Update app.py

app.py

@@ -10,19 +10,19 @@ from datetime import datetime, timedelta
 import gradio as gr
 import logging
 from jinja2 import Template
-# ===== 字型與樣式 =====
+# ===== Font and Style Settings =====
 plt.rcParams['font.sans-serif'] = ['Microsoft JhengHei', 'Noto Sans TC', 'SimHei', 'Arial Unicode MS']
 plt.rcParams['axes.unicode_minus'] = False
 plt.style.use("seaborn-v0_8")
-# ===== 日誌 =====
+# ===== Logging =====
 logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
-# ===== 參數 =====
+# ===== Parameters =====
 candidates = ["許智傑", "邱議瑩", "賴瑞隆", "林岱樺", "柯志恩"]
 days_back = 7
 max_tweets_per_candidate = 20
 news_file = "news_sample.csv"
 history_file = "history_sentiment.csv"
-# ===== 情緒分析 =====
+# ===== Sentiment Analysis =====
 try:
     from transformers import pipeline
     sentiment_pipeline = pipeline(
@@ -37,25 +37,25 @@ except:
             "label": random.choice(["positive", "negative", "neutral"]),
             "score": random.uniform(0.3, 0.9)
         }
-# ===== 模擬貼文抓取 =====
+# ===== Simulate Tweet Fetching =====
 def fetch_tweets(candidate):
     sample_texts = {
-        "許智傑": ["許智傑積極參與地方活動", "許智傑被指政策空洞", "支持許智傑，打造高雄新未來！"],
-        "邱議瑩": ["邱議瑩強勢表態選市長", "邱議瑩批林岱樺", "邱議瑩推客家文化"],
-        "賴瑞隆": ["賴瑞隆推海洋經濟", "賴瑞隆民調領先", "賴瑞隆被質疑經驗不足"],
-        "林岱樺": ["林岱樺積極跑基層", "林岱樺涉助理費爭議", "林岱樺獲正國會支持"],
-        "柯志恩": ["柯志恩民調大幅領先", "柯志恩被批勘災缺席", "柯志恩推青年政策"]
+        "許智傑": ["許智傑 actively participates in local events", "許智傑 criticized for vague policies", "Support 許智傑 for Kaohsiung's future!"],
+        "邱議瑩": ["邱議瑩 strongly announces mayoral candidacy", "邱議瑩 criticizes 林岱樺", "邱議瑩 promotes Hakka culture"],
+        "賴瑞隆": ["賴瑞隆 pushes marine economy", "賴瑞隆 leads in polls", "賴瑞隆 questioned for lack of experience"],
+        "林岱樺": ["林岱樺 actively engages grassroots", "林岱樺 involved in assistant fee controversy", "林岱樺 backed by New Tide faction"],
+        "柯志恩": ["柯志恩 leads significantly in polls", "柯志恩 criticized for absence during disaster inspection", "柯志恩 promotes youth policies"]
     }
     return pd.DataFrame([
         {
             "Date": datetime.now() - timedelta(days=random.randint(0, days_back - 1)),
             "User": f"user{random.randint(1, 100)}",
-            "Content": random.choice(sample_texts.get(candidate, [f"{candidate} 的貼文 {i}"])),
+            "Content": random.choice(sample_texts.get(candidate, [f"{candidate}'s post {i}"])),
             "Candidate": candidate
         }
         for i in range(random.randint(5, max_tweets_per_candidate))
     ])
-# ===== 工具: Matplotlib → base64 =====
+# ===== Utility: Matplotlib to Base64 =====
 def fig_to_base64():
     buf = io.BytesIO()
     plt.savefig(buf, format="png", dpi=120, bbox_inches="tight")
@@ -64,103 +64,76 @@ def fig_to_base64():
     buf.close()
     plt.close()
     return img_b64
-# ===== 多圖產生器 =====
+# ===== Chart Generator =====
 def generate_charts(all_df, summary, df_hist):
     results = {}
-    # 1. 每日情緒比例
-    # ===== 字型與樣式 =====
-    plt.rcParams['font.sans-serif'] = ['Microsoft JhengHei', 'Noto Sans TC', 'SimHei', 'Arial Unicode MS']
-    plt.rcParams['axes.unicode_minus'] = False
-    plt.style.use("seaborn-v0_8")
-
+    # 1. Daily Sentiment Ratio
