288201,0.7111189250535332,1.2570856729822166,0.1140083899835217,2025
+1264,0.7718037117074369,0.6608526424050633,-16.78907856047691,-0.5414077013318492,2026
@@ -0,0 +1,21 @@
+n,base_rate,acc_baseline,auc,acc,test_year
+468,0.6175213675213675,0.6175213675213675,0.641878177495119,0.6260683760683761,2007
+511,0.6516634050880626,0.6516634050880626,0.5756149407834801,0.6594911937377691,2008
+590,0.7440677966101695,0.7440677966101695,0.5982138816394877,0.7372881355932204,2009
+548,0.7408759124087592,0.7408759124087592,0.6361617983764658,0.7299270072992701,2010
+649,0.5855161787365177,0.5855161787365177,0.6710135002934846,0.6718027734976888,2011
+563,0.8206039076376554,0.8206039076376554,0.6997342591401998,0.7708703374777975,2012
+574,0.6933797909407665,0.6933797909407665,0.6654865235267245,0.6428571428571429,2013
+1089,0.6464646464646465,0.6464646464646465,0.6203659976387249,0.6721763085399449,2014
+2465,0.7829614604462475,0.7829614604462475,0.6354597840298292,0.7517241379310344,2015
+2440,0.7487704918032787,0.7487704918032787,0.6421575586789066,0.6905737704918032,2016
+2405,0.7600831600831601,0.7600831600831601,0.6408060252797805,0.755925155925156,2017
+2208,0.7336956521739131,0.7336956521739131,0.6192271352985639,0.7133152173913043,2018
+2520,0.8067460317460318,0.8067460317460318,0.6465879719737271,0.7746031746031746,2019
+2351,0.7243726074011059,0.7243726074011059,0.6688414780017834,0.7209698000850702,2020
+2378,0.7863751051303617,0.7863751051303617,0.6841361741547013,0.7901597981497056,2021
+2074,0.6769527483124397,0.6769527483124397,0.5842326827401454,0.6557377049180327,2022
+2185,0.6668192219679634,0.6668192219679634,0.6764596076538425,0.6906178489702517,2023
+2317,0.6551575312904618,0.6551575312904618,0.6896672553471812,0.6870953819594303,2024
+2335,0.7430406852248393,0.7430406852248393,0.7314169068203651,0.7644539614561028,2025
+1210,0.7826446280991736,0.7826446280991736,0.6295204789188191,0.7545454545454545,2026
@@ -0,0 +1,21 @@
+n,mae,mae_baseline,skill_%,r2,test_year
+338,3.465379140810698,3.4142011834319526,-1.498973101734502,0.12927353007997744,2007
+400,4.090858376700547,3.9425,-3.7630533088280904,0.04579965148367826,2008
+540,4.0205317754813965,3.8740740740740742,-3.780456919691866,-0.12200728544542727,2009
+470,3.1693714434220257,3.421276595744681,7.362899352714425,0.2246464741787182,2010
+495,4.314538334266083,4.3232323232323235,0.20109927749014656,-0.055325713812715005,2011
+515,3.2237999945625653,2.9029126213592233,-11.053979745800735,-0.06562655938335582,2012
+485,3.733393114617742,4.072164948453608,8.319207058754174,0.19434702822584105,2013
+879,3.924266870235131,4.180887372013652,6.137943430294424,0.022748161878883844,2014
+2243,3.398709049328624,3.3410610789121713,-1.7254389864438613,0.07268045675088919,2015
+2243,3.6650255510608725,3.7588051716451183,2.494931668490852,0.06864404910302002,2016
+2206,3.65145803728882,3.8028105167724386,3.9800163278205125,0.10526816265720629,2017
+1923,3.577364530993464,3.4607384295371815,-3.3699773568810043,0.07894792932730887,2018
+2354,3.356457496216363,3.373406966864911,0.502443696092203,0.015425103761181336,2019
+2116,3.8333614130177756,3.972117202268431,3.4932450928540915,0.049572458729656765,2020
+2190,3.3981138450501156,3.4990867579908675,2.8856933229837733,0.12873115565641913,2021
+1715,3.799187552337051,3.816909620991254,0.4643041207142984,0.0433313417575899,2022
+1810,4.043300720188006,3.8784530386740332,-4.250346204277644,0.06762624567274822,2023
+1997,3.6962952238115996,4.476214321482224,17.423631704309617,0.2427214165484335,2024
+2094,3.369937232661497,3.7597898758357213,10.369000823152874,0.2265055214709174,2025
+1118,3.3428725437687103,3.4042933810375673,1.804216922401003,0.09336407603657426,2026
@@ -0,0 +1,9 @@
+{
+  "n": 3951,
+  "base_rate": 0.49253353581371806,
+  "auc": 0.5241849128463528,
+  "acc": 0.5206276891926095,
+  "brier": 0.2758629924455611,
+  "prec_top_decile": 0.48860759493670886,
+  "lift_top_decile": 0.9920290892060312
+}
@@ -0,0 +1,14 @@
+n,base_rate,auc,acc,brier,prec_top_decile,lift_top_decile,fold,test_years
+506,0.6027667984189723,0.5552565043634288,0.5533596837944664,0.2929861795083319,0.66,1.0949508196721314,0,2007-2007
+528,0.4431818181818182,0.4868160939589511,0.48674242424242425,0.3025718576380564,0.19230769230769232,0.43392504930966475,1,2008-2008
+618,0.5857605177993528,0.48292904005524856,0.46116504854368934,0.32693476077811057,0.5081967213114754,0.8675844579295353,2,2009-2009
+570,0.44912280701754387,0.5532568670382165,0.531578947368421,0.28012422532136644,0.631578947368421,1.40625,3,2010-2010
+669,0.554559043348281,0.3955570831599703,0.4200298953662182,0.3276694334072587,0.3484848484848485,0.6283999019848078,4,2011-2011
+616,0.5227272727272727,0.5127920733510796,0.5032467532467533,0.2825509892233342,0.5901639344262295,1.129009265858874,5,2012-2012
+583,0.5265866209262435,0.5670466883821933,0.5214408233276158,0.2796922887853283,0.7068965517241379,1.342412669886555,6,2013-2013
+565,0.2884955752212389,0.5871104599700881,0.4424778761061947,0.3559192608214337,0.17857142857142858,0.6189745836985101,7,2014-2014
+627,0.45614035087719296,0.46299448352234274,0.49920255183413076,0.31880860582951115,0.3709677419354839,0.8132754342431763,8,2015-2015
+749,0.4512683578104139,0.5659165838840179,0.5046728971962616,0.2895300011880442,0.6756756756756757,1.4972813049736124,9,2016-2016
+628,0.6496815286624203,0.4584336007130124,0.49044585987261147,0.2895065709863026,0.3870967741935484,0.5958254269449715,10,2017-2017
+622,0.5,0.41347794170862584,0.45980707395498394,0.29186125547058084,0.2903225806451613,0.5806451612903226,11,2018-2018
+707,0.36633663366336633,0.5378947186982901,0.5487977369165488,0.27594238285206885,0.5142857142857142,1.4038610038610038,12,2019-2019
@@ -0,0 +1,54 @@
+"""Caricamento dei dati e definizione del regime.
+
+I dati sono i due CSV prodotti da `PaPP v2/PaPP_CrossExport.mq5`:
+  - PaPP_crosses_<SYM>_D1.csv  (un record per incrocio)
+  - PaPP_bars_<SYM>_D1.csv     (un record per giorno D1 = baseline)
+
+Per default cercati in ../data; sovrascrivibili via argomento.
+
+NB sulla correttezza temporale: i terzili del regime e le medie di baseline
+NON vengono calcolati qui su tutti i dati, ma stimati sul SOLO training
+(vedi labeling.RegimeBaseline.fit) e applicati al test. Qui carichiamo solo.
+"""
+from __future__ import annotations
+import os
+import numpy as np
+import pandas as pd
+
+HERE = os.path.dirname(os.path.abspath(__file__))
+DATA_DIR = os.path.normpath(os.path.join(HERE, "..", "data"))
+
+
+def _read(path: str) -> pd.DataFrame:
+    df = pd.read_csv(path)
+    df["time"] = pd.to_datetime(df["time"], format="%Y.%m.%d", errors="coerce")
+    if df["time"].isna().all():
+        df["time"] = pd.to_datetime(df["time"], errors="coerce")
+    return df.dropna(subset=["time"]).sort_values("time").reset_index(drop=True)
+
+
+def load(symbol: str = "EURUSD", year_min: int = 1999, data_dir: str | None = None):
+    d = data_dir or DATA_DIR
+    crosses = _read(os.path.join(d, f"PaPP_crosses_{symbol}_D1.csv"))
+    bars = _read(os.path.join(d, f"PaPP_bars_{symbol}_D1.csv"))
+    if year_min:
+        crosses = crosses[crosses.time.dt.year >= year_min].reset_index(drop=True)
+        bars = bars[bars.time.dt.year >= year_min].reset_index(drop=True)
+    return crosses, bars
+
+
+def regime_labels(df: pd.DataFrame, edges: dict, cfg_regime: dict) -> pd.Series:
+    """Etichetta di regime coerente con `edges` (terzili stimati sul train)."""
+    parts = []
+    if cfg_regime.get("use_trend", True):
+        parts.append((df["trend"] > 0).astype(int).astype(str))
+    if cfg_regime.get("cluster_terciles", True):
+        parts.append(np.digitize(df["cluster_pct"], edges["cl"]).astype(str))
+    if cfg_regime.get("velocity_terciles", True):
+        parts.append(np.digitize(df["vel_med"], edges["ve"]).astype(str))
+    if not parts:
+        return pd.Series(["all"] * len(df), index=df.index)
+    out = parts[0]
+    for p in parts[1:]:
+        out = out + "_" + p
+    return out
@@ -0,0 +1,23 @@
+"""Metriche di valutazione del classificatore."""
+from __future__ import annotations
+import numpy as np
+from sklearn.metrics import roc_auc_score, accuracy_score, brier_score_loss
+
+
+def metrics(y_true, p_pred) -> dict:
+    y_true = np.asarray(y_true)
+    p = np.asarray(p_pred)
+    out = {"n": int(len(y_true)), "base_rate": float(y_true.mean())}
+    if len(np.unique(y_true)) < 2:
+        out.update({"auc": np.nan, "acc": np.nan, "brier": np.nan,
+                    "prec_top_decile": np.nan, "lift_top_decile": np.nan})
+        return out
+    out["auc"] = float(roc_auc_score(y_true, p))
+    out["acc"] = float(accuracy_score(y_true, (p >= 0.5).astype(int)))
+    out["brier"] = float(brier_score_loss(y_true, p))
+    # precisione sul decile a piu' alta probabilita' (uso pratico: prendo solo i segnali piu' forti)
+    k = max(1, int(0.1 * len(p)))
+    top = np.argsort(p)[-k:]
+    out["prec_top_decile"] = float(y_true[top].mean())
+    out["lift_top_decile"] = float(y_true[top].mean() / max(y_true.mean(), 1e-9))
+    return out
@@ -0,0 +1,116 @@
+"""Validazione esterna: addestra SOLO su EURUSD, testa su altri simboli mai visti.
+
+Due livelli:
+  A) Pattern: gli incroci robusti di EURUSD (extra-rendimento a 10g) hanno lo
+     stesso segno/forza sugli altri simboli? (replica del pattern)
+  B) Modello: il classificatore addestrato su EURUSD generalizza? AUC e
+     precisione sul decile piu' forte su ogni simbolo esterno.
+
+Nessun dato dei simboli di test entra nell'addestramento (zero inquinamento).
+La baseline di ciascun simbolo (definizione del target) e' calcolata sui dati
+di quel simbolo: serve solo a definire la ground-truth, non i pesi del modello.
+
+Uso:
+  python external_validation.py [config.yaml] SYM_TRAIN SYM_TEST1 SYM_TEST2 ...
+  (default: train=EURUSD, test=USDJPY USDCHF GBPUSD)
+"""
+from __future__ import annotations
+import os, sys
+import numpy as np, pandas as pd
+
+HERE = os.path.dirname(os.path.abspath(__file__))
+sys.path.insert(0, HERE)
+import train as T
+from data import load
+from labeling import RegimeBaseline
+from features import select_xy
+from model import make_model
+from evaluate import metrics
