streamlit_app.py

import streamlit as st
import yfinance as yf
import FinanceDataReader as fdr
import pandas as pd
import plotly.graph_objects as go
from huggingface_hub import InferenceClient
from duckduckgo_search import DDGS
import json
import datetime
import re
import time
import random

# 1. 페이지 설정
st.set_page_config(page_title="Pocket Quant AI", page_icon="🧠", layout="wide")

# 2. 토큰 확인
if "HF_TOKEN" in st.secrets:
    client = InferenceClient(api_key=st.secrets["HF_TOKEN"])
else:
    st.error("🚨 HF_TOKEN required in secrets.")
    st.stop()

# ==============================================================================
# 🌐 [UI] 다국어 딕셔너리
# ==============================================================================
UI_TEXT = {
    "KR": {
        "sidebar_title": "🧠 Pocket Quant AI",
        "sidebar_weather": "📊 오늘의 시장 날씨 (Market Weather)",
        "menu_search": "🔍 AI 스마트 검색 (실적+뉴스)",
        "menu_scanner": "📡 글로벌 시장 스캐너",
        "search_title": "🧠 AI 주식 비서 (분기 실적 분석)",
        "search_placeholder": "예: 삼성전자 실적 분석, 몽골 고비 캐시미어...",
        "btn_analyze": "분석 시작",
        "status_thinking": "🧠 AI가 분기 실적과 시장을 분석 중입니다...",
        "status_news": "📰 뉴스 및 재무제표 수집 중...",
        "metric_price": "현재가",
        "metric_source": "출처",
        "expander_news": "📰 뉴스 원문 보기",
        "insight_title": "🧠 AI 종합 분석 리포트",
        "scanner_title": "📡 글로벌 시장 전광판 (Frontier Included)",
        "scanner_caption": "※ 100개 스캔 후, 상위 종목의 분기 실적 흐름을 분석합니다.",
        "btn_scan": "전체 종목 스캔 & AI 리포트",
        "tab_gainers": "🔥 급등 Top 10",
        "tab_losers": "💧 급락 Top 10",
        "col_name": "기업명",
        "col_price": "가격",
        "col_change": "등락률",
        "col_per": "PER",
        "col_pbr": "PBR",
        "col_source": "출처",
        "briefing_title": "🧠 AI Market Briefing (오늘의 시장 분석)",
        "msg_fail": "데이터 수집 실패",
        "llm_lang_instruction": "Korean"
    },
    "EN": {
        "sidebar_title": "🧠 Pocket Quant AI",
        "sidebar_weather": "📊 Market Weather",
        "menu_search": "🔍 AI Smart Search (Financials)",
        "menu_scanner": "📡 Global Market Scanner",
        "search_title": "🧠 AI Stock Assistant (Quarterly Analysis)",
        "search_placeholder": "e.g. Analyze Samsung Electronics financials...",
        "btn_analyze": "Analyze",
        "status_thinking": "🧠 AI is analyzing quarterly financials...",
        "status_news": "📰 Fetching news & financials...",
        "metric_price": "Price",
        "metric_source": "Source",
        "expander_news": "📰 View Source News",
        "insight_title": "🧠 AI Comprehensive Report",
        "scanner_title": "📡 Global Market Scanner (Frontier Included)",
        "scanner_caption": "※ Scans stocks, then analyzes quarterly trends for top movers.",
        "btn_scan": "Scan & Generate Report",
        "tab_gainers": "🔥 Top 10 Gainers",
        "tab_losers": "💧 Top 10 Losers",
        "col_name": "Company",
        "col_price": "Price",
        "col_change": "Change(%)",
        "col_per": "PER",
        "col_pbr": "PBR",
        "col_source": "Source",
        "briefing_title": "🧠 AI Market Briefing",
        "msg_fail": "Data collection failed",
        "llm_lang_instruction": "English"
    }
}

