Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,6 +1,7 @@
 import warnings
 warnings.filterwarnings("ignore")
 
+import os
 import streamlit as st
 import yfinance as yf
 import pandas as pd
@@ -8,9 +9,74 @@ import numpy as np
 import matplotlib.pyplot as plt
 from numpy.lib.stride_tricks import sliding_window_view
 from sklearn.ensemble import GradientBoostingClassifier
+from huggingface_hub import HfApi, hf_hub_download
 
 st.set_page_config(page_title="Market Dashboard", page_icon="📊", layout="wide")
 
+# =========================================================
+# SHARED: PERSISTENT SIGNAL LOG (Hugging Face Dataset backend)
+# =========================================================
+
+HF_TOKEN = os.environ.get("HF_TOKEN")
+DATASET_REPO = os.environ.get("HF_DATASET_REPO")
+LOG_FILENAME = "signal_log.csv"
+
+
+def _log_configured() -> bool:
+    return bool(HF_TOKEN and DATASET_REPO)
+
+
+def load_signal_log() -> pd.DataFrame:
+    if not _log_configured():
+        return pd.DataFrame()
+    try:
+        local_path = hf_hub_download(
+            repo_id=DATASET_REPO, repo_type="dataset", filename=LOG_FILENAME, token=HF_TOKEN
+        )
+        df = pd.read_csv(local_path)
+        if "FlagDate" in df.columns:
+            df["FlagDate"] = pd.to_datetime(df["FlagDate"])
+        return df
+    except Exception:
+        return pd.DataFrame()
+
+
+def save_signal_log(df: pd.DataFrame) -> bool:
+    if not _log_configured():
+        return False
+    try:
+        api = HfApi(token=HF_TOKEN)
+        csv_bytes = df.to_csv(index=False).encode("utf-8")
+        api.upload_file(
+            path_or_fileobj=csv_bytes,
+            path_in_repo=LOG_FILENAME,
+            repo_id=DATASET_REPO,
+            repo_type="dataset",
+            commit_message=f"Update signal log ({len(df)} total signals)",
+        )
+        return True
+    except Exception as e:
+        st.warning(f"Could not save signal log: {e}")
+        return False
+
+
+def append_hits_to_log(hits_df: pd.DataFrame, settings: dict) -> bool:
+    if hits_df.empty or not _log_configured():
+        return False
+    existing = load_signal_log()
+    new_rows = hits_df.copy()
+    new_rows["FlagDate"] = pd.Timestamp.now().normalize()
+    new_rows["RSI_Threshold"] = settings["rsi_threshold"]
+    new_rows["Stretch_Threshold"] = settings["stretch_threshold"]
+    new_rows["Strict_Window"] = settings["strict_window"]
+    new_rows["Lookback"] = settings["lookback"]
+    new_rows["WinRate_Min"] = settings["win_rate_min"]
+
+    combined = pd.concat([existing, new_rows], ignore_index=True) if not existing.empty else new_rows
+    combined = combined.drop_duplicates(subset=["Ticker", "FlagDate"], keep="last")
+    return save_signal_log(combined)
+
+
 # =========================================================
 # TAB 1: WHALE MONITOR
 # =========================================================
@@ -363,6 +429,7 @@ def analyze_ticker(df, rsi_threshold, stretch_threshold, strict_window, lookback
     result = {
         "rsi": rsi.iloc[-1],
         "stretch": current_stretch,
+        "price": close.iloc[-1],
         "stats": None,
         "fractal_target": None,
         "df": df,
@@ -445,209 +512,4 @@ def run_full_scan(universe_label, extra_tickers_tuple, rsi_threshold, stretch_th
             continue
 
         for ticker in batch:
-            try:
-                try:
-                    raw = data[ticker]
-                except Exception:
-                    raw = data
-                df = raw.dropna()
-                if len(df) < 200:
-                    continue
-                result = analyze_ticker(df, rsi_threshold, stretch_threshold, strict_window, lookback, win_rate_min)
-                if result and result["signal_met"]:
-                    stats = result["stats"]
-                    results.append({
-                        "Ticker": ticker,