     fig = plt.figure(figsize=(8, 5))
     summary[['Positive Ratio', 'Negative Ratio', 'Neutral Ratio']].plot(
         kind='bar', stacked=True, colormap='coolwarm', ax=fig.gca()
     )
-    plt.title("候選人每日社群情緒比例")
-    plt.ylabel("比例")
-    plt.xlabel("候選人")
+    plt.title("Daily Sentiment Ratio by Candidate")
+    plt.ylabel("Ratio")
+    plt.xlabel("Candidate")
+    plt.legend(["Positive", "Negative", "Neutral"])
     results["img_b64_today"] = fig_to_base64()
-    # 2. 歷史情緒趨勢
-    # ===== 字型與樣式 =====
-    plt.rcParams['font.sans-serif'] = ['Microsoft JhengHei', 'Noto Sans TC', 'SimHei', 'Arial Unicode MS']
-    plt.rcParams['axes.unicode_minus'] = False
-    plt.style.use("seaborn-v0_8")
-
+    # 2. Historical Sentiment Trend
     fig = plt.figure(figsize=(10, 5))
     for c in candidates:
         temp = df_hist[df_hist['Candidate'] == c]
         if not temp.empty:
-            plt.plot(temp['Date'], temp['Positive Ratio'], marker='o', label=f"{c} 正面")
-            plt.plot(temp['Date'], temp['Negative Ratio'], marker='x', label=f"{c} 負面")
-            plt.plot(temp['Date'], temp['Neutral Ratio'], marker='s', label=f"{c} 中性")
-    plt.title("候選人歷史情緒趨勢")
+            plt.plot(temp['Date'], temp['Positive Ratio'], marker='o', label=f"{c} Positive")
+            plt.plot(temp['Date'], temp['Negative Ratio'], marker='x', label=f"{c} Negative")
+            plt.plot(temp['Date'], temp['Neutral Ratio'], marker='s', label=f"{c} Neutral")
+    plt.title("Historical Sentiment Trend by Candidate")
     plt.xticks(rotation=45)
-    plt.ylabel("比例")
+    plt.ylabel("Ratio")
+    plt.xlabel("Date")
     plt.legend()
     results["img_b64_trend"] = fig_to_base64()
-    # 3. 社群情緒趨勢
-    # ===== 字型與樣式 =====
-    plt.rcParams['font.sans-serif'] = ['Microsoft JhengHei', 'Noto Sans TC', 'SimHei', 'Arial Unicode MS']
-    plt.rcParams['axes.unicode_minus'] = False
-    plt.style.use("seaborn-v0_8")
-
+    # 3. Social Sentiment Trend
     sentiment_trend = all_df.groupby([pd.Grouper(key='Date', freq='D'), 'Sentiment']).size().unstack(fill_value=0)
     sentiment_trend = sentiment_trend.div(sentiment_trend.sum(axis=1), axis=0).fillna(0)
     fig = plt.figure(figsize=(8, 5))
     for s in ['positive', 'negative', 'neutral']:
         if s in sentiment_trend.columns:
             plt.plot(sentiment_trend.index, sentiment_trend[s], marker='o', label=s.capitalize())
-    plt.title("社群情緒趨勢")
-    plt.xlabel("日期")
-    plt.ylabel("比例")
+    plt.title("Social Sentiment Trend")
+    plt.xlabel("Date")
+    plt.ylabel("Ratio")
     plt.legend()
     results["img_social_sentiment"] = fig_to_base64()
-    # 4. 平台表現
-    # ===== 字型與樣式 =====
-    plt.rcParams['font.sans-serif'] = ['Microsoft JhengHei', 'Noto Sans TC', 'SimHei', 'Arial Unicode MS']
-    plt.rcParams['axes.unicode_minus'] = False
-    plt.style.use("seaborn-v0_8")
-
+    # 4. Platform Performance
     platforms = ["X", "Facebook", "Instagram", "PTT", "Line"]
     platform_counts = pd.Series({p: random.randint(10, 100) for p in platforms})
     fig = plt.figure(figsize=(8, 5))
     plt.bar(platforms, platform_counts, color='skyblue')
-    plt.title("平台貼文聲量")
-    plt.xlabel("平台")
-    plt.ylabel("貼文數量")
