PROSTLE commited on
Commit
57ee2b0
Β·
unverified Β·
0 Parent(s):

Add files via upload

Browse files
Files changed (12) hide show
  1. .gitignore +8 -0
  2. README.md +116 -0
  3. app.js +660 -0
  4. app.py +352 -0
  5. index.html +205 -0
  6. model.py +211 -0
  7. portfolio.json +8 -0
  8. sentiment.py +151 -0
  9. step4_install.sh +12 -0
  10. stock_data.py +118 -0
  11. style.css +274 -0
  12. trader.py +287 -0
.gitignore ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ __pycache__/
2
+ *.pyc
3
+ venv/
4
+ .env
5
+ trained_models/
6
+ portfolio.json
7
+ node_modules/
8
+ .DS_Store
README.md ADDED
@@ -0,0 +1,116 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # πŸ“ˆ StockSense AI β€” AI-Powered Stock Market Prediction
2
+
3
+ > **Hackathon Project** | Built in 48 hours
4
+
5
+ ##🎀 Elevator Pitch (30 seconds)
6
+
7
+ *"StockSense AI uses deep learning and NLP to predict stock prices 5 days ahead.
8
+ Enter any ticker β€” our LSTM model analyzes 2 years of market data and technical
9
+ indicators, while FinBERT reads the latest financial news to gauge market
10
+ sentiment. You get an interactive chart with predictions, a confidence score,
11
+ a risk level, and a clear sentiment breakdown β€” all in seconds."*
12
+
13
+ ---
14
+
15
+ ## πŸš€ Quick Start
16
+
17
+ ### Prerequisites
18
+ - Python 3.10+
19
+ - Node.js (optional – only if you want a dev server for frontend)
20
+ - ~2 GB disk for FinBERT model weights (auto-downloaded)
21
+
22
+ ### 1. Backend Setup
23
+
24
+ ```bash
25
+ cd backend
26
+ python -m venv venv
27
+ source venv/bin/activate # Windows: venv\Scripts\activate
28
+ pip install -r requirements.txt
29
+ uvicorn app:app --reload --port 8000
30
+ ```
31
+
32
+ The API will be live at **http://localhost:8000**.
33
+
34
+ ### 2. Frontend Setup
35
+
36
+ Simply open `frontend/index.html` in your browser, **or** serve it:
37
+
38
+ ```bash
39
+ cd frontend
40
+ python -m http.server 3000
41
+ ```
42
+
43
+ Then visit **http://localhost:3000**.
44
+
45
+ ---
46
+
47
+ ## πŸ”— API Endpoints
48
+
49
+ | Method | Endpoint | Description |
50
+ |--------|----------------------------|------------------------------------|
51
+ | GET | `/api/stock/{ticker}` | Historical data + indicators |
52
+ | GET | `/api/predict/{ticker}` | LSTM 5-day price prediction |
53
+ | GET | `/api/sentiment/{ticker}` | FinBERT news sentiment analysis |
54
+ | GET | `/api/summary/{ticker}` | Combined analysis (all of above) |
55
+
56
+ ---
57
+
58
+ ## πŸ—οΈ Architecture
59
+
60
+ ```
61
+ User β†’ React/HTML Frontend β†’ FastAPI Backend
62
+ β”œβ”€β”€ yfinance (stock data)
63
+ β”œβ”€β”€ ta (technical indicators)
64
+ β”œβ”€β”€ PyTorch LSTM (price prediction)
65
+ └── FinBERT (sentiment analysis)
66
+ ```
67
+
68
+ ---
69
+
70
+ ## 🧠 ML Pipeline
71
+
72
+ 1. **Data**: 2 years of daily OHLCV via Yahoo Finance
73
+ 2. **Features**: Close price (normalized via MinMaxScaler)
74
+ 3. **Model**: 2-layer LSTM (64 hidden units) β†’ FC β†’ 5-day output
75
+ 4. **Training**: 30 epochs, Adam optimizer, MSE loss, 85/15 train/test split
76
+ 5. **Inference**: Last 60-day window β†’ next 5 closing prices
77
+
78
+ ---
79
+
80
+ ## ☁️ Deployment (Optional)
81
+
82
+ ### Docker
83
+
84
+ ```dockerfile
85
+ FROM python:3.11-slim
86
+ WORKDIR /app
87
+ COPY backend/ .
88
+ RUN pip install --no-cache-dir -r requirements.txt
89
+ EXPOSE 8000
90
+ CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8000"]
91
+ ```
92
+
93
+ ```bash
94
+ docker build -t stocksense-ai .
95
+ docker run -p 8000:8000 stocksense-ai
96
+ ```
97
+
98
+ ### Cloud (Render / Railway / Fly.io)
99
+ 1. Push to GitHub
100
+ 2. Connect repo on Render β†’ set build command: `pip install -r requirements.txt`
101
+ 3. Set start command: `uvicorn app:app --host 0.0.0.0 --port 8000`
102
+
103
+ ---
104
+
105
+ ## ⚠️ Disclaimer
106
+
107
+ This project is for **educational and hackathon demonstration purposes only**.
108
+ Stock market predictions generated by this tool are **not financial advice**.
109
+ Past performance does not guarantee future results. Always consult a qualified
110
+ financial advisor before making investment decisions.
111
+
112
+ ---
113
+
114
+ ## πŸ“œ License
115
+
116
+ MIT β€” feel free to fork and improve!
app.js ADDED
@@ -0,0 +1,660 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ /* ══════════════════════════════════════════════════════
2
+ StockSense AI β€” Frontend v3.0 (COMPLETE FILE)
3
+ Live Charts + Prediction + Auto Trading Bot
4
+ ══════════════════════════════════════════════════════ */
5
+
6
+ const API = "http://127.0.0.1:8000";
7
+ let currentTicker = "";
8
+ let liveInterval = null;
9
+ let portfolioInterval = null;
10
+ let mainChart = null;
11
+ let volumeChart = null;
12
+ let predChart = null;
13
+ let activeTimeframe = "1d";
14
+
15
+ /* ══ INIT ══════════════════════════════════════════════ */
16
+ document.addEventListener("DOMContentLoaded", () => {
17
+ loadHighPotential();
18
+ loadPortfolio();
19
+ setupTimeframeButtons();
20
+ portfolioInterval = setInterval(loadPortfolio, 15000);
21
+
22
+ document.getElementById("tickerInput").addEventListener("keydown", (e) => {
23
+ if (e.key === "Enter") loadTicker();
24
+ });
25
+ });
26
+
27
+ /* ══ TAB SWITCHING ═════════════════════════════════════ */
28
+ function switchTab(tab) {
29
+ document.querySelectorAll(".nav-tab").forEach((t) => t.classList.remove("active"));
30
+ document.querySelectorAll(".tab-content").forEach((t) => t.classList.add("hidden"));
31
+
32
+ if (tab === "charts") {
33
+ document.getElementById("chartsTab").classList.remove("hidden");
34
+ document.querySelectorAll(".nav-tab")[0].classList.add("active");
35
+ } else {
36
+ document.getElementById("tradingTab").classList.remove("hidden");
37
+ document.querySelectorAll(".nav-tab")[1].classList.add("active");
38
+ loadPortfolio();
39
+ }
40
+ }
41
+
42
+ /* ══ TIMEFRAME BUTTONS ═════════════════════════════════ */
43
+ function setupTimeframeButtons() {
44
+ document.querySelectorAll(".tf-btn").forEach((btn) => {
45
+ btn.addEventListener("click", () => {
46
+ document.querySelectorAll(".tf-btn").forEach((b) => b.classList.remove("active"));
47
+ btn.classList.add("active");
48
+ activeTimeframe = btn.dataset.tf;
49
+ if (currentTicker) loadChartData(currentTicker, activeTimeframe);
50
+ });
51
+ });
52
+ }
53
+
54
+ /* ══ MAIN LOAD TICKER ══════════════════════════════════ */
55
+ async function loadTicker(ticker) {
56
+ ticker = ticker || document.getElementById("tickerInput").value.trim().toUpperCase();
57
+ if (!ticker) return;
58
+
59
+ currentTicker = ticker;
60
+ document.getElementById("tickerInput").value = ticker;
61
+
62
+ if (liveInterval) clearInterval(liveInterval);
63
+
64
+ await Promise.all([
65
+ loadLivePrice(ticker),
66
+ loadChartData(ticker, activeTimeframe),
67
+ loadPrediction(ticker),
68
+ loadSentimentAndIndicators(ticker),
69
+ ]);
70
+
71
+ liveInterval = setInterval(() => loadLivePrice(ticker), 10000);
72
+ }
73
+
74
+ /* ══ LIVE PRICE ════════════════════════════════════════ */
75
+ async function loadLivePrice(ticker) {
76
+ try {
77
+ const res = await fetch(`${API}/api/live/${ticker}`);
78
+ const data = await res.json();
79
+
80
+ document.getElementById("priceBanner").classList.remove("hidden");
81
+ document.getElementById("bannerName").textContent = ticker;
82
+ document.getElementById("bannerPrice").textContent = formatPrice(data.price);
83
+
84
+ const changeEl = document.getElementById("bannerChange");
85
+ const sign = data.change >= 0 ? "+" : "";
86
+ changeEl.textContent = `${sign}${data.change} (${sign}${data.change_pct}%)`;
87
+ changeEl.className = `price-change ${data.direction}`;
88
+
89
+ document.getElementById("statHigh").textContent = formatPrice(data.day_high);
90
+ document.getElementById("statLow").textContent = formatPrice(data.day_low);
91
+ document.getElementById("statVol").textContent = formatVolume(data.volume);
92
+ } catch (e) {
93
+ console.error("Live price error:", e);
94
+ }
95
+ }
96
+
97
+ /* ══ CHART DATA ════════════════════════════════════════ */
98
+ async function loadChartData(ticker, timeframe) {
99
+ try {
100
+ const [chartRes, infoRes] = await Promise.all([
101
+ fetch(`${API}/api/chart/${ticker}?timeframe=${timeframe}`),
102
+ fetch(`${API}/api/stock/${ticker}`),
103
+ ]);
104
+ const chartData = await chartRes.json();
105
+ const stockData = await infoRes.json();
106
+
107
+ if (stockData.info) {
108
+ const info = stockData.info;
109
+ document.getElementById("bannerName").textContent = `${info.name} (${ticker})`;
110
+ document.getElementById("statOpen").textContent = formatPrice(info.open);
111
+ document.getElementById("statHigh").textContent = formatPrice(info.day_high);
112
+ document.getElementById("statLow").textContent = formatPrice(info.day_low);
113
+ document.getElementById("statVol").textContent = formatVolume(info.volume);
114
+ document.getElementById("stat52H").textContent = formatPrice(info.fifty_two_week_high);
115
+ document.getElementById("stat52L").textContent = formatPrice(info.fifty_two_week_low);
116
+ }
117
+
118
+ drawMainChart(chartData.data);
119
+ drawVolumeChart(chartData.data);
120
+ } catch (e) {
121
+ console.error("Chart error:", e);
122
+ }
123
+ }
124
+
125
+ /* ══ DRAW MAIN CHART ═══════════════════════════════════ */
126
+ function drawMainChart(data) {
127
+ const labels = data.map((d) => d.time);
128
+ const closes = data.map((d) => d.close);
129
+ const highs = data.map((d) => d.high);
130
+ const lows = data.map((d) => d.low);
131
+
132
+ const isUp = closes[closes.length - 1] >= closes[0];
133
+ const lineColor = isUp ? "#22c55e" : "#ef4444";
134
+ const fillColor = isUp ? "rgba(34,197,94,0.08)" : "rgba(239,68,68,0.08)";
135
+
136
+ if (mainChart) mainChart.destroy();
137
+
138
+ mainChart = new Chart(document.getElementById("mainChart").getContext("2d"), {
139
+ type: "line",
140
+ data: {
141
+ labels,
142
+ datasets: [
143
+ { label: "Close", data: closes, borderColor: lineColor, backgroundColor: fillColor, fill: true, tension: 0.3, pointRadius: 0, borderWidth: 2 },
144
+ { label: "High", data: highs, borderColor: "rgba(34,197,94,0.2)", borderDash: [2, 4], pointRadius: 0, borderWidth: 1, fill: false },
145
+ { label: "Low", data: lows, borderColor: "rgba(239,68,68,0.2)", borderDash: [2, 4], pointRadius: 0, borderWidth: 1, fill: false },
146
+ ],
147
+ },
148
+ options: {
149
+ responsive: true,
150
+ maintainAspectRatio: false,
151
+ interaction: { mode: "index", intersect: false },
152
+ plugins: {
153
+ legend: { labels: { color: "#6b7280", font: { size: 11 } } },
154
+ tooltip: { backgroundColor: "#1a1f2e", borderColor: "#242a38", borderWidth: 1, titleColor: "#fff", bodyColor: "#d1d5db" },
155
+ },
156
+ scales: {
157
+ x: { ticks: { color: "#4b5563", maxTicksLimit: 10, maxRotation: 0, font: { size: 10 } }, grid: { color: "#1f2937" } },
158
+ y: { ticks: { color: "#4b5563", font: { size: 10 } }, grid: { color: "#1f2937" } },
159
+ },
160
+ },
161
+ });
162
+ }
163
+
164
+ /* ══ DRAW VOLUME CHART ═════════════════════════════════ */
165
+ function drawVolumeChart(data) {
166
+ const labels = data.map((d) => d.time);
167
+ const volumes = data.map((d) => d.volume);
168
+ const colors = data.map((d, i) => {
169
+ if (i === 0) return "rgba(59,130,246,0.5)";
170
+ return d.close >= data[i - 1].close ? "rgba(34,197,94,0.5)" : "rgba(239,68,68,0.5)";
171
+ });
172
+
173
+ if (volumeChart) volumeChart.destroy();
174
+
175
+ volumeChart = new Chart(document.getElementById("volumeChart").getContext("2d"), {
176
+ type: "bar",
177
+ data: {
178
+ labels,
179
+ datasets: [{ label: "Volume", data: volumes, backgroundColor: colors, borderWidth: 0 }],
180
+ },
181
+ options: {
182
+ responsive: true,
183
+ maintainAspectRatio: false,
184
+ plugins: { legend: { display: false } },
185
+ scales: {
186
+ x: { display: false },
187
+ y: { ticks: { color: "#4b5563", font: { size: 9 } }, grid: { color: "#1f2937" } },
188
+ },
189
+ },
190
+ });
