Update app.py

app.py

@@ -1,25 +1,32 @@
 # -*- coding: utf-8 -*-
 """keyword_extraction"""
 
-# 1. 安裝必要的套件
-#!pip install jieba
-#!pip install keybert
-#!pip install streamlit
-#!pip install matplotlib
-
+import requests
 import jieba
 from keybert import KeyBERT
 from sklearn.feature_extraction.text import CountVectorizer
 import streamlit as st
 import matplotlib.pyplot as plt
+from matplotlib.font_manager import FontProperties
+
+# 下載字體
+def download_font(url, save_path):
+    response = requests.get(url)
+    with open(save_path, 'wb') as f:
+        f.write(response.content)
+
+# 字體URL和保存路徑
+font_url = 'https://drive.google.com/uc?id=1eGAsTN1HBpJAkeVM57_C7ccp7hbgSz3_&export=download'
+font_path = 'TaipeiSansTCBeta-Regular.ttf'
 
-!wget -O TaipeiSansTCBeta-Regular.ttf https://drive.google.com/uc?id=1eGAsTN1HBpJAkeVM57_C7ccp7hbgSz3_&export=download
-import matplotlib as mpl
-import matplotlib.font_manager as fm
-#字型設定
-fm.fontManager.addfont('TaipeiSansTCBeta-Regular.ttf')
-mpl.rc('font', family='Taipei Sans TC Beta')
-[f.name for f in fm.fontManager.ttflist]
+# 下載字體
+download_font(font_url, font_path)
+
+# 設置字體
+font_prop = FontProperties(fname=font_path)
+
+# 讀取繁體中文詞典
+# jieba.set_dictionary('path_to_your_dict.txt')  # 繁體中文詞典的實際路徑，若需要繁體字典請取消註解並設置正確路徑
 
 # 2. 定義斷詞函數
 def jieba_tokenizer(text):
@@ -41,9 +48,11 @@ def plot_keywords(keywords, title):
 
     plt.figure(figsize=(10, 6))
     plt.barh(words, scores, color='skyblue')
-    plt.xlabel('Score')
-    plt.title(title)
+    plt.xlabel('分數', fontproperties=font_prop)
+    plt.title(title, fontproperties=font_prop)
     plt.gca().invert_yaxis()  # 反轉Y軸，使得分數最高的關鍵詞在最上面
+    plt.xticks(fontproperties=font_prop)
+    plt.yticks(fontproperties=font_prop)
     st.pyplot(plt)
 
 # 6. 建立Streamlit網頁應用程式
@@ -69,7 +78,3 @@ if st.button("提取關鍵詞"):
         plot_keywords(keywords_multilingual, "多語言模型關鍵詞提取結果")
     else:
         st.write("請輸入文章內容以進行關鍵詞提取。")
-
-# 7. 運行Streamlit應用程式
-# 在終端或命令提示字元中輸入以下命令來運行應用程式：
-# streamlit run your_script_name.py