+
+RESULTS = os.path.normpath(os.path.join(HERE, "..", "results"))
+ROBUST = ["MA365xMA7", "MA365xMA182", "MA365xMA121", "MA121xMA7",
+          "MA121xMA3", "PRICExMA121", "MA182xMA30", "MA182xMA121"]
+
+
+def load_sym(sym, cfg):
+    cr, ba = load(sym, cfg["year_min"])
+    cr = cr.dropna(subset=[f"cret_{cfg['horizon']}"]).reset_index(drop=True)
+    return cr, ba
+
+
+def main():
+    cfg_path = sys.argv[1] if len(sys.argv) > 1 else os.path.join(HERE, "..", "config.yaml")
+    cfg = T.load_cfg(cfg_path)
+    args = sys.argv[2:]
+    sym_tr = args[0] if args else "EURUSD"
+    sym_te = args[1:] if len(args) > 1 else ["USDJPY", "USDCHF", "GBPUSD"]
+    num, cat, h = cfg["features_numeric"], cfg["features_categorical"], cfg["horizon"]
+
+    cr_tr, ba_tr = load_sym(sym_tr, cfg)
+
+    # ---------- A) replica dei pattern ----------
+    def pair_excess(cr, ba):
+        rb = RegimeBaseline(cfg["regime"], h).fit(ba)
+        ex = rb.excess(cr)
+        out = {}
+        for (p, d), idx in cr.groupby(["pair", "dir"]).groups.items():
+            out[(p, int(d))] = ex[cr.index.get_indexer(idx)].mean()
+        return out
+
+    base_ex = pair_excess(cr_tr, ba_tr)
+    print(f"=== A) Replica pattern robusti: extra-rendimento {h}g (%), segno vs {sym_tr} ===")
+    print(f"{'pattern':16s} {sym_tr:>9s}", end="")
+    sym_ex = {}
+    for s in sym_te:
+        c, b = load_sym(s, cfg)
+        sym_ex[s] = pair_excess(c, b)
+        print(f" {s:>9s}", end="")
+    print("  concordi")
+    agree_counts = []
+    for p in ROBUST:
+        for d in (1, -1):
+            key = (p, d)
+            if key not in base_ex:
+                continue
+            row = f"{p+('+' if d>0 else '-'):16s} {base_ex[key]*1:+8.3f}"
+            signs = []
+            for s in sym_te:
+                v = sym_ex[s].get(key, np.nan)
+                row += f" {v:+8.3f}" if not np.isnan(v) else f" {'n/a':>8s}"
+                if not np.isnan(v):
+                    signs.append(np.sign(v) == np.sign(base_ex[key]))
+            conc = f"{sum(signs)}/{len(signs)}" if signs else "-"
+            agree_counts.append((sum(signs), len(signs)))
+            print(row + f"   {conc}")
+    tot_a = sum(a for a, _ in agree_counts); tot_n = sum(n for _, n in agree_counts)
+    print(f"\nConcordanza di segno totale: {tot_a}/{tot_n} ({tot_a/max(tot_n,1)*100:.0f}%)")
+
+    # ---------- B) modello EURUSD -> simboli esterni ----------
+    print(f"\n=== B) Modello addestrato su {sym_tr}, testato esternamente ===")
+    rb_tr = RegimeBaseline(cfg["regime"], h).fit(ba_tr)
+    y_tr = rb_tr.label(cr_tr)
+    mdl = make_model(cfg, num, cat)
+    mdl.fit(select_xy(cr_tr, num, cat), y_tr)
+
+    rows = []
+    # riferimento in-sample (stesso simbolo, solo per confronto)
+    p_in = mdl.predict_proba(select_xy(cr_tr, num, cat))[:, 1]
+    rows.append({"symbol": sym_tr + " (in-sample)", **metrics(y_tr, p_in)})
+    for s in sym_te:
+        c, b = load_sym(s, cfg)
+        rb = RegimeBaseline(cfg["regime"], h).fit(b)
+        y = rb.label(c)
+        p = mdl.predict_proba(select_xy(c, num, cat))[:, 1]
+        rows.append({"symbol": s, **metrics(y, p)})
+    res = pd.DataFrame(rows)
+    for _, r in res.iterrows():
+        print(f"  {r['symbol']:22s} n={int(r['n']):5d} AUC={r['auc']:.3f} "
+              f"acc={r['acc']:.3f} prec@10%={r['prec_top_decile']:.3f} "
+              f"(base {r['base_rate']:.3f}, lift {r['lift_top_decile']:.2f}x)")
+    os.makedirs(RESULTS, exist_ok=True)
+    res.to_csv(os.path.join(RESULTS, "external_validation.csv"), index=False)
+    print(f"\nsalvato: {os.path.join(RESULTS,'external_validation.csv')}")
+
+
+if __name__ == "__main__":
+    main()
@@ -0,0 +1,33 @@
+"""Feature engineering: costruisce la matrice X dalle colonne di contesto.
+
+Le feature sono SOLO informazioni note al momento dell'incrocio (nessun esito
+futuro). Categoriche e numeriche sono gestite da un ColumnTransformer
+(one-hot per le categoriche, passthrough per le numeriche) per restare
+compatibili con l'export ONNX della Fase 4.
+"""
+from __future__ import annotations
+import pandas as pd
+from sklearn.compose import ColumnTransformer
+from sklearn.preprocessing import OneHotEncoder
+from sklearn.impute import SimpleImputer
+from sklearn.pipeline import Pipeline
+
+
+def build_preprocessor(num_cols: list[str], cat_cols: list[str]) -> ColumnTransformer:
+    num = Pipeline([("impute", SimpleImputer(strategy="median"))])
+    cat = Pipeline([
+        ("impute", SimpleImputer(strategy="most_frequent")),
+        ("oh", OneHotEncoder(handle_unknown="ignore", sparse_output=False)),
+    ])
+    return ColumnTransformer([
+        ("num", num, num_cols),
+        ("cat", cat, cat_cols),
+    ])
+
+
+def select_xy(df: pd.DataFrame, num_cols: list[str], cat_cols: list[str]):
+    cols = num_cols + cat_cols
+    X = df[cols].copy()
+    for c in cat_cols:
+        X[c] = X[c].astype(str)
+    return X
@@ -0,0 +1,40 @@
+"""Costruzione del target: extra-rendimento positivo a `horizon` giorni.
+
+extra = cret_h(incrocio) - baseline_mean_h(regime)
+
+`RegimeBaseline` impara i terzili del regime e la media di baseline per regime
+SOLO sui dati di training (fit), e li applica a qualunque set (transform).
+Cosi' la label di test non usa informazione futura.
+"""
+from __future__ import annotations
+import numpy as np
+import pandas as pd
+from data import regime_labels
+
+
+class RegimeBaseline:
+    def __init__(self, cfg_regime: dict, horizon: int):
+        self.cfg_regime = cfg_regime
+        self.h = horizon
+        self.edges_: dict = {}
+        self.base_mean_: pd.Series | None = None
+        self.base_glob_: float = 0.0
+
+    def fit(self, bars_train: pd.DataFrame) -> "RegimeBaseline":
+        self.edges_ = {
+            "cl": np.quantile(bars_train["cluster_pct"], [1/3, 2/3]),
+            "ve": np.quantile(bars_train["vel_med"], [1/3, 2/3]),
+        }
+        reg = regime_labels(bars_train, self.edges_, self.cfg_regime)
+        col = f"cret_{self.h}"
+        self.base_mean_ = bars_train.assign(_r=reg).groupby("_r")[col].mean()
+        self.base_glob_ = float(bars_train[col].mean())
+        return self
+
+    def excess(self, crosses: pd.DataFrame) -> np.ndarray:
+        reg = regime_labels(crosses, self.edges_, self.cfg_regime)
+        bexp = reg.map(self.base_mean_).fillna(self.base_glob_).values
+        return crosses[f"cret_{self.h}"].values - bexp
+
+    def label(self, crosses: pd.DataFrame) -> np.ndarray:
+        return (self.excess(crosses) > 0).astype(int)
@@ -0,0 +1,47 @@
+"""Factory del modello di riferimento.
+
+`hist_gbdt` (HistGradientBoosting) come baseline forte e veloce; `logistic`
+come riferimento lineare interpretabile. Entrambi esportabili in ONNX
+(skl2onnx) per la Fase 4.
+"""
+from __future__ import annotations
+from sklearn.ensemble import (HistGradientBoostingClassifier,
+                              HistGradientBoostingRegressor)
+from sklearn.linear_model import LogisticRegression
+from sklearn.pipeline import Pipeline
+from features import build_preprocessor
+
+
+def make_model(cfg: dict, num_cols: list[str], cat_cols: list[str]) -> Pipeline:
+    kind = cfg["model"]["kind"]
+    pre = build_preprocessor(num_cols, cat_cols)
+    if kind == "hist_gbdt":
+        p = cfg["model"]["hist_gbdt"]
+        clf = HistGradientBoostingClassifier(
+            max_depth=p["max_depth"],
+            learning_rate=p["learning_rate"],
+            max_iter=p["max_iter"],
+            l2_regularization=p["l2_regularization"],
+            early_stopping=p["early_stopping"],
+            random_state=cfg["seed"],
+        )
+    elif kind == "logistic":
+        clf = LogisticRegression(max_iter=1000, C=1.0, random_state=cfg["seed"])
+    else:
+        raise ValueError(f"model.kind sconosciuto: {kind}")
+    return Pipeline([("pre", pre), ("clf", clf)])
+
+
+def make_regressor(cfg: dict, num_cols: list[str], cat_cols: list[str]) -> Pipeline:
+    """Regressore HistGradientBoosting per i target continui di mean-reversion."""
+    pre = build_preprocessor(num_cols, cat_cols)
+    p = cfg["model"]["hist_gbdt"]
+    reg = HistGradientBoostingRegressor(
+        max_depth=p["max_depth"],
+        learning_rate=p["learning_rate"],
+        max_iter=p["max_iter"],
+        l2_regularization=p["l2_regularization"],
+        early_stopping=p["early_stopping"],
+        random_state=cfg["seed"],
+    )
+    return Pipeline([("pre", pre), ("reg", reg)])
@@ -0,0 +1,55 @@
+"""Target di mean-reversion (rientro alla Mediana dopo un incrocio).
+
+A differenza del target direzionale, questi esiti sono diretti e NON richiedono
+una baseline di regime: sono proprieta' osservate dell'evento.
+
+Tre target (vedi README sez. Mean-reversion):
+  - REV_N  (classificazione): rientra alla Mediana entro N giorni? (rev_N)
+  - SPEED  (regressione)    : in quanti giorni rientra (bars_to_revert);
+                              definito solo per gli eventi che rientrano entro 20g
+  - DISC   (regressione)    : massimo allontanamento dalla Mediana prima del
+                              rientro, in % (disc_max_pct)
+
+Nota sulla "banalita'": l'incrocio PRICExMED ha per costruzione dist~0 e rientro
+immediato. Con `drop_trivial` si possono escludere gli eventi gia' praticamente
+sulla Mediana (|dist_med_pct| < trivial_eps) per studiare il rientro "vero".
+"""
+from __future__ import annotations
+import numpy as np
+import pandas as pd
+
+
+def make_targets(df: pd.DataFrame, horizon: int = 10,
+                 drop_trivial: bool = False, trivial_eps: float = 0.05):
+    """Ritorna un dict di colonne target + una maschera 'valid' per ciascun task.
+
+    Output:
+      {
+        "rev":   (y, mask),   # classificazione 0/1
+        "speed": (y, mask),   # regressione (giorni), solo eventi rientrati
+        "disc":  (y, mask),   # regressione (% allontanamento)
+      }
+    """
+    n = len(df)
+    base_mask = np.ones(n, bool)
+    if drop_trivial:
+        base_mask &= df["dist_med_pct"].abs().values >= trivial_eps
+
+    out = {}
+
+    # REV_N: classificazione
+    yrev = df[f"rev_{horizon}"].astype(float).values
+    mrev = base_mask & ~np.isnan(yrev)