# ==============================================================================
# 💾 [데이터] 티커 매핑 (Full List)
# ==============================================================================
TICKER_NAMES = {
    # (기존 리스트 유지 - 너무 길어서 생략하지만 실제 코드엔 꼭 넣으세요!)
    "VIC.VN": "Vingroup", "VHM.VN": "Vinhomes", "VCB.VN": "Vietcombank", "VNM.VN": "Vinamilk",
    "005930.KS": "Samsung Elec", "000660.KS": "SK Hynix", "AAPL": "Apple", "NVDA": "NVIDIA",
    "APU.MN": "APU JSC", "GP.BD": "Grameenphone", # Frontier
    # ... (나머지 국가들 포함) ...
}

# (스캐너용 MARKET_SAMPLES도 기존 유지)
MARKET_SAMPLES = {
    "🇻🇳 Vietnam": ["VIC.VN", "VHM.VN", "VRE.VN", "VNM.VN", "MSN.VN", "GAS.VN", "HPG.VN", "NVL.VN", "PDR.VN", "DIG.VN", "SSI.VN", "VND.VN", "MWG.VN", "FRT.VN", "FPT.VN", "STB.VN", "TCB.VN", "VCB.VN"],
    "🇺🇸 USA": ["AAPL", "MSFT", "GOOGL", "AMZN", "NVDA", "META", "TSLA", "AMD", "INTC", "PLTR", "COIN", "LLY", "XOM", "DIS"],
    "🇰🇷 Korea": ["005930.KS", "000660.KS", "005380.KS", "000270.KS", "035420.KS", "035720.KS", "005490.KS", "086520.KQ", "247540.KQ", "207940.KS"],
    "🇲🇳 Mongolia (Frontier)": ["APU.MN", "TTL.MN", "GOV.MN", "MNDL.MN", "SUU.MN"],
    "🇧🇩 Bangladesh (Frontier)": ["GP.BD", "SQURPHARMA.BD", "BATBC.BD", "BEXIMCO.BD"],
    "🇭🇰 Hong Kong": ["1299.HK", "0388.HK", "0005.HK", "0700.HK", "9988.HK", "3690.HK"],
    "🇹🇭 Thailand": ["PTT.BK", "AOT.BK", "CPALL.BK", "ADVANC.BK", "KBANK.BK"],
    "🇮🇩 Indonesia": ["BBCA.JK", "BBRI.JK", "BMRI.JK", "TLKM.JK", "ASII.JK", "GOTO.JK"],
    "🇹🇼 Taiwan": ["2330.TW", "2317.TW", "2454.TW", "2881.TW", "2308.TW"],
    "🇯🇵 Japan": ["7203.T", "6758.T", "9984.T", "8035.T", "6861.T"],
    "🇮🇳 India": ["RELIANCE.NS", "TCS.NS", "HDFCBANK.NS", "INFY.NS"]
}


# ==============================================================================
# 🛠️ [엔진] 지수 & 데이터 수집 (Fundamentals 강화)
# ==============================================================================
def get_market_indices():
    indices = {"S&P 500": "^GSPC", "NASDAQ": "^IXIC", "KOSPI": "^KS11", "VN-INDEX": "^VNINDEX"}
    data = {}
    try:
        df = yf.download(list(indices.values()), period="5d", progress=False)['Close']
        for name, ticker in indices.items():
            if ticker in df.columns:
                series = df[ticker].dropna()
                if len(series) >= 2:
                    curr, prev = series.iloc[-1], series.iloc[-2]
                    data[name] = (curr, ((curr - prev)/prev)*100)
    except: pass
    return data

# [NEW] 재무 데이터 + 분기 실적 가져오기
def get_fundamentals(ticker):
    """
    기본 지표(PER/PBR) + 최근 4분기 실적(매출/이익) 추출
    """
    data = {"PER": "N/A", "PBR": "N/A", "ROE": "N/A", "Quarterly": pd.DataFrame()}
    try:
        stock = yf.Ticker(ticker)
        info = stock.info
        
        # 1. 기본 지표
        per = info.get('trailingPE')
        pbr = info.get('priceToBook')
        roe = info.get('returnOnEquity')
        data["PER"] = f"{per:.2f}" if per else "N/A"
        data["PBR"] = f"{pbr:.2f}" if pbr else "N/A"
        data["ROE"] = f"{roe*100:.2f}%" if roe else "N/A"

