Spaces:
Sleeping
Sleeping
Update streamlit_app.py
Browse files- streamlit_app.py +76 -96
streamlit_app.py
CHANGED
|
@@ -22,7 +22,7 @@ else:
|
|
| 22 |
st.stop()
|
| 23 |
|
| 24 |
# ==============================================================================
|
| 25 |
-
# ๐ [UI] ๋ค๊ตญ์ด ๋์
๋๋ฆฌ
|
| 26 |
# ==============================================================================
|
| 27 |
UI_TEXT = {
|
| 28 |
"KR": {
|
|
@@ -33,21 +33,22 @@ UI_TEXT = {
|
|
| 33 |
"search_title": "๐ง ๋ค๊ตญ์ด AI ์ฃผ์ ๋น์ (๋ฉํฐ ํ๊ฒ)",
|
| 34 |
"search_placeholder": "์: ์ผ์ฑ์ ์๋ TSMC ๋น๊ตํด์ค, ๋ชฝ๊ณจ ๊ณ ๋น ์บ์๋ฏธ์ด...",
|
| 35 |
"btn_analyze": "๋ถ์ ์์",
|
| 36 |
-
"status_thinking": "๐ง AI๊ฐ
|
| 37 |
"status_news": "๐ฐ ๋ด์ค ์์ง ์ค...",
|
| 38 |
"metric_price": "ํ์ฌ๊ฐ",
|
| 39 |
"metric_source": "์ถ์ฒ",
|
| 40 |
"expander_news": "๐ฐ ๋ด์ค ์๋ฌธ ๋ณด๊ธฐ",
|
| 41 |
"insight_title": "๐ง AI ์ข
ํฉ ๋ถ์ ๋ฆฌํฌํธ",
|
| 42 |
"scanner_title": "๐ก ๊ธ๋ก๋ฒ ์์ฅ ์ ๊ดํ (Frontier Included)",
|
| 43 |
-
"scanner_caption": "โป
|
| 44 |
-
"btn_scan": "์ ์ฒด ์ข
๋ชฉ ์ค์บ
|
| 45 |
"tab_gainers": "๐ฅ ๊ธ๋ฑ Top 10",
|
| 46 |
"tab_losers": "๐ง ๊ธ๋ฝ Top 10",
|
| 47 |
"col_name": "๊ธฐ์
๋ช
",
|
| 48 |
"col_price": "๊ฐ๊ฒฉ",
|
| 49 |
"col_change": "๋ฑ๋ฝ๋ฅ ",
|
| 50 |
"col_source": "์ถ์ฒ",
|
|
|
|
| 51 |
"msg_fail": "๋ฐ์ดํฐ ์์ง ์คํจ",
|
| 52 |
"llm_lang_instruction": "Korean"
|
| 53 |
},
|
|
@@ -59,32 +60,33 @@ UI_TEXT = {
|
|
| 59 |
"search_title": "๐ง AI Stock Assistant (Multi-Target)",
|
| 60 |
"search_placeholder": "e.g. Compare Samsung vs TSMC...",
|
| 61 |
"btn_analyze": "Analyze",
|
| 62 |
-
"status_thinking": "๐ง AI is analyzing
|
| 63 |
"status_news": "๐ฐ Fetching news...",
|
| 64 |
"metric_price": "Price",
|
| 65 |
"metric_source": "Source",
|
| 66 |
"expander_news": "๐ฐ View Source News",
|
| 67 |
"insight_title": "๐ง AI Comprehensive Report",
|
| 68 |
"scanner_title": "๐ก Global Market Scanner (Frontier Included)",
|
| 69 |
-
"scanner_caption": "โป
|
| 70 |
-
"btn_scan": "
|
| 71 |
"tab_gainers": "๐ฅ Top 10 Gainers",
|
| 72 |
"tab_losers": "๐ง Top 10 Losers",
|
| 73 |
"col_name": "Company",
|
| 74 |
"col_price": "Price",
|
| 75 |
"col_change": "Change(%)",
|
| 76 |
"col_source": "Source",
|
|
|
|
| 77 |
"msg_fail": "Data collection failed",
|
| 78 |
"llm_lang_instruction": "English"
|
| 79 |
}
|
| 80 |
}
|
| 81 |
|
| 82 |
# ==============================================================================
|
| 83 |
-
# ๐พ [๋ฐ์ดํฐ] ํฐ์ปค ๋งคํ (
|
| 84 |
# ==============================================================================
|