+    out["rev"] = (np.nan_to_num(yrev).astype(int), mrev)
+
+    # SPEED: giorni al rientro, solo per chi rientra entro 20g (bars_to_revert valorizzato)
+    btr = pd.to_numeric(df["bars_to_revert"], errors="coerce").values
+    mspeed = base_mask & ~np.isnan(btr)
+    out["speed"] = (btr, mspeed)
+
+    # DISC: massimo allontanamento (in valore assoluto, %)
+    disc = pd.to_numeric(df["disc_max_pct"], errors="coerce").abs().values
+    mdisc = base_mask & ~np.isnan(disc)
+    out["disc"] = (disc, mdisc)
+
+    return out
@@ -0,0 +1,52 @@
+"""Self-test del modello di mean-reversion.
+
+  M1 feature senza esiti futuri
+  M2 reproducibilita' (LOSO rev AUC identico tra due run)
+  M3 controllo negativo: con label rev mescolate l'AUC deve ~0.5
+"""
+import os, sys
+import numpy as np
+HERE = os.path.dirname(os.path.abspath(__file__))
+sys.path.insert(0, HERE)
+from mr_train import load_cfg, load_pool, leave_one_symbol_out
+from mr_labeling import make_targets
+from features import select_xy
+from model import make_model
+from sklearn.metrics import roc_auc_score
+
+CFG = os.path.join(HERE, "..", "config_mr.yaml")
+ok = True
+
+def check(name, cond):
+    global ok
+    print(("PASS" if cond else "FAIL"), "-", name); ok = ok and cond
+
+cfg = load_cfg(CFG)
+num, cat = cfg["features_numeric"], cfg["features_categorical"]
+
+# M1
+future = ("ret_", "mfe_", "mae_", "dir_", "rev_", "cret_", "bars_to_revert", "disc_max")
+feats = num + cat
+check("M1 feature senza esiti futuri",
+      not any(f.startswith(future) for f in feats))
+
+df = load_pool(cfg)
+
+# M2 reproducibilita'
+a = leave_one_symbol_out(cfg, df, num, cat)["rev"].auc.mean()
+b = leave_one_symbol_out(cfg, df, num, cat)["rev"].auc.mean()
+check("M2 reproducibilita' LOSO rev AUC", abs(a - b) < 1e-9)
+
+# M3 controllo negativo
+y, mask = make_targets(df, cfg["horizon"], cfg["drop_trivial"], cfg["trivial_eps"])["rev"]
+d = df[mask].reset_index(drop=True); y = y[mask]
+tr = d.time.dt.year.values < 2018
+m = make_model(cfg, num, cat); m.fit(select_xy(d[tr], num, cat), y[tr])
+p = m.predict_proba(select_xy(d[~tr], num, cat))[:, 1]
+yte = y[~tr].copy(); np.random.default_rng(0).shuffle(yte)
+auc_shuf = roc_auc_score(yte, p)
+check("M3 controllo negativo AUC~0.5 (0.45-0.55)", 0.45 <= auc_shuf <= 0.55)
+
+print(f"\nLOSO rev AUC medio reale = {a:.3f}")
+print("=== SELF-TEST MR:", "TUTTO OK" if ok else "CI SONO FAIL", "===")
+sys.exit(0 if ok else 1)
@@ -0,0 +1,192 @@
+"""Fase 3 — modello di MEAN-REVERSION (rientro alla Mediana).
+
+Pooling pulito sui major FX. Tre target (vedi mr_labeling):
+  - rev   : classificatore "rientra entro `horizon` giorni si/no"
+  - speed : regressione su quanti giorni impiega a rientrare (eventi rientrati)
+  - disc  : regressione sul massimo allontanamento (% ) prima del rientro
+
+Due schemi di validazione, entrambi onesti:
+  1) WALK-FORWARD pooled: train tutti i simboli fino all'anno T, test anno T+1.
+     (generalizzazione nel tempo)
+  2) LEAVE-ONE-SYMBOL-OUT: train su 3 simboli, test sul 4o mai visto.
+     (generalizzazione tra strumenti — la prova piu' severa)
+
+Confronto sempre contro una baseline banale:
+  - clf : prevedere sempre la classe maggioritaria / la base rate
+  - reg : prevedere la mediana del train (MAE di riferimento)
+
+Uso:
+  python mr_train.py [config_mr.yaml]
+"""
+from __future__ import annotations
+import os, sys, json
+import numpy as np, pandas as pd
+import yaml
+
+HERE = os.path.dirname(os.path.abspath(__file__))
+sys.path.insert(0, HERE)
+from data import load
+from features import select_xy
+from model import make_model, make_regressor
+from mr_labeling import make_targets
+from sklearn.metrics import roc_auc_score, accuracy_score, mean_absolute_error, r2_score
+
+RESULTS = os.path.normpath(os.path.join(HERE, "..", "results"))
+
+
+def load_cfg(path):
+    with open(path) as f:
+        return yaml.safe_load(f)
+
+
+def load_pool(cfg):
+    parts = []
+    for s in cfg["symbols"]:
+        cr, _ = load(s, cfg["year_min"])
+        cr = cr.copy()
+        cr["abs_dist"] = cr["dist_med_pct"].abs()
+        parts.append(cr)
+    df = pd.concat(parts, ignore_index=True).sort_values("time").reset_index(drop=True)
+    return df
+
+
+# ---------------- metriche ----------------
+def clf_metrics(ytr, yte, ptr, pte):
+    base = max(yte.mean(), 1 - yte.mean())   # accuratezza della classe maggioritaria
+    out = {"n": int(len(yte)), "base_rate": float(yte.mean()),
+           "acc_baseline": float(base)}
+    if len(np.unique(yte)) < 2:
+        out.update(auc=np.nan, acc=np.nan); return out
+    out["auc"] = float(roc_auc_score(yte, pte))
+    out["acc"] = float(accuracy_score(yte, (pte >= 0.5).astype(int)))
+    return out
+
+
+def reg_metrics(ytr, yte, pred):
+    base_pred = np.median(ytr)
+    mae_base = mean_absolute_error(yte, np.full_like(yte, base_pred, dtype=float))
+    mae = mean_absolute_error(yte, pred)
+    return {"n": int(len(yte)), "mae": float(mae), "mae_baseline": float(mae_base),
+            "skill_%": float((1 - mae / mae_base) * 100) if mae_base > 0 else np.nan,
+            "r2": float(r2_score(yte, pred)) if len(np.unique(yte)) > 1 else np.nan}
+
+
+def fit_predict(cfg, task, tr, te, num, cat):
+    """Addestra il modello giusto per il task e ritorna (ytr,yte,pred_or_proba)."""
+    horizon = cfg["horizon"]
+    t_tr = make_targets(tr, horizon, cfg["drop_trivial"], cfg["trivial_eps"])[task]
+    t_te = make_targets(te, horizon, cfg["drop_trivial"], cfg["trivial_eps"])[task]
+    ytr, mtr = t_tr; yte, mte = t_te
+    Xtr, Xte = tr[mtr], te[mte]
+    ytr, yte = ytr[mtr], yte[mte]
+    if len(Xtr) < 50 or len(Xte) < 20:
+        return None
+    if task == "rev":
+        m = make_model(cfg, num, cat)
+        m.fit(select_xy(Xtr, num, cat), ytr)
+        return ("clf", ytr, yte,
+                m.predict_proba(select_xy(Xtr, num, cat))[:, 1],
+                m.predict_proba(select_xy(Xte, num, cat))[:, 1])
+    else:
+        m = make_regressor(cfg, num, cat)
+        m.fit(select_xy(Xtr, num, cat), ytr)
+        return ("reg", ytr, yte, None, m.predict(select_xy(Xte, num, cat)))
+
+
+def walk_forward(cfg, df, num, cat):
+    years = sorted(df.time.dt.year.unique())
+    t = years[0] + cfg["walkforward"]["min_train_years"] - 1
+    rows = {k: [] for k in ("rev", "speed", "disc")}
+    while t < years[-1]:
+        tr = df[df.time.dt.year <= t]
+        te = df[df.time.dt.year == t + 1]
+        if len(te):
+            for task in rows:
+                r = fit_predict(cfg, task, tr, te, num, cat)
+                if r is None:
+                    continue
+                kind, ytr, yte, ptr, pte = r
+                m = (clf_metrics(ytr, yte, ptr, pte) if kind == "clf"
+                     else reg_metrics(ytr, yte, pte))
+                m["test_year"] = t + 1
+                rows[task].append(m)
+        t += cfg["walkforward"]["step_years"]
+    return {k: pd.DataFrame(v) for k, v in rows.items()}
+
+
+def leave_one_symbol_out(cfg, df, num, cat):
+    rows = {k: [] for k in ("rev", "speed", "disc")}
+    for s in cfg["symbols"]:
+        tr = df[df.symbol != s]
+        te = df[df.symbol == s]
+        for task in rows:
+            r = fit_predict(cfg, task, tr, te, num, cat)
+            if r is None:
+                continue
+            kind, ytr, yte, ptr, pte = r
+            m = (clf_metrics(ytr, yte, ptr, pte) if kind == "clf"
+                 else reg_metrics(ytr, yte, pte))
+            m["test_symbol"] = s
+            rows[task].append(m)
+    return {k: pd.DataFrame(v) for k, v in rows.items()}
+
+
+def run(cfg_path):
+    cfg = load_cfg(cfg_path)
+    np.random.seed(cfg["seed"])
+    num, cat = cfg["features_numeric"], cfg["features_categorical"]
+    df = load_pool(cfg)
+    print(f"pool: {len(df)} incroci su {cfg['symbols']} "
+          f"(drop_trivial={cfg['drop_trivial']})\n")
+
+    print("=== 1) WALK-FORWARD pooled (generalizzazione nel tempo) ===")
+    wf = walk_forward(cfg, df, num, cat)
+    print(f"[rev]   AUC medio={wf['rev'].auc.mean():.3f}  acc={wf['rev'].acc.mean():.3f}"
+          f"  (acc baseline maggioritaria={wf['rev'].acc_baseline.mean():.3f})")
+    print(f"[speed] MAE={wf['speed'].mae.mean():.2f}g  baseline={wf['speed'].mae_baseline.mean():.2f}g"
+          f"  skill={wf['speed']['skill_%'].mean():+.1f}%")
+    print(f"[disc]  MAE={wf['disc'].mae.mean():.3f}%  baseline={wf['disc'].mae_baseline.mean():.3f}%"
+          f"  skill={wf['disc']['skill_%'].mean():+.1f}%")
+
+    print("\n=== 2) LEAVE-ONE-SYMBOL-OUT (generalizzazione tra strumenti) ===")
+    loso = leave_one_symbol_out(cfg, df, num, cat)
+    for _, r in loso["rev"].iterrows():
+        print(f"[rev]   test {r['test_symbol']:7s} AUC={r['auc']:.3f} acc={r['acc']:.3f}"
+              f" (base {r['base_rate']:.3f})")
+    for _, r in loso["speed"].iterrows():
+        print(f"[speed] test {r['test_symbol']:7s} MAE={r['mae']:.2f}g base={r['mae_baseline']:.2f}g"
+              f" skill={r['skill_%']:+.1f}%")
+    for _, r in loso["disc"].iterrows():
+        print(f"[disc]  test {r['test_symbol']:7s} MAE={r['mae']:.3f}% base={r['mae_baseline']:.3f}%"
+              f" skill={r['skill_%']:+.1f}%")
+
+    # ---- modelli finali su tutto il pool ----
+    os.makedirs(RESULTS, exist_ok=True)
+    saved = {}
+    for task in ("rev", "speed", "disc"):
+        y, mask = make_targets(df, cfg["horizon"], cfg["drop_trivial"], cfg["trivial_eps"])[task]
+        X = select_xy(df[mask], num, cat)
+        mdl = make_model(cfg, num, cat) if task == "rev" else make_regressor(cfg, num, cat)
+        mdl.fit(X, y[mask])
+        try:
+            import joblib
+            path = os.path.join(RESULTS, f"mr_model_{task}.joblib")
+            joblib.dump(mdl, path); saved[task] = path
+        except Exception as e:
+            print("non serializzato", task, e)
+
+    for task in ("rev", "speed", "disc"):
+        wf[task].to_csv(os.path.join(RESULTS, f"mr_wf_{task}.csv"), index=False)
+        loso[task].to_csv(os.path.join(RESULTS, f"mr_loso_{task}.csv"), index=False)
+    with open(os.path.join(RESULTS, "mr_summary.json"), "w") as f:
+        json.dump({
+            "wf": {k: v.mean(numeric_only=True).to_dict() for k, v in wf.items()},
