added app.py

app.py

@@ -0,0 +1,162 @@
+import streamlit as st
+import requests
+import re
+import torch
+from transformers import BertTokenizer, BertForSequenceClassification
+
+# Load tokenizer and model
+tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
+model_path = '/Users/kartikrathi/Documents/News_sentiment_analysis/model'
+model = BertForSequenceClassification.from_pretrained(model_path)
+
+# Function to analyze sentiment
+def analyze_sentiment(text):
+    # Tokenize inputs
+    inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=512)
+    
+    # Perform inference
+    with torch.no_grad():
+        outputs = model(**inputs)
+    
+    # Get predicted logits
+    logits = outputs.logits
+    
+    # Determine predicted sentiment
+    predicted_class_id = torch.argmax(logits, dim=1).item()
+    sentiment = {0: "positive", 1: "negative", 2: "neutral"}
+    return sentiment[predicted_class_id]
+
+# Function to fetch news using an API
+def fetch_stock_news(symbol):
+    api_token = '6679177763bcd9.48465511'  # Replace with your actual API token
+    url = f'https://eodhd.com/api/news?s={symbol}&offset=0&limit=2&api_token={api_token}&fmt=json'
+    
+    try:
+        response = requests.get(url)
+        response.raise_for_status()  # Raise exception for bad status codes
+        data = response.json()
+        
+        news_list = []
+        for article in data:
+            title = article.get('title', 'Title not available')
+            content = article.get('content', 'Content not available')
+            url = article.get('url', 'URL not available')
+            date = article.get('date', 'Date not available')
+            
+            # Remove unwanted sections from content
+            cleaned_content = remove_sections(content)
+            
+            news_list.append({'title': title, 'content': cleaned_content, 'url': url, 'date': date})
+        
+        return news_list
+    
+    except requests.exceptions.RequestException as e:
+        print(f"Error fetching news for {symbol}: {e}")
+        return None
+
+# Function to remove unwanted sections
+def remove_sections(content):
+    # Patterns to remove
+    patterns = [
+        r'About\s+.*?[\n\r]+',  # 'About {stock}' section
+        r'Safe\s+Harbor.*',  # 'Safe Harbor' section
+        r'Story\s+continues.*',  # 'Story continues'
+        r'Visit\s+www\.infosys\.com.*',  # 'Visit www.infosys.com...'
+        r'Logo',  # 'Logo'
+    ]
+    
+    for pattern in patterns:
+        content = re.sub(pattern, '', content, flags=re.IGNORECASE)
+    
+    return content.strip()
+
+# Streamlit app with multi-page support
+def main():
+    st.sidebar.title('Navigation')
+    page = st.sidebar.radio("Go to", ('Home', 'Portfolio & News'))
+
+    if page == 'Home':
+        st.title("Financial News Sentiment Analysis")
+        st.markdown("""
+            This app performs sentiment analysis on financial news using FinBERT model.
+            """)
+
+        # Input text box for user input
+        user_input = st.text_area("Enter your financial news text here:", height=200)
+
+        # Perform sentiment analysis when user clicks the button
+        if st.button("Analyze"):
+            if user_input:
+                sentiment = analyze_sentiment(user_input)
+                if sentiment == "positive":
+                    st.markdown(f"<p style='color:green;font-size:40px;font-weight:bold'>{sentiment}</p>", unsafe_allow_html=True)
+                elif sentiment == "negative":
+                    st.markdown(f"<p style='color:red;font-size:40px;font-weight:bold'>{sentiment}</p>", unsafe_allow_html=True)
+                elif sentiment == "neutral":
+                    st.markdown(f"<p style='color:blue;font-size:40px;font-weight:bold'>{sentiment}</p>", unsafe_allow_html=True)
+            else:
+                st.warning("Please enter some text.")
+
+    elif page == 'Portfolio & News':
+        st.title('Portfolio & News')
+
+        # Sidebar to manage portfolio and fetch news
+        st.sidebar.subheader('Manage Portfolio & Fetch News')
+        st.sidebar.info("Enter your portfolio/company names here to fetch news.")
+
+        # Input fields for portfolio management and news fetching
+        portfolio = st.sidebar.text_area("Enter your portfolio/company names (one per line):", height=200)
+        
+        if st.sidebar.button("Save"):
+            # Add ".NSE" suffix to each company name
+            shares = portfolio.split("\n")
+            shares = [share.strip() + ".NSE" for share in shares if share.strip()]
+            st.sidebar.markdown("**Shares**")
+            st.sidebar.markdown("\n".join(shares))
+
+        # Button to fetch news and perform sentiment analysis
+        if st.sidebar.button("Fetch News & Analyze Sentiment"):
+            if portfolio:
+                companies = portfolio.split("\n")
+                companies = [company.strip() + ".NSE" for company in companies if company.strip()]
+                for company in companies:
+                    st.subheader(f"Latest News for {company}:")
+                    news = fetch_stock_news(company)
+
+                    if news:
+                        for article in news:
+                            title = article['title']
+                            content = article['content']
+                            url = article['url']
+                            date = article['date']
+                            st.markdown(f"**Title:** [{title}]({url}) <span style='color:green;font-size:12px;'>({date})</span>", unsafe_allow_html=True)
+                            
+                            # Display a truncated version of the content
+                            truncated_content = content[:200] + "..."
+                            st.markdown(f"**Content:** {truncated_content}")
+                            
+                            # Expander for full content
+                            with st.expander("Expand more"):
+                                st.markdown(f"{content}")
+
+                            st.markdown("---")
+
+                            # Analyze sentiment of news content (assuming content is available)
+                            if content:
+                                sentiment = analyze_sentiment(content)
+                                if sentiment == "positive":
+                                    sentiment_color = "green"
+                                elif sentiment == "negative":
+                                    sentiment_color = "red"
+                                elif sentiment == "neutral":
+                                    sentiment_color = "blue"
+                                
+                                st.markdown(f"**Sentiment:** <span style='color:{sentiment_color};font-weight:bold'>{sentiment}</span>", unsafe_allow_html=True)
+                                st.markdown("---")
+                    else:
+                        st.warning(f"No news articles found for {company}.")
+            else:
+                st.warning("Please enter portfolio/company names to fetch news.")
+
+if __name__ == '__main__':
+    main()