Upload 42 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+models/yahoo_history_cache.sqlite3 filter=lfs diff=lfs merge=lfs -text

app.py

@@ -452,6 +452,18 @@ def kotak_account() -> dict:
         raise HTTPException(status_code=502, detail=str(exc)) from exc
 
 
+@app.get("/kotak/nifty50-quote")
+def kotak_nifty50_quote() -> dict:
+    try:
+        return kotak_neo_manager.fetch_nifty50_quote()
+    except KotakNeoConfigError as exc:
+        raise HTTPException(status_code=503, detail=str(exc)) from exc
+    except KotakNeoSessionRequired as exc:
+        raise HTTPException(status_code=401, detail=str(exc)) from exc
+    except KotakNeoError as exc:
+        raise HTTPException(status_code=502, detail=str(exc)) from exc
+
+
 @app.get("/kotak/activity-log")
 def kotak_activity_log() -> dict:
     try:

data/nifty50_1d.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be744722b6c72c2fade81cc25551e32edcbda4737d02e6bc6ff8f0dff4b31d90
-size 78275
+oid sha256:4d0830f9d3cfa91f02ce717b556983beb12f897bc537a623c67e38f22ce05caf
+size 78366

data/nifty50_1m.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:216816fb4cb1b022029e3e1ab88b344e2c6dcfb65a51d2e1b70ab76dc3320a45
-size 18580743
+oid sha256:b5d6022df273daa1f020676214ec35536426fd84f2d7efb669797287e27ffa2d
+size 18589635

data/opening_direction_training_dataset.parquet

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5293909811782086d6c16ea35e8b4313dbcea6c928e6ffc07b342502dc94f466
-size 4463019
+oid sha256:722c8225451abcb49463d2a57354bc0c9b5eb519f31a25fa3c5242adc4dbbada
+size 4463631

kotak_neo.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import os
 import threading
+import time
 from csv import DictReader
 from concurrent.futures import ThreadPoolExecutor, as_completed
 from datetime import datetime, timezone
@@ -22,6 +23,7 @@ DEFAULT_TIMEOUT_SECONDS = 20
 ACCOUNT_TIMEOUT_SECONDS = 7
 DATA_DIR = Path(__file__).resolve().parent / "data"
 KOTAK_ACTIVITY_LOG_PATH = DATA_DIR / "kotak_activity_log.txt"
+NIFTY50_QUOTE_CACHE_SECONDS = 1.0
 
 
 class KotakNeoError(Exception):
@@ -133,6 +135,9 @@ class KotakNeoManager:
         self.activity_log_path.parent.mkdir(parents=True, exist_ok=True)
         self._seen_activity_keys: set[str] = set()
         self._scrip_cache: dict[str, list[dict[str, str]]] = {}
+        self._quote_cache_lock = threading.Lock()
+        self._nifty50_quote_cache: dict[str, Any] | None = None
+        self._nifty50_quote_cached_at = 0.0
         self._load_existing_activity_keys()
         self._clear_session_locked()
 
@@ -376,6 +381,42 @@ class KotakNeoManager:
             "quotes": list(quote_map.values()),
         }
 