| 85 |
TICKER_NAMES = {
|
| 86 |
# ๐ญ๐ฐ ํ์ฝฉ (HK)
|
| 87 |
-
"1299.HK": "AIA Group", "0388.HK": "HKEX
|
| 88 |
"0016.HK": "SHK Properties", "1113.HK": "CK Asset", "0002.HK": "CLP Holdings",
|
| 89 |
"0003.HK": "HK & China Gas", "0066.HK": "MTR Corp", "0011.HK": "Hang Seng Bank",
|
| 90 |
"0027.HK": "Galaxy Ent", "0019.HK": "Swire Pacific", "9988.HK": "Alibaba",
|
|
@@ -171,37 +173,22 @@ MARKET_SAMPLES = {
|
|
| 171 |
}
|
| 172 |
|
| 173 |
# ==============================================================================
|
| 174 |
-
# ๐ ๏ธ [์์ง]
|
| 175 |
# ==============================================================================
|
| 176 |
def get_market_indices():
|
| 177 |
-
"""
|
| 178 |
-
์ฌ์ด๋๋ฐ ๋ฐ AI ๋ถ์์ฉ ์์ฅ ์ง์ ์์ง
|
| 179 |
-
"""
|
| 180 |
-
indices = {
|
| 181 |
-
"S&P 500": "^GSPC",
|
| 182 |
-
"NASDAQ": "^IXIC",
|
| 183 |
-
"KOSPI": "^KS11",
|
| 184 |
-
"VN-INDEX": "^VNINDEX"
|
| 185 |
-
}
|
| 186 |
data = {}
|
| 187 |
try:
|
| 188 |
-
|
| 189 |
-
df = yf.download(tickers, period="5d", progress=False)['Close']
|
| 190 |
-
|
| 191 |
for name, ticker in indices.items():
|
| 192 |
if ticker in df.columns:
|
| 193 |
series = df[ticker].dropna()
|
| 194 |
if len(series) >= 2:
|
| 195 |
-
curr = series.iloc[-1]
|
| 196 |
-
|
| 197 |
-
pct = ((curr - prev)/prev)*100
|
| 198 |
-
data[name] = (curr, pct)
|
| 199 |
except: pass
|
| 200 |
return data
|
| 201 |
|
| 202 |
-
# ==============================================================================
|
| 203 |
-
# ๐ ๏ธ [์์ง] ๋ฐ์ดํฐ ์์ง ํจ์๋ค (Robust)
|
| 204 |
-
# ==============================================================================
|
| 205 |
FAKE_HEADERS = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'}
|
| 206 |
|
| 207 |
def fetch_news_robust(keyword):
|
|
@@ -210,18 +197,12 @@ def fetch_news_robust(keyword):
|
|
| 210 |
try:
|
| 211 |
with DDGS() as ddgs:
|
| 212 |
results = list(ddgs.news(keyword, timelimit="m", max_results=3))
|
| 213 |
-
if not results:
|
| 214 |
-
|
| 215 |
-
results = list(ddgs.news(keyword, max_results=3))
|
| 216 |
-
if not results:
|
| 217 |
-
time.sleep(random.uniform(0.5, 1.0))
|
| 218 |
-
results = list(ddgs.text(f"{keyword} latest news", max_results=3))
|
| 219 |
for r in results:
|
| 220 |
url = r.get('url') or r.get('href')
|
| 221 |
if url not in seen_urls:
|
| 222 |
-
|
| 223 |
-
title = r.get('title', '')
|
| 224 |
-
summary += f"[{date}] {title}\n"
|
| 225 |
seen_urls.add(url)
|
| 226 |
except: return "No news."
|
| 227 |
return summary if summary else "No news."