+    plt.title("Post Volume by Platform")
+    plt.xlabel("Platform")
+    plt.ylabel("Number of Posts")
     results["img_platform_performance"] = fig_to_base64()
-    # 5. 候選人聲量趨勢
-    # ===== 字型與樣式 =====
-    plt.rcParams['font.sans-serif'] = ['Microsoft JhengHei', 'Noto Sans TC', 'SimHei', 'Arial Unicode MS']
-    plt.rcParams['axes.unicode_minus'] = False
-    plt.style.use("seaborn-v0_8")
-
+    # 5. Candidate Volume Trend
     candidate_trend = all_df.groupby([pd.Grouper(key='Date', freq='D'), 'Candidate']).size().unstack(fill_value=0)
     fig = plt.figure(figsize=(8, 5))
     for c in candidates:
         if c in candidate_trend.columns:
             plt.plot(candidate_trend.index, candidate_trend[c], marker='o', label=c)
-    plt.title("候選人貼文聲量趨勢")
-    plt.xlabel("日期")
-    plt.ylabel("貼文數量")
+    plt.title("Candidate Post Volume Trend")
+    plt.xlabel("Date")
+    plt.ylabel("Number of Posts")
     plt.legend()
     results["img_candidate_volume"] = fig_to_base64()
-    # 6. 候選人情緒分析
-    # ===== 字型與樣式 =====
-    plt.rcParams['font.sans-serif'] = ['Microsoft JhengHei', 'Noto Sans TC', 'SimHei', 'Arial Unicode MS']
-    plt.rcParams['axes.unicode_minus'] = False
-    plt.style.use("seaborn-v0_8")
-
+    # 6. Candidate Sentiment Analysis
     fig = plt.figure(figsize=(8, 5))
     summary[['Positive Ratio', 'Negative Ratio', 'Neutral Ratio']].plot(
         kind='bar', stacked=True, colormap='coolwarm', ax=fig.gca()
     )
-    plt.title("候選人貼文情緒分析（正/負/中性）")
-    plt.ylabel("比例")
-    plt.xlabel("候選人")
+    plt.title("Candidate Sentiment Analysis (Positive/Negative/Neutral)")
+    plt.ylabel("Ratio")
+    plt.xlabel("Candidate")
+    plt.legend(["Positive", "Negative", "Neutral"])
     results["img_candidate_sentiment"] = fig_to_base64()
-    # 7. 知識圖譜
+    # 7. Knowledge Graph
     fig, ax = plt.subplots(figsize=(8, 6))
     G = nx.Graph()
     for c in candidates:
@@ -168,9 +141,10 @@ def generate_charts(all_df, summary, df_hist):
     for i in range(len(candidates) - 1):
         G.add_edge(candidates[i], candidates[i + 1])
     nx.draw(G, nx.spring_layout(G), with_labels=True, node_color='lightgreen', font_size=12, ax=ax)
+    plt.title("Candidate Knowledge Graph")
     results["img_knowledge_graph"] = fig_to_base64()
     return results
-# ===== 主分析函數 =====
+# ===== Main Analysis Function =====
 def run_analysis():
     try:
         # Embed the template as a string to avoid file dependency and ensure syntax is correct
@@ -180,62 +154,62 @@ def run_analysis():
 <head>
     <meta charset="UTF-8">
     <meta name="viewport" content="width=device-width, initial-scale=1.0">
-    <title>2026 高雄市長選舉輿情分析報告</title>
+    <title>2026 Kaohsiung Mayoral Election Sentiment Analysis Report</title>
     <script src="https://cdn.tailwindcss.com"></script>
 </head>
 <body class="bg-gray-100 font-sans leading-normal tracking-normal">
     <div class="container mx-auto p-4">
-        <h1 class="text-3xl font-bold mb-4">2026 高雄市長選舉輿情分析報告</h1>
-        <p class="mb-4">報告日期: {{ report_date }}</p>
+        <h1 class="text-3xl font-bold mb-4">2026 Kaohsiung Mayoral Election Sentiment Analysis Report</h1>
+        <p class="mb-4">Report Date: {{ report_date }}</p>
         