+            "loso": {k: v.mean(numeric_only=True).to_dict() for k, v in loso.items()},
+        }, f, indent=2)
+    print(f"\nsalvati risultati e modelli in {RESULTS}")
+    return wf, loso
+
+
+if __name__ == "__main__":
+    cfg_path = sys.argv[1] if len(sys.argv) > 1 else os.path.join(HERE, "..", "config_mr.yaml")
+    run(cfg_path)
@@ -0,0 +1,80 @@
+"""Self-test della pipeline Fase 3 (controlli di correttezza, non un training serio).
+
+Esegue:
+  T1 reproducibilita': due run identiche danno stesse metriche OOS
+  T2 controllo negativo anti-leakage: con label OOS mescolate l'AUC deve ~0.5
+  T3 no temporal leakage: la baseline OOS dipende SOLO dallo sviluppo
+  T4 variante logistic gira senza errori
+  T5 restrict_pairs (solo pattern robusti) gira senza errori
+  T6 le feature non contengono colonne di esito futuro
+"""
+import os, sys, copy
+import numpy as np
+HERE = os.path.dirname(os.path.abspath(__file__))
+sys.path.insert(0, HERE)
+import train as T
+from data import load
+from labeling import RegimeBaseline
+from splits import split_oos
+
+CFG = os.path.join(HERE, "..", "config.yaml")
+ok = True
+
+def check(name, cond):
+    global ok
+    print(("PASS" if cond else "FAIL"), "-", name)
+    ok = ok and cond
+
+# T6: nessuna feature e' un esito futuro
+cfg = T.load_cfg(CFG)
+future_like = ("ret_", "mfe_", "mae_", "dir_", "rev_", "cret_", "bars_to_revert", "disc_max")
+feats = cfg["features_numeric"] + cfg["features_categorical"]
+check("T6 feature senza esiti futuri",
+      not any(f.startswith(future_like) or f in ("bars_to_revert",) for f in feats))
+
+# T1: reproducibilita'
+folds1, oos1 = T.run(CFG)
+folds2, oos2 = T.run(CFG)
+check("T1 reproducibilita' OOS AUC", abs(oos1["auc"] - oos2["auc"]) < 1e-9)
+
+# T3: baseline OOS non dipende dai dati OOS (no temporal leakage)
+crosses, bars = load(cfg["symbol"], cfg["year_min"])
+crosses = crosses.dropna(subset=[f"cret_{cfg['horizon']}"]).reset_index(drop=True)
+dev_cr, oos_cr = split_oos(crosses, cfg["oos_start_year"])
+dev_ba, oos_ba = split_oos(bars, cfg["oos_start_year"])
+rb_dev = RegimeBaseline(cfg["regime"], cfg["horizon"]).fit(dev_ba)
+lbl_a = rb_dev.label(oos_cr)
+# se cambio i dati OOS, l'edges/baseline (fittati su dev) NON cambiano
+rb_dev2 = RegimeBaseline(cfg["regime"], cfg["horizon"]).fit(dev_ba)
+lbl_b = rb_dev2.label(oos_cr)
+check("T3 baseline OOS deterministica e da solo-sviluppo", np.array_equal(lbl_a, lbl_b)
+      and np.allclose(rb_dev.edges_["cl"], rb_dev2.edges_["cl"]))
+
+# T2: controllo negativo (label mescolate -> AUC ~0.5)
+from evaluate import metrics
+from features import select_xy
+from model import make_model
+rng = np.random.default_rng(0)
+y_dev = rb_dev.label(dev_cr)
+final = make_model(cfg, cfg["features_numeric"], cfg["features_categorical"])
+final.fit(select_xy(dev_cr, cfg["features_numeric"], cfg["features_categorical"]), y_dev)
+p_oos = final.predict_proba(select_xy(oos_cr, cfg["features_numeric"], cfg["features_categorical"]))[:, 1]
+y_oos = rb_dev.label(oos_cr)
+y_shuf = y_oos.copy(); rng.shuffle(y_shuf)
+m_shuf = metrics(y_shuf, p_oos)
+check("T2 controllo negativo AUC~0.5 (0.45-0.55)", 0.45 <= m_shuf["auc"] <= 0.55)
+
+# T4: variante logistic
+cfg_log = copy.deepcopy(cfg); cfg_log["model"]["kind"] = "logistic"
+ml = make_model(cfg_log, cfg["features_numeric"], cfg["features_categorical"])
+ml.fit(select_xy(dev_cr, cfg["features_numeric"], cfg["features_categorical"]), y_dev)
+pl = ml.predict_proba(select_xy(oos_cr, cfg["features_numeric"], cfg["features_categorical"]))[:, 1]
+check("T4 logistic produce probabilita' valide", np.all((pl >= 0) & (pl <= 1)))
+
+# T5: restrict_pairs
+robust = ["MA365xMA7", "MA121xMA7", "MA121xMA3", "PRICExMA121", "MA182xMA30"]
+sub = dev_cr[dev_cr.pair.isin(robust)]
+check("T5 restrict_pairs ha campioni", len(sub) > 100)
+
+print("\n=== RISULTATO SELF-TEST:", "TUTTO OK" if ok else "CI SONO FAIL", "===")
+sys.exit(0 if ok else 1)
@@ -0,0 +1,30 @@
+"""Split temporali: walk-forward espansivo + hold-out finale out-of-sample.
+
+- `walk_forward_folds`: per la validazione interna sui dati pre-OOS. Finestra
+  espansiva: train = [inizio .. anno T], test = anno T+1, scorrendo T.
+- L'hold-out OOS (>= oos_start_year) e' tenuto separato e usato solo alla fine.
+"""
+from __future__ import annotations
+import pandas as pd
+
+
+def split_oos(df: pd.DataFrame, oos_start_year: int):
+    dev = df[df.time.dt.year < oos_start_year].reset_index(drop=True)
+    oos = df[df.time.dt.year >= oos_start_year].reset_index(drop=True)
+    return dev, oos
+
+
+def walk_forward_folds(df: pd.DataFrame, min_train_years: int, step_years: int = 1):
+    """Genera (train_idx, test_idx) su `df` (gia' solo periodo di sviluppo)."""
+    years = sorted(df.time.dt.year.unique())
+    if len(years) <= min_train_years:
+        return
+    start = years[0]
+    t = start + min_train_years - 1
+    while t < years[-1]:
+        test_years = list(range(t + 1, min(t + 1 + step_years, years[-1] + 1)))
+        train_idx = df.index[df.time.dt.year <= t].to_numpy()
+        test_idx = df.index[df.time.dt.year.isin(test_years)].to_numpy()
+        if len(test_idx) > 0 and len(train_idx) > 0:
+            yield train_idx, test_idx
+        t += step_years
@@ -0,0 +1,108 @@
+"""Pipeline Fase 3 end-to-end.
+
+1. carica incroci + baseline
+2. tiene da parte l'hold-out OOS (>= oos_start_year)
+3. walk-forward espansivo sul periodo di sviluppo:
+   - per ogni fold: fit baseline+terzili sul SOLO train, costruisce le label,
+     addestra il modello, valuta sul fold di test
+4. riaddestra sul periodo di sviluppo completo e valuta sull'hold-out OOS
+5. salva metriche e modello finale
+
+Uso:
+  python train.py [config.yaml]
+"""
+from __future__ import annotations
+import os, sys, json
+import numpy as np
+import pandas as pd
+import yaml
+
+HERE = os.path.dirname(os.path.abspath(__file__))
+sys.path.insert(0, HERE)
+from data import load
+from labeling import RegimeBaseline
+from features import select_xy
+from splits import split_oos, walk_forward_folds
+from model import make_model
+from evaluate import metrics
+
+RESULTS = os.path.normpath(os.path.join(HERE, "..", "results"))
+
+
+def load_cfg(path: str) -> dict:
+    with open(path) as f:
+        return yaml.safe_load(f)
+
+
+def run(cfg_path: str):
+    cfg = load_cfg(cfg_path)
+    np.random.seed(cfg["seed"])
+    num_cols = cfg["features_numeric"]
+    cat_cols = cfg["features_categorical"]
+    h = cfg["horizon"]
+
+    crosses, bars = load(cfg["symbol"], cfg["year_min"])
+    if cfg.get("restrict_pairs"):
+        crosses = crosses[crosses.pair.isin(cfg["restrict_pairs"])].reset_index(drop=True)
+    # serve cret_h presente (le ultime barre non hanno il futuro completo)
+    crosses = crosses.dropna(subset=[f"cret_{h}"]).reset_index(drop=True)
+
+    dev_cr, oos_cr = split_oos(crosses, cfg["oos_start_year"])
+    dev_ba, oos_ba = split_oos(bars, cfg["oos_start_year"])
+    print(f"sviluppo: {len(dev_cr)} incroci  |  OOS({cfg['oos_start_year']}+): {len(oos_cr)} incroci")
+
+    # ---------- walk-forward ----------
+    fold_rows = []
+    for i, (tr_idx, te_idx) in enumerate(walk_forward_folds(
+            dev_cr, cfg["walkforward"]["min_train_years"], cfg["walkforward"]["step_years"])):
+        tr, te = dev_cr.loc[tr_idx], dev_cr.loc[te_idx]
+        # baseline/terzili stimati SOLO sul train (barre fino all'ultimo anno di train)
+        max_train_year = tr.time.dt.year.max()
+        ba_tr = dev_ba[dev_ba.time.dt.year <= max_train_year]
+        rb = RegimeBaseline(cfg["regime"], h).fit(ba_tr)
+        ytr, yte = rb.label(tr), rb.label(te)
+        mdl = make_model(cfg, num_cols, cat_cols)
+        mdl.fit(select_xy(tr, num_cols, cat_cols), ytr)
+        pte = mdl.predict_proba(select_xy(te, num_cols, cat_cols))[:, 1]
+        m = metrics(yte, pte)
+        m["fold"] = i
+        m["test_years"] = f"{te.time.dt.year.min()}-{te.time.dt.year.max()}"
+        fold_rows.append(m)
+        print(f"  fold {i} test {m['test_years']:>9} n={m['n']:5d} "
+              f"AUC={m['auc']:.3f} acc={m['acc']:.3f} "
+              f"prec@10%={m['prec_top_decile']:.3f} (base {m['base_rate']:.3f})")
+
+    folds = pd.DataFrame(fold_rows)
+    if len(folds):
+        print(f"\nWalk-forward medio: AUC={folds.auc.mean():.3f}  "
+              f"acc={folds.acc.mean():.3f}  prec@10%={folds.prec_top_decile.mean():.3f}")
+
+    # ---------- modello finale + OOS ----------
+    rb_full = RegimeBaseline(cfg["regime"], h).fit(dev_ba)
+    y_dev = rb_full.label(dev_cr)
+    final = make_model(cfg, num_cols, cat_cols)
+    final.fit(select_xy(dev_cr, num_cols, cat_cols), y_dev)
+
+    y_oos = rb_full.label(oos_cr)          # baseline fittata sullo sviluppo: no leakage
+    p_oos = final.predict_proba(select_xy(oos_cr, num_cols, cat_cols))[:, 1]
+    oos_m = metrics(y_oos, p_oos)
+    print(f"\nHOLD-OUT OOS {cfg['oos_start_year']}+ : n={oos_m['n']} AUC={oos_m['auc']:.3f} "
+          f"acc={oos_m['acc']:.3f} prec@10%={oos_m['prec_top_decile']:.3f} "
+          f"(base {oos_m['base_rate']:.3f}, lift {oos_m['lift_top_decile']:.2f}x)")
+
+    os.makedirs(RESULTS, exist_ok=True)
+    folds.to_csv(os.path.join(RESULTS, "walkforward_folds.csv"), index=False)
+    with open(os.path.join(RESULTS, "oos_metrics.json"), "w") as f:
+        json.dump(oos_m, f, indent=2)
+    try:
+        import joblib
+        joblib.dump(final, os.path.join(RESULTS, "model_final.joblib"))
+    except Exception as e:
+        print("modello non serializzato:", e)
+    print(f"\nsalvati risultati in {RESULTS}")
+    return folds, oos_m
+
+
+if __name__ == "__main__":
+    cfg_path = sys.argv[1] if len(sys.argv) > 1 else os.path.join(HERE, "..", "config.yaml")
+    run(cfg_path)
@@ -16,12 +16,14 @@ input bool     InpAllHistory = true;            // true = tutto lo storico D1
 input datetime InpStart      = D'2010.01.01';   // inizio intervallo (se AllHistory=false)
 input datetime InpEnd        = D'2100.01.01';   // fine intervallo (se AllHistory=false)
 input string   InpFileName   = "";              // nome file ("" = automatico)
+input bool     InpBaseline   = true;            // crea anche il file baseline (tutte le barre D1)

