fix: populate sector benchmark values for ratios tab

1 files changed, 96 insertions, 5 deletions

diff --git a/backend/app/services/data_service.py b/backend/app/services/data_service.py
index e356cb4..ab06723 100644
--- a/backend/app/services/data_service.py
+++ b/backend/app/services/data_service.py
@@ -3,6 +3,7 @@ from __future__ import annotations
 
 import math
 import os
+import statistics
 from typing import Any
 
 import httpx
@@ -30,6 +31,7 @@ FINANCIALS_CACHE = TTLCache(maxsize=128, ttl=3600)
 VALUATION_CACHE = TTLCache(maxsize=128, ttl=3600)
 HIST_RATIOS_CACHE: TTLCache = TTLCache(maxsize=128, ttl=3600)
 RATIOS_ENDPOINT_CACHE: TTLCache = TTLCache(maxsize=128, ttl=3600)
+SECTOR_BENCHMARK_CACHE: TTLCache = TTLCache(maxsize=128, ttl=3600)
 
 PERIODS = {"1m", "3m", "6m", "1y", "2y", "5y"}
 YF_PERIOD_MAP = {"1m": "1mo", "3m": "3mo", "6m": "6mo", "1y": "1y", "2y": "2y", "5y": "5y"}
@@ -750,6 +752,7 @@ def get_ratios(symbol: str) -> dict:
     ttm = compute_ttm_ratios(sym)
     hist = compute_historical_ratios(sym)
     info = get_company_info(sym)
+    sector_bench = compute_sector_ratio_benchmarks(sym)
 
     income = get_income_statement(sym, quarterly=True)
     balance = get_balance_sheet(sym, quarterly=True)
@@ -785,10 +788,17 @@ def get_ratios(symbol: str) -> dict:
     fwd_pe = _safe_float(info.get("forwardPE")) if info else None
     forward_pe = fwd_pe if fwd_pe and 0 < fwd_pe < 500 else None
 
-    def point(ttm_key: str | None, hist_key: str | None, override: float | None = None) -> dict:
+    def point(
+        ttm_key: str | None,
+        hist_key: str | None,
+        override: float | None = None,
+        sector_key: str | None = None,
+    ) -> dict:
         val = override if override is not None else (ttm.get(ttm_key) if ttm_key else None)
         spark = hist.get(hist_key, []) if hist_key else []
-        return {"value": val, "spark": spark, "vs_sector": None}
+        skey = sector_key if sector_key is not None else ttm_key
+        vs_sector = sector_bench.get(skey) if skey else None
+        return {"value": val, "spark": spark, "vs_sector": vs_sector}
 
     return {
         "pe_ttm": point("trailing_pe", "trailing_pe"),
@@ -799,22 +809,103 @@ def get_ratios(symbol: str) -> dict:
         "price_to_sales": point("price_to_sales", "price_to_sales"),
         "ev_to_sales": point("ev_to_sales", None),
         "p_fcf": point(None, None, p_fcf),
-        "forward_pe": point(None, None, forward_pe),
+        "forward_pe": point(None, None, forward_pe, "trailing_pe"),
         "operating_margin": point("operating_margin_ttm", "operating_margin"),
-        "ebitda_margin": point(None, "ebitda_margin", ebitda_margin),
+        "ebitda_margin": point(None, "ebitda_margin", ebitda_margin, "operating_margin_ttm"),
         "fcf_margin": point(None, None, fcf_margin),
         "roe": point("roe_ttm", "roe"),
         "roa": point("roa_ttm", "roa"),
         "roic": point("roic_ttm", None),
         "debt_to_equity": point("debt_to_equity", "debt_to_equity"),
         "current_ratio": point("current_ratio", "current_ratio"),
-        "quick_ratio": point(None, None, quick_ratio),
+        "quick_ratio": point(None, None, quick_ratio, "current_ratio"),
         "interest_coverage": point(None, None, interest_coverage),
         "dividend_yield": point("dividend_yield_ttm", None),
         "dividend_payout": point("dividend_payout_ratio_ttm", None),
     }
 
 
+@cached(SECTOR_BENCHMARK_CACHE)
+def compute_sector_ratio_benchmarks(symbol: str) -> dict[str, float]:
+    """Median TTM ratio benchmarks from same-sector peers (FMP-backed when available)."""
+    sym = normalize_symbol(symbol)
+    fmp_key = os.getenv("FMP_API_KEY")
+    if not fmp_key:
+        return {}
+
+    info = get_company_info(sym)
+    sector_raw = info.get("sector") if isinstance(info, dict) else None
+    sector = str(sector_raw or "").strip()
+    if not sector:
+        enrichment = get_profile_enrichment(sym)
+        sector = str((enrichment or {}).get("sector") or "").strip()
+    if not sector:
+        return {}
+
+    peer_symbols: list[str] = []
+    try:
+        with httpx.Client(timeout=3.5) as client:
+            res = client.get(
+                "https://financialmodelingprep.com/api/v3/stock-screener",
+                params={
+                    "sector": sector,
+                    "isEtf": "false",
+                    "isActivelyTrading": "true",
+                    "limit": 12,
+                    "apikey": fmp_key,
+                },
+            )
+            rows = res.json()
+            if isinstance(rows, list):
+                for row in rows:
+                    psym = normalize_symbol((row or {}).get("symbol"))
+                    if not psym or psym == sym:
+                        continue
+                    peer_symbols.append(psym)
+    except Exception:
+        return {}
+
+    if not peer_symbols:
+        return {}
+
+    keys = [
+        "trailing_pe",
+        "ev_to_ebitda",
+        "gross_margin_ttm",
+        "net_margin_ttm",
+        "price_to_book",
+        "price_to_sales",
+        "ev_to_sales",
+        "operating_margin_ttm",
+        "roe_ttm",
+        "roa_ttm",
+        "roic_ttm",
+        "debt_to_equity",
+        "current_ratio",
+        "dividend_yield_ttm",
+        "dividend_payout_ratio_ttm",
+    ]
+    buckets: dict[str, list[float]] = {k: [] for k in keys}
+
+    for psym in peer_symbols[:6]:
+        try:
+            ratios = compute_ttm_ratios(psym)
+        except Exception:
+            continue
+        if not isinstance(ratios, dict):
+            continue
+        for key in keys:
+            val = _safe_float(ratios.get(key))
+            if val is not None:
+                buckets[key].append(val)
+
+    out: dict[str, float] = {}
+    for key, values in buckets.items():
+        if values:
+            out[key] = float(statistics.median(values))
+    return out
+
+
 def _pick_search_match(symbol: str) -> dict[str, Any]:
     sym = normalize_symbol(symbol)
     results = search_tickers(sym)