|
|
@@ -246,11 +227,8 @@ def get_price_data_robust(ticker, name):
|
|
| 246 |
elif ".KS" in ticker or ".KQ" in ticker: fdr_symbol = ticker.split('.')[0]
|
| 247 |
hist = fdr.DataReader(fdr_symbol, start=(datetime.datetime.now() - datetime.timedelta(days=7)))
|
| 248 |
if not hist.empty:
|
| 249 |
-
curr = hist['Close'].iloc[-1]
|
| 250 |
-
|
| 251 |
-
pct = 0.0
|
| 252 |
-
if prev != 0: pct = ((curr - prev)/prev)*100
|
| 253 |
-
return curr, pct, "FDR"
|
| 254 |
except: pass
|
| 255 |
try:
|
| 256 |
stock = yf.Ticker(ticker)
|
|
@@ -268,8 +246,7 @@ def get_chart_data(ticker):
|
|
| 268 |
if ".VN" in ticker: fdr_symbol = ticker.split('.')[0]
|
| 269 |
elif ".JK" in ticker: fdr_symbol = f"IDX:{ticker.split('.')[0]}"
|
| 270 |
elif ".T" in ticker: fdr_symbol = f"TSE:{ticker.split('.')[0]}"
|
| 271 |
-
|
| 272 |
-
hist = fdr.DataReader(fdr_symbol, start)
|
| 273 |
if not hist.empty: return hist.rename(columns={'Close':'Close', 'Open':'Open', 'High':'High', 'Low':'Low'}), "FDR"
|
| 274 |
except: pass
|
| 275 |
try:
|
|
@@ -318,39 +295,35 @@ with st.sidebar:
|
|
| 318 |
T = UI_TEXT[lang_code]
|
| 319 |
st.title(T['sidebar_title'])
|
| 320 |
|
| 321 |
-
# ๐ [NEW] ์์ฅ ๋ ์จ (Market Weather)
|
| 322 |
st.divider()
|
| 323 |
st.caption(T['sidebar_weather'])
|
| 324 |
-
|
| 325 |
market_data = get_market_indices()
|
| 326 |
-
market_context_str = ""
|
| 327 |
|
| 328 |
if market_data:
|
| 329 |
-
|
| 330 |
-
col_w1, col_w2 = st.columns(2)
|
| 331 |
if "S&P 500" in market_data:
|
| 332 |
p, c = market_data["S&P 500"]
|
| 333 |
-
|
| 334 |
-
market_context_str += f"S&P 500
|
| 335 |
if "NASDAQ" in market_data:
|
| 336 |
p, c = market_data["NASDAQ"]
|
| 337 |
-
|
| 338 |
-
market_context_str += f"NASDAQ
|
| 339 |
-
|
| 340 |
-
col_w3, col_w4 = st.columns(2)
|
| 341 |
if "KOSPI" in market_data:
|
| 342 |
p, c = market_data["KOSPI"]
|
| 343 |
-
|
| 344 |
if "VN-INDEX" in market_data:
|
| 345 |
p, c = market_data["VN-INDEX"]
|
| 346 |
-
|
| 347 |
-
market_context_str += f"Vietnam Index
|
| 348 |
-
else:
|
| 349 |
-
st.caption("Load failed.")
|
| 350 |
|
| 351 |
st.divider()
|
| 352 |
menu = st.radio("MENU", [T['menu_search'], T['menu_scanner']], index=0)
|
| 353 |
|
|
|
|
| 354 |
if menu == T['menu_search']:
|
| 355 |
st.subheader(T['search_title'])
|
| 356 |
c1, c2 = st.columns([3, 1])
|
|
@@ -373,12 +346,9 @@ if menu == T['menu_search']:
|
|
| 373 |
h, src = get_chart_data(ticker)
|
| 374 |
news_data = get_polyglot_news(eng_key, native_key)
|
| 375 |
curr, pct = "N/A", 0
|
| 376 |
-
|
| 377 |
if not h.empty:
|
| 378 |
-
curr = h['Close'].iloc[-1]
|
| 379 |
-
|
| 380 |
-
prev = h['Close'].iloc[-2]
|
| 381 |
-
if prev != 0: pct = ((curr - prev)/prev)*100
|
| 382 |
else:
|
| 383 |
c_web, p_web, s_web = get_price_data_robust(ticker, name)
|
| 384 |
if c_web: curr, pct, src = c_web, p_web, s_web
|
|
@@ -389,7 +359,6 @@ if menu == T['menu_search']:
|
|
| 389 |
|
| 390 |
if not h.empty: st.plotly_chart(plot_candle_chart(h, name, src), use_container_width=True)
|
| 391 |
else: st.warning(f"Chart N/A")
|
| 392 |
-
|
| 393 |
with st.expander(T['expander_news']): st.text(news_data)
|
| 394 |
|
| 395 |
collected_data.append(f"[TARGET {i+1}] {name} ({ticker})\nPrice: {curr}, Change: {pct:.2f}%\nNews: {news_data[:500]}...")