-        <h2 class="text-2xl font-bold mb-2">參與度摘要</h2>
+        <h2 class="text-2xl font-bold mb-2">Engagement Summary</h2>
         {{ engagement_table | safe }}
         
-        <h2 class="text-2xl font-bold mb-2">新聞摘要</h2>
+        <h2 class="text-2xl font-bold mb-2">News Summary</h2>
         <ul class="list-disc pl-5 mb-4">
             {% for key, value in news_summary %}
             <li><strong>{{ key }}</strong>: {{ value }}</li>
             {% endfor %}
         </ul>
         
-        <h2 class="text-2xl font-bold mb-2">新聞詳情</h2>
+        <h2 class="text-2xl font-bold mb-2">News Details</h2>
         {{ news_table | safe }}
         
-        <h2 class="text-2xl font-bold mb-2">今日情緒比例</h2>
-        <img src="data:image/png;base64,{{ img_b64_today }}" alt="今日情緒比例" class="mb-4">
+        <h2 class="text-2xl font-bold mb-2">Daily Sentiment Ratio</h2>
+        <img src="data:image/png;base64,{{ img_b64_today }}" alt="Daily Sentiment Ratio" class="mb-4">
         
-        <h2 class="text-2xl font-bold mb-2">歷史情緒趨勢</h2>
-        <img src="data:image/png;base64,{{ img_b64_trend }}" alt="歷史情緒趨勢" class="mb-4">
+        <h2 class="text-2xl font-bold mb-2">Historical Sentiment Trend</h2>
+        <img src="data:image/png;base64,{{ img_b64_trend }}" alt="Historical Sentiment Trend" class="mb-4">
         
-        <h2 class="text-2xl font-bold mb-2">社群情緒趨勢</h2>
-        <img src="data:image/png;base64,{{ img_social_sentiment }}" alt="社群情緒趨勢" class="mb-4">
+        <h2 class="text-2xl font-bold mb-2">Social Sentiment Trend</h2>
+        <img src="data:image/png;base64,{{ img_social_sentiment }}" alt="Social Sentiment Trend" class="mb-4">
         
-        <h2 class="text-2xl font-bold mb-2">平台表現</h2>
-        <img src="data:image/png;base64,{{ img_platform_performance }}" alt="平台表現" class="mb-4">
+        <h2 class="text-2xl font-bold mb-2">Platform Performance</h2>
+        <img src="data:image/png;base64,{{ img_platform_performance }}" alt="Platform Performance" class="mb-4">
         
-        <h2 class="text-2xl font-bold mb-2">候選人聲量趨勢</h2>
-        <img src="data:image/png;base64,{{ img_candidate_volume }}" alt="候選人聲量趨勢" class="mb-4">
+        <h2 class="text-2xl font-bold mb-2">Candidate Volume Trend</h2>
+        <img src="data:image/png;base64,{{ img_candidate_volume }}" alt="Candidate Volume Trend" class="mb-4">
         
-        <h2 class="text-2xl font-bold mb-2">候選人情緒分析</h2>
-        <img src="data:image/png;base64,{{ img_candidate_sentiment }}" alt="候選人情緒分析" class="mb-4">
+        <h2 class="text-2xl font-bold mb-2">Candidate Sentiment Analysis</h2>
+        <img src="data:image/png;base64,{{ img_candidate_sentiment }}" alt="Candidate Sentiment Analysis" class="mb-4">
         