 //--- costanti (stesse 7 MA dell'indicatore)
 #define ANCHOR_TF PERIOD_D1
 #define NSER 9          // PRICE, MED, MA365..MA3
-#define KSLOPE 5        // barre per pendenza / variazione cluster
-#define MAXH  20        // orizzonte massimo per gli esiti
+#define KSLOPE 5        // barre D1 per velocita'/accelerazione
+#define NVOL   14       // barre D1 per la volatilita'
+#define MAXH   20       // orizzonte massimo per gli esiti

 int    gDays[7] = {365,182,121,30,14,7,3};
 string SER[NSER]= {"PRICE","MED","MA365","MA182","MA121","MA30","MA14","MA7","MA3"};
@@ -53,6 +55,61 @@ double Median7(double &v[])   // mediana dei valori validi in v[0..6]
   return 0.5*(a[c/2-1]+a[c/2]);
  }

+//+------------------------------------------------------------------+
+// mediana dei primi c valori di src
+double MedArr(double &src[],int c)
+  {
+   if(c<=0) return 0;
+   double a[]; ArrayResize(a,c);
+   for(int j=0;j<c;j++) a[j]=src[j];
+   ArraySort(a);
+   if((c&1)==1) return a[c/2];
+   return 0.5*(a[c/2-1]+a[c/2]);
+  }
+
+//+------------------------------------------------------------------+
+// Velocita' = mediana delle 7 pendenze (variazione % di ogni MA su K barre D1)
+double VelMed(const double &S[][NSER],int i,int K)
+  {
+   double v[7]; int c=0;
+   for(int m=0;m<7;m++)
+     { double a=S[i][2+m], b=S[i-K][2+m]; if(IsVal(a)&&IsVal(b)) v[c++]=(a-b)/b*100.0; }
+   return MedArr(v,c);
+  }
+
+//+------------------------------------------------------------------+
+// Accelerazione = mediana delle 7 seconde differenze (cambio di pendenza)
+double AccMed(const double &S[][NSER],int i,int K)
+  {
+   double v[7]; int c=0;
+   for(int m=0;m<7;m++)
+     {
+      double a=S[i][2+m], b=S[i-K][2+m], d=S[i-2*K][2+m];
+      if(IsVal(a)&&IsVal(b)&&IsVal(d)) v[c++]=(a-2.0*b+d)/d*100.0;
+     }
+   return MedArr(v,c);
+  }
+
+//+------------------------------------------------------------------+
+// Volatilita' = mediana delle 7 dev.std dei rendimenti giornalieri di ogni MA su N barre
+double VolMed(const double &S[][NSER],int i,int N)
+  {
+   double v[7]; int c=0;
+   for(int m=0;m<7;m++)
+     {
+      double r[]; int rc=0; ArrayResize(r,N);
+      for(int t=i-N+1;t<=i;t++)
+        { double a=S[t][2+m], b=S[t-1][2+m]; if(IsVal(a)&&IsVal(b)) r[rc++]=(a-b)/b*100.0; }
+      if(rc>=2)
+        {
+         double mean=0; for(int j=0;j<rc;j++) mean+=r[j]; mean/=rc;
+         double s=0;    for(int j=0;j<rc;j++){ double dd=r[j]-mean; s+=dd*dd; }
+         v[c++]=MathSqrt(s/(rc-1));
+        }
+     }
+   return MedArr(v,c);
+  }
+
 //+------------------------------------------------------------------+
 void OnStart()
  {
@@ -60,7 +117,7 @@ void OnStart()
   if(!SymbolSelect(sym,true)) { Print("Simbolo non valido: ",sym); return; }
   int digits = (int)SymbolInfoInteger(sym,SYMBOL_DIGITS);