|
|
@@ -398,27 +367,17 @@ if menu == T['menu_search']:
|
|
| 398 |
st.divider()
|
| 399 |
st.subheader(T['insight_title'])
|
| 400 |
|
| 401 |
-
target_lang = T['llm_lang_instruction']
|
| 402 |
-
|
| 403 |
-
# [NEW] ํ๋กฌํํธ์ ์์ฅ ์ํฉ ์ฃผ์
(AI Context Injection)
|
| 404 |
prompt = f"""
|
| 405 |
-
[ROLE] Global
|
| 406 |
-
[
|
| 407 |
-
[
|
| 408 |
-
[DATA OF TARGETS] {chr(10).join(collected_data)}
|
| 409 |
-
|
| 410 |
-
[TASK]
|
| 411 |
-
1. Compare targets based on data and news.
|
| 412 |
-
2. Evaluate their 'Relative Strength' against the market context (e.g., Is the stock strong while S&P 500 is weak?).
|
| 413 |
-
3. Provide a verdict.
|
| 414 |
-
|
| 415 |
-
[OUTPUT LANGUAGE] **{target_lang}** (Strictly output in {target_lang}).
|
| 416 |
"""
|
| 417 |
msg = [{"role": "user", "content": prompt}]
|
| 418 |
stream = client.chat.completions.create(model="Qwen/Qwen2.5-72B-Instruct", messages=msg, stream=True)
|
| 419 |
st.write_stream(parse_stream(stream))
|
| 420 |
else: st.error("AI Error")
|
| 421 |
|
|
|
|
| 422 |
elif menu == T['menu_scanner']:
|
| 423 |
st.subheader(T['scanner_title'])
|
| 424 |
st.caption(T['scanner_caption'])
|
|
@@ -438,24 +397,14 @@ elif menu == T['menu_scanner']:
|
|
| 438 |
for i, t in enumerate(tickers):
|
| 439 |
name_display = TICKER_NAMES.get(t, t)
|
| 440 |
p, c, s = None, None, None
|
| 441 |
-
|
| 442 |
if not batch_data.empty and t in batch_data.columns:
|
| 443 |
series = batch_data[t].dropna()
|
| 444 |
if len(series) >= 2:
|
| 445 |
-
p = series.iloc[-1]
|
| 446 |
-
|
| 447 |
-
|
| 448 |
-
c = ((p - prev)/prev)*100
|
| 449 |
-
s = "Yahoo (Batch)"
|
| 450 |
-
|
| 451 |
-
if p is None:
|
| 452 |
-
p, c, s = get_price_data_robust(t, name_display)
|
| 453 |
-
|
| 454 |
if p is not None:
|
| 455 |
-
results.append({
|
| 456 |
-
T['col_name']: name_display, 'Ticker': t,
|
| 457 |
-
T['col_price']: p, 'Change(%)': c, T['col_source']: s
|
| 458 |
-
})
|
| 459 |
bar.progress((i+1)/len(tickers))
|
| 460 |
|
| 461 |
if results:
|
|
@@ -463,10 +412,41 @@ elif menu == T['menu_scanner']:
|
|
| 463 |
st.plotly_chart(plot_bar_chart(df, T), use_container_width=True)
|
| 464 |
|
| 465 |
disp_cols = [T['col_name'], 'Ticker', T['col_price'], 'Change(%)', T['col_source']]
|
| 466 |
-
|
| 467 |
df_gainers = df[df['Change(%)'] > 0].head(10)
|
| 468 |
df_losers = df[df['Change(%)'] < 0].sort_values('Change(%)', ascending=True).head(10)
|
| 469 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 470 |
c_up, c_down = st.columns(2)
|
| 471 |
with c_up:
|
| 472 |
st.success(T['tab_gainers'])
|
|
|
|
| 22 |
st.stop()
|
| 23 |
|
| 24 |