-                        "RSI": round(result["rsi"], 1),
-                        "Stretch %": round(result["stretch"], 2),
-                        "Matches": stats["count"],
-                        "Avg 1D %": round(stats["avg_1d"], 2),
-                        "Avg 5D %": round(stats["avg_5d"], 2),
-                        "Avg 3M %": round(stats["avg_3m"], 2),
-                        "3M Win Rate %": round(stats["win_3m"], 1),
-                    })
-            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_sniper_dashboard(ticker, result):
-    df = result["df"]
-    rsi_series = result["rsi_series"]
-    stats = result["stats"]
-    target = result["fractal_target"]
-
-    fig = plt.figure(figsize=(12, 8))
-    gs = fig.add_gridspec(2, 2)
-
-    ax1 = fig.add_subplot(gs[0, :])
-    ax1.plot(df.index, df["Close"], color="gray", alpha=0.3, label="History")
-    recent = df.tail(120)
-    ax1.plot(recent.index, recent["Close"], color="black", linewidth=1.5, label="Current Trend")
-
-    if stats:
-        ax1.scatter(stats["match_dates"], stats["match_prices"], color="limegreen", s=20, zorder=5,
-                     label="Strict Matches")
-    if target is not None:
-        ax1.axhline(target, color="blue", ls="--", alpha=0.6, label="Single best-match analog (not a target)")
-
-    ax1.set_title(f"{ticker}", fontsize=16, fontweight="bold")
-    ax1.legend(loc="upper left", fontsize=9)
-    ax1.grid(True, alpha=0.1)
-
-    if stats:
-        stats_text = (
-            f"Historical Matches: {stats['count']}\n"
-            f"Avg Change 1D:  {stats['avg_1d']:+.2f}%\n"
-            f"Avg Change 5D:  {stats['avg_5d']:+.2f}%\n"
-            f"Avg Change 3M:  {stats['avg_3m']:+.2f}%\n"
-            f"3M Win Rate: {stats['win_3m']:.1f}% (n={stats['count']})"
-        )
-        ax1.text(0.98, 0.05, stats_text, transform=ax1.transAxes, va="bottom", ha="right",
-                  bbox=dict(boxstyle="round", facecolor="white", alpha=0.9, edgecolor="darkgreen"),
-                  fontsize=10, family="monospace")
-
-    ax2 = fig.add_subplot(gs[1, 0])
-    ax2.plot(recent.index, rsi_series.tail(120), color="purple")
-    ax2.axhline(result["rsi"], color="orange", ls=":")
-    ax2.set_title(f"RSI: {result['rsi']:.1f}")
-
-    ax3 = fig.add_subplot(gs[1, 1])
-    if stats:
-        horizons = ["1D", "5D", "3M"]
-        values = [stats["avg_1d"], stats["avg_5d"], stats["avg_3m"]]
-        ax3.bar(horizons, values, color="limegreen", alpha=0.8)
-        ax3.axhline(0, color="black", linewidth=0.8)
-        ax3.set_title("Historical Edge by Horizon")
-    else:
-        ax3.set_title("No matches to show")
-
-    plt.tight_layout()
-    st.pyplot(fig)
-    plt.close(fig)
-
-
-def render_sniper_tab():
-    st.title("🎯 Sniper Scanner")
-    st.caption(
-        "Looks for 'triple-positive' historical analog setups: today's RSI/SMA-stretch combination "
-        "compared against similar conditions earlier in a ticker's own price history, scored by average "
-        "forward returns and win rate."
-    )
-    st.warning(
-        "⚠️ Two things worth keeping in mind:\n\n"
-        "1. **Small samples** — many qualifying setups have only 10-30 historical matches. An '80% win rate' "
-        "on 10 matches (8 wins) has a much wider true range than the headline number suggests — treat it as "
-        "a lean, not a precise probability.\n\n"
-        "2. **Full-universe scans test thousands of tickers at once.** With that many independent tests, some "
-        "will clear an 80%+ historical win-rate bar by chance alone, with no real edge behind it. A hit showing "
-        "up in a scan is a reason to look closer, not a standalone signal.\n\n"
-        "The dashed blue line ('best-match analog') is one single closest-matching historical window, shown "
-        "for context — not a statistical price target."