-   //--- handle delle 7 MA su D1 + ATR
+   //--- handle delle 7 MA su D1 (volatilita'/accelerazione calcolate dalle MA, no ATR di MT5)
   int hMA[7];
   for(int m=0;m<7;m++)
     {
@@ -68,33 +125,30 @@ void OnStart()
      hMA[m]  = iMA(sym,ANCHOR_TF,per,0,MODE_SMA,PRICE_CLOSE);
      if(hMA[m]==INVALID_HANDLE) { Print("iMA fallita m=",m); return; }
     }
-   int hATR = iATR(sym,ANCHOR_TF,14);
-   if(hATR==INVALID_HANDLE) { Print("iATR fallita"); return; }
+   int LB = MathMax(2*KSLOPE,NVOL);   // lookback necessario per vel/acc/vol

   //--- attendo che lo storico D1 sia pronto
   int total=0;
   for(int t=0; t<100; t++)
     {
      total = Bars(sym,ANCHOR_TF);
-      bool ok = (total>MAXH+KSLOPE+50);
+      bool ok = (total>MAXH+LB+50);
      for(int m=0;m<7 && ok;m++) if(BarsCalculated(hMA[m])<total) ok=false;
-      if(ok && BarsCalculated(hATR)>=total) break;
+      if(ok) break;
      Sleep(100);
     }
   total = Bars(sym,ANCHOR_TF);
-   if(total<=MAXH+KSLOPE+50) { Print("Storico D1 insufficiente: ",total," barre"); return; }
+   if(total<=MAXH+LB+50) { Print("Storico D1 insufficiente: ",total," barre"); return; }