# ==============================================================================
|
| 25 |
+
# ๐ [UI] ๋ค๊ตญ์ด ๋์
๋๋ฆฌ
|
| 26 |
# ==============================================================================
|
| 27 |
UI_TEXT = {
|
| 28 |
"KR": {
|
|
|
|
| 33 |
"search_title": "๐ง ๋ค๊ตญ์ด AI ์ฃผ์ ๋น์ (๋ฉํฐ ํ๊ฒ)",
|
| 34 |
"search_placeholder": "์: ์ผ์ฑ์ ์๋ TSMC ๋น๊ตํด์ค, ๋ชฝ๊ณจ ๊ณ ๋น ์บ์๋ฏธ์ด...",
|
| 35 |
"btn_analyze": "๋ถ์ ์์",
|
| 36 |
+
"status_thinking": "๐ง AI๊ฐ ๋ถ์ ์ค์
๋๋ค...",
|
| 37 |
"status_news": "๐ฐ ๋ด์ค ์์ง ์ค...",
|
| 38 |
"metric_price": "ํ์ฌ๊ฐ",
|
| 39 |
"metric_source": "์ถ์ฒ",
|
| 40 |
"expander_news": "๐ฐ ๋ด์ค ์๋ฌธ ๋ณด๊ธฐ",
|
| 41 |
"insight_title": "๐ง AI ์ข
ํฉ ๋ถ์ ๋ฆฌํฌํธ",
|
| 42 |
"scanner_title": "๐ก ๊ธ๋ก๋ฒ ์์ฅ ์ ๊ดํ (Frontier Included)",
|
| 43 |
+
"scanner_caption": "โป 100๊ฐ ๊ธฐ์
์ค์บ ํ, AI๊ฐ ์์ฅ ์ ์ฒด๋ฅผ ์์ฝํ๊ณ ์ ๋ง ์ข
๋ชฉ์ ๋ธ๋ฆฌํํฉ๋๋ค.",
|
| 44 |
+
"btn_scan": "์ ์ฒด ์ข
๋ชฉ ์ค์บ & AI ๋ฆฌํฌํธ ์์ฑ",
|
| 45 |
"tab_gainers": "๐ฅ ๊ธ๋ฑ Top 10",
|
| 46 |
"tab_losers": "๐ง ๊ธ๋ฝ Top 10",
|
| 47 |
"col_name": "๊ธฐ์
๋ช
",
|
| 48 |
"col_price": "๊ฐ๊ฒฉ",
|
| 49 |
"col_change": "๋ฑ๋ฝ๋ฅ ",
|
| 50 |
"col_source": "์ถ์ฒ",
|
| 51 |
+
"briefing_title": "๐ง AI Market Briefing (์ค๋์ ์์ฅ ๋ถ์)",
|
| 52 |
"msg_fail": "๋ฐ์ดํฐ ์์ง ์คํจ",
|
| 53 |
"llm_lang_instruction": "Korean"
|
| 54 |
},
|
|
|
|
| 60 |
"search_title": "๐ง AI Stock Assistant (Multi-Target)",
|
| 61 |
"search_placeholder": "e.g. Compare Samsung vs TSMC...",
|
| 62 |
"btn_analyze": "Analyze",
|
| 63 |
+
"status_thinking": "๐ง AI is analyzing...",
|
| 64 |
"status_news": "๐ฐ Fetching news...",
|
| 65 |
"metric_price": "Price",
|
| 66 |
"metric_source": "Source",
|
| 67 |
"expander_news": "๐ฐ View Source News",
|
| 68 |
"insight_title": "๐ง AI Comprehensive Report",
|
| 69 |
"scanner_title": "๐ก Global Market Scanner (Frontier Included)",
|
| 70 |
+
"scanner_caption": "โป Scans 100+ stocks and generates an AI market briefing.",
|
| 71 |
+
"btn_scan": "Scan & Generate AI Report",
|
| 72 |
"tab_gainers": "๐ฅ Top 10 Gainers",
|
| 73 |
"tab_losers": "๐ง Top 10 Losers",
|
| 74 |
"col_name": "Company",
|
| 75 |
"col_price": "Price",
|
| 76 |
"col_change": "Change(%)",
|
| 77 |
"col_source": "Source",
|
| 78 |
+
"briefing_title": "๐ง AI Market Briefing",
|
| 79 |
"msg_fail": "Data collection failed",
|
| 80 |
"llm_lang_instruction": "English"
|
| 81 |
}
|
| 82 |
}
|
| 83 |
|
| 84 |
# ==============================================================================
|
| 85 |
+
# ๐พ [๋ฐ์ดํฐ] ํฐ์ปค ๋งคํ (Full List)
|
| 86 |
# ==============================================================================
|
| 87 |
TICKER_NAMES = {
|
| 88 |
# ๐ญ๐ฐ ํ์ฝฉ (HK)
|