-        <h2 class="text-2xl font-bold mb-2">知識圖譜</h2>
-        <img src="data:image/png;base64,{{ img_knowledge_graph }}" alt="知識圖譜" class="mb-4">
+        <h2 class="text-2xl font-bold mb-2">Knowledge Graph</h2>
+        <img src="data:image/png;base64,{{ img_knowledge_graph }}" alt="Knowledge Graph" class="mb-4">
     </div>
 </body>
 </html>
         """
-        # --- 貼文 & 情緒分析 ---
+        # --- Tweet & Sentiment Analysis ---
         all_df = pd.concat([fetch_tweets(c) for c in candidates], ignore_index=True)
         all_df['Sentiment'] = all_df['Content'].apply(lambda x: sentiment(x)['label'])
         all_df['Confidence'] = all_df['Content'].apply(lambda x: sentiment(x)['score'])
-        # --- 統計 ---
+        # --- Statistics ---
         summary = all_df.groupby(['Candidate', 'Sentiment']).size().unstack(fill_value=0)
         summary['Total Posts'] = summary.sum(axis=1)
         summary['Positive Ratio'] = summary.get('positive', 0) / summary['Total Posts'].replace(0, 1)
         summary['Negative Ratio'] = summary.get('negative', 0) / summary['Total Posts'].replace(0, 1)
         summary['Neutral Ratio'] = summary.get('neutral', 0) / summary['Total Posts'].replace(0, 1)
-        # --- 歷史資料 ---
+        # --- Historical Data ---
         today_str = datetime.now().strftime('%Y-%m-%d')
         hist_row = summary[['Positive Ratio', 'Negative Ratio', 'Neutral Ratio']].copy()
         hist_row['Date'] = today_str
@@ -245,56 +219,56 @@ def run_analysis():
             ignore_index=True
         ) if os.path.exists(history_file) else hist_row
         df_hist.to_csv(history_file, index=False)
-        # --- 圖表 ---
+        # --- Charts ---
         charts = generate_charts(all_df, summary, df_hist)
-        # --- 新聞 ---
+        # --- News ---
         if os.path.exists(news_file):
             df_news = pd.read_csv(news_file)
             news_summary = df_news.groupby('Category').size().to_dict()
             news_table = df_news.to_html(index=False, classes="min-w-full border border-gray-200")
         else:
             news_summary = {
-                "民調": "柯志恩在多份民調中領先綠營候選人。",
-                "黨內競爭": "民進黨初選競爭激烈。",
-                "爭議": "林岱樺涉助理費爭議。"
+                "Polls": "柯志恩 leads green camp candidates in multiple polls.",
+                "Party Competition": "DPP primary competition is intense.",
+                "Controversy": "林岱樺 involved in assistant fee controversy."
             }
-            news_table = "<p>無新聞資料</p>"
+            news_table = "<p>No news data available</p>"
         # Convert news_summary to list of tuples to support iteration in template
         news_summary = list(news_summary.items())
-        # --- 參與表 ---
+        # --- Engagement Table ---
         engagement_table = f"""
         <table class="min-w-full bg-white border border-gray-200">
             <tr class="bg-gray-100 border-b">
-                <th class="py-2 px-4 border-r">總參與度</th>
+                <th class="py-2 px-4 border-r">Total Engagement</th>
                 <td class="py-2 px-4 border-r">{len(all_df)}</td>
-                <th class="py-2 px-4 border-r">正面情緒比例</th>
+                <th class="py-2 px-4 border-r">Positive Sentiment Ratio</th>
                 <td class="py-2 px-4 border-r">{all_df['Sentiment'].value_counts(normalize=True).get('positive', 0):.1%}</td>
-                <th class="py-2 px-4 border-r">平均互動率</th>
+                <th class="py-2 px-4 border-r">Average Interaction Rate</th>
                 <td class="py-2 px-4 border-r">3.9%</td>
-                <th class="py-2 px-4 border-r">活躍平台數</th>
+                <th class="py-2 px-4 border-r">Active Platforms</th>
                 <td class="py-2 px-4">{5}</td>
             </tr>
         </table>
         """
-        # --- HTML 渲染 ---
+        # --- HTML Rendering ---
         template = Template(html_template)
         html_content = template.render(
             report_date=datetime.now().strftime('%Y-%m-%d %H:%M'),
-            engagement_table=engagement_table if engagement_table else "<p>未提供互動數據</p>",
-            news_summary=news_summary if news_summary else "<p>未提供新聞摘要</p>",
-            news_table=news_table if news_table else "<p>未提供新聞資料</p>",
+            engagement_table=engagement_table if engagement_table else "<p>No engagement data provided</p>",
+            news_summary=news_summary if news_summary else "<p>No news summary provided</p>",
+            news_table=news_table if news_table else "<p>No news data provided</p>",
             **charts
         )
        
         return html_content
     except Exception:
-        return f"<pre>❌ 分析失敗:\n{traceback.format_exc()}</pre>"
-# ===== Gradio 前端 =====
+        return f"<pre>❌ Analysis Failed:\n{traceback.format_exc()}</pre>"
+# ===== Gradio Frontend =====
 if __name__ == "__main__":
     iface = gr.Interface(
         fn=run_analysis,
         inputs=[],
         outputs=gr.HTML(),
-        title="2026 高雄市長選舉輿情分析"
+        title="2026 Kaohsiung Mayoral Election Sentiment Analysis"
     )
     iface.launch(server_name="0.0.0.0", server_port=7860)