Update app.py

app.py

@@ -3,16 +3,13 @@ import requests
 import pandas as pd
 from datetime import datetime, timedelta
 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
 from plotly.subplots import make_subplots
 import yfinance as yf
 import torch
-from transformers import AutoTokenizer, AutoModelForSequenceClassification
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
 
 # --------------------------
 # CONFIG
@@ -31,11 +28,21 @@ def load_finbert():
 
 tokenizer, model = load_finbert()
 
+# --------------------------
+# โหลด Zero-shot classifier สำหรับธีมข่าว
+# --------------------------
+@st.cache_resource
+def load_theme_classifier():
+    return pipeline("zero-shot-classification", model="facebook/bart-large-mnli")
+
+theme_classifier = load_theme_classifier()
+candidate_labels = ["Stock Movement", "Earnings", "M&A", "Regulation", "Product Launch", "Market Analysis"]
+
 # --------------------------
 # UTILITIES
 # --------------------------
 def analyze_text(text):
-    """วิเคราะห์อารมณ์ของข่าว"""
+    """วิเคราะห์อารมณ์ของข่าวด้วย FinBERT"""
     if not text or not text.strip():
         return 0
 
@@ -57,13 +64,15 @@ def analyze_text(text):
     return float(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()
-
+def summarize_themes(news_texts):
+    """สรุปธีมข่าวด้วย Zero-shot classification"""
+    themes = []
+    for text in news_texts:
+        if not text.strip():
+            continue
+        result = theme_classifier(text, candidate_labels)
+        themes.append(result["labels"][0])
+    return themes
 
 # --------------------------
 # แปลงชื่อ/ตัวย่อ → (Company Name, Symbol)
@@ -96,7 +105,6 @@ def resolve_company_symbol(keyword: str):
 
     return name, ticker
 
-
 # --------------------------
 # ดึงข่าว 7 วัน
 # --------------------------
@@ -143,7 +151,6 @@ def fetch_financial_news(keyword):
 
     return pd.DataFrame(all_articles)
 
-
 # --------------------------
 # ดึงราคาหุ้น
 # --------------------------
@@ -169,7 +176,6 @@ def fetch_stock_price(symbol, start_date, end_date):
         st.warning(f"ดึงราคาหุ้นล้มเหลว: {e}")
         return pd.DataFrame()
 
-
 # --------------------------
 # MAIN APP
 # --------------------------
@@ -208,14 +214,16 @@ def main():
     col2.metric("ข่าวเชิงบวก", f"{pos_pct:.1f}%")
     col3.metric("ข่าวเชิงลบ", f"{neg_pct:.1f}%")
 
-    # WordCloud
-    st.subheader("☁️ Word Cloud")
-    all_text = " ".join(news_df["text"].tolist())
-    img = generate_wordcloud(all_text)
-    st.image(f"data:image/png;base64,{img}", use_column_width=True)
+    # ---------------------------------------------------------
+    # ธีมข่าวแทน Word Cloud
+    # ---------------------------------------------------------
+    st.subheader("📰 ธีมข่าว (Top Theme per Article)")
+    news_df["theme"] = summarize_themes(news_df["text"].tolist())
+    theme_counts = news_df["theme"].value_counts()
+    st.bar_chart(theme_counts)
 
     # ---------------------------------------------------------
-    # เตรียมข้อมูลสำหรับกราฟ Sentiment & Price
+    # ส่วนกราฟ Sentiment & Price (เหมือนเดิม)
     # ---------------------------------------------------------
     st.subheader("📈 แนวโน้มอารมณ์ของข่าว & ราคาหุ้น")
 
@@ -243,28 +251,21 @@ def main():
     # ดึงราคาหุ้น
     _, symbol = resolve_company_symbol(keyword)
     min_date, max_date = df_sorted["date_day"].min(), df_sorted["date_day"].max()
-
     st.info(f"กำลังดึงราคาหุ้น {symbol} ...")
     stock_df = fetch_stock_price(symbol, min_date, max_date)
 
     plot_data = pd.merge(df_sorted, stock_df, left_on="date_day", right_on="date", how="left")
 
-    # ---------------------------------------------------------
     # Correlation
-    # ---------------------------------------------------------
     correlation = plot_data['price'].corr(plot_data['avg_sentiment'])
-
     corr_text = "ไม่มีความสัมพันธ์"
     if correlation > 0.5:
         corr_text = "มีความสัมพันธ์ในทิศทางเดียวกัน"
     elif correlation < -0.5:
         corr_text = "มีความสัมพันธ์ในทิศท��งตรงข้าม"
+    st.metric("วิเคราะห์ความสัมพันธ์ระหว่างอารมณ์ของข่าวกับราคาหุ้น (Correlation)", corr_text, f"{correlation:.2f}")
 
-    st.metric("วิเคราะห์ความสัมพันธ์ระหว่างอารมณ์ของข่าวกับราคาหุ้น", corr_text, f"{correlation:.2f}")
-
-    # ---------------------------------------------------------
     # Forecast Sentiment
-    # ---------------------------------------------------------
     plot_data["timestamp"] = (plot_data["date_day"] - plot_data["date_day"].min()).dt.days
     train_data = plot_data.dropna(subset=['avg_sentiment'])
 