| 89 |
+
"1299.HK": "AIA Group", "0388.HK": "HKEX", "0005.HK": "HSBC Holdings",
|
| 90 |
"0016.HK": "SHK Properties", "1113.HK": "CK Asset", "0002.HK": "CLP Holdings",
|
| 91 |
"0003.HK": "HK & China Gas", "0066.HK": "MTR Corp", "0011.HK": "Hang Seng Bank",
|
| 92 |
"0027.HK": "Galaxy Ent", "0019.HK": "Swire Pacific", "9988.HK": "Alibaba",
|
|
|
|
| 173 |
}
|
| 174 |
|
| 175 |
# ==============================================================================
|
| 176 |
+
# ๐ ๏ธ [์์ง] ์ง์ & ๋ฐ์ดํฐ ์์ง
|
| 177 |
# ==============================================================================
|
| 178 |
def get_market_indices():
|
| 179 |
+
indices = {"S&P 500": "^GSPC", "NASDAQ": "^IXIC", "KOSPI": "^KS11", "VN-INDEX": "^VNINDEX"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 180 |
data = {}
|
| 181 |
try:
|
| 182 |
+
df = yf.download(list(indices.values()), period="5d", progress=False)['Close']
|
|
|
|
|
|
|
| 183 |
for name, ticker in indices.items():
|
| 184 |
if ticker in df.columns:
|
| 185 |
series = df[ticker].dropna()
|
| 186 |
if len(series) >= 2:
|
| 187 |
+
curr, prev = series.iloc[-1], series.iloc[-2]
|
| 188 |
+
data[name] = (curr, ((curr - prev)/prev)*100)
|
|
|
|
|
|
|
| 189 |
except: pass
|
| 190 |
return data
|
| 191 |
|
|
|
|
|
|
|
|
|
|
| 192 |
FAKE_HEADERS = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36'}
|
| 193 |
|
| 194 |
def fetch_news_robust(keyword):
|
|
|
|
| 197 |
try:
|
| 198 |
with DDGS() as ddgs:
|
| 199 |
results = list(ddgs.news(keyword, timelimit="m", max_results=3))
|
| 200 |
+
if not results: results = list(ddgs.news(keyword, max_results=3))
|
| 201 |
+
if not results: results = list(ddgs.text(f"{keyword} latest news", max_results=3))
|
|
|
|
|
|
|
|
|
|
|
|
|
| 202 |
for r in results:
|
| 203 |
url = r.get('url') or r.get('href')
|
| 204 |
if url not in seen_urls:
|
| 205 |
+
summary += f"[{r.get('date', '?')}] {r.get('title', '')}\n"
|
|
|
|
|
|
|
| 206 |
seen_urls.add(url)
|
| 207 |
except: return "No news."
|
| 208 |
return summary if summary else "No news."
|
|
|
|
| 227 |
elif ".KS" in ticker or ".KQ" in ticker: fdr_symbol = ticker.split('.')[0]
|
| 228 |
hist = fdr.DataReader(fdr_symbol, start=(datetime.datetime.now() - datetime.timedelta(days=7)))
|
| 229 |
if not hist.empty:
|
| 230 |
+
curr, prev = hist['Close'].iloc[-1], hist['Close'].iloc[-2]
|
| 231 |
+
return curr, ((curr - prev)/prev)*100, "FDR"
|
|
|
|
|
|
|
|
|
|
| 232 |
except: pass
|
| 233 |
try:
|
| 234 |
stock = yf.Ticker(ticker)
|
|
|
|
| 246 |
if ".VN" in ticker: fdr_symbol = ticker.split('.')[0]
|
| 247 |
elif ".JK" in ticker: fdr_symbol = f"IDX:{ticker.split('.')[0]}"