191
+ }
192
+
193
+ /* ══ PREDICTION ════════════════════════════════════════ */
194
+ async function loadPrediction(ticker) {
195
+ const section = document.getElementById("predSection");
196
+ try {
197
+ const res = await fetch(`${API}/api/predict/${ticker}`);
198
+ const data = await res.json();
199
+
200
+ section.classList.remove("hidden");
201
+
202
+ document.getElementById("predConf").textContent = data.confidence + "%";
203
+ document.getElementById("predConf").style.color =
204
+ data.confidence >= 70 ? "#22c55e" : data.confidence >= 45 ? "#eab308" : "#ef4444";
205
+
206
+ document.getElementById("predRisk").textContent = data.risk;
207
+ document.getElementById("predRisk").style.color =
208
+ data.risk === "Low" ? "#22c55e" : data.risk === "Medium" ? "#eab308" : "#ef4444";
209
+
210
+ document.getElementById("predDay1").textContent = "$" + data.predicted_prices[0];
211
+ document.getElementById("predDay5").textContent = "$" + data.predicted_prices[4];
212
+
213
+ drawPredictionChart(data);
214
+ } catch (e) {
215
+ console.error("Prediction error:", e);
216
+ section.classList.add("hidden");
217
+ }
218
+ }
219
+
220
+ function drawPredictionChart(pred) {
221
+ const hist = pred.historical_last_30;
222
+ const future = pred.predicted_prices;
223
+
224
+ const labels = [];
225
+ for (let i = 0; i < hist.length; i++) labels.push(`D-${hist.length - i}`);
226
+ for (let i = 1; i <= future.length; i++) labels.push(`+${i}d`);
227
+
228
+ const histData = [...hist, ...Array(future.length).fill(null)];
229
+ const predData = [...Array(hist.length - 1).fill(null), hist[hist.length - 1], ...future];
230
+
231
+ if (predChart) predChart.destroy();
232
+
233
+ predChart = new Chart(document.getElementById("predChart").getContext("2d"), {
234
+ type: "line",
235
+ data: {
236
+ labels,
237
+ datasets: [
238
+ { label: "Historical", data: histData, borderColor: "#3b82f6", backgroundColor: "rgba(59,130,246,0.05)", fill: true, tension: 0.3, pointRadius: 0, borderWidth: 2 },
239
+ { label: "Predicted", data: predData, borderColor: "#22c55e", borderDash: [6, 3], backgroundColor: "rgba(34,197,94,0.08)", fill: true, tension: 0.3, pointRadius: 4, borderWidth: 2, pointBackgroundColor: "#22c55e" },
240
+ ],
241
+ },
242
+ options: {
243
+ responsive: true,
244
+ plugins: { legend: { labels: { color: "#6b7280" } } },
245
+ scales: {
246
+ x: { ticks: { color: "#4b5563", maxTicksLimit: 12, font: { size: 10 } }, grid: { color: "#1f2937" } },
247
+ y: { ticks: { color: "#4b5563", font: { size: 10 } }, grid: { color: "#1f2937" } },
248
+ },
249
+ },
250
+ });
251
+ }
252
+
253
+ /* ══ SENTIMENT + INDICATORS ════════════════════════════ */
254
+ async function loadSentimentAndIndicators(ticker) {
255
+ try {
256
+ const res = await fetch(`${API}/api/summary/${ticker}`);
257
+ const data = await res.json();
258
+
259
+ // Sentiment
260
+ const sentPanel = document.getElementById("sentPanel");
261
+ sentPanel.classList.remove("hidden");
262
+
263
+ const sent = data.sentiment;
264
+ const gauge = document.getElementById("gaugeCircle");
265
+ gauge.className = `gauge-circle ${sent.overall_sentiment}`;
266
+ document.getElementById("gaugeText").textContent = sent.overall_score;
267
+ document.getElementById("gaugeLabel").textContent = sent.overall_sentiment.toUpperCase();
268
+ document.getElementById("gaugeLabel").style.color =
269
+ sent.overall_sentiment === "positive" ? "#22c55e" :
270
+ sent.overall_sentiment === "negative" ? "#ef4444" : "#eab308";
271
+
272
+ const sentList = document.getElementById("sentList");
273
+ sentList.innerHTML = "";
274
+ (sent.details || []).forEach((d) => {
275
+ const li = document.createElement("li");
276
+ const cls = d.label === "positive" ? "s-pos" : d.label === "negative" ? "s-neg" : "s-neu";
277
+ li.innerHTML = `<span class="${cls}">● ${d.label}</span> ${d.text}`;
278
+ sentList.appendChild(li);
279
+ });
280
+
281
+ // Indicators
282
+ const indPanel = document.getElementById("indPanel");
283
+ indPanel.classList.remove("hidden");
284
+ const indBody = document.getElementById("indBody");
285
+ indBody.innerHTML = "";
286
+ Object.entries(data.indicators).forEach(([key, val]) => {
287
+ const tr = document.createElement("tr");
288
+ tr.innerHTML = `<td>${key}</td><td>${val}</td>`;
289
+ indBody.appendChild(tr);
290
+ });
291
+ } catch (e) {
292
+ console.error("Summary error:", e);
293
+ }
294
+ }
295
+
296
+ /* ══ HIGH POTENTIAL STOCKS ═════════════════════════════ */
297
+ async function loadHighPotential() {
298
+ try {
299
+ const res = await fetch(`${API}/api/high-potential`);
300
+ const data = await res.json();
301
+
302
+ document.getElementById("hpLoader").classList.add("hidden");
303
+ const list = document.getElementById("hpList");
304
+ list.innerHTML = "";
305
+
306
+ data.stocks.forEach((s) => {
307
+ const div = document.createElement("div");
308
+ div.className = "hp-item";
309
+ div.onclick = () => {
310
+ document.getElementById("tickerInput").value = s.ticker;
311
+ loadTicker(s.ticker);
312
+ };
313
+
314
+ const changeClass = s.change_pct >= 0 ? "up" : "down";
315
+ const sign = s.change_pct >= 0 ? "+" : "";
316
+ const scoreClass = s.score >= 70 ? "high" : s.score >= 45 ? "med" : "low";
317
+
318
+ div.innerHTML = `
319
+ <div>
320
+ <div class="hp-ticker">${s.ticker}</div>
321
+ <div class="hp-name">${s.name}</div>
322
+ </div>
323
+ <div>
324
+ <div class="hp-price">$${s.price}</div>
325
+ <div class="hp-change ${changeClass}">${sign}${s.change_pct}%</div>
326
+ </div>
327
+ <div class="hp-score ${scoreClass}">${s.signal}</div>
328
+ `;
329
+ list.appendChild(div);
330
+ });
331
+ } catch (e) {
332
+ document.getElementById("hpLoader").textContent = "⚠️ Scanner unavailable";
333
+ console.error("High potential error:", e);
334
+ }
335
+ }
336
+
337
+ /* ══════════════════════════════════════════════════════
338
+ TRADING FUNCTIONS
339
+ ══════════════════════════════════════════════════════ */
340
+
341
+ /* ══ LOAD PORTFOLIO ════════════════════════════════════ */
342
+ async function loadPortfolio() {
343
+ try {
344
+ const res = await fetch(`${API}/api/trade/portfolio`);
345
+ const data = await res.json();
346
+
347
+ // Portfolio header cards
348
+ document.getElementById("portValue").textContent = "$" + formatNumber(data.total_value || data.balance);
349
+ document.getElementById("portBalance").textContent = "$" + formatNumber(data.balance);
350
+
351
+ const unrealized = data.total_unrealized_pnl || 0;
352
+ const unrealizedEl = document.getElementById("portUnrealized");
353
+ unrealizedEl.textContent = (unrealized >= 0 ? "+$" : "-$") + formatNumber(Math.abs(unrealized));
354
+ unrealizedEl.style.color = unrealized >= 0 ? "#22c55e" : "#ef4444";
355
+
356
+ const realized = data.total_realized_pnl || 0;
357
+ const realizedEl = document.getElementById("portRealized");
358
+ realizedEl.textContent = (realized >= 0 ? "+$" : "-$") + formatNumber(Math.abs(realized));
359
+ realizedEl.style.color = realized >= 0 ? "#22c55e" : "#ef4444";
360
+
361
+ document.getElementById("portWinRate").textContent = (data.win_rate || 0) + "%";
362
+ document.getElementById("portWinRate").style.color = data.win_rate >= 50 ? "#22c55e" : "#ef4444";
363
+
364
+ document.getElementById("portTrades").textContent = data.total_trades || 0;
365
+
366
+ // Bot status
367
+ const botDot = document.getElementById("botDot");
368
+ const botStatus = document.getElementById("botStatus");
369
+ const toggleBtn = document.getElementById("toggleBotBtn");
370
+
371
+ if (data.bot_active) {
372
+ botDot.className = "bot-dot active";
373
+ botStatus.textContent = "Bot: ACTIVE";
374
+ botStatus.style.color = "#22c55e";
375
+ toggleBtn.textContent = "⏹ Deactivate Bot";
376
+ toggleBtn.classList.add("active");
377
+ } else {
378
+ botDot.className = "bot-dot";
379
+ botStatus.textContent = "Bot: OFF";
380
+ botStatus.style.color = "#ef4444";
381
+ toggleBtn.textContent = "⚑ Activate Bot";
382
+ toggleBtn.classList.remove("active");
383
+ }
384
+
385
+ // Open positions table
386
+ renderPositions(data.positions || {});
387
+
388
+ // Trade history
389
+ renderTradeHistory(data.trade_history || []);
390
+
391
+ } catch (e) {
392
+ console.error("Portfolio error:", e);
393
+ }
394
+ }
395
+
396
+ /* ══ RENDER POSITIONS TABLE ════════════════════════════ */
397
+ function renderPositions(positions) {
398
+ const tbody = document.getElementById("positionsBody");
399
+
400
+ if (Object.keys(positions).length === 0) {
401
+ tbody.innerHTML = '<tr><td colspan="9" class="empty-msg">No open positions β€” activate the bot or trade manually</td></tr>';
402
+ return;
403
+ }
404
+
405
+ tbody.innerHTML = "";
406
+ Object.entries(positions).forEach(([ticker, pos]) => {
407
+ const pnl = pos.unrealized_pnl || 0;
408
+ const pnlPct = pos.pnl_pct || 0;
409
+ const pnlClass = pnl >= 0 ? "pnl-positive" : "pnl-negative";
410
+ const pnlSign = pnl >= 0 ? "+" : "";
411
+
412
+ const tr = document.createElement("tr");
413
+ tr.innerHTML = `
414
+ <td class="ticker-col">${ticker}</td>
415
+ <td>${pos.shares}</td>
416
+ <td>$${pos.buy_price}</td>
417
+ <td>$${pos.current_price || pos.buy_price}</td>
418
+ <td class="${pnlClass}">${pnlSign}$${formatNumber(Math.abs(pnl))}</td>
419
+ <td class="${pnlClass}">${pnlSign}${pnlPct}%</td>
420
+ <td style="color:#ef4444">$${pos.stop_loss}</td>
421
+ <td style="color:#22c55e">$${pos.take_profit}</td>
422
+ <td><button class="btn-sell-small" onclick="forceSell('${ticker}')">SELL</button></td>
423
+ `;
424
+ tbody.appendChild(tr);
425
+ });
426
+ }
427
+
428
+ /* ══ RENDER TRADE HISTORY ══════════════════════════════ */
429
+ function renderTradeHistory(trades) {
430
+ const log = document.getElementById("tradeLog");
431
+
432
+ if (trades.length === 0) {
433
+ log.innerHTML = '<div class="empty-msg">No trades yet. Activate the bot or execute a trade.</div>';
434
+ return;
435
+ }
436
+
437
+ log.innerHTML = "";
438
+ // Show most recent first
439
+ [...trades].reverse().forEach((t) => {
440
+ const profitClass = t.profit >= 0 ? "pnl-positive" : "pnl-negative";
441
+ const profitSign = t.profit >= 0 ? "+" : "";
442
+ const time = new Date(t.sell_time).toLocaleString();
443
+
444
+ const entry = document.createElement("div");
445
+ entry.className = "trade-entry";
446
+ entry.innerHTML = `
447
+ <span class="te-time">${time}</span>
448
+ <span>
449
+ <span class="te-ticker">${t.ticker}</span>
450
+ β€” ${t.shares} shares @ $${t.buy_price} β†’ $${t.sell_price}
451
+ <span style="color:#6b7280;font-size:0.7rem;"> (${t.reason})</span>
452
+ </span>
453
+ <span class="${profitClass}">${profitSign}$${formatNumber(Math.abs(t.profit))}</span>
454
+ <span class="${profitClass}">${profitSign}${t.profit_pct}%</span>
455
+ `;
456
+ log.appendChild(entry);
457
+ });
458
+ }
459
+
460
+ /* ══ ADD TO TRADE FEED ═════════════════════════════════ */
461
+ function addToFeed(message, type) {
462
+ const feed = document.getElementById("tradeFeed");
463
+ const time = new Date().toLocaleTimeString();
464
+
465
+ const item = document.createElement("div");
466
+ item.className = `feed-item ${type}`;
467
+ item.innerHTML = `<span style="color:#6b7280;font-size:0.7rem;">[${time}]</span> ${message}`;
468
+
469
+ // Add to top
470
+ feed.insertBefore(item, feed.firstChild);
471
+
472
+ // Keep only last 50 entries
473
+ while (feed.children.length > 50) {
474
+ feed.removeChild(feed.lastChild);
475
+ }
476
+ }
477
+
478
+ /* ══ TOGGLE BOT ════════════════════════════════════════ */
479
+ async function toggleBot() {
480
+ try {
481
+ const res = await fetch(`${API}/api/trade/toggle`, { method: "POST" });
482
+ const data = await res.json();
483
+
484
+ if (data.bot_active) {
485
+ addToFeed("πŸ€– <strong>Auto-trading bot ACTIVATED</strong> β€” scanning for opportunities...", "buy");
486
+ } else {
487
+ addToFeed("⏹ <strong>Auto-trading bot DEACTIVATED</strong>", "sell");
488
+ }
489
+
490
+ loadPortfolio();
491
+ } catch (e) {
492
+ console.error("Toggle error:", e);
