Update app.py

app.py

@@ -7,12 +7,14 @@ import yfinance as yf
 import numpy as np
 from transformers import pipeline
 from cachetools import TTLCache, cached
+from datetime import datetime, timezone
 
 # -----------------------------
 # CONFIG
 # -----------------------------
 NEWSAPI_KEY = os.environ.get("NEWSAPI_KEY", "").strip()
 MAX_HEADLINES = 10  # fetch more for robustness
+DECAY_HALF_LIFE_HOURS = 12  # half-life for old news
 
 MODEL_A = "yiyanghkust/finbert-tone"
 MODEL_B = "ProsusAI/finbert"
@@ -49,7 +51,7 @@ def is_relevant_headline(headline: str) -> bool:
 # -----------------------------
 # News fetchers
 # -----------------------------
-def fetch_news_newsapi(stock: str, limit: int = MAX_HEADLINES) -> List[str]:
+def fetch_news_newsapi(stock: str, limit: int = MAX_HEADLINES) -> List[Dict]:
     if not NEWSAPI_KEY:
         return []
     url = "https://newsapi.org/v2/everything"
@@ -65,30 +67,33 @@ def fetch_news_newsapi(stock: str, limit: int = MAX_HEADLINES) -> List[str]:
         r = requests.get(url, params=params, timeout=6)
         r.raise_for_status()
         articles = r.json().get("articles", [])
-        headlines = [a.get("title") for a in articles if a.get("title")]
-        filtered = [h for h in headlines if is_relevant_headline(h)]
+        filtered = [
+            {"title": a.get("title"), "publishedAt": a.get("publishedAt")}
+            for a in articles if a.get("title") and is_relevant_headline(a.get("title"))
+        ]
         return filtered[:limit]
     except Exception as e:
         print(f"[NewsAPI error] {e}")
         return []
 
-def fetch_news_yfinance(stock: str, limit: int = MAX_HEADLINES) -> List[str]:
+def fetch_news_yfinance(stock: str, limit: int = MAX_HEADLINES) -> List[Dict]:
     try:
         t = yf.Ticker(stock)
         news_items = getattr(t, "news", None) or []
-        headlines = [n.get("title") for n in news_items if n.get("title")]
-        filtered = [h for h in headlines if is_relevant_headline(h)]
+        filtered = [
+            {"title": n.get("title"), "publishedAt": n.get("providerPublishTime")}
+            for n in news_items if n.get("title") and is_relevant_headline(n.get("title"))
+        ]
         return filtered[:limit]
     except Exception as e:
         print(f"[Yahoo Finance error] {e}")
         return []
 
-def fetch_headlines(stock: str, limit: int = MAX_HEADLINES) -> List[str]:
+def fetch_headlines(stock: str, limit: int = MAX_HEADLINES) -> List[Dict]:
     headlines = fetch_news_newsapi(stock, limit)
-    if len(headlines) < 2:  # fallback if insufficient headlines
+    if len(headlines) < 2:
         headlines_yf = fetch_news_yfinance(stock, limit)
-        # combine and remove duplicates
-        headlines = list(dict.fromkeys(headlines + headlines_yf))[:limit]
+        headlines = list({h['title']: h for h in (headlines + headlines_yf)}.values())[:limit]
     return headlines
 
 # -----------------------------
@@ -114,10 +119,17 @@ def headline_score_ensemble(headline: str) -> np.ndarray:
     b = sentiment_b(headline)[0]
     return (model_to_vector(a) + model_to_vector(b)) / 2.0
 
-def aggregate_headlines_vectors(vectors: List[np.ndarray]) -> np.ndarray:
+def aggregate_headlines_vectors(vectors: List[np.ndarray], timestamps: List[float]) -> np.ndarray:
     if not vectors:
         return np.array([0.0,1.0,0.0])
-    mean_vec = np.mean(vectors, axis=0)
+    
+    # Apply decay weights based on timestamps
+    now = datetime.now(timezone.utc).timestamp()
+    weights = np.array([0.5 ** ((now - ts)/(DECAY_HALF_LIFE_HOURS*3600)) for ts in timestamps])
+    weighted_vecs = np.array(vectors) * weights[:, None]
+    mean_vec = weighted_vecs.sum(axis=0) / weights.sum()
+    
+    mean_vec = np.clip(mean_vec, 0.0, None)
     total = mean_vec.sum()
     return mean_vec / total if total > 0 else np.array([0.0,1.0,0.0])
 
@@ -128,24 +140,42 @@ def vector_to_score(vec: np.ndarray) -> float:
 # -----------------------------
 # FastAPI app
 # -----------------------------
-app = FastAPI(title="Financial Sentiment API")
+app = FastAPI(title="Financial Sentiment API with Decay")
 
 class StocksRequest(BaseModel):
     stocks: List[str]
 
 @cached(stock_cache)
 def analyze_single_stock(stock: str) -> float | str:
-    headlines = fetch_headlines(stock)
-    headlines = [h for h in headlines if h and len(h.strip()) > 10]
-    if not headlines:
+    headlines_data = fetch_headlines(stock)
+    headlines_data = [h for h in headlines_data if h.get("title") and len(h["title"].strip()) > 10]
+
+    if not headlines_data:
         return "NO_DATA"
-    vectors = [headline_score_ensemble(h) for h in headlines]
-    agg = aggregate_headlines_vectors(vectors)
+
+    vectors = []
+    timestamps = []
+    for h in headlines_data:
+        vectors.append(headline_score_ensemble(h["title"]))
+        # convert publishedAt to timestamp
+        try:
+            ts = h.get("publishedAt")
+            if isinstance(ts, str):
+                ts = datetime.fromisoformat(ts.replace("Z","+00:00")).timestamp()
+            elif isinstance(ts, (int, float)):
+                ts = float(ts)
+            else:
+                ts = datetime.now(timezone.utc).timestamp()
+        except:
+            ts = datetime.now(timezone.utc).timestamp()
+        timestamps.append(ts)
+
+    agg = aggregate_headlines_vectors(vectors, timestamps)
     return vector_to_score(agg)
 
 @app.get("/")
 def root():
-    return {"message": "Fin-senti API is running! Use POST /analyze"}
+    return {"message": "Fin-senti API with Decay is running! Use POST /analyze"}
 
 @app.post("/analyze")
 def analyze(req: StocksRequest):