Update app.py

app.py

@@ -6,7 +6,6 @@ from prophet import Prophet
 import matplotlib.pyplot as plt
 import gradio as gr
 
-# 1️⃣ 模型初始化
 embedder = SentenceTransformer("sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2")
 sentiment_model = pipeline(
     "text-classification",
@@ -14,26 +13,20 @@ sentiment_model = pipeline(
     tokenizer="uer/roberta-base-finetuned-dianping-chinese"
 )
 
-# 2️⃣ 主處理流程
 def full_pipeline(file, num_clusters):
-    try:
-    df = pd.read_csv(file, encoding="utf-8")
-except UnicodeDecodeError:
-    try:
-        df = pd.read_csv(file, encoding="utf-8-sig")
-    except UnicodeDecodeError:
-        try:
-            df = pd.read_csv(file, encoding="big5")
-        except Exception as e:
-            return f"❌ 無法讀取 CSV 檔案，錯誤原因：{str(e)}"
+    df = pd.read_csv(file)
+
+    if "text" not in df.columns:
+        return "❌ 錯誤：CSV 檔案需包含 text 欄位"
+    if "timestamp" not in df.columns:
+        return "❌ 錯誤：CSV 檔案需包含 timestamp 欄位（例如新聞時間）"
 
-    # 向量化並聚類
     texts = df["text"].astype(str).tolist()
     embeddings = embedder.encode(texts, show_progress_bar=True)
     kmeans = KMeans(n_clusters=num_clusters, random_state=42)
     df["topic"] = kmeans.fit_predict(embeddings)
 
-    # 情緒分析
+
     sentiments = []
     for text in texts:
         try:
@@ -52,7 +45,7 @@ except UnicodeDecodeError:
         sentiments.append(sentiment)
     df["sentiment"] = sentiments
 
-    # 熱度預測（以 topic=0 為例）
+
     df["timestamp"] = pd.to_datetime(df["timestamp"])
     topic0 = df[df["topic"] == 0]
     daily_counts = topic0.groupby(df["timestamp"].dt.date).size().reset_index(name="count")
@@ -86,6 +79,6 @@ gr.Interface(
         gr.File(label="結果 CSV（含 topic, sentiment）"),
         gr.Image(label="topic=0 熱度預測圖（Prophet）")
     ],
-    title="話題雷達",
-    description="自動分群、分析情緒，並預測熱度走勢"
+    title=,"話題雷達"
+    description="自動分群、分析情緒，並預測熱度走勢（topic=0 為例）"
 ).launch()