493
+ addToFeed("❌ Failed to toggle bot", "sell");
494
+ }
495
+ }
496
+
497
+ /* ══ EXECUTE MANUAL TRADE ══════════════════════════════ */
498
+ async function executeManualTrade() {
499
+ const ticker = currentTicker || document.getElementById("tickerInput").value.trim().toUpperCase();
500
+ if (!ticker) {
501
+ alert("Enter a ticker first!");
502
+ return;
503
+ }
504
+
505
+ addToFeed(`πŸ”„ Analyzing <strong>${ticker}</strong> β€” running LSTM prediction...`, "hold");
506
+
507
+ try {
508
+ const res = await fetch(`${API}/api/trade/execute/${ticker}`, { method: "POST" });
509
+ const data = await res.json();
510
+
511
+ const action = data.action;
512
+ const price = data.current_price;
513
+
514
+ if (action === "BUY") {
515
+ const tr = data.trade_result;
516
+ addToFeed(
517
+ `🟒 <strong>BOUGHT ${tr.shares} x ${ticker}</strong> @ $${price} | ` +
518
+ `SL: $${tr.stop_loss} | TP: $${tr.take_profit} | Cost: $${tr.cost}`,
519
+ "buy"
520
+ );
521
+ } else if (action === "SELL") {
522
+ const tr = data.trade_result;
523
+ const profitSign = tr.profit >= 0 ? "+" : "";
524
+ addToFeed(
525
+ `πŸ”΄ <strong>SOLD ${ticker}</strong> @ $${price} | ` +
526
+ `P&L: ${profitSign}$${tr.profit} (${profitSign}${tr.profit_pct}%) | Reason: ${tr.reason}`,
527
+ "sell"
528
+ );
529
+ } else if (action === "HOLD") {
530
+ addToFeed(
531
+ `🟑 <strong>HOLD ${ticker}</strong> @ $${price} β€” position within thresholds ` +
532
+ `(P&L: ${data.position.current_pnl}%)`,
533
+ "hold"
534
+ );
535
+ } else {
536
+ addToFeed(
537
+ `βšͺ <strong>WAIT on ${ticker}</strong> @ $${price} β€” ${data.reason || "conditions not met for entry"} ` +
538
+ `(Pred: ${data.pred_direction} ${data.pred_change_pct}%, Conf: ${data.confidence}%)`,
539
+ "wait"
540
+ );
541
+ }
542
+
543
+ loadPortfolio();
544
+ } catch (e) {
545
+ console.error("Trade error:", e);
546
+ addToFeed(`❌ Trade execution failed for ${ticker}: ${e.message}`, "sell");
547
+ }
548
+ }
549
+
550
+ /* ══ AUTO SCAN & TRADE ═════════════════════════════════ */
551
+ async function runAutoScan() {
552
+ addToFeed("πŸ” <strong>Auto-scan started</strong> β€” scanning 8 stocks with LSTM...", "hold");
553
+
554
+ try {
555
+ const res = await fetch(`${API}/api/trade/auto-scan`, { method: "POST" });
556
+ const data = await res.json();
557
+
558
+ if (data.status === "inactive") {
559
+ addToFeed("⚠️ Bot is OFF β€” activate it first before scanning", "wait");
560
+ return;
561
+ }
562
+
563
+ addToFeed(`βœ… <strong>Scan complete</strong> β€” analyzed ${data.scanned} stocks`, "hold");
564
+
565
+ // Log each result
566
+ (data.results || []).forEach((r) => {
567
+ const action = r.action;
568
+ const ticker = r.ticker;
569
+
570
+ if (action === "BUY" && r.trade_result) {
571
+ const tr = r.trade_result;
572
+ if (tr.status === "bought") {
573
+ addToFeed(
574
+ `🟒 <strong>AUTO-BUY ${tr.shares} x ${ticker}</strong> @ $${tr.price} | ` +
575
+ `SL: $${tr.stop_loss} | TP: $${tr.take_profit}`,
576
+ "buy"
577
+ );
578
+ } else {
579
+ addToFeed(`βšͺ ${ticker}: ${tr.reason || "skipped"}`, "wait");
580
+ }
581
+ } else if (action === "SELL" && r.trade_result) {
582
+ const tr = r.trade_result || r.result;
583
+ const profitSign = tr.profit >= 0 ? "+" : "";
584
+ addToFeed(
585
+ `πŸ”΄ <strong>AUTO-SELL ${ticker}</strong> | P&L: ${profitSign}$${tr.profit} | ${tr.reason}`,
586
+ "sell"
587
+ );
588
+ } else if (action === "WAIT") {
589
+ addToFeed(
590
+ `βšͺ ${ticker}: WAIT (Pred: ${r.pred_direction} ${r.pred_change_pct}%, Conf: ${r.confidence}%)`,
591
+ "wait"
592
+ );
593
+ }
594
+ });
595
+
596
+ loadPortfolio();
597
+ } catch (e) {
598
+ console.error("Scan error:", e);
599
+ addToFeed(`❌ Auto-scan failed: ${e.message}`, "sell");
600
+ }
601
+ }
602
+
603
+ /* ══ FORCE SELL ════════════════════════════════════════ */
604
+ async function forceSell(ticker) {
605
+ if (!confirm(`Force sell all ${ticker} shares at market price?`)) return;
606
+
607
+ addToFeed(`πŸ”„ Force-selling <strong>${ticker}</strong>...`, "hold");
608
+
609
+ try {
610
+ const res = await fetch(`${API}/api/trade/sell/${ticker}`, { method: "POST" });
611
+ const data = await res.json();
612
+
613
+ if (data.status === "sold") {
614
+ const profitSign = data.profit >= 0 ? "+" : "";
615
+ addToFeed(
616
+ `πŸ”΄ <strong>FORCE-SOLD ${ticker}</strong> @ $${data.price} | ` +
617
+ `P&L: ${profitSign}$${data.profit} (${profitSign}${data.profit_pct}%)`,
618
+ "sell"
619
+ );
620
+ } else {
621
+ addToFeed(`⚠️ ${ticker}: ${data.reason}`, "wait");
622
+ }
623
+
624
+ loadPortfolio();
625
+ } catch (e) {
626
+ console.error("Force sell error:", e);
627
+ addToFeed(`❌ Force sell failed: ${e.message}`, "sell");
628
+ }
629
+ }
630
+
631
+ /* ══ RESET PORTFOLIO ═══════════════════════════════════ */
632
+ async function resetPortfolio() {
633
+ if (!confirm("Reset portfolio to $100,000? All positions and history will be lost.")) return;
634
+
635
+ try {
636
+ await fetch(`${API}/api/trade/reset`, { method: "POST" });
637
+ addToFeed("πŸ”„ <strong>Portfolio reset</strong> to $100,000.00", "hold");
638
+ loadPortfolio();
639
+ } catch (e) {
640
+ console.error("Reset error:", e);
641
+ }
642
+ }
643
+
644
+ /* ══ HELPERS ═══════════════════════════════════════════ */
645
+ function formatPrice(p) {
646
+ if (!p) return "β€”";
647
+ return parseFloat(p).toLocaleString("en-US", { minimumFractionDigits: 2, maximumFractionDigits: 2 });
648
+ }
649
+
650
+ function formatVolume(v) {
651
+ if (!v) return "β€”";
652
+ if (v >= 1e9) return (v / 1e9).toFixed(2) + "B";
653
+ if (v >= 1e6) return (v / 1e6).toFixed(2) + "M";
654
+ if (v >= 1e3) return (v / 1e3).toFixed(1) + "K";
655
+ return v.toString();
656
+ }
657
+
658
+ function formatNumber(n) {
659
+ return parseFloat(n).toLocaleString("en-US", { minimumFractionDigits: 2, maximumFractionDigits: 2 });
660
+ }
app.py ADDED
@@ -0,0 +1,352 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ """
2
+ StockSense AI β€” FastAPI Backend (v3.0)
3
+ Includes: Stock Data, Prediction, Sentiment, Charts, High Potential, AUTO TRADING
4
+ """
5
+
6
+ from fastapi import FastAPI, HTTPException, Query
7
+ from fastapi.middleware.cors import CORSMiddleware
8
+ from stock_data import fetch_stock_data, add_technical_indicators, get_stock_info, fetch_live_price, fetch_chart_data
9
+ from sentiment import analyze_sentiment
10
+ from model import train_and_predict
11
+ from trader import (
12
+ get_portfolio, reset_portfolio, toggle_bot,
13
+ evaluate_trade_signal, execute_sell, check_position,
14
+ )
15
+ import concurrent.futures
16
+
17
+ app = FastAPI(title="StockSense AI", version="3.0.0")
18
+
19
+ app.add_middleware(
20
+ CORSMiddleware,
21
+ allow_origins=["*"],
22
+ allow_methods=["*"],
23
+ allow_headers=["*"],
24
+ )
25
+
26
+
27
+ @app.get("/")
28
+ def root():
29
+ return {"message": "StockSense AI API v3.0 is running πŸš€"}
30
+
31
+
32
+ # ══ STOCK DATA ═══════════════════════════════════════
33
+ @app.get("/api/stock/{ticker}")
34
+ def get_stock(ticker: str):
35
+ try:
36
+ df = fetch_stock_data(ticker)
37
+ df = add_technical_indicators(df)
38
+ records = df.tail(200).to_dict(orient="records")
39
+ for r in records:
40
+ if "Date" in r:
41
+ r["Date"] = str(r["Date"])
42
+ info = get_stock_info(ticker)
43
+ return {"info": info, "data": records}
44
+ except Exception as e:
45
+ raise HTTPException(status_code=400, detail=str(e))
46
+
47
+
48
+ @app.get("/api/live/{ticker}")
49
+ def live_price(ticker: str):
50
+ try:
51
+ return fetch_live_price(ticker)
52
+ except Exception as e:
53
+ raise HTTPException(status_code=400, detail=str(e))
54
+
55
+
56
+ @app.get("/api/chart/{ticker}")
57
+ def chart_data(ticker: str, timeframe: str = Query("1mo", regex="^(1d|5d|1wk|1mo|3mo|6mo|1y|2y)$")):
58
+ try:
59
+ data = fetch_chart_data(ticker, timeframe)
60
+ return {"ticker": ticker, "timeframe": timeframe, "data": data}
61
+ except Exception as e:
62
+ raise HTTPException(status_code=400, detail=str(e))
63
+
64
+
65
+ # ══ ML PREDICTION ════════════════════════════════════
66
+ # In app.py / predict endpoint
67
+ @app.get("/api/predict/{ticker}")
68
+ def predict(ticker: str):
69
+ try:
70
+ df = fetch_stock_data(ticker)
71
+ df = add_technical_indicators(df)
72
+ result = train_and_predict(df)
73
+ return {"ticker": ticker, **result}
74
+ except Exception as e:
75
+ raise HTTPException(status_code=400, detail=str(e))
76
+
77
+
78
+ # ══ SENTIMENT ════════════════════════════════════════
79
+ @app.get("/api/sentiment/{ticker}")
80
+ def sentiment(ticker: str):
81
+ try:
82
+ return analyze_sentiment(ticker)
83
+ except Exception as e:
84
+ raise HTTPException(status_code=400, detail=str(e))
85
+
86
+
87
+ # ══ COMBINED SUMMARY ═════════════════════════════════
88
+ @app.get("/api/summary/{ticker}")
89
+ def summary(ticker: str):
90
+ try:
91
+ info = get_stock_info(ticker)
92
+ df = fetch_stock_data(ticker)
93
+ df_ind = add_technical_indicators(df)
94
+ prediction = train_and_predict(df_ind)
95
+ sent = analyze_sentiment(ticker)
96
+
97
+ latest = df_ind.iloc[-1]
98
+ indicators = {
99
+ "RSI": round(float(latest["RSI"]), 2),
100
+ "MACD": round(float(latest["MACD"]), 4),
101
+ "MACD_Signal": round(float(latest["MACD_Signal"]), 4),
102
+ "SMA_20": round(float(latest["SMA_20"]), 2),
103
+ "SMA_50": round(float(latest["SMA_50"]), 2),
104
+ }
105
+
106
+ return {
107
+ "info": info,
108
+ "indicators": indicators,
109
+ "prediction": prediction,
110
+ "sentiment": sent,
111
+ }
112
+ except Exception as e:
113
+ raise HTTPException(status_code=400, detail=str(e))
114
+
115
+
116
+ # ══ HIGH POTENTIAL SCANNER ═══════════════════════════
117
+ SCAN_TICKERS = [
118
+ "AAPL", "TSLA", "MSFT", "GOOGL", "AMZN", "NVDA", "META",
119
+ "NFLX", "AMD", "JPM", "V", "BA", "DIS", "PYPL", "INTC",
120
+ ]
121
+
122
+
123
+ def _analyze_one(ticker: str) -> dict | None:
124
+ try:
125
+ info = get_stock_info(ticker)
126
+ df = fetch_stock_data(ticker, period="3mo")
127
+ df = add_technical_indicators(df)
128
+ latest = df.iloc[-1]
129
+
130
+ rsi = float(latest["RSI"])
131
+ macd = float(latest["MACD"])
132
+ macd_signal = float(latest["MACD_Signal"])
133
+ sma_20 = float(latest["SMA_20"])
134
+ price = float(latest["Close"])
135
+
136
+ score = 50
137
+ if rsi < 30: score += 20
138
+ elif rsi < 40: score += 10
139
+ elif rsi > 70: score -= 15
140
+ elif rsi > 60: score -= 5
141
+
142
+ if macd > macd_signal: score += 15
143
+ else: score -= 10
144
+
145
+ if price > sma_20: score += 10
146
+ else: score -= 10
147
+
148
+ vol = float(latest["Volume"])
149
+ vol_avg = float(latest["Volume_SMA_20"])
150
+ if vol_avg > 0 and vol > vol_avg * 1.3: score += 10
151
+
152
+ score = max(0, min(100, score))
153
+
154
+ if score >= 70: signal_text = "🟒 Strong Buy"
155
+ elif score >= 55: signal_text = "πŸ”΅ Buy"
156
+ elif score >= 40: signal_text = "🟑 Hold"
157
+ else: signal_text = "πŸ”΄ Sell"
158
+
159
+ prev_close = float(df.iloc[-2]["Close"])
160
+ change_pct = round(((price - prev_close) / prev_close) * 100, 2)
161
+
162
+ return {
163
+ "ticker": ticker, "name": info.get("name", ticker),
164
+ "price": round(price, 2), "change_pct": change_pct,
165
+ "rsi": round(rsi, 2), "score": score,
166
+ "signal": signal_text, "currency": info.get("currency", "USD"),
167
+ }
168
+ except Exception:
169
+ return None
170
+
171
+
172
+ @app.get("/api/high-potential")
173
+ def high_potential():
174
+ results = []
175
+ with concurrent.futures.ThreadPoolExecutor(max_workers=5) as executor:
176
+ futures = {executor.submit(_analyze_one, t): t for t in SCAN_TICKERS}
177
+ for future in concurrent.futures.as_completed(futures):
178
+ result = future.result()
179
+ if result:
180
+ results.append(result)
181
+ results.sort(key=lambda x: x["score"], reverse=True)
182
+ return {"stocks": results, "count": len(results)}
183
+
184
+
185
+ # ══ AUTO TRADING ENDPOINTS ═══════════════════════════
186
+
187
+ @app.get("/api/trade/portfolio")
188
+ def trade_portfolio():
189
+ """Get current portfolio state."""