        # 2. 분기별 실적 (최근 4분기)
        q_fin = stock.quarterly_financials
        if not q_fin.empty:
            # 주요 항목만 추출 (Total Revenue, Net Income) - 키 이름은 야후 버전에 따라 다를 수 있어 예외처리
            target_rows = [r for r in ['Total Revenue', 'Operating Revenue', 'Net Income', 'Net Income Common Stockholders'] if r in q_fin.index]
            if target_rows:
                # 최근 4개 분기만, 보기 좋게 Transpose
                recent_q = q_fin.loc[target_rows].iloc[:, :4].T
                # 날짜 포맷 정리 (YYYY-MM-DD)
                recent_q.index = [d.strftime('%Y-%m') for d in recent_q.index]
                data["Quarterly"] = recent_q
    except: pass
    return data

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'}

def fetch_news_robust(keyword):
    summary = ""
    seen_urls = set()
    try:
        with DDGS() as ddgs:
            results = list(ddgs.news(keyword, timelimit="m", max_results=3))
            if not results: results = list(ddgs.news(keyword, max_results=3))
            if not results: results = list(ddgs.text(f"{keyword} latest news", max_results=3))
            for r in results:
                url = r.get('url') or r.get('href')
                if url not in seen_urls:
                    summary += f"[{r.get('date', '?')}] {r.get('title', '')}\n"
                    seen_urls.add(url)
    except: return "No news."
    return summary if summary else "No news."

def scrape_price_from_web(name, ticker):
    try:
        time.sleep(random.uniform(1.0, 1.5))
        with DDGS() as ddgs:
            query = f"{name} {ticker} stock price quote today"
            results = ddgs.text(query, max_results=2)
            blob = " ".join([r['body'] for r in results])
            match = re.search(r'(\d{1,3}(,\d{3})*(\.\d+)?)', blob)
            if match: return float(match.group(0).replace(",", "")), 0.0
    except: pass
    return None, None

def get_price_data_robust(ticker, name):
    try:
        fdr_symbol = ticker
        if ".VN" in ticker: fdr_symbol = ticker.split('.')[0]
        elif ".JK" in ticker: fdr_symbol = f"IDX:{ticker.split('.')[0]}"
        elif ".KS" in ticker or ".KQ" in ticker: fdr_symbol = ticker.split('.')[0]
        hist = fdr.DataReader(fdr_symbol, start=(datetime.datetime.now() - datetime.timedelta(days=7)))
        if not hist.empty:
            curr, prev = hist['Close'].iloc[-1], hist['Close'].iloc[-2]
            return curr, ((curr - prev)/prev)*100, "FDR"
    except: pass
    try:
        stock = yf.Ticker(ticker)
        price = stock.fast_info.last_price
        prev = stock.fast_info.previous_close
        if price and prev: return price, ((price - prev)/prev)*100, "Yahoo"
    except: pass
    price, pct = scrape_price_from_web(name, ticker)
    if price is not None: return price, pct, "Web Search"
    return None, None, "Fail"

def get_chart_data(ticker):
    try:
        fdr_symbol = ticker
        if ".VN" in ticker: fdr_symbol = ticker.split('.')[0]
        elif ".JK" in ticker: fdr_symbol = f"IDX:{ticker.split('.')[0]}"
        elif ".T" in ticker: fdr_symbol = f"TSE:{ticker.split('.')[0]}"
        hist = fdr.DataReader(fdr_symbol, start=(datetime.datetime.now() - datetime.timedelta(days=90)).strftime('%Y-%m-%d'))
        if not hist.empty: return hist.rename(columns={'Close':'Close', 'Open':'Open', 'High':'High', 'Low':'Low'}), "FDR"
    except: pass
    try:
        hist = yf.Ticker(ticker).history(period="3mo")
        if not hist.empty: return hist, "Yahoo"
    except: pass
    return pd.DataFrame(), "None"

def identify_targets_with_ai(user_query):
    try:
        prompt = f"""
        [ROLE] Entity Resolver. [QUERY] "{user_query}"
        [TASK] Identify ALL companies. [OUTPUT JSON LIST]
        [ {{ "name": "EngName", "ticker": "TICKER", "eng_key": "Name news", "native_key": "LocalName news" }} ]
        """
        messages = [{"role": "user", "content": prompt}]
        response = client.chat.completions.create(model="Qwen/Qwen2.5-72B-Instruct", messages=messages, max_tokens=300)
        content = re.sub(r"```json|```", "", response.choices[0].message.content.strip()).strip()
        return json.loads(content)
    except: return []