@@ -280,87 +281,51 @@ def main():
         future_dates = [plot_data["date_day"].max() + timedelta(days=i) for i in range(1, future_days + 1)]
         future_preds = model_lr.predict(future_timestamps.reshape(-1, 1))
 
-    # ---------------------------------------------------------
     # Plot
-    # ---------------------------------------------------------
     fig = make_subplots(rows=2, cols=1, specs=[[{"secondary_y": True}], [{}]],
                         row_heights=[0.7, 0.3], vertical_spacing=0.1,
                         shared_xaxes=True)
 
     # ราคาหุ้น
-    fig.add_trace(
-        go.Scatter(
-            x=plot_data["date_day"], y=plot_data["price"],
-            name=f"{symbol} Price", mode="lines+markers", line=dict(color="orange")
-        ),
-        row=1, col=1, secondary_y=False
-    )
-
+    fig.add_trace(go.Scatter(x=plot_data["date_day"], y=plot_data["price"], name=f"{symbol} Price",
+                             mode="lines+markers", line=dict(color="orange")), row=1, col=1, secondary_y=False)
     # Sentiment จริง
-    fig.add_trace(
-        go.Scatter(
-            x=plot_data["date_day"], y=plot_data["avg_sentiment"],
-            name="Actual Sentiment", mode="lines+markers", line=dict(color="blue")
-        ),
-        row=1, col=1, secondary_y=True
-    )
-
+    fig.add_trace(go.Scatter(x=plot_data["date_day"], y=plot_data["avg_sentiment"], name="Actual Sentiment",
+                             mode="lines+markers", line=dict(color="blue")), row=1, col=1, secondary_y=True)
     # Sentiment พยากรณ์
     if "future_preds" in locals():
-        fig.add_trace(
-            go.Scatter(
-                x=future_dates, y=future_preds,
-                name="Predicted Sentiment", mode="lines+markers", line=dict(color="#05a0fa", dash="dash")
-            ),
-            row=1, col=1, secondary_y=True
-        )
-
-        # ---------------------------------------------------------
+        fig.add_trace(go.Scatter(x=future_dates, y=future_preds, name="Predicted Sentiment",
+                                 mode="lines+markers", line=dict(color="#05a0fa", dash="dash")), row=1, col=1, secondary_y=True)
         # เส้นเชื่อม Actual -> Predicted
-        # ---------------------------------------------------------
         last_actual_date = plot_data["date_day"].max()
         last_actual_value = plot_data["avg_sentiment"].iloc[-1]
         first_pred_date = future_dates[0]
         first_pred_value = future_preds[0]
-
-        fig.add_trace(
-            go.Scatter(
-                x=[last_actual_date, first_pred_date],
-                y=[last_actual_value, first_pred_value],
-                mode="lines",
-                line=dict(color="#05a0fa", dash="dot"),
-                name="Connector Actual→Predicted"
-            ),
-            row=1, col=1, secondary_y=True
-        )
+        fig.add_trace(go.Scatter(x=[last_actual_date, first_pred_date],
+                                 y=[last_actual_value, first_pred_value],
+                                 mode="lines",
+                                 line=dict(color="#05a0fa", dash="dot"),
+                                 name="Connector Actual→Predicted"), row=1, col=1, secondary_y=True)
 
     # จำนวนข่าว
     for col in ["neutral", "negative", "positive"]:
         if col not in plot_data.columns:
             plot_data[col] = 0
-
     fig.add_trace(go.Bar(x=plot_data["date_day"], y=plot_data["neutral"], name="Neutral",
-                     marker_color='rgba(128, 128, 128, 0.7)'), row=2, col=1)
+                         marker_color='rgba(128, 128, 128, 0.7)'), row=2, col=1)
     fig.add_trace(go.Bar(x=plot_data["date_day"], y=plot_data["negative"], name="Negative",
-                     marker_color='rgba(255, 0, 0, 0.7)'), row=2, col=1)
+                         marker_color='rgba(255, 0, 0, 0.7)'), row=2, col=1)
     fig.add_trace(go.Bar(x=plot_data["date_day"], y=plot_data["positive"], name="Positive",
-                     marker_color='rgba(0, 128, 0, 0.7)'), row=2, col=1)
-
+                         marker_color='rgba(0, 128, 0, 0.7)'), row=2, col=1)
 
-    fig.update_layout(
-        title=f"แนวโน้มอารมณ์ของข่าว + ราคาหุ้น ({symbol})",
-        barmode="stack",
-        height=650,
-        hovermode="x unified",
-        template="plotly_white"
-    )
+    fig.update_layout(title=f"แนวโน้มอารมณ์ของข่าว + ราคาหุ้น ({symbol})",
+                      barmode="stack", height=650, hovermode="x unified", template="plotly_white")
 
     st.plotly_chart(fig, use_container_width=True)
 
     # แสดงรายการข่าว
     st.subheader("📰 รายการข่าวทั้งหมด")
-    st.dataframe(news_df[["date", "source", "text", "sentiment", "url"]], use_container_width=True)
-
+    st.dataframe(news_df[["date", "source", "text", "sentiment", "theme", "url"]], use_container_width=True)
 
 # ---------------------------------------------------------
 # RUN APP