|
| 248 |
elif ".T" in ticker: fdr_symbol = f"TSE:{ticker.split('.')[0]}"
|
| 249 |
+
hist = fdr.DataReader(fdr_symbol, start=(datetime.datetime.now() - datetime.timedelta(days=90)).strftime('%Y-%m-%d'))
|
|
|
|
| 250 |
if not hist.empty: return hist.rename(columns={'Close':'Close', 'Open':'Open', 'High':'High', 'Low':'Low'}), "FDR"
|
| 251 |
except: pass
|
| 252 |
try:
|
|
|
|
| 295 |
T = UI_TEXT[lang_code]
|
| 296 |
st.title(T['sidebar_title'])
|
| 297 |
|
|
|
|
| 298 |
st.divider()
|
| 299 |
st.caption(T['sidebar_weather'])
|
|
|
|
| 300 |
market_data = get_market_indices()
|
| 301 |
+
market_context_str = ""
|
| 302 |
|
| 303 |
if market_data:
|
| 304 |
+
c1, c2 = st.columns(2)
|
|
|
|
| 305 |
if "S&P 500" in market_data:
|
| 306 |
p, c = market_data["S&P 500"]
|
| 307 |
+
c1.metric("๐บ๐ธ S&P 500", f"{p:,.0f}", f"{c:+.2f}%")
|
| 308 |
+
market_context_str += f"S&P 500 {c:+.2f}%, "
|
| 309 |
if "NASDAQ" in market_data:
|
| 310 |
p, c = market_data["NASDAQ"]
|
| 311 |
+
c2.metric("๐บ๐ธ NASDAQ", f"{p:,.0f}", f"{c:+.2f}%")
|
| 312 |
+
market_context_str += f"NASDAQ {c:+.2f}%, "
|
| 313 |
+
c3, c4 = st.columns(2)
|
|
|
|
| 314 |
if "KOSPI" in market_data:
|
| 315 |
p, c = market_data["KOSPI"]
|
| 316 |
+
c3.metric("๐ฐ๐ท KOSPI", f"{p:,.0f}", f"{c:+.2f}%")
|
| 317 |
if "VN-INDEX" in market_data:
|
| 318 |
p, c = market_data["VN-INDEX"]
|
| 319 |
+
c4.metric("๐ป๐ณ VN-IDX", f"{p:,.0f}", f"{c:+.2f}%")
|
| 320 |
+
market_context_str += f"Vietnam Index {c:+.2f}%."
|
| 321 |
+
else: st.caption("Loading failed.")
|
|
|
|
| 322 |
|
| 323 |
st.divider()
|
| 324 |
menu = st.radio("MENU", [T['menu_search'], T['menu_scanner']], index=0)
|
| 325 |
|
| 326 |
+
# --- AI ๊ฒ์ ---
|
| 327 |
if menu == T['menu_search']:
|
| 328 |
st.subheader(T['search_title'])
|
| 329 |
c1, c2 = st.columns([3, 1])
|
|
|
|
| 346 |
h, src = get_chart_data(ticker)
|
| 347 |
news_data = get_polyglot_news(eng_key, native_key)
|
| 348 |
curr, pct = "N/A", 0
|
|
|
|
| 349 |
if not h.empty:
|
| 350 |
+
curr, prev = h['Close'].iloc[-1], h['Close'].iloc[-2]
|
| 351 |
+
pct = ((curr - prev)/prev)*100
|
|
|
|
|
|
|
| 352 |
else:
|
| 353 |
c_web, p_web, s_web = get_price_data_robust(ticker, name)
|
| 354 |
if c_web: curr, pct, src = c_web, p_web, s_web
|
|
|
|
| 359 |
|
| 360 |
if not h.empty: st.plotly_chart(plot_candle_chart(h, name, src), use_container_width=True)
|
| 361 |
else: st.warning(f"Chart N/A")
|
|
|
|
| 362 |
with st.expander(T['expander_news']): st.text(news_data)
|
| 363 |
|
| 364 |
collected_data.append(f"[TARGET {i+1}] {name} ({ticker})\nPrice: {curr}, Change: {pct:.2f}%\nNews: {news_data[:500]}...")
