Create app.py

app.py

@@ -0,0 +1,82 @@
+# -*- coding: utf-8 -*-
+"""keyword_extraction"""
+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
+
+# Download font
+@st.cache_data
+def download_font(url, save_path):
+    response = requests.get(url)
+    with open(save_path, 'wb') as f:
+        f.write(response.content)
+
+# Font URL and save path
+font_url = 'https://drive.google.com/uc?id=1eGAsTN1HBpJAkeVM57_C7ccp7hbgSz3_&export=download'
+font_path = 'TaipeiSansTCBeta-Regular.ttf'
+
+# Download font
+download_font(font_url, font_path)
+
+# Set font
+font_prop = FontProperties(fname=font_path)
+
+# Define tokenizer function
+def jieba_tokenizer(text):
+    return jieba.lcut(text)
+
+# Initialize CountVectorizer and KeyBERT model
+@st.cache_resource
+def load_models():
+    vectorizer = CountVectorizer(tokenizer=jieba_tokenizer)
+    kw_model = KeyBERT()
+    kw_model_multilingual = KeyBERT(model='distiluse-base-multilingual-cased-v1')
+    return vectorizer, kw_model, kw_model_multilingual
+
+vectorizer, kw_model, kw_model_multilingual = load_models()
+
+# Extract keywords function
+def extract_keywords(doc, model):
+    keywords = model.extract_keywords(doc, vectorizer=vectorizer)
+    return keywords
+
+# Plot keywords function
+def plot_keywords(keywords, title):
+    words = [kw[0] for kw in keywords]
+    scores = [kw[1] for kw in keywords]
+    fig, ax = plt.subplots(figsize=(10, 6))
+    ax.barh(words, scores, color='skyblue')
+    ax.set_xlabel('分數', fontproperties=font_prop)
+    ax.set_title(title, fontproperties=font_prop)
+    ax.invert_yaxis()  # Invert Y-axis so that the highest scoring keyword is on top
+    ax.tick_params(axis='both', which='major', labelsize=10)
+    plt.xticks(fontproperties=font_prop)
+    plt.yticks(fontproperties=font_prop)
+    st.pyplot(fig)
+
+# Streamlit app
+st.title("中文關鍵詞提取工具")
+
+doc = st.text_area("請輸入文章：")
+
+if st.button("提取關鍵詞"):
+    if doc:
+        keywords = extract_keywords(doc, kw_model)
+        st.write("關鍵詞提取結果：")
+        for keyword in keywords:
+            st.write(f"{keyword[0]}: {keyword[1]:.4f}")
+        
+        plot_keywords(keywords, "關鍵詞提取結果")
+
+        keywords_multilingual = extract_keywords(doc, kw_model_multilingual)
+        st.write("多語言模型關鍵詞提取結果：")
+        for keyword in keywords_multilingual:
+            st.write(f"{keyword[0]}: {keyword[1]:.4f}")
+        
+        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。")