def get_polyglot_news(eng_key, native_key):
    return f"Global:\n{fetch_news_robust(eng_key)}\nLocal:\n{fetch_news_robust(native_key)}"

def parse_stream(stream):
    for chunk in stream:
        if chunk.choices: yield chunk.choices[0].delta.content or ""

def plot_candle_chart(hist, title, source):
    fig = go.Figure(data=[go.Candlestick(x=hist.index, open=hist['Open'], high=hist['High'], low=hist['Low'], close=hist['Close'], name="Price")])
    fig.update_layout(title=f"{title} ({source})", height=350, margin=dict(l=10, r=10, t=30, b=10), template="plotly_dark", paper_bgcolor='rgba(0,0,0,0)')
    return fig

def plot_bar_chart(df, lang_data):
    target_col = lang_data['col_name']
    colors = ['#00FF00' if x > 0 else '#FF0000' for x in df['Change(%)']]
    fig = go.Figure(go.Bar(x=df[target_col], y=df['Change(%)'], marker_color=colors, text=df['Change(%)'].apply(lambda x: f"{x:.2f}%")))
    fig.update_layout(title="Market Heatmap", height=350, margin=dict(l=10, r=10, t=30, b=10), template="plotly_dark", paper_bgcolor='rgba(0,0,0,0)')
    return fig

# ==============================================================================
# UI
# ==============================================================================
with st.sidebar:
    lang_code = st.selectbox("Language / 언어", ["KR", "EN"])
    T = UI_TEXT[lang_code]
    st.title(T['sidebar_title'])
    
    st.divider()
    st.caption(T['sidebar_weather'])
    market_data = get_market_indices()
    market_context_str = ""
    
    if market_data:
        c1, c2 = st.columns(2)
        if "S&P 500" in market_data:
            p, c = market_data["S&P 500"]
            c1.metric("🇺🇸 S&P 500", f"{p:,.0f}", f"{c:+.2f}%")
            market_context_str += f"S&P 500 {c:+.2f}%, "
        if "NASDAQ" in market_data:
            p, c = market_data["NASDAQ"]
            c2.metric("🇺🇸 NASDAQ", f"{p:,.0f}", f"{c:+.2f}%")
            market_context_str += f"NASDAQ {c:+.2f}%, "
        c3, c4 = st.columns(2)
        if "KOSPI" in market_data:
            p, c = market_data["KOSPI"]
            c3.metric("🇰🇷 KOSPI", f"{p:,.0f}", f"{c:+.2f}%")
        if "VN-INDEX" in market_data:
            p, c = market_data["VN-INDEX"]
            c4.metric("🇻🇳 VN-IDX", f"{p:,.0f}", f"{c:+.2f}%")
            market_context_str += f"Vietnam Index {c:+.2f}%."
    else: st.caption("Loading failed.")
    
    st.divider()
    menu = st.radio("MENU", [T['menu_search'], T['menu_scanner']], index=0)

# --- AI 검색 (재무제표 + 분기 실적 포함) ---
if menu == T['menu_search']:
    st.subheader(T['search_title'])
    c1, c2 = st.columns([3, 1])
    with c1: query = st.text_input("Query", placeholder=T['search_placeholder'], label_visibility="collapsed")
    with c2: btn = st.button(T['btn_analyze'], use_container_width=True)

    if btn:
        with st.status(T['status_thinking'], expanded=True) as status:
            targets = identify_targets_with_ai(query)
            if targets:
                collected_data = []
                tabs = st.tabs([t.get('name', 'Unknown') for t in targets])
                
                for i, target in enumerate(targets):
                    name, ticker = target.get('name'), target.get('ticker')
                    eng_key, native_key = target.get('eng_key'), target.get('native_key')
                    
                    with tabs[i]:
                        st.info(f"📍 **{name} ({ticker})**")
                        
