Update app.py

app.py

@@ -1,220 +1,203 @@
 import streamlit as st
-import pandas as pd
 import requests
-import yfinance as yf
+import pandas as pd
+from datetime import datetime, timedelta
 from transformers import pipeline
 from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer
 from textblob import TextBlob
-from datetime import datetime, timedelta
-import plotly.graph_objects as go
 import nltk
+from wordcloud import WordCloud
+import base64
+from io import BytesIO
 import numpy as np
-from sklearn.linear_model import Ridge
-from sklearn.preprocessing import PolynomialFeatures
-from sklearn.pipeline import make_pipeline
-import os
-
-# -------------------------------
-# 🔧 CONFIG
-# -------------------------------
-st.set_page_config(page_title="📈 News Sentiment & Stock Tracker", layout="wide")
+from sklearn.linear_model import LinearRegression
+import plotly.graph_objects as go
+
+# --------------------------
+# CONFIG
+# --------------------------
+st.set_page_config(page_title="📰 SentimentSync NewsAI", layout="wide")
 API_KEY = "88bc396d4eab4be494a4b86ec842db47"
 
-# -------------------------------
-# 📦 โหลดโมเดล
-# -------------------------------
+# --------------------------
+# UTILITIES
+# --------------------------
 @st.cache_resource
 def load_models():
-    bert = pipeline("sentiment-analysis", model="nlptown/bert-base-multilingual-uncased-sentiment")
+    st.info("Loading sentiment models...")
+    bert_model = pipeline("sentiment-analysis", model="nlptown/bert-base-multilingual-uncased-sentiment")
     vader = SentimentIntensityAnalyzer()
-    return bert, vader
-
-bert_model, vader_analyzer = load_models()
-
-# -------------------------------
-# 🧠 ฟังก์ชันแปลงชื่อบริษัท <-> ตัวย่อหุ้น
-# -------------------------------
-@st.cache_data(ttl=86400)
-def resolve_company_symbol(keyword: str):
-    keyword = keyword.strip()
-    ticker = None
-    name = None
-    try:
-        data = yf.Ticker(keyword)
-        info = data.info
-        if "symbol" in info and info["symbol"]:
-            ticker = info["symbol"]
-            name = info.get("longName", info.get("shortName", keyword))
-        else:
-            url = f"https://query2.finance.yahoo.com/v1/finance/search?q={keyword}"
-            res = requests.get(url).json()
-            if "quotes" in res and len(res["quotes"]) > 0:
-                q = res["quotes"][0]
-                ticker = q.get("symbol")
-                name = q.get("longname", q.get("shortname", keyword))
-    except Exception as e:
-        st.warning(f"⚠️ ไม่สามารถค้นหาข้อมูลบริษัทได้: {e}")
-
-    if not ticker:
-        ticker = keyword.upper()
-    if not name:
-        name = keyword.capitalize()
-    return name, ticker
-
-# -------------------------------
-# 📰 ดึงข่าวย้อนหลัง 7 วัน
-# -------------------------------
-@st.cache_data(ttl=3600)
-def fetch_news(company, symbol):
-    to_date = datetime.utcnow()
-    from_date = to_date - timedelta(days=7)
-    query = f"({company} OR {symbol}) finance stock"
-
-    url = (
-        f"https://newsapi.org/v2/everything?"
-        f"q={query}&from={from_date.date()}&to={to_date.isoformat()}&"
-        f"language=en&sortBy=publishedAt&pageSize=100&apiKey={API_KEY}"
-    )
+    return bert_model, vader
 
-    res = requests.get(url)
-    data = res.json()
-    if data.get("status") != "ok":
-        st.error("❌ ดึงข้อมูลข่าวไม่สำเร็จ")
-        return pd.DataFrame()
-
-    articles = data.get("articles", [])
-    df = pd.DataFrame([{
-        "date": datetime.fromisoformat(a["publishedAt"].replace("Z", "+00:00")),
-        "title": a["title"],
-        "description": a["description"],
-        "source": a["source"]["name"],
-        "url": a["url"],
-    } for a in articles])
-
-    df["text"] = df["title"].fillna('') + " " + df["description"].fillna('')
-    df["company"] = company
-    df["symbol"] = symbol
-    return df
-
-# -------------------------------
-# 💬 วิเคราะห์อารมณ์ข่าว
-# -------------------------------
-def analyze_sentiment(text, models):
-    bert, vader = models
+
+def analyze_text(text, bert_model, vader):
     if not text.strip():
         return 0
-    try:
-        vader_score = vader.polarity_scores(text)["compound"]
-        tb_score = TextBlob(text).sentiment.polarity
-        bert_res = bert(text[:512])[0]
-        label_map = {
-            "1 star": -1, "2 stars": -0.5, "3 stars": 0,
-            "4 stars": 0.5, "5 stars": 1
-        }
-        bert_score = label_map.get(bert_res["label"], 0)
-        return np.mean([vader_score, tb_score, bert_score])
-    except Exception:
-        return 0
 
-# -------------------------------
-# 📈 สร้างโมเดลพยากรณ์
-# -------------------------------
-def forecast_sentiment_trend(df):
-    # ensure datetime format
-    df["date"] = pd.to_datetime(df["date"], errors="coerce")
-    df = df.dropna(subset=["date"])
-    df_daily = df.groupby(df["date"].dt.date)["sentiment"].mean().reset_index()
-    df_daily["date"] = pd.to_datetime(df_daily["date"])
-    df_daily["days"] = (df_daily["date"] - df_daily["date"].min()).dt.days
-
-    X = df_daily["days"].values.reshape(-1, 1)
-    y = df_daily["sentiment"].values
-    model = make_pipeline(PolynomialFeatures(2), Ridge(alpha=1.0))
-    model.fit(X, y)
-
-    last_day = df_daily["days"].max()
-    future_days = np.arange(last_day + 1, last_day + 8).reshape(-1, 1)
-    future_preds = model.predict(future_days)
-    future_dates = [df_daily["date"].max() + timedelta(days=i) for i in range(1, 8)]
-    forecast_df = pd.DataFrame({"date": future_dates, "predicted_sentiment": future_preds})
-
-    return df_daily, forecast_df
-
-# -------------------------------
-# 📊 ส่วนแสดงผลหลัก
-# -------------------------------
-st.title("📈 News Sentiment & Stock Tracker")
-
-keyword = st.text_input("🔍 ค้นหาบริษัทหรือตัวย่อหุ้น (เช่น Apple หรือ AAPL):", "AAPL")
-if st.button("Analyze"):
-    company, symbol = resolve_company_symbol(keyword)
-    st.info(f"📊 กำลังวิเคราะห์ข่าวของ **{company} ({symbol})**...")
-
-    news_df = fetch_news(company, symbol)
-    if news_df.empty:
-        st.warning("ไม่พบข่าวในช่วง 7 วันที่ผ่านมา")
-        st.stop()
+    vader_score = vader.polarity_scores(text)["compound"]
+    textblob_score = TextBlob(text).sentiment.polarity
+    bert_result = bert_model(text[:512])[0]
+    label_map = {
+        "1 star": -1,
+        "2 stars": -0.5,
+        "3 stars": 0,
+        "4 stars": 0.5,
+        "5 stars": 1
+    }
+    bert_score = label_map.get(bert_result["label"], 0)
+    return np.mean([vader_score, textblob_score, bert_score])
 
-    news_df["sentiment"] = news_df["text"].apply(lambda x: analyze_sentiment(x, (bert_model, vader_analyzer)))
 
-    avg_sent = news_df["sentiment"].mean()
-    st.metric("📈 ค่าเฉลี่ยอารมณ์ข่าว (7 วัน)", f"{avg_sent:.2f}",
-              "Positive" if avg_sent > 0 else "Negative" if avg_sent < 0 else "Neutral")
-
-    # -------------------------------
-    # 📈 แนวโน้มอารมณ์ + ราคาหุ้น
-    # -------------------------------
-    st.subheader("📊 แนวโน้มอารมณ์ข่าว & ราคาหุ้น")
-
-    df_actual, df_forecast = forecast_sentiment_trend(news_df)
-
-    # ดึงราคาหุ้นจาก yfinance
-    price_df = yf.download(symbol, period="14d", interval="1d")
-    price_df = price_df.reset_index()[["Date", "Close"]]
-    price_df.rename(columns={"Date": "date"}, inplace=True)
-    price_df["date"] = pd.to_datetime(price_df["date"]).dt.date
-    df_actual["date"] = pd.to_datetime(df_actual["date"]).dt.date
-    df_forecast["date"] = pd.to_datetime(df_forecast["date"]).dt.date
-
-    # สร้างกราฟรวม
+@st.cache_data(ttl=3600)
+def fetch_financial_news(keyword):
+    """ดึงข่าวย้อนหลัง 7 วันจาก NewsAPI.org"""
+    to_date = datetime.now().strftime('%Y-%m-%d')
+    from_date = (datetime.now() - timedelta(days=7)).strftime('%Y-%m-%d')
+
+    all_articles = []
+    page = 1
+    while True:
+        url = (
+            f"https://newsapi.org/v2/everything?"
+            f"q={keyword}+finance+stock&"
+            f"from={from_date}&to={to_date}&"
+            f"language=en&sortBy=publishedAt&"
+            f"pageSize=100&page={page}&apiKey={API_KEY}"
+        )
+        r = requests.get(url)
+        data = r.json()
+
+        if data.get("status") != "ok":
+            st.error(f"API Error: {data}")
+            break
+
+        articles = data.get("articles", [])
+        if not articles:
+            break
+
+        for a in articles:
+            if a["description"]:
+                all_articles.append({
+                    "date": pd.to_datetime(a["publishedAt"]),
+                    "text": f"{a['title']} {a['description']}",
+                    "source": a["source"]["name"],
+                    "url": a["url"]
+                })
+
+        if len(articles) < 100:
+            break  # หมดแล้ว
+        page += 1
+
+    return pd.DataFrame(all_articles)
+
+
+def generate_wordcloud(text):
+    stopwords = nltk.corpus.stopwords.words('english')
+    wordcloud = WordCloud(width=800, height=400, background_color="white", stopwords=stopwords).generate(text)
+    buf = BytesIO()
+    wordcloud.to_image().save(buf, format="PNG")
+    return base64.b64encode(buf.getvalue()).decode()
+
+
+# --------------------------
+# MAIN APP
+# --------------------------
+def main():
+    st.title("📰 SentimentSync NewsAI")
+    st.markdown("วิเคราะห์แนวโน้มอารมณ์ของข่าวการเงินย้อนหลัง 7 วัน พร้���มพยากรณ์แนวโน้มในอนาคต")
+
+    # Sidebar
+    with st.sidebar:
+        keyword = st.text_input("ค้นหาคำ (เช่น Tesla, Bitcoin, Inflation):", "")
+        analyze_btn = st.button("วิเคราะห์เลย")
+
+    if not analyze_btn:
+        st.info("กรอกคำค้นแล้วกด 'วิเคราะห์เลย' เพื่อเริ่มต้น")
+        return
+
+    bert_model, vader = load_models()
+
+    # ดึงข่าว
+    st.info(f"กำลังดึงข่าวย้อนหลัง 7 วันจาก NewsAPI.org สำหรับ '{keyword}' ...")
+    news_df = fetch_financial_news(keyword)
+    if news_df.empty:
+        st.warning("ไม่พบบทความข่าวในช่วง 7 วันที่ผ่านมา")
+        return
+
+    # วิเคราะห์ sentiment
+    st.info("กำลังวิเคราะห์อารมณ์ของข่าว...")
+    news_df["sentiment"] = news_df["text"].apply(lambda x: analyze_text(x, bert_model, vader))
+    news_df["date"] = pd.to_datetime(news_df["date"])
+
+    avg_sentiment = news_df["sentiment"].mean()
+    pos_pct = (news_df["sentiment"] > 0.1).mean() * 100
+    neg_pct = (news_df["sentiment"] < -0.1).mean() * 100
+
+    col1, col2, col3 = st.columns(3)
+    col1.metric("ค่าเฉลี่ยอารมณ์ข่าว", f"{avg_sentiment:.2f}",
+                "Positive" if avg_sentiment > 0 else "Negative" if avg_sentiment < 0 else "Neutral")
+    col2.metric("ข่าวเชิงบวก", f"{pos_pct:.1f}%")
+    col3.metric("ข่าวเชิงลบ", f"{neg_pct:.1f}%")
+
+    # Wordcloud
+    st.subheader("☁️ Word Cloud ของข่าว")
+    all_text = " ".join(news_df["text"].tolist())
+    img = generate_wordcloud(all_text)
+    st.image(f"data:image/png;base64,{img}", use_column_width=True)
+
+    # แนวโน้มและพยากรณ์ในกราฟเดียว
+    st.subheader("📈 แนวโน้มและพยากรณ์อารมณ์ของข่าว")
+
+    df_sorted = news_df.sort_values("date").copy()
+    df_sorted["timestamp"] = (df_sorted["date"] - df_sorted["date"].min()).dt.days
+
+    # Train model
+    model = LinearRegression()
+    model.fit(df_sorted[["timestamp"]], df_sorted["sentiment"])
+
+    # Forecast next 7 days
+    future_days = 7
+    future_timestamps = np.arange(df_sorted["timestamp"].max() + 1, df_sorted["timestamp"].max() + future_days + 1)
+    future_dates = [df_sorted["date"].max() + timedelta(days=i) for i in range(1, future_days + 1)]
+    future_preds = model.predict(future_timestamps.reshape(-1, 1))
+
+    # Plot both actual + prediction
     fig = go.Figure()
+
     fig.add_trace(go.Scatter(
-        x=df_actual["date"], y=df_actual["sentiment"],
-        mode="lines+markers", name="Actual Sentiment", line=dict(color="blue")
+        x=df_sorted["date"], y=df_sorted["sentiment"],
+        mode="lines+markers", name="Actual Sentiment",
+        line=dict(color="blue")
     ))
+
     fig.add_trace(go.Scatter(
-        x=df_forecast["date"], y=df_forecast["predicted_sentiment"],
-        mode="lines+markers", name="Predicted Sentiment (Next 7 Days)",
+        x=future_dates, y=future_preds,
+        mode="lines+markers", name="Predicted Sentiment (7-day Forecast)",
         line=dict(color="orange", dash="dash")
     ))
+
     fig.add_trace(go.Scatter(
-        x=price_df["date"], y=price_df["Close"],
-        mode="lines+markers", name=f"{symbol} Stock Price",
-        line=dict(color="green"), yaxis="y2"
+        x=future_dates + future_dates[::-1],
+        y=list(future_preds + 0.1) + list((future_preds - 0.1)[::-1]),
+        fill='toself', fillcolor='rgba(255,165,0,0.2)',
+        line=dict(color='rgba(255,255,255,0)'),
+        hoverinfo="skip",
+        showlegend=False
     ))
 
     fig.update_layout(
-        title=f"📈 แนวโน้มอารมณ์ข่าว & ราคาหุ้น ({symbol})",
-        xaxis=dict(title="วันที่"),
-        yaxis=dict(title="Sentiment", side="left", range=[-1, 1]),
-        yaxis2=dict(title="Stock Price (USD)", overlaying="y", side="right", showgrid=False),
-        legend=dict(x=0, y=1.1, orientation="h"),
+        title=f"แนวโน้มและพยากรณ์อารมณ์ของข่าว '{keyword}'",
+        xaxis_title="วันที่",
+        yaxis_title="ค่าอารมณ์ (Sentiment)",
         hovermode="x unified",
         template="plotly_white"
     )
     st.plotly_chart(fig, use_container_width=True)
 
-    # -------------------------------
-    # 📰 แสดงข่าวที่ใช้วิเคราะห์
-    # -------------------------------
-    st.subheader("📰 ข่าวที่ใช้วิเคราะห์")
-    st.dataframe(news_df[["date", "source", "title", "sentiment"]])
-
-# -------------------------------
-# ��� โหลด NLTK
-# -------------------------------
-try:
-    nltk.download("punkt", quiet=True)
+    st.subheader("📰 รายการข่าว")
+    st.dataframe(news_df[["date", "source", "text", "sentiment", "url"]], use_container_width=True)
+
+
+if __name__ == "__main__":
     nltk.download("stopwords", quiet=True)
-except:
-    pass
+    main()