Update app.py

app.py

@@ -3,6 +3,7 @@ import requests
 from bs4 import BeautifulSoup
 from transformers import pipeline
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
+import time
 
 model_id = "LinkLinkWu/Boss_Stock_News_Analysis"
 
@@ -11,9 +12,9 @@ tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForSequenceClassification.from_pretrained(model_id)
 
 # Initialize sentiment analysis pipeline
-sentiment_pipeline = pipeline("sentiment-analysis")
+sentiment_pipeline = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)
 
-# Function to fetch top 3 news articles from FinViz
+# Function to fetch top 50 news articles from FinViz
 def fetch_news(ticker):
     try:
         url = f"https://finviz.com/quote.ashx?t={ticker}"
@@ -22,7 +23,7 @@ def fetch_news(ticker):
         soup = BeautifulSoup(response.text, 'html.parser')
         news_table = soup.find(id='news-table')
         news = []
-        for row in news_table.findAll('tr')[:3]:  # Limit to top 3
+        for row in news_table.findAll('tr')[:50]:  # Fetch up to 50 articles
             title = row.a.get_text()
             link = row.a['href']
             news.append({'title': title, 'link': link})
@@ -54,16 +55,37 @@ if st.button("Get News and Sentiment"):
         if len(tickers) != 5:
             st.error("Please enter exactly five stock tickers.")
         else:
-            # Process each ticker
-            for ticker in tickers:
-                st.subheader(f"Top 3 News Articles for {ticker}")
+            progress_bar = st.progress(0)
+            total_stocks = len(tickers)
+            for idx, ticker in enumerate(tickers):
+                st.subheader(f"Analyzing {ticker}...")
                 news_list = fetch_news(ticker)
                 
                 if news_list:
-                    for i, news in enumerate(news_list, 1):
+                    # Analyze sentiment for all news articles (up to 50)
+                    sentiments = []
+                    for news in news_list:
                         sentiment = analyze_sentiment(news['title'])
+                        sentiments.append(sentiment)
+                    
+                    # Determine overall sentiment based on majority
+                    positive_count = sentiments.count("Positive")
+                    negative_count = sentiments.count("Negative")
+                    overall_sentiment = "Positive" if positive_count > negative_count else "Negative"
+                    
+                    # Display top 3 news articles with sentiment
+                    st.write(f"**Top 3 News Articles for {ticker}**")
+                    for i, news in enumerate(news_list[:3], 1):
+                        sentiment = sentiments[i-1]
                         st.markdown(f"{i}. [{news['title']}]({news['link']}) - **{sentiment}**")
+                    
+                    # Display overall sentiment
+                    st.write(f"**Overall Sentiment for {ticker}: {overall_sentiment}**")
                 else:
-                    st.write("No news available for this ticker.")
+                    st.write(f"No news available for {ticker}.")
+                
+                # Update progress bar
+                progress_bar.progress((idx + 1) / total_stocks)
+                time.sleep(0.1)  # Simulate processing time
     else:
         st.warning("Please enter stock tickers.")