                        # [NEW] 재무 데이터 (분기 포함)
                        fund_data = get_fundamentals(ticker)
                        q_df = fund_data['Quarterly']
                        
                        # 기본 지표 카드
                        f1, f2, f3 = st.columns(3)
                        f1.metric("PER", fund_data["PER"])
                        f2.metric("PBR", fund_data["PBR"])
                        f3.metric("ROE", fund_data["ROE"])
                        
                        # [NEW] 분기 실적 표 (있을 경우만)
                        if not q_df.empty:
                            st.caption("📊 Recent Quarterly Financials (4 Quarters)")
                            st.dataframe(q_df.style.format("{:,.0f}"), use_container_width=True)
                        else:
                            st.caption("⚠️ No quarterly data available via API.")
                        
                        st.divider()

                        h, src = get_chart_data(ticker)
                        news_data = get_polyglot_news(eng_key, native_key)
                        curr, pct = "N/A", 0
                        if not h.empty:
                            curr, prev = h['Close'].iloc[-1], h['Close'].iloc[-2]
                            pct = ((curr - prev)/prev)*100
                        else:
                            c_web, p_web, s_web = get_price_data_robust(ticker, name)
                            if c_web: curr, pct, src = c_web, p_web, s_web
                        
                        m1, m2 = st.columns(2)
                        m1.metric(T['metric_price'], f"{curr:,.0f}" if isinstance(curr, (int, float)) else curr, f"{pct:.2f}%")
                        m2.metric(T['metric_source'], src)
                        
                        if not h.empty: st.plotly_chart(plot_candle_chart(h, name, src), use_container_width=True)
                        else: st.warning(f"Chart N/A")
                        with st.expander(T['expander_news']): st.text(news_data)
                        
                        # AI에게 줄 데이터에 분기 실적 추가
                        q_str = q_df.to_string() if not q_df.empty else "N/A"
                        collected_data.append(f"""
                        [TARGET {i+1}] {name} ({ticker})
                        - Price: {curr}, Change: {pct:.2f}%
                        - Fundamentals: PER {fund_data['PER']}, PBR {fund_data['PBR']}, ROE {fund_data['ROE']}
                        - Quarterly Trend: \n{q_str}
                        - News: {news_data[:500]}...
                        """)
                
                status.update(label="✅ OK", state="complete", expanded=False)
                st.divider()
                st.subheader(T['insight_title'])
                
                prompt = f"""
                [ROLE] Global Analyst. [MARKET CONTEXT] {market_context_str}
                [USER QUERY] "{query}" [DATA] {chr(10).join(collected_data)}
                [TASK]
                1. Comparative Analysis based on price and FUNDAMENTALS (Valuation).
                2. Analyze QUARTERLY TRENDS (Revenue/Income growing or shrinking?).
                3. Verdict based on Market Context + Fundamentals + News.
                [LANG] {T['llm_lang_instruction']}.
                """
                msg = [{"role": "user", "content": prompt}]
                stream = client.chat.completions.create(model="Qwen/Qwen2.5-72B-Instruct", messages=msg, stream=True)
                st.write_stream(parse_stream(stream))
            else: st.error("AI Error")

# --- 시장 스캐너 & 리포트 (Top 10 분기 실적 추가) ---
elif menu == T['menu_scanner']:
    st.subheader(T['scanner_title'])
    st.caption(T['scanner_caption'])
    
    c1, c2 = st.columns([3, 1])
    with c1: target = st.selectbox("Market", list(MARKET_SAMPLES.keys()), label_visibility="collapsed")
    with c2: scan = st.button(T['btn_scan'])
        
    if scan:
        tickers = MARKET_SAMPLES[target]
        results = []
        bar = st.progress(0)
        
        try: batch_data = yf.download(tickers, period="5d", progress=False)['Close']
        except: batch_data = pd.DataFrame()
        
        for i, t in enumerate(tickers):
            name_display = TICKER_NAMES.get(t, t)
            p, c, s = None, None, None
            if not batch_data.empty and t in batch_data.columns:
                series = batch_data[t].dropna()
                if len(series) >= 2:
                    p, prev = series.iloc[-1], series.iloc[-2]
                    c, s = ((p - prev)/prev)*100, "Yahoo (Batch)"
            if p is None: p, c, s = get_price_data_robust(t, name_display)
            if p is not None:
                results.append({T['col_name']: name_display, 'Ticker': t, T['col_price']: p, 'Change(%)': c, T['col_source']: s})
            bar.progress((i+1)/len(tickers))
        
        if results:
            df = pd.DataFrame(results).sort_values('Change(%)', ascending=False)
            st.plotly_chart(plot_bar_chart(df, T), use_container_width=True)
            
