Update app.py

app.py

@@ -17,58 +17,102 @@ svm_model = joblib.load(model_path)
 print("SVM model loaded.")
 
 # --- 2. 文本情绪分析：规则+zero-shot ---
-zero_shot = pipeline("zero-shot-classification", model="joeddav/xlm-roberta-large-xnli")
+try:
+    zero_shot = pipeline("zero-shot-classification", model="joeddav/xlm-roberta-large-xnli")
+except Exception as e:
+    print("加载 zero-shot pipeline 失败：", e)
+    zero_shot = None
+
 candidate_labels = ["joy", "sadness", "anger", "fear", "surprise", "disgust"]
 label_map_en2cn = {
     "joy": "高興", "sadness": "悲傷", "anger": "憤怒",
     "fear": "恐懼", "surprise": "驚訝", "disgust": "厭惡"
 }
+
+# 关键词列表：注意繁简体一致，或可添加两种形式
 emo_keywords = {
     "happy": ["開心","快樂","愉快","喜悦","喜悅","歡喜","興奮","高興"],
     "angry": ["生氣","憤怒","不爽","發火","火大","氣憤"],
     "sad": ["傷心","難過","哭","難受","心酸","憂","悲","哀","痛苦","慘","愁"],
     "surprise": ["驚訝","意外","嚇","驚詫","詫異","訝異","好奇"],
-    "fear": ["怕","恐懼","緊張","懼","膽怯","畏"]
+    "fear": ["怕","恐懼","緊張","懼","膽怯","畏"],
+    "disgust": ["噁心","厭惡","反感"]  # 如需“厭惡”等
 }
+# 否定词列表
 negations = ["不","沒","沒有","別","勿","非"]
 
 def keyword_emotion(text: str):
+    """
+    规则方法：扫描 emo_keywords，处理前置否定词。
+    返回 None 或 {} 表示规则未命中；否则返回非空 dict，例如 {'angry': 2, 'sad':1} 或归一化 {'angry':0.67,'sad':0.33}。
+    """
+    if not text or text.strip() == "":
+        return None
+    text_proc = text.strip()  # 中文不需要 lower
     counts = {emo: 0 for emo in emo_keywords}
     for emo, kws in emo_keywords.items():
         for w in kws:
-            idx = text.find(w)
+            idx = text_proc.find(w)
             if idx != -1:
-                # 简单否定检测
+                # 检查前一到两字符是否否定词
                 neg = False
                 for neg_word in negations:
                     plen = len(neg_word)
-                    if idx - plen >= 0 and text[idx-plen:idx] == neg_word:
+                    if idx - plen >= 0 and text_proc[idx-plen:idx] == neg_word:
                         neg = True
                         break
                 if not neg:
                     counts[emo] += 1
+                else:
+                    # 若否定，可选择减分或忽略；这里忽略
+                    pass
     total = sum(counts.values())
     if total > 0:
-        return {emo: counts[emo]/total for emo in counts}
+        # 归一化
+        return {emo: counts[emo] / total for emo in counts if counts[emo] > 0}
     else:
         return None
 
 def predict_text_mixed(text: str):
+    """
+    文本情绪分析：先规则，若规则命中返回最高情绪及其比例；否则fallback zero-shot返回多类别分布。
+    返回 dict[str, float]，供 Gradio Label 显示。
+    """
+    print("predict_text_mixed called, text:", repr(text))
     if not text or text.strip() == "":
+        print("輸入為空，返回空")
         return {}
+    # 规则优先
     res = keyword_emotion(text)
+    print("keyword_emotion result:", res)
     if res:
-        top_emo = max(res, key=res.get)
-        mapping = {"happy":"高兴","angry":"愤怒","sad":"悲伤","surprise":"惊讶","fear":"恐惧"}
+        # 只返回最高项：也可返回完整分布 res
+        top_emo = max(res, key=res.get)  # 例如 "angry"
+        mapping = {
+            "happy": "高興",
+            "angry": "憤怒",
+            "sad": "悲傷",
+            "surprise": "驚訝",
+            "fear": "恐懼",
+            "disgust": "厭惡"
+        }
         cn = mapping.get(top_emo, top_emo)
-        return {cn: res[top_emo]}
+        prob = float(res[top_emo])
+        print(f"使用規則方法，返回: {{'{cn}': {prob}}}")
+        return {cn: prob}
+    # 规则未命中，zero-shot fallback
+    if zero_shot is None:
+        print("zero_shot pipeline 未加载，返回中性")
+        return {"中性": 1.0}
     try:
         out = zero_shot(text, candidate_labels=candidate_labels,
-                        hypothesis_template="這句話表達了{}情緒")
+                        hypothesis_template="这句話表達了{}情緒")
+        print("zero-shot 返回:", out)
         result = {}
         for lab, sc in zip(out["labels"], out["scores"]):
             cn = label_map_en2cn.get(lab.lower(), lab)
             result[cn] = float(sc)
+        print("zero-shot 结果映射中文:", result)
         return result
     except Exception as e:
         print("zero-shot error:", e)
@@ -133,12 +177,15 @@ with gr.Blocks() as demo:
                 voice_out = gr.Label(label="語音情緒結果")
             audio.change(fn=predict_voice, inputs=audio, outputs=voice_out)
         # 文字情緒 Tab
-        with gr.TabItem("文字情緒"):
-            gr.Markdown("### 文字情緒 分析 (规则+zero-shot)")
-            with gr.Row():
-                text = gr.Textbox(lines=3, placeholder="請輸入中文文字…")
-                text_out = gr.Label(label="文字情緒結果")
-            text.submit(fn=predict_text_mixed, inputs=text, outputs=text_out)
+        with gr.Blocks() as demo:
+    with gr.TabItem("文字情緒"):
+        gr.Markdown("### 文字情緒 分析 (规则+zero-shot)")
+        with gr.Row():
+            text = gr.Textbox(lines=3, placeholder="請輸入中文文字…")
+            text_out = gr.Label(label="文字情緒結果")
+        btn = gr.Button("分析")
+        btn.click(fn=predict_text_mixed, inputs=text, outputs=text_out)
+)
 
 if __name__ == "__main__":
     demo.launch()