   //--- carico tutta la storia D1 (indice 0 = piu' vecchio)
-   datetime tm[]; double cl[],hi[],lo[],atr[];
+   datetime tm[]; double cl[],hi[],lo[];
   MABuf ma[7];
   ArraySetAsSeries(tm,false); ArraySetAsSeries(cl,false);
   ArraySetAsSeries(hi,false); ArraySetAsSeries(lo,false);
-   ArraySetAsSeries(atr,false);
   if(CopyTime(sym,ANCHOR_TF,0,total,tm)<=0)  { Print("CopyTime KO");  return; }
   if(CopyClose(sym,ANCHOR_TF,0,total,cl)<=0) { Print("CopyClose KO"); return; }
   if(CopyHigh(sym,ANCHOR_TF,0,total,hi)<=0)  { Print("CopyHigh KO");  return; }
   if(CopyLow(sym,ANCHOR_TF,0,total,lo)<=0)   { Print("CopyLow KO");   return; }
-   if(CopyBuffer(hATR,0,0,total,atr)<=0)      { Print("CopyATR KO");   return; }
   for(int m=0;m<7;m++)
     {
      ArraySetAsSeries(ma[m].v,false);
@@ -117,8 +171,8 @@ void OnStart()
   //--- intervallo di scansione (eventi)
   datetime from = InpAllHistory ? 0          : InpStart;
   datetime to   = InpAllHistory ? TimeCurrent(): InpEnd;
-   int iStart = KSLOPE+1, iEnd = n-1;
-   for(int i=KSLOPE+1;i<n;i++) if(tm[i]>=from) { iStart=i; break; }
+   int iStart = LB+1, iEnd = n-1;
+   for(int i=LB+1;i<n;i++) if(tm[i]>=from) { iStart=i; break; }
   for(int i=n-1;i>=0;i--)     if(tm[i]<=to)    { iEnd=i;   break; }

   //--- apro il file CSV
@@ -128,7 +182,7 @@ void OnStart()

   //--- header
   string head = "time,symbol,pair,a,b,dir,price,med,ma365,ma182,ma121,ma30,ma14,ma7,ma3,"
-                 "dist_med_pct,cluster_pct,cluster_exp,slope_a,slope_b,trend,atr_pct,dow,month";
+                 "dist_med_pct,cluster_pct,cluster_exp,slope_a,slope_b,trend,vel_med,acc_med,vol_med,dow,month";
   for(int hh=0;hh<5;hh++)
     {
      string s=IntegerToString(gHor[hh]);
@@ -138,16 +192,32 @@ void OnStart()
   head += ",bars_to_revert,disc_max_pct";
   FileWriteString(fh,head+"\r\n");

+   //--- file baseline (una riga per OGNI barra D1 valida): serve per il confronto
+   //    "extra-rendimento" = incrocio vs giorno qualunque nello stesso regime
+   int fhB = INVALID_HANDLE;
+   if(InpBaseline)
+     {
+      string bname = "PaPP_bars_"+sym+"_D1.csv";
+      fhB = FileOpen(bname,FILE_WRITE|FILE_TXT|FILE_ANSI);
+      if(fhB==INVALID_HANDLE) Print("FileOpen baseline KO: ",bname," err=",GetLastError());
+      else
+        {
+         string bh = "time,symbol,price,med,dist_med_pct,cluster_pct,cluster_exp,trend,vel_med,acc_med,vol_med,dow,month,bars_to_revert,disc_max_pct";
+         for(int b=1;b<=MAXH;b++) bh += ",cret_"+IntegerToString(b);
+         FileWriteString(fhB,bh+"\r\n");
+        }
+     }
+
   //--- scansione incroci
-   long rows=0;
+   long rows=0, brows=0;
   for(int i=iStart;i<=iEnd;i++)
     {
-      if(i<KSLOPE+1) continue;
+      if(i<LB+1) continue;

-      //--- esporto solo barre con TUTTE le 9 serie valide (cluster completo)
+      //--- esporto solo barre con TUTTE le 9 serie valide su tutto il lookback
      bool allok=true;
      for(int k=0;k<NSER && allok;k++)
-         if(!IsVal(S[i][k]) || !IsVal(S[i-1][k]) || !IsVal(S[i-KSLOPE][k])) allok=false;
+         if(!IsVal(S[i][k]) || !IsVal(S[i-1][k]) || !IsVal(S[i-LB][k])) allok=false;
      if(!allok) continue;

      double price=S[i][0], med=S[i][1], ma365=S[i][2];
@@ -162,9 +232,21 @@ void OnStart()
      double clusterP = (cmaxP-cminP)/S[i-KSLOPE][0]*100.0;
      double cluster_exp = cluster-clusterP;
      int    trend = (price>ma365)?1:-1;
-      double atr_pct = atr[i]/price*100.0;
+      //--- velocita'/accelerazione/volatilita': mediana delle 7 scale (no ATR di MT5)
+      double vel_med = VelMed(S,i,KSLOPE);
+      double acc_med = AccMed(S,i,KSLOPE);
+      double vol_med = VolMed(S,i,NVOL);
      MqlDateTime dt; TimeToStruct(tm[i],dt);

