Update src/streamlit_app.py

src/streamlit_app.py

@@ -143,7 +143,131 @@ def render_whale_monitor():
         render_premarket_scan()
 
 
-# --- Premarket scan section unchanged, omitted here for brevity ---
+@st.cache_data(ttl=24 * 3600, show_spinner="Loading curated ticker list...")
+def get_clean_premarket_universe():
+    try:
+        local_path = hf_hub_download(
+            repo_id="Trebor1009/clean-premarket-data", repo_type="dataset",
+            filename="clean_premarket_data.csv", token=HF_TOKEN,
+        )
+        df = pd.read_csv(local_path, usecols=["Ticker"])
+        return sorted(df["Ticker"].dropna().unique().tolist())
+    except Exception as e:
+        st.warning(f"Could not load curated ticker list from Trebor1009/clean-premarket-data: {e}")
+        return []
+
+
+@st.cache_data(ttl=3600, show_spinner="Fetching prior-close reference prices...")
+def get_daily_reference_data(tickers_tuple):
+    ref = {}
+    batch_size = 10
+    total_batches = max(1, (len(tickers_tuple) + batch_size - 1) // batch_size)
+    progress = st.progress(0, text="Fetching reference prices...")
+    today_date = pd.Timestamp.now(tz="America/New_York").normalize().tz_localize(None)
+
+    for b, i in enumerate(range(0, len(tickers_tuple), batch_size)):
+        batch = tickers_tuple[i:i + batch_size]
+        try:
+            data = yf.download(list(batch), period="1mo", interval="1d", group_by="ticker",
+                                progress=False, threads=True)
+        except Exception:
+            progress.progress((b + 1) / total_batches)
+            continue
+
+        for ticker in batch:
+            try:
+                try:
+                    raw = data[ticker]
+                except Exception:
+                    raw = data
+                closes = raw["Close"].dropna()
+                vol = raw["Volume"].dropna()
+                if closes.empty:
+                    continue
+                idx = closes.index.tz_localize(None) if closes.index.tz is not None else closes.index
+                prior = closes[idx.normalize() < today_date]
+                if not prior.empty:
+                    prev_close = float(prior.iloc[-1])
+                elif len(closes) >= 2:
+                    prev_close = float(closes.iloc[-2])
+                else:
+                    prev_close = float(closes.iloc[-1])
+                avg_vol = float(vol.mean()) if len(vol) >= 5 else None
+                ref[ticker] = {"prev_close": prev_close, "avg_vol": avg_vol}
+            except Exception:
+                continue
+
+        progress.progress((b + 1) / total_batches, text=f"Reference data: batch {b + 1}/{total_batches}...")
+
+    progress.empty()
+    return ref
+
+
+@st.cache_data(ttl=300, show_spinner=False)
+def run_premarket_scan(tickers_tuple, min_gap_pct, direction):
+    ref_data = get_daily_reference_data(tickers_tuple)
+    results = []
+    batch_size = 10
+    total_batches = max(1, (len(tickers_tuple) + batch_size - 1) // batch_size)
+    progress = st.progress(0, text="Scanning premarket activity...")
+
+    for b, i in enumerate(range(0, len(tickers_tuple), batch_size)):
+        batch = tickers_tuple[i:i + batch_size]
+        try:
+            data = yf.download(list(batch), period="1d", interval="1m", prepost=True,
+                                group_by="ticker", progress=False, threads=True)
+        except Exception:
+            progress.progress((b + 1) / total_batches, text=f"Batch {b + 1}/{total_batches} failed, continuing...")
+            continue
+
+        for ticker in batch:
+            try:
+                try:
+                    raw = data[ticker]
+                except Exception:
+                    raw = data
+                df = raw.dropna(subset=["Close"])
+                if df.empty:
+                    continue
+                if df.index.tz is not None:
+                    df = df.copy()
+                    df.index = df.index.tz_convert("America/New_York")
+                else:
+                    df = df.copy()
+                    df.index = df.index.tz_localize("America/New_York")
+                premarket = df[df.index.time < dt_time(9, 30)]
+                if premarket.empty:
+                    continue
+                ref = ref_data.get(ticker)
+                if not ref or not ref.get("prev_close"):
+                    continue
+                prev_close = ref["prev_close"]
+                last_price = float(premarket["Close"].iloc[-1])
+                if not prev_close:
+                    continue
+                gap_pct = (last_price - prev_close) / prev_close * 100
+                if abs(gap_pct) < min_gap_pct:
+                    continue
+                if direction == "Up only" and gap_pct <= 0:
+                    continue
+                if direction == "Down only" and gap_pct >= 0:
+                    continue
+                pm_volume = int(premarket["Volume"].sum())
+                results.append({
+                    "Ticker": ticker,
+                    "Prev Close": round(prev_close, 2),
+                    "Premarket Price": round(last_price, 2),
+                    "Gap %": round(gap_pct, 2),
+                    "Premarket Volume": pm_volume,
+                    "Avg Daily Vol": int(ref["avg_vol"]) if ref.get("avg_vol") else None,
+                })
+            except Exception:
+                continue
+
+        progress.progress((b + 1) / total_batches, text=f"Scanned batch {b + 1}/{total_batches}...")
+
+    progress.empty()
+    return pd.DataFrame(results)
 
 
 def render_whale_single_ticker():