Update app.py

app.py

@@ -10,8 +10,8 @@ from transformers import BertTokenizer, BertForSequenceClassification, pipeline
 
 st.set_page_config(page_title="Stock News Sentiment Analyzer", layout="wide")
 
-# Initialize FinBERT (yiyanghkust/finbert-tone) pipeline
-@st.cache_resource
+# Initialize FinBERT (yiyanghkust/finbert-tone) pipeline only once and cache
+@st.cache_resource(show_spinner=False)
 def load_model():
     model = BertForSequenceClassification.from_pretrained('yiyanghkust/finbert-tone', num_labels=3)
     tokenizer = BertTokenizer.from_pretrained('yiyanghkust/finbert-tone')
@@ -30,13 +30,17 @@ def verify_link(url, timeout=10, retries=3):
     return False
 
 def get_news(ticker):
-    finviz_url = 'https://finviz.com/quote.ashx?t='
-    url = finviz_url + ticker
-    req = Request(url=url, headers={'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:20.0) Gecko/20100101 Firefox/20.0'}) 
-    response = urlopen(req)    
-    html = BeautifulSoup(response, 'html.parser')
-    news_table = html.find(id='news-table')
-    return news_table
+    try:
+        finviz_url = 'https://finviz.com/quote.ashx?t='
+        url = finviz_url + ticker
+        req = Request(url=url, headers={'User-Agent': 'Mozilla/5.0'}) 
+        response = urlopen(req)    
+        html = BeautifulSoup(response, 'html.parser')
+        news_table = html.find(id='news-table')
+        return news_table
+    except Exception as e:
+        st.write("Error fetching news:", str(e))
+        return None
 
 def parse_news(news_table):
     parsed_news = []
@@ -71,34 +75,35 @@ def parse_news(news_table):
     return parsed_news_df
 
 def score_news(parsed_news_df):
-    # Get FinBERT predictions
-    predictions = finbert(parsed_news_df['headline'].tolist())
-    
-    # Convert predictions to sentiment scores
+    # Send headlines in smaller batches to speed up processing
+    batch_size = 10
+    parsed_news_df = parsed_news_df.reset_index(drop=True)
     sentiment_scores = []
-    for pred in predictions:
-        label = pred['label']
-        score = pred['score']
+
+    for i in range(0, len(parsed_news_df), batch_size):
+        batch_headlines = parsed_news_df['headline'][i:i+batch_size].tolist()
+        predictions = finbert(batch_headlines)
         
-        # Map 'LABEL_0' (neutral), 'LABEL_1' (positive), and 'LABEL_2' (negative)
-        if label == 'LABEL_1':
-            sentiment_score = score
-        elif label == 'LABEL_2':
-            sentiment_score = -score
-        else:  # neutral
-            sentiment_score = 0
+        for pred in predictions:
+            label = pred['label']
+            score = pred['score']
             
-        sentiment_scores.append({
-            'sentiment_score': sentiment_score,
-            'label': label,
-            'confidence': score
-        })
-    
-    # Convert to DataFrame
+            # Map 'LABEL_0' (neutral), 'LABEL_1' (positive), and 'LABEL_2' (negative)
+            if label == 'LABEL_1':
+                sentiment_score = score
+            elif label == 'LABEL_2':
+                sentiment_score = -score
+            else:  # neutral
+                sentiment_score = 0
+                
+            sentiment_scores.append({
+                'sentiment_score': sentiment_score,
+                'label': label,
+                'confidence': score
+            })
+
     scores_df = pd.DataFrame(sentiment_scores)
-    
-    # Join with original news DataFrame
-    parsed_and_scored_news = parsed_news_df.join(scores_df)
+    parsed_and_scored_news = pd.concat([parsed_news_df, scores_df], axis=1)
     parsed_and_scored_news = parsed_and_scored_news.set_index('datetime')
     
     return parsed_and_scored_news
@@ -154,43 +159,47 @@ ticker = st.text_input('Enter Stock Ticker', '').upper()
 try:
     st.subheader(f"Sentiment Analysis and Recommendation for {ticker} Stock")
     news_table = get_news(ticker)
-    parsed_news_df = parse_news(news_table)
-    parsed_and_scored_news = score_news(parsed_news_df)
-    
-    # Generate and display recommendation
-    recommendation = get_recommendation(parsed_and_scored_news)
-    st.write(recommendation)
-    
-    # Display a disclaimer
-    st.warning("Disclaimer: This recommendation is based solely on recent news sentiment and should not be considered as financial advice. Always do your own research and consult with a qualified financial advisor before making investment decisions.")
-    
-    fig_hourly = plot_hourly_sentiment(parsed_and_scored_news, ticker)
-    fig_daily = plot_daily_sentiment(parsed_and_scored_news, ticker) 
-     
-    st.plotly_chart(fig_hourly)
-    st.plotly_chart(fig_daily)
-
-    description = f"""
-        The above charts average the sentiment scores of {ticker} stock hourly and daily.
-        The table below shows recent headlines with their sentiment scores and classifications.
-        The news headlines are obtained from the FinViz website.
-        Sentiments are analyzed using the yiyanghkust/finbert-tone model, which is specifically trained for financial text.
-        Links have been verified for validity.
-        """
+    if news_table:
+        parsed_news_df = parse_news(news_table)
+        parsed_and_scored_news = score_news(parsed_news_df)
+
+        # Generate and display recommendation
+        recommendation = get_recommendation(parsed_and_scored_news)
+        st.write(recommendation)
         
-    st.write(description)     
-    
-    parsed_and_scored_news['link'] = parsed_and_scored_news.apply(
-        lambda row: f'<a href="{row["link"]}" target="_blank">{"Valid✅" if row["is_valid"] else "Invalid❌"} Link</a>', 
-        axis=1
-    )
-    
-    display_df = parsed_and_scored_news.drop(columns=['is_valid'])
-    st.write(display_df.to_html(escape=False), unsafe_allow_html=True)
+        # Display a disclaimer
+        st.warning("Disclaimer: This recommendation is based solely on recent news sentiment and should not be considered as financial advice. Always do your own research and consult with a qualified financial advisor before making investment decisions.")
+        
+        fig_hourly = plot_hourly_sentiment(parsed_and_scored_news, ticker)
+        fig_daily = plot_daily_sentiment(parsed_and_scored_news, ticker) 
+        
+        st.plotly_chart(fig_hourly)
+        st.plotly_chart(fig_daily)
+
+        description = f"""
+            The above charts average the sentiment scores of {ticker} stock hourly and daily.
+            The table below shows recent headlines with their sentiment scores and classifications.
+            The news headlines are obtained from the FinViz website.
+            Sentiments are analyzed using the ProsusAI/finbert model, which is specifically trained for financial text.
+            Links have been verified for validity.
+            """
+            
+        st.write(description)     
+        
+        parsed_and_scored_news['link'] = parsed_and_scored_news.apply(
+            lambda row: f'<a href="{row["link"]}" target="_blank">{"Valid✅" if row["is_valid"] else "Invalid❌"} Link</a>', 
+            axis=1
+        )
+        
+        display_df = parsed_and_scored_news.drop(columns=['is_valid'])
+        st.write(display_df.to_html(escape=False), unsafe_allow_html=True)
+
+    else:
+        st.write("No news available or invalid ticker symbol.")
     
 except Exception as e:
     print(str(e))
-    st.write("Enter a correct stock ticker, e.g. 'AAPL' above and hit Enter.")    
+    st.write("Enter a correct stock ticker, e.g. 'AAPL' above and hit Enter.")
 
 hide_streamlit_style = """
 <style>