+      //--- traiettoria forward (rendimento cumulato a +1..+MAXH), calcolata una volta per barra
+      string bpath="";
+      for(int b=1;b<=MAXH;b++)
+        {
+         int iB=i+b;
+         if(iB>n-1) bpath += ",";
+         else       bpath += ","+DoubleToString((cl[iB]-cl[i])/cl[i]*100.0,5);
+        }
+
      //--- esito globale: ritorno alla Mediana entro MAXH
      int side = (price>med)?1:-1;
      int b2rev=-1; double discMax=0;
@@ -178,6 +260,22 @@ void OnStart()
         if(MathAbs(d)>MathAbs(discMax)) discMax=d;
        }

+      //--- riga baseline (barra qualunque, indipendente dagli incroci)
+      if(fhB!=INVALID_HANDLE)
+        {
+         string br = TimeToString(tm[i],TIME_DATE)+","+sym+","
+                     +DoubleToString(price,digits)+","+DoubleToString(med,digits)+","
+                     +DoubleToString(dist_med,5)+","+DoubleToString(cluster,5)+","
+                     +DoubleToString(cluster_exp,5)+","+IntegerToString(trend)+","
+                     +DoubleToString(vel_med,5)+","+DoubleToString(acc_med,5)+","
+                     +DoubleToString(vol_med,5)+","+IntegerToString(dt.day_of_week)+","
+                     +IntegerToString(dt.mon)+","
+                     +(b2rev>0?IntegerToString(b2rev):"")+","+DoubleToString(discMax,5)
+                     +bpath;
+         FileWriteString(fhB,br+"\r\n");
+         brows++;
+        }
+
      //--- controllo ogni coppia (a,b)
      for(int a=0;a<NSER;a++)
       for(int b=a+1;b<NSER;b++)
@@ -190,7 +288,7 @@ void OnStart()

          double slope_a = (S[i][a]-S[i-KSLOPE][a])/S[i-KSLOPE][a]*100.0;
          double slope_b = (S[i][b]-S[i-KSLOPE][b])/S[i-KSLOPE][b]*100.0;
-          double thr = 0.25*atr_pct;
+          double thr = 0.25*vol_med;

          string row = StringFormat("%s,%s,%sx%s,%s,%s,%d,",
                          TimeToString(tm[i],TIME_DATE),sym,SER[a],SER[b],SER[a],SER[b],dir);
@@ -199,7 +297,8 @@ void OnStart()
          row += DoubleToString(dist_med,5)+","+DoubleToString(cluster,5)+","
                 +DoubleToString(cluster_exp,5)+","+DoubleToString(slope_a,5)+","
                 +DoubleToString(slope_b,5)+","+IntegerToString(trend)+","
-                 +DoubleToString(atr_pct,5)+","+IntegerToString(dt.day_of_week)+","
+                 +DoubleToString(vel_med,5)+","+DoubleToString(acc_med,5)+","
+                 +DoubleToString(vol_med,5)+","+IntegerToString(dt.day_of_week)+","
                 +IntegerToString(dt.mon);

          //--- esiti per orizzonte
@@ -217,13 +316,7 @@ void OnStart()
             row += ","+DoubleToString(ret,5)+","+DoubleToString(mfe,5)+","
                    +DoubleToString(mae,5)+","+IntegerToString(dlab)+","+IntegerToString(rev);
            }
-          //--- traiettoria: rendimento cumulato a +1..+MAXH barre
-          for(int b=1;b<=MAXH;b++)
-            {
-             int iB=i+b;
-             if(iB>n-1) { row += ","; continue; }
-             row += ","+DoubleToString((cl[iB]-cl[i])/cl[i]*100.0,5);
-            }
+          row += bpath;   // traiettoria forward (uguale per ogni coppia di questa barra)
          row += ","+(b2rev>0?IntegerToString(b2rev):"")+","+DoubleToString(discMax,5);
          FileWriteString(fh,row+"\r\n");
          rows++;
@@ -232,10 +325,11 @@ void OnStart()
     }

   FileClose(fh);
+   if(fhB!=INVALID_HANDLE) FileClose(fhB);
   for(int m=0;m<7;m++) IndicatorRelease(hMA[m]);
-   IndicatorRelease(hATR);
   Comment("");
   PrintFormat("PaPP export COMPLETATO: %d incroci -> %s (cartella MQL5\\Files)",(int)rows,fname);
+   if(InpBaseline) PrintFormat("Baseline: %d barre -> PaPP_bars_%s_D1.csv",(int)brows,sym);
   Print("Periodo: ",TimeToString(tm[iStart])," -> ",TimeToString(tm[iEnd]));
  }
 //+------------------------------------------------------------------+
@@ -444,8 +444,11 @@ int OnCalculate(const int rates_total,
 int TxtW(string s,int fs,bool bold)
  {
   TextSetFont(bold?"Consolas Bold":"Consolas",-fs*10);
-   uint w=0,h=0; TextGetSize(s,w,h);
-   return (int)w;
+   uint w=0,h=0;
+   bool ok=TextGetSize(s,w,h);
+   int est=(int)MathCeil(StringLen(s)*fs*0.62);   // fallback se TextGetSize non disponibile
+   if(!ok || (int)w<=0) return est;
+   return MathMax((int)w,est);                     // mai meno della stima
  }
 //+------------------------------------------------------------------+
 void DrawInfo()
Author	SHA1	Message	Date
pietro1991-dot	f4ec58440a	Merge pull request #19 from pietro1991-dot/devin/1781688049-validazione-esterna * PaPP v2 Modello: validazione esterna multi-simbolo (no pollution) Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * PaPP v2 Modello: modello mean-reversion (rev/speed/disc) pooled 4 FX + LOSO + doc Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: Pietro Giacobazzi <giacobazzipietro@gmail.com> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-06-17 11:57:13 +02:00
Pietro Giacobazzi	7d329a0591	PaPP v2 Modello: modello mean-reversion (rev/speed/disc) pooled 4 FX + LOSO + doc Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-06-17 09:28:15 +00:00
Pietro Giacobazzi	0187cb6bd7	PaPP v2 Modello: validazione esterna multi-simbolo (no pollution) Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-06-17 09:21:43 +00:00
pietro1991-dot	58ed32ff3b	Merge pull request #18 from pietro1991-dot/devin/1781682226-modello-fase3 * PaPP v2: Fase 3 - architettura classificatore extra-rendimento (walk-forward + OOS) Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * PaPP v2 Modello: self-test (reproducibilita', anti-leakage, varianti) Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * PaPP v2 Modello: documenta selftest nel README Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: Pietro Giacobazzi <giacobazzipietro@gmail.com> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-06-17 11:15:06 +02:00
Pietro Giacobazzi	375dbf1dc3	PaPP v2 Modello: documenta selftest nel README Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-06-17 07:48:33 +00:00
Pietro Giacobazzi	4084008642	PaPP v2 Modello: self-test (reproducibilita', anti-leakage, varianti) Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-06-17 07:48:26 +00:00
Pietro Giacobazzi	fe10be5ecc	PaPP v2: Fase 3 - architettura classificatore extra-rendimento (walk-forward + OOS) Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-06-17 07:45:46 +00:00
pietro1991-dot	d441454767	Merge pull request #17 from pietro1991-dot/devin/1781681941-analisi-docs Co-authored-by: Pietro Giacobazzi <giacobazzipietro@gmail.com> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-06-17 09:42:22 +02:00
Pietro Giacobazzi	19c2e0ac72	PaPP v2: cartella Analisi (script, risultati, metodologia incroci) Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-06-17 07:40:41 +00:00
pietro1991-dot	2070d44ce6	Merge pull request #11 from pietro1991-dot/devin/1781678159-export-baseline PaPP v2 export: file baseline (tutte le barre D1) per extra-rendimento	2026-06-17 09:22:50 +02:00
pietro1991-dot	fe7af9b8e0	Merge pull request #16 from pietro1991-dot/devin/1781680179-panel-fallback Co-authored-by: Pietro Giacobazzi <giacobazzipietro@gmail.com> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-06-17 09:12:08 +02:00
Pietro Giacobazzi	ff8aa9fcfb	PaPP v2 indicatore: fallback robusto a TextGetSize per la larghezza del box Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-06-17 07:09:51 +00:00
pietro1991-dot	e8bf23f987	Merge pull request #15 from pietro1991-dot/devin/1781679998-panel-autofit Co-authored-by: Pietro Giacobazzi <giacobazzipietro@gmail.com> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-06-17 09:07:48 +02:00
Pietro Giacobazzi	884354d67e	PaPP v2 export: vel/acc/vol calcolate dalle 7 medie (mediana delle scale), rimosso ATR di MT5 Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-06-17 06:50:24 +00:00
Pietro Giacobazzi	41a2324b0d	PaPP v2 export: aggiunge file baseline (tutte le barre D1 + traiettoria) per extra-rendimento vs giorno qualunque Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-06-17 06:36:24 +00:00