190
+ try:
191
+ portfolio = get_portfolio()
192
+ # Calculate live P&L for open positions
193
+ total_unrealized = 0
194
+ for ticker, pos in portfolio["positions"].items():
195
+ try:
196
+ live = fetch_live_price(ticker)
197
+ current = live["price"]
198
+ pnl = (current - pos["buy_price"]) * pos["shares"]
199
+ pos["current_price"] = current
200
+ pos["unrealized_pnl"] = round(pnl, 2)
201
+ pos["pnl_pct"] = round(((current - pos["buy_price"]) / pos["buy_price"]) * 100, 2)
202
+ total_unrealized += pnl
203
+ except Exception:
204
+ pos["current_price"] = pos["buy_price"]
205
+ pos["unrealized_pnl"] = 0
206
+ pos["pnl_pct"] = 0
207
+
208
+ portfolio["total_unrealized_pnl"] = round(total_unrealized, 2)
209
+ portfolio["total_value"] = round(portfolio["balance"] + total_unrealized + sum(
210
+ p["shares"] * p.get("current_price", p["buy_price"]) for p in portfolio["positions"].values()
211
+ ), 2)
212
+
213
+ # Calculate total realized P&L
214
+ portfolio["total_realized_pnl"] = round(
215
+ sum(t["profit"] for t in portfolio["trade_history"]), 2
216
+ )
217
+ portfolio["total_trades"] = len(portfolio["trade_history"])
218
+ portfolio["winning_trades"] = sum(1 for t in portfolio["trade_history"] if t["profit"] > 0)
219
+ portfolio["losing_trades"] = sum(1 for t in portfolio["trade_history"] if t["profit"] <= 0)
220
+
221
+ if portfolio["total_trades"] > 0:
222
+ portfolio["win_rate"] = round(
223
+ (portfolio["winning_trades"] / portfolio["total_trades"]) * 100, 1
224
+ )
225
+ else:
226
+ portfolio["win_rate"] = 0
227
+
228
+ return portfolio
229
+ except Exception as e:
230
+ raise HTTPException(status_code=400, detail=str(e))
231
+
232
+
233
+ @app.post("/api/trade/reset")
234
+ def trade_reset():
235
+ """Reset portfolio to $100,000."""
236
+ return reset_portfolio()
237
+
238
+
239
+ @app.post("/api/trade/toggle")
240
+ def trade_toggle():
241
+ """Toggle auto-trading bot ON/OFF."""
242
+ return toggle_bot()
243
+
244
+
245
+ @app.post("/api/trade/execute/{ticker}")
246
+ def trade_execute(ticker: str):
247
+ """
248
+ Run the LSTM prediction for a ticker and auto-execute
249
+ the trade signal (BUY/SELL/HOLD/WAIT).
250
+ """
251
+ try:
252
+ # Get current price
253
+ live = fetch_live_price(ticker)
254
+ current_price = live["price"]
255
+
256
+ # Get LSTM prediction
257
+ df = fetch_stock_data(ticker)
258
+ df = add_technical_indicators(df)
259
+ prediction = train_and_predict(df)
260
+
261
+ # Evaluate and execute trade signal
262
+ signal = evaluate_trade_signal(
263
+ ticker=ticker,
264
+ current_price=current_price,
265
+ predicted_prices=prediction["predicted_prices"],
266
+ confidence=prediction["confidence"],
267
+ )
268
+
269
+ signal["live"] = live
270
+ signal["prediction_details"] = prediction
271
+ return signal
272
+
273
+ except Exception as e:
274
+ raise HTTPException(status_code=400, detail=str(e))
275
+
276
+
277
+ @app.post("/api/trade/sell/{ticker}")
278
+ def trade_force_sell(ticker: str):
279
+ """Force-sell a position at current market price."""
280
+ try:
281
+ live = fetch_live_price(ticker)
282
+ result = execute_sell(ticker, live["price"], "Manual sell (forced)")
283
+ return result
284
+ except Exception as e:
285
+ raise HTTPException(status_code=400, detail=str(e))
286
+
287
+
288
+ @app.get("/api/trade/check/{ticker}")
289
+ def trade_check(ticker: str):
290
+ """Check if a position should be sold (stop-loss / take-profit)."""
291
+ try:
292
+ live = fetch_live_price(ticker)
293
+ result = check_position(ticker, live["price"])
294
+ result["live"] = live
295
+ return result
296
+ except Exception as e:
297
+ raise HTTPException(status_code=400, detail=str(e))
298
+
299
+
300
+ @app.post("/api/trade/auto-scan")
301
+ def trade_auto_scan():
302
+ """
303
+ Scan all high-potential stocks, run predictions,
304
+ and auto-execute trades for the best signals.
305
+ Only works when bot is active.
306
+ """
307
+ try:
308
+ portfolio = get_portfolio()
309
+ if not portfolio["bot_active"]:
310
+ return {"status": "inactive", "message": "Bot is OFF. Toggle it on first."}
311
+
312
+ results = []
313
+
314
+ # First: check existing positions for stop-loss / take-profit
315
+ for ticker in list(portfolio["positions"].keys()):
316
+ try:
317
+ live = fetch_live_price(ticker)
318
+ check = check_position(ticker, live["price"])
319
+ if check["action"] == "sell":
320
+ sell_result = execute_sell(ticker, live["price"], check["reason"])
321
+ results.append({"ticker": ticker, "action": "SELL", "result": sell_result})
322
+ except Exception:
323
+ continue
324
+
325
+ # Then: scan for new buy opportunities
326
+ for scan_ticker in SCAN_TICKERS[:8]: # Limit to top 8 for speed
327
+ if scan_ticker in portfolio["positions"]:
328
+ continue
329
+ try:
330
+ live = fetch_live_price(scan_ticker)
331
+ df = fetch_stock_data(scan_ticker)
332
+ df = add_technical_indicators(df)
333
+ pred = train_and_predict(df, epochs=30) # fewer epochs for speed
334
+
335
+ signal = evaluate_trade_signal(
336
+ ticker=scan_ticker,
337
+ current_price=live["price"],
338
+ predicted_prices=pred["predicted_prices"],
339
+ confidence=pred["confidence"],
340
+ )
341
+ results.append(signal)
342
+ except Exception:
343
+ continue
344
+
345
+ return {
346
+ "status": "completed",
347
+ "scanned": len(results),
348
+ "results": results,
349
+ "portfolio": get_portfolio(),
350
+ }
351
+ except Exception as e:
352
+ raise HTTPException(status_code=400, detail=str(e))
index.html ADDED
@@ -0,0 +1,205 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ <!DOCTYPE html>
2
+ <html lang="en">
3
+ <head>
4
+ <meta charset="UTF-8" />
5
+ <meta name="viewport" content="width=device-width, initial-scale=1.0" />
6
+ <title>StockSense AI β€” Live Trading Dashboard</title>
7
+ <link rel="stylesheet" href="style.css" />
8
+ <script src="https://cdn.jsdelivr.net/npm/chart.js@4.4.0"></script>
9
+ </head>
10
+ <body>
11
+
12
+ <!-- ══ TOP BAR ══════════════════════════════════════ -->
13
+ <nav class="topbar">
14
+ <div class="brand">πŸ“ˆ <span>StockSense AI</span></div>
15
+ <div class="search-area">
16
+ <input id="tickerInput" type="text" placeholder="Search ticker… (AAPL, TSLA, NVDA)" spellcheck="false" />
17
+ <button id="analyzeBtn" onclick="loadTicker()">Analyze</button>
18
+ </div>
19
+ <div class="nav-tabs">
20
+ <button class="nav-tab active" onclick="switchTab('charts')">πŸ“Š Charts</button>
21
+ <button class="nav-tab" onclick="switchTab('trading')">πŸ€– Auto Trade</button>
22
+ </div>
23
+ <div class="live-badge" id="liveBadge">
24
+ <span class="dot"></span> LIVE
25
+ </div>
26
+ </nav>
27
+
28
+ <!-- ══ LIVE PRICE BANNER ════════════════════════════ -->
29
+ <section class="price-banner hidden" id="priceBanner">
30
+ <div class="price-main">
31
+ <h1 id="bannerName">β€”</h1>
32
+ <span class="price-value" id="bannerPrice">0.00</span>
33
+ <span class="price-change" id="bannerChange">0.00 (0.00%)</span>
34
+ </div>
35
+ <div class="price-stats">
36
+ <div><label>Open</label><span id="statOpen">β€”</span></div>
37
+ <div><label>High</label><span id="statHigh">β€”</span></div>
38
+ <div><label>Low</label><span id="statLow">β€”</span></div>
39
+ <div><label>Vol</label><span id="statVol">β€”</span></div>
40
+ <div><label>52W H</label><span id="stat52H">β€”</span></div>
41
+ <div><label>52W L</label><span id="stat52L">β€”</span></div>
42
+ </div>
43
+ </section>
44
+
45
+ <!-- ══ TAB: CHARTS ══════════════════════════════════ -->
46
+ <div id="chartsTab" class="tab-content">
47
+ <div class="dashboard">
48
+ <div class="chart-area">
49
+ <div class="timeframe-bar">
50
+ <button class="tf-btn active" data-tf="1d">1D</button>
51
+ <button class="tf-btn" data-tf="5d">5D</button>
52
+ <button class="tf-btn" data-tf="1mo">1M</button>
53
+ <button class="tf-btn" data-tf="3mo">3M</button>
54
+ <button class="tf-btn" data-tf="1y">1Y</button>
55
+ <button class="tf-btn" data-tf="2y">2Y</button>
56
+ </div>
57
+ <div class="chart-container"><canvas id="mainChart"></canvas></div>
58
+ <div class="chart-container volume-chart"><canvas id="volumeChart"></canvas></div>
59
+
60
+ <div class="prediction-section hidden" id="predSection">
61
+ <h3>πŸ€– Next 5-Day Price Prediction</h3>
62
+ <div class="chart-container"><canvas id="predChart"></canvas></div>
63
+ <div class="pred-metrics">
64
+ <div class="metric-card">
65
+ <span class="m-label">Confidence</span>
66
+ <span class="m-value" id="predConf">β€”</span>
67
+ </div>
68
+ <div class="metric-card">
69
+ <span class="m-label">Risk Level</span>
70
+ <span class="m-value" id="predRisk">β€”</span>
71
+ </div>
72
+ <div class="metric-card">
73
+ <span class="m-label">Pred Day 1</span>
74
+ <span class="m-value" id="predDay1">β€”</span>
75
+ </div>
76
+ <div class="metric-card">
77
+ <span class="m-label">Pred Day 5</span>
78
+ <span class="m-value" id="predDay5">β€”</span>
79
+ </div>
80
+ </div>
81
+ </div>
82
+ </div>
83
+
84
+ <aside class="sidebar">
85
+ <div class="panel">
86
+ <h3>πŸ”₯ High Potential Stocks</h3>
87
+ <p class="panel-sub">Ranked by momentum + indicators</p>
88
+ <div id="hpLoader" class="mini-loader">Loading scanner...</div>
89
+ <div id="hpList" class="hp-list"></div>
90
+ </div>
91
+ <div class="panel hidden" id="sentPanel">
92
+ <h3>πŸ“° News Sentiment</h3>
93
+ <div class="sent-gauge">
94
+ <div class="gauge-circle" id="gaugeCircle"><span id="gaugeText">β€”</span></div>
95
+ <span class="gauge-label" id="gaugeLabel">Neutral</span>
96
+ </div>
97
+ <ul id="sentList" class="sent-list"></ul>
98
+ </div>
99
+ <div class="panel hidden" id="indPanel">
100
+ <h3>πŸ“Š Technical Indicators</h3>
101
+ <table class="ind-table"><tbody id="indBody"></tbody></table>
102
+ </div>
103
+ </aside>
104
+ </div>
105
+ </div>
106
+
107
+ <!-- ══ TAB: AUTO TRADING ════════════════════════════ -->
108
+ <div id="tradingTab" class="tab-content hidden">
109
+ <div class="trading-dashboard">
110
+
111
+ <!-- Portfolio Overview -->
112
+ <div class="trade-grid">
113
+ <div class="portfolio-header">
114
+ <div class="port-card balance">
115
+ <span class="pc-label">Portfolio Value</span>
116
+ <span class="pc-value" id="portValue">$100,000.00</span>
117
+ </div>
118
+ <div class="port-card">
119
+ <span class="pc-label">Cash Balance</span>
120
+ <span class="pc-value" id="portBalance">$100,000.00</span>
121
+ </div>
122
