app.py

# -*- 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

# 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'

# 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):
    return jieba.lcut(text)

# 3. 初始化CountVectorizer並定義KeyBERT模型
vectorizer = CountVectorizer(tokenizer=jieba_tokenizer)
kw_model = KeyBERT()

# 4. 提取關鍵詞的函數
def extract_keywords(doc):
    keywords = kw_model.extract_keywords(doc, vectorizer=vectorizer)
    return keywords

# 5. 畫圖函數
def plot_keywords(keywords, title):
    words = [kw[0] for kw in keywords]
    scores = [kw[1] for kw in keywords]

    plt.figure(figsize=(10, 6))
    plt.barh(words, scores, color='skyblue')
    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
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)
        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")

        # 使用另一個模型進行關鍵詞提取
        kw_model_multilingual = KeyBERT(model='distiluse-base-multilingual-cased-v1')
        keywords_multilingual = kw_model_multilingual.extract_keywords(doc, vectorizer=vectorizer)
        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。")