Update app.py

app.py

@@ -97,31 +97,32 @@ demo.launch()'''
 
 import gradio as gr
 import tensorflow as tf
-import numpy as np
 import pickle
 
 # ---------------- 載入模型 ----------------
-model = tf.keras.models.load_model("AIDetect.h5")  # 你的模型資料夾
+model = tf.keras.models.load_model("AIDetect.h5")  # 你的模型檔案
 with open("vectorizer.pkl", "rb") as f:
     vectorizer = pickle.load(f)
 with open("scaler.pkl", "rb") as f:
     scaler = pickle.load(f)
 
-# ---------------- 特徵計算 ----------------
+# ---------------- 特徵計算（純 Python） ----------------
 def compute_features(text):
     words = text.split()
     word_count = len(words)
     unique_word_ratio = len(set(words)) / (word_count + 1e-6)
     repeat_rate = 1 - unique_word_ratio
-    punctuation_ratio = sum(1 for c in text if c in ".,!?;:") / (len(text) + 1e-6)
-    avg_word_length = np.mean([len(w) for w in words]) if words else 0
-    return np.array([word_count, unique_word_ratio, repeat_rate, punctuation_ratio, avg_word_length]).reshape(1, -1)
+    punctuation_count = sum(1 for c in text if c in ".,!?;:")
+    punctuation_ratio = punctuation_count / (len(text) + 1e-6)
+    avg_word_length = sum(len(w) for w in words) / (word_count + 1e-6) if words else 0
+    # 直接返回列表，不用 numpy
+    return [[word_count, unique_word_ratio, repeat_rate, punctuation_ratio, avg_word_length]]
 
 # ---------------- 生成解釋 ----------------
 def explain_prediction(text):
     # 文字向量化
-    seq = vectorizer.transform([text])
-    seq = tf.keras.utils.pad_sequences(seq.toarray(), maxlen=50, padding='pre')
+    seq = vectorizer([text])
+    seq = tf.keras.preprocessing.sequence.pad_sequences(seq, maxlen=50, padding='pre')
 
     # 統計特徵
     feat = compute_features(text)
@@ -134,11 +135,11 @@ def explain_prediction(text):
 
     # 判斷依據
     reasons = []
-    if feat[0,0] > 100: reasons.append("句子長度偏長")
-    if feat[0,2] > 0.3: reasons.append("重複率高")
-    if feat[0,1] < 0.2: reasons.append("詞彙多樣性低")
-    if feat[0,3] < 0.01: reasons.append("標點符號少")
-    if feat[0,4] > 6: reasons.append("平均詞長偏長")
+    if feat[0][0] > 100: reasons.append("句子長度偏長")
+    if feat[0][2] > 0.3: reasons.append("重複率高")
+    if feat[0][1] < 0.2: reasons.append("詞彙多樣性低")
+    if feat[0][3] < 0.01: reasons.append("標點符號少")
+    if feat[0][4] > 6: reasons.append("平均詞長偏長")
     if not reasons: reasons.append("句子長度與用詞平均")
     explanation = "；".join(reasons)