+ <div class="port-card">
123
+ <span class="pc-label">Unrealized P&L</span>
124
+ <span class="pc-value" id="portUnrealized">$0.00</span>
125
+ </div>
126
+ <div class="port-card">
127
+ <span class="pc-label">Realized P&L</span>
128
+ <span class="pc-value" id="portRealized">$0.00</span>
129
+ </div>
130
+ <div class="port-card">
131
+ <span class="pc-label">Win Rate</span>
132
+ <span class="pc-value" id="portWinRate">0%</span>
133
+ </div>
134
+ <div class="port-card">
135
+ <span class="pc-label">Total Trades</span>
136
+ <span class="pc-value" id="portTrades">0</span>
137
+ </div>
138
+ </div>
139
+
140
+ <!-- Bot Controls -->
141
+ <div class="bot-controls">
142
+ <div class="bot-status">
143
+ <span class="bot-dot" id="botDot"></span>
144
+ <span id="botStatus">Bot: OFF</span>
145
+ </div>
146
+ <div class="bot-buttons">
147
+ <button class="btn-bot" id="toggleBotBtn" onclick="toggleBot()">⚑ Activate Bot</button>
148
+ <button class="btn-scan" onclick="runAutoScan()">πŸ” Auto Scan & Trade</button>
149
+ <button class="btn-trade" onclick="executeManualTrade()">πŸ“ˆ Trade Current Ticker</button>
150
+ <button class="btn-reset" onclick="resetPortfolio()">πŸ”„ Reset Portfolio</button>
151
+ </div>
152
+ </div>
153
+
154
+ <!-- Open Positions -->
155
+ <div class="trade-panel">
156
+ <h3>πŸ“‚ Open Positions</h3>
157
+ <div class="positions-table-wrap">
158
+ <table class="positions-table">
159
+ <thead>
160
+ <tr>
161
+ <th>Ticker</th>
162
+ <th>Shares</th>
163
+ <th>Buy Price</th>
164
+ <th>Current</th>
165
+ <th>P&L</th>
166
+ <th>P&L %</th>
167
+ <th>Stop Loss</th>
168
+ <th>Take Profit</th>
169
+ <th>Action</th>
170
+ </tr>
171
+ </thead>
172
+ <tbody id="positionsBody">
173
+ <tr><td colspan="9" class="empty-msg">No open positions</td></tr>
174
+ </tbody>
175
+ </table>
176
+ </div>
177
+ </div>
178
+
179
+ <!-- Trade Log -->
180
+ <div class="trade-panel">
181
+ <h3>πŸ“‹ Trade History</h3>
182
+ <div class="trade-log" id="tradeLog">
183
+ <div class="empty-msg">No trades yet. Activate the bot or execute a trade.</div>
184
+ </div>
185
+ </div>
186
+
187
+ <!-- Live Trade Feed -->
188
+ <div class="trade-panel">
189
+ <h3>⚑ Live Trade Feed</h3>
190
+ <div class="trade-feed" id="tradeFeed"></div>
191
+ </div>
192
+
193
+ </div>
194
+ </div>
195
+ </div>
196
+
197
+ <!-- ══ DISCLAIMER FOOTER ════════════════════════════ -->
198
+ <footer>
199
+ <p>⚠️ <strong>PAPER TRADING ONLY</strong> β€” Simulated portfolio with fake money. Not real trades.</p>
200
+ <p>For <strong>educational purposes only</strong>. Not financial advice. | StockSense AI β€” Hackathon 2026</p>
201
+ </footer>
202
+
203
+ <script src="app.js"></script>
204
+ </body>
205
+ </html>
model.py ADDED
@@ -0,0 +1,211 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ """
2
+ LSTM-based stock price predictor (v2.0).
3
+ Multi-feature model using Close + technical indicators.
4
+ Trains with mini-batches, LR scheduling, gradient clipping, and early stopping.
5
+ """
6
+
7
+ import numpy as np
8
+ import pandas as pd
9
+ import torch
10
+ import torch.nn as nn
11
+ from torch.utils.data import DataLoader, TensorDataset
12
+ from sklearn.preprocessing import MinMaxScaler
13
+
14
+
15
+ # ── Feature columns used by the model ─────────────────────────
16
+ FEATURE_COLS = ["Close", "SMA_20", "EMA_20", "RSI", "MACD", "Volume"]
17
+ LOOK_BACK = 60 # 60 trading days as input window
18
+ PREDICT_DAYS = 5
19
+
20
+
21
+ # ── LSTM Architecture ─────────────────────────────────────────
22
+ class StockLSTM(nn.Module):
23
+ def __init__(self, input_size: int = 6, hidden_size: int = 128,
24
+ num_layers: int = 3, output_size: int = 5, dropout: float = 0.3):
25
+ super().__init__()
26
+ self.hidden_size = hidden_size
27
+ self.num_layers = num_layers
28
+
29
+ self.lstm = nn.LSTM(
30
+ input_size, hidden_size, num_layers,
31
+ batch_first=True, dropout=dropout if num_layers > 1 else 0.0,
32
+ )
33
+
34
+ # Deeper head: hidden β†’ hidden/2 β†’ output
35
+ self.head = nn.Sequential(
36
+ nn.Linear(hidden_size, hidden_size // 2),
37
+ nn.ReLU(),
38
+ nn.Dropout(dropout),
39
+ nn.Linear(hidden_size // 2, output_size),
40
+ )
41
+
42
+ def forward(self, x):
43
+ h0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size, device=x.device)
44
+ c0 = torch.zeros(self.num_layers, x.size(0), self.hidden_size, device=x.device)
45
+ out, _ = self.lstm(x, (h0, c0))
46
+ out = self.head(out[:, -1, :]) # last time-step
47
+ return out
48
+
49
+
50
+ # ── Data helpers ──────────────────────────────────────────────
51
+ def _prepare_features(df: pd.DataFrame):
52
+ """
53
+ Extract feature matrix and target vector from a DataFrame
54
+ that already contains technical indicators.
55
+ """
56
+ # Ensure required columns exist; fall back to Close-only if not
57
+ available = [c for c in FEATURE_COLS if c in df.columns]
58
+ if len(available) < 2:
59
+ available = ["Close"]
60
+
61
+ features = df[available].values.astype(np.float32)
62
+ close = df["Close"].values.astype(np.float32)
63
+ return features, close, len(available)
64
+
65
+
66
+ def _prepare_data(features: np.ndarray, close_col_idx: int = 0):
67
+ """
68
+ Scale features, build sliding-window X/y arrays.
69
+ Returns X, y, scaler, and the split index so the scaler is fit
70
+ ONLY on training data (no data leakage).
71
+ """
72
+ n_samples = len(features)
73
+ split = int(n_samples * 0.85)
74
+
75
+ # Fit scaler on training portion ONLY
76
+ scaler = MinMaxScaler()
77
+ scaler.fit(features[:split])
78
+
79
+ scaled = scaler.transform(features)
80
+
81
+ X, y = [], []
82
+ # y targets are next-5-day Close prices (column 0 after scaling)
83
+ for i in range(LOOK_BACK, len(scaled) - PREDICT_DAYS):
84
+ X.append(scaled[i - LOOK_BACK:i]) # shape (LOOK_BACK, n_features)
85
+ y.append(scaled[i:i + PREDICT_DAYS, close_col_idx]) # shape (PREDICT_DAYS,)
86
+
87
+ X = np.array(X, dtype=np.float32)
88
+ y = np.array(y, dtype=np.float32)
89
+
90
+ # Adjust split index for the windowed arrays
91
+ adj_split = split - LOOK_BACK
92
+ adj_split = max(1, min(adj_split, len(X) - 1))
93
+
94
+ return X, y, scaler, adj_split
95
+
96
+
97
+ # ── Train + Predict pipeline ─────────────────────────────────
98
+ def train_and_predict(
99
+ df: pd.DataFrame,
100
+ epochs: int = 100,
101
+ lr: float = 0.001,
102
+ batch_size: int = 32,
103
+ patience: int = 10,
104
+ ):
105
+ """
106
+ Train an LSTM on multi-feature data and return the next 5 predicted
107
+ prices, a confidence score, and risk level.
108
+ """
109
+ features, close, n_features = _prepare_features(df)
110
+ X, y, scaler, split = _prepare_data(features)
111
+
112
+ X_train, y_train = X[:split], y[:split]
113
+ X_test, y_test = X[split:], y[split:]
114
+
115
+ # Torch tensors
116
+ X_train_t = torch.tensor(X_train)
117
+ y_train_t = torch.tensor(y_train)
118
+ X_test_t = torch.tensor(X_test)
119
+ y_test_t = torch.tensor(y_test)
120
+
121
+ # Mini-batch DataLoader
122
+ train_ds = TensorDataset(X_train_t, y_train_t)
123
+ train_loader = DataLoader(train_ds, batch_size=batch_size, shuffle=True)
124
+
125
+ model = StockLSTM(
126
+ input_size=n_features,
127
+ hidden_size=128,
128
+ num_layers=3,
129
+ output_size=PREDICT_DAYS,
130
+ )
131
+ criterion = nn.MSELoss()
132
+ optimizer = torch.optim.Adam(model.parameters(), lr=lr, weight_decay=1e-5)
133
+ scheduler = torch.optim.lr_scheduler.ReduceLROnPlateau(
134
+ optimizer, mode="min", factor=0.5, patience=5, min_lr=1e-6,
135
+ )
136
+
137
+ # ── Training loop with early stopping ──
138
+ best_val_loss = float("inf")
139
+ epochs_no_improve = 0
140
+
141
+ for epoch in range(epochs):
142
+ model.train()
143
+ for xb, yb in train_loader:
144
+ optimizer.zero_grad()
145
+ preds = model(xb)
146
+ loss = criterion(preds, yb)
147
+ loss.backward()
148
+ torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm=1.0)
149
+ optimizer.step()
150
+
151
+ # Validation
152
+ model.eval()
153
+ with torch.no_grad():
154
+ val_preds = model(X_test_t)
155
+ val_loss = float(criterion(val_preds, y_test_t))
156
+
157
+ scheduler.step(val_loss)
158
+
159
+ # Early stopping
160
+ if val_loss < best_val_loss:
161
+ best_val_loss = val_loss
162
+ epochs_no_improve = 0
163
+ best_state = {k: v.clone() for k, v in model.state_dict().items()}
164
+ else:
165
+ epochs_no_improve += 1
166
+ if epochs_no_improve >= patience:
167
+ break
168
+
169
+ # Restore best model
170
+ if best_val_loss < float("inf"):
171
+ model.load_state_dict(best_state)
172
+
173
+ # ── Final test evaluation ──
174
+ model.eval()
175
+ with torch.no_grad():
176
+ test_preds = model(X_test_t).numpy()
177
+ test_loss = float(criterion(torch.tensor(test_preds), y_test_t))
178
+
179
+ # Confidence & risk (based on test MSE, lower is better)
180
+ confidence = max(0, min(100, round((1 - test_loss * 10) * 100, 1)))
181
+ if confidence >= 70:
182
+ risk = "Low"
183
+ elif confidence >= 45:
184
+ risk = "Medium"
185
+ else:
186
+ risk = "High"
187
+
188
+ # ── Predict next 5 days ──
189
+ last_window = features[-LOOK_BACK:]
190
+ last_scaled = scaler.transform(last_window).reshape(1, LOOK_BACK, n_features)
191
+ last_seq = torch.tensor(last_scaled, dtype=torch.float32)
192
+
193
+ with torch.no_grad():
194
+ raw_pred = model(last_seq).numpy().flatten()
195
+
196
+ # Inverse-transform: raw_pred is in scaled Close space (column 0)
197
+ # Build a dummy array with all features set to 0, then set column 0
198
+ dummy = np.zeros((len(raw_pred), n_features), dtype=np.float32)
199
+ dummy[:, 0] = raw_pred
200
+ predicted_prices = scaler.inverse_transform(dummy)[:, 0].tolist()
201
+
202
+ # Historical last 30 days for chart overlay
203
+ historical_prices = close[-30:].tolist()
204
+
205
+ return {
206
+ "predicted_prices": [round(p, 2) for p in predicted_prices],
207
+ "confidence": confidence,
208
+ "risk": risk,
209
+ "test_mse": round(test_loss, 6),
210
+ "historical_last_30": [round(float(p), 2) for p in historical_prices],
211
+ }
portfolio.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "balance": 100000.0,
3
+ "initial_balance": 100000.0,
4
+ "positions": {},
5
+ "trade_history": [],
6
+ "bot_active": true,
7
+ "created_at": "2026-02-13T02:02:57.620862"
8
+ }
sentiment.py ADDED
@@ -0,0 +1,151 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ """
2
+ News sentiment analysis using NLTK VADER + ProsusAI/FinBERT ensemble.