|
|
|
|
| 367 |
st.divider()
|
| 368 |
st.subheader(T['insight_title'])
|
| 369 |
|
|
|
|
|
|
|
|
|
|
| 370 |
prompt = f"""
|
| 371 |
+
[ROLE] Global Analyst. [MARKET CONTEXT] {market_context_str}
|
| 372 |
+
[USER QUERY] "{query}" [DATA] {chr(10).join(collected_data)}
|
| 373 |
+
[TASK] Comparative Analysis & Verdict (Consider Relative Strength). [LANG] {T['llm_lang_instruction']}.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 374 |
"""
|
| 375 |
msg = [{"role": "user", "content": prompt}]
|
| 376 |
stream = client.chat.completions.create(model="Qwen/Qwen2.5-72B-Instruct", messages=msg, stream=True)
|
| 377 |
st.write_stream(parse_stream(stream))
|
| 378 |
else: st.error("AI Error")
|
| 379 |
|
| 380 |
+
# --- ์์ฅ ์ค์บ๋ & ๋ฆฌํฌํธ ---
|
| 381 |
elif menu == T['menu_scanner']:
|
| 382 |
st.subheader(T['scanner_title'])
|
| 383 |
st.caption(T['scanner_caption'])
|
|
|
|
| 397 |
for i, t in enumerate(tickers):
|
| 398 |
name_display = TICKER_NAMES.get(t, t)
|
| 399 |
p, c, s = None, None, None
|
|
|
|
| 400 |
if not batch_data.empty and t in batch_data.columns:
|
| 401 |
series = batch_data[t].dropna()
|
| 402 |
if len(series) >= 2:
|
| 403 |
+
p, prev = series.iloc[-1], series.iloc[-2]
|
| 404 |
+
c, s = ((p - prev)/prev)*100, "Yahoo (Batch)"
|
| 405 |
+
if p is None: p, c, s = get_price_data_robust(t, name_display)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 406 |
if p is not None:
|
| 407 |
+
results.append({T['col_name']: name_display, 'Ticker': t, T['col_price']: p, 'Change(%)': c, T['col_source']: s})
|
|
|
|
|
|
|
|
|
|
| 408 |
bar.progress((i+1)/len(tickers))
|
| 409 |
|
| 410 |
if results:
|
|
|
|
| 412 |
st.plotly_chart(plot_bar_chart(df, T), use_container_width=True)
|
| 413 |
|
| 414 |
disp_cols = [T['col_name'], 'Ticker', T['col_price'], 'Change(%)', T['col_source']]
|
|
|
|
| 415 |
df_gainers = df[df['Change(%)'] > 0].head(10)
|
| 416 |
df_losers = df[df['Change(%)'] < 0].sort_values('Change(%)', ascending=True).head(10)
|
| 417 |
|
| 418 |
+
# [NEW] AI Market Briefing (์์ฅ ์์ฝ ๋ฆฌํฌํธ)
|
| 419 |
+
st.divider()
|
| 420 |
+
st.subheader(T['briefing_title'])
|
| 421 |
+
|
| 422 |
+
# AI์๊ฒ ๋์ง ๋ฐ์ดํฐ ์์ฝ
|
| 423 |
+
gainers_str = ", ".join([f"{r[T['col_name']]} ({r['Change(%)']:.2f}%)" for _, r in df_gainers.head(5).iterrows()])
|
| 424 |
+
losers_str = ", ".join([f"{r[T['col_name']]} ({r['Change(%)']:.2f}%)" for _, r in df_losers.head(5).iterrows()])
|
| 425 |
+
|
| 426 |
+
prompt = f"""
|
| 427 |
+
[ROLE] Chief Market Strategist.
|
| 428 |
+
[TARGET MARKET] {target}
|
| 429 |
+
[GLOBAL CONTEXT] {market_context_str}
|
| 430 |
+
[SCAN DATA]
|
| 431 |
+
- Top Gainers: {gainers_str}
|
| 432 |
+
- Top Losers: {losers_str}
|
| 433 |
+
|
| 434 |
+
[TASK]
|
| 435 |
+
1. **Market Summary**: Briefly describe today's market sentiment based on gainers/losers.
|
| 436 |
+
2. **Sector Insight**: Why are these stocks moving? (e.g., Tech rally, Energy dip).
|
| 437 |
+
3. **Top Pick**: Recommend 1 stock from the gainers with strong momentum.
|
| 438 |
+
4. **Caution**: Warn about 1 stock/sector from the losers.
|
| 439 |
+
|
| 440 |
+
[OUTPUT LANGUAGE] **{T['llm_lang_instruction']}** (Use professional financial tone).
|
| 441 |
+
"""
|
| 442 |
+
|
| 443 |
+
# ๋ฆฌํฌํธ ์คํธ๋ฆฌ๋ฐ
|
| 444 |
+
msg = [{"role": "user", "content": prompt}]
|
| 445 |
+
stream = client.chat.completions.create(model="Qwen/Qwen2.5-72B-Instruct", messages=msg, stream=True)
|
| 446 |
+
st.write_stream(parse_stream(stream))
|
| 447 |
+
st.divider()
|
| 448 |
+
|
| 449 |
+
# ๊ธฐ์กด ๋ฐ์ดํฐํ๋ ์ ํ์
|
| 450 |
c_up, c_down = st.columns(2)
|
| 451 |
with c_up:
|
| 452 |
st.success(T['tab_gainers'])
|