-    )
-
-    with st.sidebar:
-        st.markdown("---")
-        st.header("Sniper Scanner Settings")
-        rsi_threshold = st.slider("RSI threshold (oversold below this)", 20, 60, 45, 1, key="sn_rsi")
-        stretch_threshold = st.slider("Max SMA20 stretch %", -8.0, 0.0, -2.0, 0.5, key="sn_stretch")
-        strict_window = st.slider("Match strictness (± stretch %)", 0.1, 2.0, 0.5, 0.1, key="sn_window")
-        lookback = st.slider("Fractal lookback (days)", 20, 120, 60, 5, key="sn_lookback")
-        win_rate_min = st.slider("Min 3M win rate to flag (%)", 50, 95, 80, 5, key="sn_winrate")
-        extra_input = st.text_input("Extra tickers for full scan (comma-separated)", value="GC=F,BTC-USD",
-                                     key="sn_extra")
-        include_russell = st.checkbox("Include Russell 2000 in full scan (~2,000 more tickers, much slower)",
-                                       value=False, key="sn_russell")
-
-    extra_tickers = tuple(t.strip().upper() for t in extra_input.split(",") if t.strip())
-
-    st.subheader("Analyze a single ticker")
-    single_ticker = st.text_input("Ticker", value="BTC-USD", key="sn_single").strip().upper()
-    if st.button("Analyze", key="sn_analyze_btn") and single_ticker:
-        raw = get_sniper_ticker_data(single_ticker)
-        if raw.empty:
-            st.error(f"No data for '{single_ticker}'.")
-        else:
-            result = analyze_ticker(raw, rsi_threshold, stretch_threshold, strict_window, lookback, win_rate_min)
-            if result is None:
-                st.error("Not enough history for this ticker.")
-            else:
-                entry_met = result["rsi"] < rsi_threshold and result["stretch"] < stretch_threshold
-                if not entry_met:
-                    st.info(
-                        f"RSI {result['rsi']:.1f} / Stretch {result['stretch']:.2f}% — entry conditions "
-                        f"(RSI < {rsi_threshold}, stretch < {stretch_threshold}%) not currently met. "
-                        "Showing current state for reference."
-                    )
-                elif result["stats"] is None:
-                    st.info(
-                        f"Entry conditions met (RSI {result['rsi']:.1f}, stretch {result['stretch']:.2f}%) "
-                        "but fewer than 10 historical analogs found — not enough data to score."
-                    )
-                elif result["signal_met"]:
-                    st.success(
-                        f"✅ Full signal met — {result['stats']['win_3m']:.1f}% historical 3M win rate "
-                        f"over {result['stats']['count']} matches."
-                    )
-                else:
-                    st.info(
-                        f"Entry conditions met but didn't clear the win-rate/triple-positive bar "
-                        f"({result['stats']['win_3m']:.1f}% win rate over {result['stats']['count']} matches)."
-                    )
-                render_sniper_dashboard(single_ticker, result)
-
-    st.markdown("---")
-    st.subheader("Full universe scan")
-    universe_label = "sp500_russell2000" if include_russell else "sp500"
-    st.caption(
-        f"Will scan the {'S&P 500 + Russell 2000' if include_russell else 'S&P 500'} plus your extra tickers "
-        f"for setups meeting the full criteria. First run can take several minutes — results are cached for "
-        f"12 hours after that. Start with Russell 2000 unchecked to see how long a run takes on this host "
-        f"before opting into the larger universe."
-    )
-    if st.button("🔍 Run Full Universe Scan", key="sn_scan_btn"):
-        tickers = get_universe_tickers(include_russell, extra_tickers)
-        st.write(f"Scanning {len(tickers)} tickers...")
-        results_df = run_full_scan(
-            universe_label, extra_tickers, rsi_threshold, stretch_threshold,
-            strict_window, lookback, win_rate_min, tickers,
-        )
-        st.session_state["sn_results"] = results_df
-
-    if "sn_results" in st.session_state:
-        results_df = st.session_state["sn_results"]
-        if results_df.empty:
-            st.info("No tickers met the full signal criteria with current settings.")
-        else:
-            st.success(f"{len(results_df)} ticker(s) met the criteria.")
-            sorted_df = results_df.sort_values("3M Win Rate %", ascending=False).reset_index(drop=True)
-            st.dataframe(sorted_df, use_container_width=True, hide_index=True)
-
-            pick = st.selectbox("View chart for:", sorted_df["Ticker"].tolist(), key="sn_pick")
-            if pick:
-                raw = get_sniper_ticker_data(pick)
-                if not raw.empty:
-                    result = analyze_ticker(raw, rsi_threshold, stretch_threshold, strict_window, lookback,
-                                             win_rate_min)
-                    if result:
-                        render_sniper_dashboard(pick, result)
-
-
-# =========================================================
-# MAIN LAYOUT
-# =========================================================
-
-tab1, tab2, tab3 = st.tabs(["🐋 Whale Monitor", "📉 Peak Detector", "🎯 Sniper Scanner"])
-
-with tab1:
-    render_whale_monitor()
-
-with tab2:
-    render_peak_detector()
-
-with tab3:
-    render_sniper_tab()
+