            # [NEW] Top 10 Gainers/Losers에 대해서만 재무 데이터 및 실적 추이 추가 로딩
            df_gainers = df[df['Change(%)'] > 0].head(10).copy()
            df_losers = df[df['Change(%)'] < 0].sort_values('Change(%)', ascending=True).head(10).copy()
            
            # AI에게 줄 요약 텍스트를 담을 리스트
            gainers_analysis_data = []
            losers_analysis_data = []

            def process_funds(sub_df, analysis_list):
                if sub_df.empty: return sub_df
                pers, pbrs = [], []
                for idx, row in sub_df.iterrows():
                    t = row['Ticker']
                    f = get_fundamentals(t) # 분기 실적도 여기서 가져옴
                    pers.append(f['PER'])
                    pbrs.append(f['PBR'])
                    
                    # AI에게 넘길 데이터 문자열 생성 (종목명, 등락률, PER, 분기 추이)
                    q_data = "N/A"
                    if not f['Quarterly'].empty:
                        # 데이터프레임을 문자열로 (최근 2분기만 간략하게)
                        q_data = f['Quarterly'].iloc[:, :2].to_string()
                    
                    analysis_list.append(f"{row[T['col_name']]} ({row['Change(%)']:.1f}%, PER:{f['PER']}) -> Quarterly:\n{q_data}")
                
                sub_df[T['col_per']] = pers
                sub_df[T['col_pbr']] = pbrs
                return sub_df

            with st.spinner("Analyzing fundamentals & quarterly trends for top movers..."):
                df_gainers = process_funds(df_gainers, gainers_analysis_data)
                df_losers = process_funds(df_losers, losers_analysis_data)

            disp_cols = [T['col_name'], 'Ticker', T['col_price'], 'Change(%)', T['col_per'], T['col_pbr'], T['col_source']]
            
            # AI Market Briefing
            st.divider()
            st.subheader(T['briefing_title'])
            
            prompt = f"""
            [ROLE] Chief Market Strategist.
            [TARGET MARKET] {target}
            [GLOBAL CONTEXT] {market_context_str}
            
            [TOP GAINERS DATA (With Quarterly Trends)]
            {chr(10).join(gainers_analysis_data)}
            
            [TOP LOSERS DATA (With Quarterly Trends)]
            {chr(10).join(losers_analysis_data)}
            
            [TASK]
            1. **Market Summary**: Sentiment analysis.
            2. **Fundamental Check**: Are the gainers actually making money? (Check Quarterly Revenue/Income trends).
            3. **Top Pick**: Recommend 1 solid stock (Good price action + Good financials).
            4. **Caution**: Warn about a risky stock (Bad financials).
            [OUTPUT LANGUAGE] **{T['llm_lang_instruction']}** (Professional tone).
            """
            
            msg = [{"role": "user", "content": prompt}]
            stream = client.chat.completions.create(model="Qwen/Qwen2.5-72B-Instruct", messages=msg, stream=True)
            st.write_stream(parse_stream(stream))
            st.divider()

            c_up, c_down = st.columns(2)
            with c_up:
                st.success(T['tab_gainers'])
                if not df_gainers.empty: st.dataframe(df_gainers[disp_cols].style.format({T['col_price']: "{:,.2f}", "Change(%)": "{:,.2f}%"}), use_container_width=True)
                else: st.info("No gainers.")
            with c_down:
                st.error(T['tab_losers'])
                if not df_losers.empty: st.dataframe(df_losers[disp_cols].style.format({T['col_price']: "{:,.2f}", "Change(%)": "{:,.2f}%"}), use_container_width=True)
                else: st.info("No losers.")
        else: st.warning(T['msg_fail'])