3
+ VADER provides fast rule-based scoring; FinBERT provides deep financial context.
4
+ The final score is a weighted blend (40% VADER, 60% FinBERT).
5
+ """
6
+
7
+ import torch
8
+ from transformers import BertTokenizer, BertForSequenceClassification
9
+ import numpy as np
10
+ import yfinance as yf
11
+ import nltk
12
+ from nltk.sentiment.vader import SentimentIntensityAnalyzer
13
+
14
+ # ── Download VADER lexicon if missing ──────────────────────────
15
+ try:
16
+ nltk.data.find("sentiment/vader_lexicon.zip")
17
+ except LookupError:
18
+ nltk.download("vader_lexicon", quiet=True)
19
+
20
+ # ── Load models once at import ─────────────────────────────────
21
+ # VADER
22
+ _vader = SentimentIntensityAnalyzer()
23
+
24
+ # FinBERT
25
+ MODEL_NAME = "ProsusAI/finbert"
26
+ _tokenizer = BertTokenizer.from_pretrained(MODEL_NAME)
27
+ _finbert = BertForSequenceClassification.from_pretrained(MODEL_NAME)
28
+ _finbert.eval()
29
+ FINBERT_LABELS = ["negative", "neutral", "positive"]
30
+
31
+ # Ensemble weights
32
+ VADER_WEIGHT = 0.4
33
+ FINBERT_WEIGHT = 0.6
34
+
35
+
36
+ # ── Individual scorers ─────────────────────────────────────────
37
+ def _score_vader(text: str) -> dict:
38
+ """VADER compound score mapped to label + confidence."""
39
+ scores = _vader.polarity_scores(text)
40
+ compound = scores["compound"]
41
+
42
+ if compound >= 0.05:
43
+ label = "positive"
44
+ elif compound <= -0.05:
45
+ label = "negative"
46
+ else:
47
+ label = "neutral"
48
+
49
+ confidence = round(abs(compound), 4)
50
+ return {"label": label, "score": round(compound, 4), "confidence": confidence}
51
+
52
+
53
+ def _score_finbert(text: str) -> dict:
54
+ """FinBERT probability-based label + confidence."""
55
+ tokens = _tokenizer(text, return_tensors="pt", padding=True,
56
+ truncation=True, max_length=128)
57
+ with torch.no_grad():
58
+ logits = _finbert(**tokens).logits
59
+ probs = torch.nn.functional.softmax(logits, dim=-1).squeeze().tolist()
60
+ idx = int(np.argmax(probs))
61
+
62
+ # Convert to a signed score: positive=+1, neutral=0, negative=βˆ’1
63
+ signed_score = probs[2] - probs[0] # positive_prob - negative_prob
64
+ return {
65
+ "label": FINBERT_LABELS[idx],
66
+ "score": round(signed_score, 4),
67
+ "confidence": round(probs[idx], 4),
68
+ }
69
+
70
+
71
+ def _score_text(text: str) -> dict:
72
+ """
73
+ Ensemble: blend VADER and FinBERT scores.
74
+ Returns per-headline detail with both individual and combined scores.
75
+ """
76
+ vader = _score_vader(text)
77
+ finbert = _score_finbert(text)
78
+
79
+ # Weighted blend of signed scores
80
+ combined_score = (VADER_WEIGHT * vader["score"]) + (FINBERT_WEIGHT * finbert["score"])
81
+
82
+ if combined_score > 0.1:
83
+ label = "positive"
84
+ elif combined_score < -0.1:
85
+ label = "negative"
86
+ else:
87
+ label = "neutral"
88
+
89
+ combined_confidence = (VADER_WEIGHT * vader["confidence"]) + (FINBERT_WEIGHT * finbert["confidence"])
90
+
91
+ return {
92
+ "text": text,
93
+ "label": label,
94
+ "confidence": round(combined_confidence, 4),
95
+ "combined_score": round(combined_score, 4),
96
+ "vader": vader,
97
+ "finbert": finbert,
98
+ }
99
+
100
+
101
+ # ── News fetcher ───────────────────────────────────────────────
102
+ def fetch_news_headlines(ticker: str, max_items: int = 10) -> list[str]:
103
+ """Fetch recent news headlines from Yahoo Finance."""
104
+ stock = yf.Ticker(ticker)
105
+ news = stock.news or []
106
+ headlines = []
107
+ for item in news[:max_items]:
108
+ # yfinance v0.2.36+ nests data under "content"
109
+ content = item.get("content", {})
110
+ title = content.get("title", "") or item.get("title", "")
111
+ if title:
112
+ headlines.append(title)
113
+ return headlines
114
+
115
+
116
+ # ── Public API ─────────────────────────────────────────────────
117
+ def analyze_sentiment(ticker: str) -> dict:
118
+ """
119
+ End-to-end: fetch headlines ➜ score each with VADER + FinBERT ➜ return aggregate.
120
+ """
121
+ headlines = fetch_news_headlines(ticker)
122
+ if not headlines:
123
+ return {
124
+ "ticker": ticker,
125
+ "articles_analyzed": 0,
126
+ "details": [],
127
+ "overall_sentiment": "neutral",
128
+ "overall_score": 0.0,
129
+ "method": "VADER (40%) + FinBERT (60%) ensemble",
130
+ }
131
+
132
+ details = [_score_text(h) for h in headlines]
133
+
134
+ # Aggregate combined scores
135
+ avg = float(np.mean([d["combined_score"] for d in details]))
136
+
137
+ if avg > 0.15:
138
+ overall = "positive"
139
+ elif avg < -0.15:
140
+ overall = "negative"
141
+ else:
142
+ overall = "neutral"
143
+
144
+ return {
145
+ "ticker": ticker,
146
+ "articles_analyzed": len(details),
147
+ "details": details,
148
+ "overall_sentiment": overall,
149
+ "overall_score": round(avg, 4),
150
+ "method": "VADER (40%) + FinBERT (60%) ensemble",
151
+ }
step4_install.sh ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ pip install --upgrade pip
2
+
3
+ pip install fastapi==0.115.0
4
+ pip install uvicorn==0.30.0
5
+ pip install yfinance==1.1.0
6
+ pip install pandas==2.2.0
7
+ pip install numpy==1.26.4
8
+ pip install scikit-learn==1.5.0
9
+ pip install transformers==4.44.0
10
+ pip install requests==2.32.0
11
+ pip install python-dateutil==2.9.0
12
+ pip install ta==0.11.0
stock_data.py ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ """
2
+ Fetches historical stock data from Yahoo Finance and computes
3
+ technical indicators: SMA, EMA, RSI, MACD, and Volume profile.
4
+ """
5
+
6
+ import yfinance as yf
7
+ import pandas as pd
8
+ import ta
9
+ from datetime import datetime
10
+
11
+
12
+ def fetch_stock_data(ticker: str, period: str = "2y", interval: str = "1d") -> pd.DataFrame:
13
+ """Download OHLCV data from Yahoo Finance."""
14
+ stock = yf.Ticker(ticker)
15
+ df = stock.history(period=period, interval=interval)
16
+ if df.empty:
17
+ raise ValueError(f"No data found for ticker: {ticker}")
18
+ df.reset_index(inplace=True)
19
+ return df
20
+
21
+
22
+ def add_technical_indicators(df: pd.DataFrame) -> pd.DataFrame:
23
+ """Add SMA, EMA, RSI, MACD, and volume-based indicators."""
24
+ close = df["Close"]
25
+ volume = df["Volume"]
26
+
27
+ df["SMA_20"] = ta.trend.sma_indicator(close, window=20)
28
+ df["SMA_50"] = ta.trend.sma_indicator(close, window=50)
29
+ df["EMA_20"] = ta.trend.ema_indicator(close, window=20)
30
+ df["RSI"] = ta.momentum.rsi(close, window=14)
31
+
32
+ macd = ta.trend.MACD(close)
33
+ df["MACD"] = macd.macd()
34
+ df["MACD_Signal"] = macd.macd_signal()
35
+ df["MACD_Hist"] = macd.macd_diff()
36
+
37
+ df["Volume_SMA_20"] = ta.trend.sma_indicator(volume, window=20)
38
+ df.dropna(inplace=True)
39
+ return df
40
+
41
+
42
+ def get_stock_info(ticker: str) -> dict:
43
+ """Return basic stock metadata."""
44
+ stock = yf.Ticker(ticker)
45
+ info = stock.info
46
+ return {
47
+ "name": info.get("shortName", ticker),
48
+ "sector": info.get("sector", "N/A"),
49
+ "currency": info.get("currency", "USD"),
50
+ "current_price": info.get("currentPrice", info.get("regularMarketPrice", 0)),
51
+ "market_cap": info.get("marketCap", 0),
52
+ "day_high": info.get("dayHigh", 0),
53
+ "day_low": info.get("dayLow", 0),
54
+ "prev_close": info.get("previousClose", 0),
55
+ "open": info.get("open", 0),
56
+ "volume": info.get("volume", 0),
57
+ "fifty_two_week_high": info.get("fiftyTwoWeekHigh", 0),
58
+ "fifty_two_week_low": info.get("fiftyTwoWeekLow", 0),
59
+ }
60
+
61
+
62
+ def fetch_live_price(ticker: str) -> dict:
63
+ """Fetch the latest price snapshot for live ticker display."""
64
+ stock = yf.Ticker(ticker)
65
+ info = stock.info
66
+
67
+ current = info.get("currentPrice", info.get("regularMarketPrice", 0))
68
+ prev_close = info.get("previousClose", 0)
69
+
70
+ change = round(current - prev_close, 2) if current and prev_close else 0
71
+ change_pct = round((change / prev_close) * 100, 2) if prev_close else 0
72
+
73
+ return {
74
+ "ticker": ticker,
75
+ "price": current,
76
+ "change": change,
77
+ "change_pct": change_pct,
78
+ "direction": "up" if change >= 0 else "down",
79
+ "day_high": info.get("dayHigh", 0),
80
+ "day_low": info.get("dayLow", 0),
81
+ "volume": info.get("volume", 0),
82
+ "timestamp": datetime.now().isoformat(),
83
+ }
84
+
85
+
86
+ TIMEFRAME_MAP = {
87
+ "1d": ("1d", "5m"),
88
+ "5d": ("5d", "15m"),
89
+ "1wk": ("5d", "15m"),
90
+ "1mo": ("1mo", "1h"),
91
+ "3mo": ("3mo", "1d"),
92
+ "6mo": ("6mo", "1d"),
93
+ "1y": ("1y", "1d"),
94
+ "2y": ("2y", "1wk"),
95
+ }
96
+
97
+
98
+ def fetch_chart_data(ticker: str, timeframe: str) -> list[dict]:
99
+ """Return OHLCV records for a given timeframe."""
100
+ period, interval = TIMEFRAME_MAP.get(timeframe, ("1mo", "1h"))
101
+ stock = yf.Ticker(ticker)
102
+ df = stock.history(period=period, interval=interval)
103
+ if df.empty:
104
+ raise ValueError(f"No chart data for {ticker}")
105
+ df.reset_index(inplace=True)
106
+
107
+ records = []
108
+ date_col = "Datetime" if "Datetime" in df.columns else "Date"
109
+ for _, row in df.iterrows():
110
+ records.append({
111
+ "time": str(row[date_col]),
112
+ "open": round(float(row["Open"]), 2),
113
+ "high": round(float(row["High"]), 2),
114
+ "low": round(float(row["Low"]), 2),
115
+ "close": round(float(row["Close"]), 2),
116
+ "volume": int(row["Volume"]),
117
+ })
118
+ return records
style.css ADDED
@@ -0,0 +1,274 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ /* ══ RESET & BASE ═══════════════════════════════════ */
2
+ *, *::before, *::after { box-sizing: border-box; margin: 0; padding: 0; }
3
+ :root {
4
+ --bg: #0b0e14; --bg2: #131720; --bg3: #1a1f2e; --border: #242a38;
5
+ --text: #d1d5db; --text-dim: #6b7280;
6
+ --green: #22c55e; --red: #ef4444; --blue: #3b82f6;
7
+ --cyan: #06b6d4; --yellow: #eab308; --accent: #22c55e;
8
+ --purple: #a855f7;
9
+ }
10
+ body {
11
+ font-family: 'SF Mono', 'Fira Code', 'Consolas', monospace;
12
+ background: var(--bg); color: var(--text);
13
+ min-height: 100vh; font-size: 14px;
14
+ }
15
+
16
+ /* ══ TOP BAR ════════════════════════════════════════ */
17
+ .topbar {
18
+ display: flex; align-items: center; justify-content: space-between;
19
+ padding: 0.6rem 1.5rem; background: var(--bg2);
20
+ border-bottom: 1px solid var(--border);
21
+ position: sticky; top: 0; z-index: 100;
22
+ }
23
+ .brand { font-size: 1.2rem; font-weight: 700; color: var(--accent); }
24
+ .brand span { color: #fff; }
25
+ .search-area { display: flex; gap: 0.4rem; }
26
+ .search-area input {
27
+ width: 260px; padding: 0.5rem 0.8rem;
28
+ background: var(--bg3); border: 1px solid var(--border);
29
+ border-radius: 6px; color: #fff; font-family: inherit; font-size: 0.9rem;
30
+ }
31
+ .search-area input:focus { outline: none; border-color: var(--accent); }
32
+ .search-area button {
33
+ padding: 0.5rem 1.2rem; border: none; border-radius: 6px;
34
+ background: var(--accent); color: #000; font-weight: 700;
35
+ cursor: pointer; font-family: inherit; transition: 0.2s;
36
+ }
37
+ .search-area button:hover { background: #16a34a; }
38
+
39
+ /* Nav Tabs */
40
+ .nav-tabs { display: flex; gap: 0.3rem; }
41
+ .nav-tab {
42
+ padding: 0.5rem 1rem; border: 1px solid var(--border);
43
+ background: transparent; color: var(--text-dim); border-radius: 6px;
44
+ cursor: pointer; font-family: inherit; font-size: 0.85rem; transition: 0.2s;
45
+ }
46
+ .nav-tab:hover { border-color: var(--text); color: var(--text); }
47
+ .nav-tab.active { background: var(--accent); color: #000; border-color: var(--accent); font-weight: 700; }
48
+
49
+ .live-badge { display: flex; align-items: center; gap: 0.4rem; color: var(--green); font-weight: 700; font-size: 0.8rem; }
50
+ .live-badge .dot {
51
+ width: 8px; height: 8px; background: var(--green); border-radius: 50%;
52
+ animation: pulse 1.5s infinite;
53
+ }
54
+ @keyframes pulse { 0%, 100% { opacity: 1; } 50% { opacity: 0.3; } }
55
+
56
+ /* ══ PRICE BANNER ═══════════════════════════════════ */
57
+ .price-banner {
58
+ display: flex; justify-content: space-between; align-items: center;
59
+ padding: 1rem 1.5rem; background: var(--bg2); border-bottom: 1px solid var(--border);
60
+ }
61
+ .price-main { display: flex; align-items: baseline; gap: 1rem; }
62
+ .price-main h1 { font-size: 1.3rem; color: #fff; }
63
+ .price-value { font-size: 2rem; font-weight: 700; color: #fff; }
64
+ .price-change { font-size: 1rem; font-weight: 600; padding: 0.2rem 0.6rem; border-radius: 4px; }
65
+ .price-change.up { color: var(--green); background: rgba(34,197,94,0.1); }
66
+ .price-change.down { color: var(--red); background: rgba(239,68,68,0.1); }
67
+ .price-stats { display: flex; gap: 1.5rem; }
68
+ .price-stats div { text-align: center; }
69
+ .price-stats label { display: block; font-size: 0.7rem; color: var(--text-dim); text-transform: uppercase; }
70
+ .price-stats span { font-size: 0.95rem; color: #fff; font-weight: 600; }
71
+
72
+ /* ══ TABS ═══════════════════════════════════════════ */
73
+ .tab-content { display: block; }
74
+ .tab-content.hidden { display: none !important; }
75
+
76
+ /* ══ DASHBOARD GRID ═════════════════════════════════ */
77
+ .dashboard {
78
+ display: grid; grid-template-columns: 1fr 340px;
79
+ gap: 0; min-height: calc(100vh - 160px);
80
+ }
81
+ .chart-area { padding: 1rem 1.5rem; border-right: 1px solid var(--border); }
82
+ .sidebar { padding: 1rem; overflow-y: auto; max-height: calc(100vh - 160px); }
83
+
84
+ /* ══ TIMEFRAME BAR ══════════════════════════════════ */
85
+ .timeframe-bar { display: flex; gap: 0.3rem; margin-bottom: 0.8rem; }
86
+ .tf-btn {
87
+ padding: 0.35rem 0.9rem; border: 1px solid var(--border);
88
+ background: transparent; color: var(--text-dim); border-radius: 4px;
89
+ cursor: pointer; font-family: inherit; font-size: 0.8rem; transition: 0.2s;
90
+ }
91
+ .tf-btn:hover { border-color: var(--text); color: var(--text); }
92
+ .tf-btn.active { background: var(--accent); color: #000; border-color: var(--accent); font-weight: 700; }
93
+
94
+ /* ══ CHART CONTAINERS ═══════════════════════════════ */
95
+ .chart-container { background: var(--bg2); border: 1px solid var(--border); border-radius: 8px; padding: 0.8rem; margin-bottom: 0.8rem; }
96
+ .volume-chart { height: 120px; }
97
+
98
+ /* ══ PREDICTION SECTION ═════════════════════════════ */
99
+ .prediction-section { margin-top: 1rem; }
100
+ .prediction-section h3 { color: var(--cyan); margin-bottom: 0.8rem; }
101
+ .pred-metrics { display: grid; grid-template-columns: repeat(4, 1fr); gap: 0.6rem; margin-top: 0.8rem; }
102
+ .metric-card { background: var(--bg3); border: 1px solid var(--border); border-radius: 8px; padding: 0.8rem; text-align: center; }
103
+ .m-label { display: block; font-size: 0.7rem; color: var(--text-dim); text-transform: uppercase; margin-bottom: 0.3rem; }
104
+ .m-value { font-size: 1.3rem; font-weight: 700; color: #fff; }
105
+
106
+ /* ══ SIDEBAR PANELS ═════════════════════════════════ */
107
+ .panel { background: var(--bg2); border: 1px solid var(--border); border-radius: 8px; padding: 1rem; margin-bottom: 0.8rem; }
108
+ .panel h3 { font-size: 0.95rem; color: var(--cyan); margin-bottom: 0.3rem; }
109
+ .panel-sub { font-size: 0.75rem; color: var(--text-dim); margin-bottom: 0.8rem; }
110
+
111
+ .hp-list { display: flex; flex-direction: column; gap: 0.4rem; }
112
+ .hp-item {
113
+ display: grid; grid-template-columns: 1fr auto auto;
114
+ align-items: center; gap: 0.5rem; padding: 0.5rem 0.6rem;
115
+ background: var(--bg3); border-radius: 6px; cursor: pointer; transition: 0.2s;
116
+ }
117
+ .hp-item:hover { background: var(--border); }
118
+ .hp-ticker { font-weight: 700; color: #fff; font-size: 0.9rem; }
119
+ .hp-name { font-size: 0.7rem; color: var(--text-dim); }
120
+ .hp-price { text-align: right; font-weight: 600; color: #fff; }
121
+ .hp-change { font-size: 0.8rem; font-weight: 600; text-align: right; }
122
+ .hp-change.up { color: var(--green); }
123
+ .hp-change.down { color: var(--red); }
124
+ .hp-score { font-size: 0.7rem; padding: 0.15rem 0.5rem; border-radius: 10px; font-weight: 700; text-align: center; }
125
+ .hp-score.high { background: rgba(34,197,94,0.15); color: var(--green); }
126
+ .hp-score.med { background: rgba(234,179,8,0.15); color: var(--yellow); }
127
+ .hp-score.low { background: rgba(239,68,68,0.15); color: var(--red); }
128
+
129
+ .sent-gauge { display: flex; align-items: center; gap: 1rem; margin: 0.8rem 0; }
130
+ .gauge-circle {
131
+ width: 64px; height: 64px; border-radius: 50%;
132
+ display: flex; align-items: center; justify-content: center;
133
+ font-weight: 700; font-size: 1rem; color: #fff; border: 3px solid var(--text-dim);
134
+ }
135
+ .gauge-circle.positive { border-color: var(--green); background: rgba(34,197,94,0.1); }
136
+ .gauge-circle.negative { border-color: var(--red); background: rgba(239,68,68,0.1); }
137
+ .gauge-circle.neutral { border-color: var(--yellow); background: rgba(234,179,8,0.1); }
138
+ .gauge-label { font-size: 1.1rem; font-weight: 700; text-transform: uppercase; }
139
+ .sent-list { list-style: none; max-height: 200px; overflow-y: auto; }
140
+ .sent-list li { padding: 0.4rem 0; border-bottom: 1px solid var(--border); font-size: 0.8rem; }
141
+ .s-pos { color: var(--green); } .s-neg { color: var(--red); } .s-neu { color: var(--yellow); }
142
+
143
+ .ind-table { width: 100%; }
144
+ .ind-table td { padding: 0.4rem 0.5rem; border-bottom: 1px solid var(--border); }
145
+ .ind-table td:first-child { color: var(--text-dim); }
146
+ .ind-table td:last-child { text-align: right; font-weight: 600; color: #fff; }
147
+
148
+ .mini-loader { text-align: center; color: var(--text-dim); padding: 1rem; font-size: 0.8rem; }
149
+
150
+ /* ══ TRADING DASHBOARD ══════════════════════════════ */
151
+ .trading-dashboard { padding: 1rem 1.5rem; }
152
+ .trade-grid { display: flex; flex-direction: column; gap: 1rem; }
153
+
154
+ /* Portfolio header cards */
155
+ .portfolio-header {
156
+ display: grid; grid-template-columns: repeat(6, 1fr); gap: 0.6rem;
157
+ }
158
+ .port-card {
159
+ background: var(--bg2); border: 1px solid var(--border);
160
+ border-radius: 8px; padding: 1rem; text-align: center;
161
+ }
162
+ .port-card.balance { border-color: var(--accent); }
163
+ .pc-label { display: block; font-size: 0.7rem; color: var(--text-dim); text-transform: uppercase; margin-bottom: 0.4rem; }
164
+ .pc-value { font-size: 1.4rem; font-weight: 700; color: #fff; }
165
+
166
+ /* Bot controls */
167
+ .bot-controls {
168
+ display: flex; align-items: center; justify-content: space-between;
169
+ background: var(--bg2); border: 1px solid var(--border);
170
+ border-radius: 8px; padding: 1rem 1.5rem;
171
+ }
172
+ .bot-status { display: flex; align-items: center; gap: 0.6rem; font-size: 1.1rem; font-weight: 700; }
173
+ .bot-dot {
174
+ width: 12px; height: 12px; border-radius: 50%; background: var(--red);
175
+ }
176
+ .bot-dot.active { background: var(--green); animation: pulse 1s infinite; }
177
+ .bot-buttons { display: flex; gap: 0.5rem; }
178
+
179
+ .btn-bot, .btn-scan, .btn-trade, .btn-reset {
180
+ padding: 0.6rem 1rem; border: none; border-radius: 6px;
181
+ font-family: inherit; font-weight: 700; font-size: 0.85rem;
182
+ cursor: pointer; transition: 0.2s;
183
+ }
184
+ .btn-bot { background: var(--purple); color: #fff; }
185
+ .btn-bot:hover { background: #9333ea; }
186
+ .btn-bot.active { background: var(--red); }
187
+ .btn-scan { background: var(--blue); color: #fff; }
188
+ .btn-scan:hover { background: #2563eb; }
189
+ .btn-trade { background: var(--green); color: #000; }
190
+ .btn-trade:hover { background: #16a34a; }
191
+ .btn-reset { background: var(--bg3); color: var(--text-dim); border: 1px solid var(--border); }
192
+ .btn-reset:hover { background: var(--border); color: #fff; }
193
+
194
+ /* Trade panels */
195
+ .trade-panel {
196
+ background: var(--bg2); border: 1px solid var(--border);
197
+ border-radius: 8px; padding: 1rem 1.5rem;
198
+ }
199
+ .trade-panel h3 { color: var(--cyan); margin-bottom: 0.8rem; font-size: 0.95rem; }
200
+
201
+ /* Positions table */
202
+ .positions-table-wrap { overflow-x: auto; }
203
+ .positions-table { width: 100%; border-collapse: collapse; font-size: 0.85rem; }
204
+ .positions-table th {
205
+ padding: 0.5rem 0.6rem; text-align: left; color: var(--text-dim);
206
+ border-bottom: 1px solid var(--border); font-size: 0.75rem; text-transform: uppercase;
207
+ }
208
+ .positions-table td {
209
+ padding: 0.6rem; border-bottom: 1px solid var(--border);
210
+ }
211
+ .positions-table .ticker-col { font-weight: 700; color: #fff; }
212
+ .pnl-positive { color: var(--green); font-weight: 700; }
213
+ .pnl-negative { color: var(--red); font-weight: 700; }
214
+
215
+ .btn-sell-small {
216
+ padding: 0.3rem 0.7rem; border: none; border-radius: 4px;
217
+ background: var(--red); color: #fff; font-weight: 700;
218
+ cursor: pointer; font-family: inherit; font-size: 0.75rem;
219
+ }
220
+ .btn-sell-small:hover { background: #dc2626; }
221
+
222
+ .empty-msg { color: var(--text-dim); text-align: center; padding: 1.5rem; font-size: 0.85rem; }
223
+
224
+ /* Trade log */
225
+ .trade-log { max-height: 300px; overflow-y: auto; }
226
+ .trade-entry {
227
+ display: grid; grid-template-columns: auto 1fr auto auto;
228
+ gap: 0.8rem; align-items: center;
229
+ padding: 0.6rem 0; border-bottom: 1px solid var(--border); font-size: 0.8rem;
230
+ }
231
+ .te-time { color: var(--text-dim); font-size: 0.75rem; }
232
+ .te-ticker { font-weight: 700; color: #fff; }
233
+ .te-action { padding: 0.15rem 0.5rem; border-radius: 4px; font-weight: 700; font-size: 0.75rem; }
234
+ .te-action.buy { background: rgba(34,197,94,0.15); color: var(--green); }
235
+ .te-action.sell { background: rgba(239,68,68,0.15); color: var(--red); }
236
+
237
+ /* Trade feed */
238
+ .trade-feed { max-height: 250px; overflow-y: auto; font-size: 0.8rem; }
239
+ .feed-item {
240
+ padding: 0.5rem 0.6rem; margin-bottom: 0.3rem;
241
+ background: var(--bg3); border-radius: 4px;
242
+ border-left: 3px solid var(--border); animation: fadeIn 0.3s ease;
243
+ }
244
+ .feed-item.buy { border-left-color: var(--green); }
245
+ .feed-item.sell { border-left-color: var(--red); }
246
+ .feed-item.hold { border-left-color: var(--yellow); }
247
+ .feed-item.wait { border-left-color: var(--text-dim); }
248
+
249
+ @keyframes fadeIn { from { opacity: 0; transform: translateY(-5px); } to { opacity: 1; transform: translateY(0); } }
250
+
251
+ /* ══ FOOTER ═════════════════════════════════════════ */
252
+ footer {
253
+ text-align: center; padding: 1.5rem;
254
+ background: var(--bg2); border-top: 1px solid var(--border);
255
+ color: var(--text-dim); font-size: 0.8rem;
256
+ }
257
+ footer p + p { margin-top: 0.3rem; }
258
+
259
+ .hidden { display: none !important; }
260
+
261
+ /* ══ RESPONSIVE ═════════════════════════════════════ */
262
+ @media (max-width: 1100px) {
263
+ .portfolio-header { grid-template-columns: repeat(3, 1fr); }
264
+ }
265
+ @media (max-width: 900px) {
266
+ .dashboard { grid-template-columns: 1fr; }
267
+ .sidebar { max-height: none; }
268
+ .price-banner { flex-direction: column; gap: 0.8rem; }
269
+ .price-stats { flex-wrap: wrap; }
270
+ .pred-metrics { grid-template-columns: repeat(2, 1fr); }
271
+ .portfolio-header { grid-template-columns: repeat(2, 1fr); }
272
+ .bot-controls { flex-direction: column; gap: 0.8rem; }
273
+ .bot-buttons { flex-wrap: wrap; }
274
+ }
trader.py ADDED
@@ -0,0 +1,287 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ """
2
+ StockSense AI β€” Auto Trading Engine (Paper Trading)
3
+ Strategy: LSTM Prediction-Based
4
+ - BUY when model predicts price going UP in next 5 days
5
+ - SELL when stop-loss / take-profit / trailing-stop / prediction reversal
6
+ """
7
+
8
+ import json
9
+ import os
10
+ from datetime import datetime
11
+ from threading import Lock
12
+
13
+ # ── CONFIG ────────────────────────────────���────────────
14
+ INITIAL_BALANCE = 100_000.00
15
+ STOP_LOSS_PCT = -3.0 # -3% from buy price
16
+ TAKE_PROFIT_PCT = 5.0 # +5% from buy price
17
+ TRAILING_STOP_PCT = -2.0 # -2% from peak after buy
18
+ MAX_HOLD_DAYS = 5 # auto-sell after 5 days
19
+ POSITION_SIZE_PCT = 10.0 # use 10% of balance per trade
20
+
21
+ DATA_FILE = "portfolio.json"
22
+ _lock = Lock()
23
+
24
+
25
+ # ── PORTFOLIO STATE ────────────────────────────────────
26
+ def _default_state():
27
+ return {
28
+ "balance": INITIAL_BALANCE,
29
+ "initial_balance": INITIAL_BALANCE,
30
+ "positions": {}, # ticker -> position dict
31
+ "trade_history": [], # list of completed trades
32
+ "bot_active": False,
33
+ "created_at": datetime.now().isoformat(),
34
+ }
35
+
36
+
37
+ def _load_state() -> dict:
38
+ if os.path.exists(DATA_FILE):
39
+ with open(DATA_FILE, "r") as f:
40
+ return json.load(f)
41
+ return _default_state()
42
+
43
+
44
+ def _save_state(state: dict):
45
+ with open(DATA_FILE, "w") as f:
46
+ json.dump(state, f, indent=2, default=str)
47
+
48
+
49
+ def get_portfolio() -> dict:
50
+ """Return current portfolio state."""
51
+ with _lock:
52
+ state = _load_state()
53
+ return state
54
+
55
+
56
+ def reset_portfolio() -> dict:
57
+ """Reset portfolio to initial state."""
58
+ with _lock:
59
+ state = _default_state()
60
+ _save_state(state)
61
+ return state
62
+
63
+
64
+ def toggle_bot() -> dict:
65
+ """Toggle auto-trading bot ON/OFF."""
66
+ with _lock:
67
+ state = _load_state()
68
+ state["bot_active"] = not state["bot_active"]
69
+ _save_state(state)
70
+ return {"bot_active": state["bot_active"]}
71
+
72
+
73
+ # ── TRADING LOGIC ──────────────────────────────────────
74
+ def execute_buy(ticker: str, current_price: float, predicted_prices: list,
75
+ confidence: float) -> dict:
76
+ """
77
+ Execute a BUY order (paper trade).
78
+ """
79
+ with _lock:
80
+ state = _load_state()
81
+
82
+ # Already holding this ticker?
83
+ if ticker in state["positions"]:
84
+ return {"status": "skipped", "reason": f"Already holding {ticker}"}
85
+
86
+ # Calculate position size
87
+ position_value = state["balance"] * (POSITION_SIZE_PCT / 100)
88
+ if position_value < current_price:
89
+ return {"status": "skipped", "reason": "Insufficient balance"}
90
+
91
+ shares = int(position_value // current_price)
92
+ if shares == 0:
93
+ return {"status": "skipped", "reason": "Cannot afford even 1 share"}
94
+
95
+ cost = shares * current_price
96
+
97
+ # Stop-loss & take-profit prices
98
+ stop_loss = round(current_price * (1 + STOP_LOSS_PCT / 100), 2)
99
+ take_profit = round(current_price * (1 + TAKE_PROFIT_PCT / 100), 2)
100
+
101
+ # Create position
102
+ position = {
103
+ "ticker": ticker,
104
+ "shares": shares,
105
+ "buy_price": current_price,
106
+ "cost": round(cost, 2),
107
+ "stop_loss": stop_loss,
108
+ "take_profit": take_profit,
109
+ "trailing_stop": stop_loss,
110
+ "peak_price": current_price,
111
+ "predicted_prices": predicted_prices,
112
+ "confidence": confidence,
113
+ "buy_time": datetime.now().isoformat(),
114
+ "day_count": 0,
115
+ }
116
+
117
+ state["balance"] -= cost
118
+ state["balance"] = round(state["balance"], 2)
119
+ state["positions"][ticker] = position
120
+ _save_state(state)
121
+
122
+ return {
123
+ "status": "bought",
124
+ "ticker": ticker,
125
+ "shares": shares,
126
+ "price": current_price,
127
+ "cost": round(cost, 2),
128
+ "stop_loss": stop_loss,
129
+ "take_profit": take_profit,
130
+ "balance": state["balance"],
131
+ }
132
+
133
+
134
+ def execute_sell(ticker: str, current_price: float, reason: str) -> dict:
135
+ """
136
+ Execute a SELL order (paper trade).
137
+ """
138
+ with _lock:
139
+ state = _load_state()
140
+
141
+ if ticker not in state["positions"]:
142
+ return {"status": "skipped", "reason": f"No position in {ticker}"}
143
+
144
+ pos = state["positions"][ticker]
145
+ revenue = pos["shares"] * current_price
146
+ profit = revenue - pos["cost"]
147
+ profit_pct = (profit / pos["cost"]) * 100
148
+
149
+ # Record trade history
150
+ trade = {
151
+ "ticker": ticker,
152
+ "shares": pos["shares"],
153
+ "buy_price": pos["buy_price"],
154
+ "sell_price": current_price,
155
+ "cost": pos["cost"],
156
+ "revenue": round(revenue, 2),
157
+ "profit": round(profit, 2),
158
+ "profit_pct": round(profit_pct, 2),
159
+ "buy_time": pos["buy_time"],
160
+ "sell_time": datetime.now().isoformat(),
161
+ "reason": reason,
162
+ "confidence": pos["confidence"],
163
+ }
164
+
165
+ state["balance"] += revenue
166
+ state["balance"] = round(state["balance"], 2)
167
+ state["trade_history"].append(trade)
168
+ del state["positions"][ticker]
169
+ _save_state(state)
170
+
171
+ return {
172
+ "status": "sold",
173
+ "ticker": ticker,
174
+ "shares": trade["shares"],
175
+ "price": current_price,
176
+ "profit": trade["profit"],
177
+ "profit_pct": trade["profit_pct"],
178
+ "reason": reason,
179
+ "balance": state["balance"],
180
+ }
181
+
182
+
183
+ def check_position(ticker: str, current_price: float) -> dict:
184
+ """
185
+ Check if a position should be sold based on stop-loss,
186
+ take-profit, or trailing stop.
187
+ """
188
+ with _lock:
189
+ state = _load_state()
190
+
191
+ if ticker not in state["positions"]:
192
+ return {"action": "none", "reason": "No position"}
193
+
194
+ pos = state["positions"][ticker]
195
+ buy_price = pos["buy_price"]
196
+ change_pct = ((current_price - buy_price) / buy_price) * 100
197
+
198
+ # ── STOP LOSS ──
199
+ if current_price <= pos["stop_loss"]:
200
+ return {"action": "sell", "reason": f"Stop-loss triggered ({STOP_LOSS_PCT}%)"}
201
+
202
+ # ── TAKE PROFIT ──
203
+ if current_price >= pos["take_profit"]:
204
+ return {"action": "sell", "reason": f"Take-profit reached (+{TAKE_PROFIT_PCT}%)"}
205
+
206
+ # ── TRAILING STOP ──
207
+ if current_price > pos["peak_price"]:
208
+ # Update peak and trailing stop
209
+ with _lock:
210
+ state = _load_state()
211
+ state["positions"][ticker]["peak_price"] = current_price
212
+ new_trailing = round(current_price * (1 + TRAILING_STOP_PCT / 100), 2)
213
+ if new_trailing > state["positions"][ticker]["trailing_stop"]:
214
+ state["positions"][ticker]["trailing_stop"] = new_trailing
215
+ _save_state(state)
216
+ elif current_price <= pos["trailing_stop"]:
217
+ return {"action": "sell", "reason": f"Trailing stop triggered ({TRAILING_STOP_PCT}%)"}
218
+
219
+ # ── MAX HOLD DAYS ──
220
+ pos["day_count"] += 1
221
+ if pos["day_count"] >= MAX_HOLD_DAYS:
222
+ return {"action": "sell", "reason": f"Max hold period ({MAX_HOLD_DAYS} days)"}
223
+
224
+ return {
225
+ "action": "hold",
226
+ "reason": "Within thresholds",
227
+ "current_pnl": round(change_pct, 2),
228
+ "current_price": current_price,
229
+ "stop_loss": pos["stop_loss"],
230
+ "take_profit": pos["take_profit"],
231
+ "trailing_stop": pos["trailing_stop"],
232
+ }
233
+
234
+
235
+ def evaluate_trade_signal(ticker: str, current_price: float,
236
+ predicted_prices: list, confidence: float) -> dict:
237
+ """
238
+ Core strategy: Decide BUY / SELL / HOLD based on LSTM prediction.
239
+ """
240
+ state = _load_state()
241
+
242
+ # Prediction analysis
243
+ pred_day1 = predicted_prices[0]
244
+ pred_day5 = predicted_prices[-1]
245
+ pred_change_pct = ((pred_day5 - current_price) / current_price) * 100
246
+ pred_direction = "up" if pred_day5 > current_price else "down"
247
+
248
+ # Count how many predicted days are above current price
249
+ days_above = sum(1 for p in predicted_prices if p > current_price)
250
+
251
+ signal = {
252
+ "ticker": ticker,
253
+ "current_price": current_price,
254
+ "predicted_day1": round(pred_day1, 2),
255
+ "predicted_day5": round(pred_day5, 2),
256
+ "pred_change_pct": round(pred_change_pct, 2),
257
+ "pred_direction": pred_direction,
258
+ "days_above_current": days_above,
259
+ "confidence": confidence,
260
+ }
261
+
262
+ # Already holding?
263
+ if ticker in state["positions"]:
264
+ check = check_position(ticker, current_price)
265
+ if check["action"] == "sell":
266
+ result = execute_sell(ticker, current_price, check["reason"])
267
+ signal["action"] = "SELL"
268
+ signal["trade_result"] = result
269
+ elif pred_direction == "down" and days_above <= 1 and confidence > 40:
270
+ result = execute_sell(ticker, current_price, "Prediction reversal (downtrend)")
271
+ signal["action"] = "SELL"
272
+ signal["trade_result"] = result
273
+ else:
274
+ signal["action"] = "HOLD"
275
+ signal["position"] = check
276
+ else:
277
+ # BUY conditions: prediction is UP + enough confidence
278
+ if (pred_direction == "up" and days_above >= 3 and
279
+ confidence >= 35 and pred_change_pct > 0.5):
280
+ result = execute_buy(ticker, current_price, predicted_prices, confidence)
281
+ signal["action"] = "BUY"
282
+ signal["trade_result"] = result
283
+ else:
284
+ signal["action"] = "WAIT"
285
+ signal["reason"] = "Conditions not met for entry"
286
+
287
+ return signal