+    def fetch_nifty50_quote(self, *, max_age_seconds: float = NIFTY50_QUOTE_CACHE_SECONDS) -> dict[str, Any]:
+        if not self._configured():
+            raise KotakNeoConfigError("Kotak Neo environment variables are incomplete.")
+
+        with self._lock:
+            context = self._context_locked()
+            cached = self._nifty50_quote_cache
+            cached_at = self._nifty50_quote_cached_at
+        cache_age = time.monotonic() - cached_at
+        if cached and cache_age < max_age_seconds:
+            return {
+                **cached,
+                "cache": {"hit": True, "max_age_seconds": max_age_seconds, "age_seconds": round(cache_age, 3)},
+            }
+
+        with self._quote_cache_lock:
+            with self._lock:
+                context = self._context_locked()
+                cached = self._nifty50_quote_cache
+                cached_at = self._nifty50_quote_cached_at
+            cache_age = time.monotonic() - cached_at
+            if cached and cache_age < max_age_seconds:
+                return {
+                    **cached,
+                    "cache": {"hit": True, "max_age_seconds": max_age_seconds, "age_seconds": round(cache_age, 3)},
+                }
+
+            fresh_quote = self._fetch_nifty50_quote_with_context(context)
+            with self._lock:
+                self._nifty50_quote_cache = fresh_quote
+                self._nifty50_quote_cached_at = time.monotonic()
+            return {
+                **fresh_quote,
+                "cache": {"hit": False, "max_age_seconds": max_age_seconds, "age_seconds": 0.0},
+            }
+
     def _ensure_authenticated_locked(self) -> None:
         if not self.edit_token or not self.edit_sid or not self.base_url:
             raise KotakNeoSessionRequired("Kotak Neo session is not authenticated.")
@@ -491,6 +532,143 @@ class KotakNeoManager:
             timeout=DEFAULT_TIMEOUT_SECONDS,
         )
 
+    def _fetch_nifty50_quote_with_context(self, context: dict[str, str]) -> dict[str, Any]:
+        candidates = self._nifty50_quote_candidates(context)
+        errors: list[str] = []
+
+        for candidate in candidates:
+            try:
+                payload = self._fetch_quotes_with_context(
+                    context,
+                    [
+                        {
+                            "exchange_segment": candidate["exchange_segment"],
+                            "instrument_token": candidate["instrument_token"],
+                        }
+                    ],
+                    timeout=ACCOUNT_TIMEOUT_SECONDS,
+                )
+                items = _extract_items(payload)
+                if not items:
+                    errors.append(
+                        f"{candidate['lookup_source']}: quotes returned no items for {candidate['instrument_token']}"
+                    )
+                    continue
+                normalized = self._normalize_nifty50_quote(items[0], candidate)
+                if normalized.get("price") is None:
+                    errors.append(
+                        f"{candidate['lookup_source']}: quote payload did not include a usable last traded price"
+                    )
+                    continue
+                return normalized
+            except KotakNeoError as exc:
+                errors.append(f"{candidate['lookup_source']}: {exc}")
+
+        error_message = "Unable to fetch the NIFTY 50 quote from Kotak Neo."
+        if errors:
+            error_message = f"{error_message} " + " | ".join(errors)
+        raise KotakNeoError(error_message)
+
+    def _nifty50_quote_candidates(self, context: dict[str, str]) -> list[dict[str, Any]]:
+        candidates: list[dict[str, Any]] = []
+        master_candidate = self._resolve_nifty50_master_candidate(context)
+        if master_candidate:
+            candidates.append(master_candidate)
+        candidates.append(
+            {
+                "exchange_segment": "nse_cm",
+                "instrument_token": "Nifty 50",
+                "display_name": "NIFTY 50",
+                "lookup_source": "quotes_doc_fallback",
+                "master_match": None,
+            }
+        )
+        return candidates
+
+    def _resolve_nifty50_master_candidate(self, context: dict[str, str]) -> dict[str, Any] | None:
+        candidates = self._load_scrip_candidates(context, "nse_cm")
+        for item in candidates:
+            normalized_values = {
+                self._normalize_scrip_text(item.get("pSymbolName")),
+                self._normalize_scrip_text(item.get("pTrdSymbol")),
+                self._normalize_scrip_text(item.get("pDesc")),
+                self._normalize_scrip_text(item.get("pCombinedSymbol")),
+                self._normalize_scrip_text(item.get("pScripRefKey")),
+            }
+            normalized_values.discard("")
+            if not normalized_values:
+                continue
+            if "NIFTY50" not in normalized_values and not any(
+                value.startswith("NIFTY50") or "NIFTY50INDEX" in value for value in normalized_values
+            ):
+                continue
+            instrument_token = _first_text(
+                item.get("pSymbol"),
+                item.get("pTrdSymbol"),
+                item.get("pSymbolName"),
+            )
+            if not instrument_token:
+                continue
+            return {
+                "exchange_segment": "nse_cm",
+                "instrument_token": instrument_token,
+                "display_name": _first_text(item.get("pDesc"), item.get("pSymbolName"), item.get("pTrdSymbol"))
+                or "NIFTY 50",
+                "lookup_source": "masterscrip",
+                "master_match": {
+                    "pSymbol": item.get("pSymbol"),
+                    "pSymbolName": item.get("pSymbolName"),
+                    "pTrdSymbol": item.get("pTrdSymbol"),
+                    "pDesc": item.get("pDesc"),
+                },
+            }
+        return None
+
+    def _normalize_scrip_text(self, value: Any) -> str:
+        return "".join(ch for ch in str(value or "").upper() if ch.isalnum())
+
+    def _normalize_nifty50_quote(
+        self,
+        item: dict[str, Any],
+        candidate: dict[str, Any],
+    ) -> dict[str, Any]:
+        price = _first_number(item.get("last_traded_price"), item.get("ltp"), item.get("iv"))
+        previous_close = _first_number(item.get("close"), item.get("c"), item.get("ic"))
+        change = _first_number(item.get("change"), item.get("cng"))
+        if change is None and price is not None and previous_close is not None:
+            change = price - previous_close
+
+        change_pct = None
+        if change is not None and previous_close not in (None, 0):
+            change_pct = change / previous_close
+        if change_pct is None:
+            change_pct = _first_number(item.get("net_change_percentage"), item.get("nc"))
+
+        return {
+            "symbol": "NIFTY 50",
+            "display_name": candidate.get("display_name") or "NIFTY 50",
+            "exchange_segment": candidate.get("exchange_segment") or _first_text(item.get("exchange_segment"), item.get("e")) or "nse_cm",
+            "instrument_token": candidate.get("instrument_token") or _first_text(item.get("instrument_token"), item.get("tk")),
+            "price": price,
+            "previous_close": previous_close,
+            "change": change,
+            "change_pct": change_pct,
+            "quote_time": _first_text(
+                item.get("updRecvTm"),
+                item.get("hsUpTm"),
+                item.get("flDtTm"),
+                item.get("exTm"),
+                item.get("ltt"),
+            ),
+            "fetched_at": _utc_now_iso(),
+            "source": {
+                "provider": "Kotak Neo Quotes API",
+                "lookup_source": candidate.get("lookup_source"),
+                "master_match": candidate.get("master_match"),
+            },
+            "raw": item,
+        }
+
     def _fetch_quotes_with_context(
         self,
         context: dict[str, str],

