app.py

import streamlit as st
from transformers import pipeline

def analyze_financial_news():
    access = "hf_"
    token = "hhbFNpjKohezoexWMlyPUpvJQLWlaFhJaa"

    # