Update app.py

app.py

@@ -3,45 +3,40 @@ import requests
 import pandas as pd
 from datetime import datetime, timedelta
 from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer
-from textblob import TextBlob
-import nltk
 from wordcloud import WordCloud
 import base64
 from io import BytesIO
 import numpy as np
-from sklearn.linear_model import LinearRegression
 import plotly.graph_objects as go
 import yfinance as yf
 
 # --------------------------
 # CONFIG
 # --------------------------
-st.set_page_config(page_title="📰 SentimentSync NewsAI", layout="wide")
-API_KEY = "88bc396d4eab4be494a4b86ec842db47"
+st.set_page_config(page_title="📰 SentimentSync News+Stock", layout="wide")
+NEWS_API_KEY = "88bc396d4eab4be494a4b86ec842db47"
 
 # --------------------------
 # UTILITIES
 # --------------------------
+@st.cache_resource
+def load_sentiment_model():
+    st.info("Loading sentiment analyzer...")
+    vader = SentimentIntensityAnalyzer()
+    return vader
+
 def analyze_text(text, vader):
     if not text.strip():
         return 0
-    vader_score = vader.polarity_scores(text)["compound"]
-    textblob_score = TextBlob(text).sentiment.polarity
-    return np.mean([vader_score, textblob_score])
-
-
-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()
-
+    return vader.polarity_scores(text)["compound"]
 
-# --------------------------
-# แปลงชื่อ/ตัวย่อ → (Company Name, Symbol)
-# --------------------------
 def resolve_company_symbol(keyword: str):
+    """
+    คืน (company_name, symbol) จากชื่อบริษัทหรือ ticker
+    """
+    import yfinance as yf
+    import requests
+
     keyword = keyword.strip()
     ticker = None
     name = None
@@ -69,27 +64,23 @@ def resolve_company_symbol(keyword: str):
 
     return name, ticker
 
-
-# --------------------------
-# ดึงข่าว 7 วัน สำหรับ Company + Symbol
-# --------------------------
 @st.cache_data(ttl=3600)
-def fetch_financial_news(keyword):
-    company, symbol = resolve_company_symbol(keyword)
+def fetch_financial_news(company, symbol):
+    """ดึงข่าวย้อนหลัง 7 วันจาก NewsAPI.org"""
     to_date = datetime.now().strftime('%Y-%m-%d')
     from_date = (datetime.now() - timedelta(days=7)).strftime('%Y-%m-%d')
 
-    query_keyword = f"({company} OR {symbol}) finance stock"
+    query_keyword = f"({company} OR {symbol})"
 
     all_articles = []
     page = 1
     while True:
         url = (
             f"https://newsapi.org/v2/everything?"
-            f"q={query_keyword}&"
+            f"q={query_keyword}+finance+stock&"
             f"from={from_date}&to={to_date}&"
             f"language=en&sortBy=publishedAt&"
-            f"pageSize=100&page={page}&apiKey={API_KEY}"
+            f"pageSize=100&page={page}&apiKey={NEWS_API_KEY}"
         )
         r = requests.get(url)
         data = r.json()
@@ -114,46 +105,54 @@ def fetch_financial_news(keyword):
             break
         page += 1
 
-    return pd.DataFrame(all_articles), company, symbol
+    return pd.DataFrame(all_articles)
 
+def generate_wordcloud(text):
+    stopwords = ["the","and","of","to","in","for","on","with","at","a","an"]
+    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()
 
-# --------------------------
-# ดึงราคาหุ้นย้อนหลัง 14 วัน
-# --------------------------
-@st.cache_data(ttl=3600)
-def fetch_stock_price(symbol):
+def get_stock_prices(symbol: str, start_date: datetime, end_date: datetime):
+    """ดึงราคาหุ้น Close price ของ symbol"""
     try:
-        df = yf.download(symbol, period="14d", interval="1d")
-        df = df.reset_index()[["Date", "Close"]]
-        df.rename(columns={"Date": "date", "Close": "price"}, inplace=True)
-        df["date"] = pd.to_datetime(df["date"])
-        return df
+        stock_df = yf.download(symbol, start=start_date.strftime('%Y-%m-%d'),
+                               end=end_date.strftime('%Y-%m-%d'), progress=False)
+        if stock_df.empty or 'Close' not in stock_df.columns:
+            return pd.DataFrame()
+        stock_df = stock_df.reset_index()[['Date', 'Close']]
+        stock_df.rename(columns={'Date': 'date', 'Close': 'price'}, inplace=True)
+        stock_df['date'] = pd.to_datetime(stock_df['date'].dt.date)
+        return stock_df
     except Exception as e:
-        st.warning(f"ไม่สามารถดึงราคาหุ้นได้: {e}")
+        print(f"Error fetching stock data: {e}")
         return pd.DataFrame()
 
-
 # --------------------------
 # MAIN APP
 # --------------------------
 def main():
-    st.title("📰 SentimentSync NewsAI")
-    st.markdown("วิเคราะห์แนวโน้มอารมณ์ของข่าวย้อนหลัง 7 วัน พร้อมราคาหุ้น")
+    st.title("📰 SentimentSync News + Stock Prices")
+    st.markdown("วิเคราะห์แนวโน้มอารมณ์ข่าวและราคาหุ้นย้อนหลัง 7 วัน")
 
-    # Sidebar
     with st.sidebar:
-        keyword = st.text_input("ค้นหาคำ / ตัวย่อหุ้น (เช่น Tesla หรือ TSLA):", "")
+        keyword = st.text_input("ค้นหาบริษัทหรือ Symbol:", "")
         analyze_btn = st.button("วิเคราะห์เลย")
 
     if not analyze_btn:
-        st.info("กรอกคำค้นแล้วกด 'วิเคราะห์เลย' เพื่อเริ่มต้น")
+        st.info("กรอกคำค้นแล้วกด 'วิเคราะห์เลย' เพื่อเริ่ม")
         return
 
-    vader = SentimentIntensityAnalyzer()
+    vader = load_sentiment_model()
+
+    # แปลงชื่อ → (company, symbol)
+    company, symbol = resolve_company_symbol(keyword)
+    st.write(f"Resolved: {company} ({symbol})")
 
     # ดึงข่าว
-    st.info(f"กำลังดึงข่าวย้อนหลัง 7 วันสำหรับ '{keyword}' ...")
-    news_df, company, symbol = fetch_financial_news(keyword)
+    st.info(f"กำลังดึงข่าวย้อนหลัง 7 วันสำหรับ '{company} / {symbol}' ...")
+    news_df = fetch_financial_news(company, symbol)
     if news_df.empty:
         st.warning("ไม่พบบทความข่าวในช่วง 7 วันที่ผ่านมา")
         return
@@ -163,6 +162,7 @@ def main():
     news_df["sentiment"] = news_df["text"].apply(lambda x: analyze_text(x, vader))
     news_df["date"] = pd.to_datetime(news_df["date"])
 
+    # สรุป sentiment
     avg_sentiment = news_df["sentiment"].mean()
     pos_pct = (news_df["sentiment"] > 0.1).mean() * 100
     neg_pct = (news_df["sentiment"] < -0.1).mean() * 100
@@ -179,62 +179,48 @@ def main():
     img = generate_wordcloud(all_text)
     st.image(f"data:image/png;base64,{img}", use_column_width=True)
 
-    # แนวโน้ม + พยากรณ์ + ราคาหุ้น
-    st.subheader("📈 แนวโน้มอารมณ์ของข่าว & ราคาหุ้น")
-    df_sorted = news_df.sort_values("date").copy()
-    df_sorted["timestamp"] = (df_sorted["date"] - df_sorted["date"].min()).dt.days
-
-    # Train sentiment 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))
-
     # ดึงราคาหุ้น
-    stock_df = fetch_stock_price(symbol)
+    stock_prices = get_stock_prices(symbol, news_df['date'].min(), news_df['date'].max())
 
-    # Plot
+    # กราฟ sentiment + stock
+    st.subheader("📈 แนวโน้มอารมณ์ข่าว + ราคาหุ้น")
     fig = go.Figure()
-    # Actual sentiment
-    fig.add_trace(go.Scatter(
-        x=df_sorted["date"], y=df_sorted["sentiment"],
-        mode="lines+markers", name="Actual Sentiment",
-        line=dict(color="blue")
-    ))
-    # Predicted sentiment
+
+    # Sentiment
     fig.add_trace(go.Scatter(
-        x=future_dates, y=future_preds,
-        mode="lines+markers", name="Predicted Sentiment (7-day Forecast)",
-        line=dict(color="orange", dash="dash")
+        x=news_df["date"], y=news_df["sentiment"],
+        mode="lines+markers", name="Sentiment",
+        line=dict(color="orange")
     ))
+
     # Stock price
-    if not stock_df.empty:
+    if not stock_prices.empty:
         fig.add_trace(go.Scatter(
-            x=stock_df["date"], y=stock_df["price"],
+            x=stock_prices["date"], y=stock_prices["price"],
             mode="lines+markers", name=f"{symbol} Stock Price",
-            line=dict(color="green"), yaxis="y2"
+            line=dict(color="blue"),
+            yaxis="y2"
         ))
+        fig.update_layout(
+            yaxis2=dict(
+                title="Stock Price",
+                overlaying="y",
+                side="right"
+            )
+        )
 
     fig.update_layout(
-        title=f"แนวโน้มและพยากรณ์อารมณ์ข่าว & ราคาหุ้น '{company} ({symbol})'",
-        xaxis_title="วันที่",
-        yaxis=dict(title="Sentiment", side="left", range=[-1, 1]),
-        yaxis2=dict(title="Stock Price", overlaying="y", side="right", showgrid=False),
+        title=f"Sentiment & Stock Price for {company} ({symbol})",
+        xaxis_title="Date",
+        yaxis_title="Sentiment Score",
         hovermode="x unified",
         template="plotly_white"
     )
-
     st.plotly_chart(fig, use_container_width=True)
 
     # แสดงข่าว
     st.subheader("📰 รายการข่าว")
     st.dataframe(news_df[["date", "source", "text", "sentiment", "url"]], use_container_width=True)
 
-
 if __name__ == "__main__":
-    nltk.download("stopwords", quiet=True)
     main()