models/latest_prediction.csv

@@ -1,2 +1,2 @@
 input_date,first5_start,first5_end,prediction,prob_up,confidence,threshold,model_name,is_overridden
-2026-05-26,2026-05-26 09:15:00,2026-05-26 09:19:00,DOWN,0.6058803888947725,0.6808803888947725,0.425,blend_extra_trees_tight_logit_overlay,True
+2026-05-27,2026-05-27 09:15:00,2026-05-27 09:19:00,UP,0.6970470349448922,0.7720470349448922,0.425,blend_extra_trees_tight_logit_overlay,False

models/tplus1_latest_prediction.csv

@@ -1,2 +1,2 @@
 input_date,target_date,forecast_for,prediction,prob_up,confidence,threshold,model_name,decision_overlay,validation_accuracy,test_accuracy,accuracy_goal
-2026-05-26,2026-05-27,next trading session after 2026-05-26,UP,0.48291233826421653,0.5170876617357835,0.578,logistic_regression_l1_C0.35_balanced,prev_target_mean10_le_0.4_up;m02_range_1m_ge_0.000479116_up,0.66,0.6368421052631579,0.63
+2026-05-27,2026-05-29,next trading session after 2026-05-27,UP,0.47376564177714775,0.5262343582228522,0.578,logistic_regression_l1_C0.35_balanced,prev_target_mean10_le_0.4_up;m02_range_1m_ge_0.000479116_up,0.66,0.6368421052631579,0.63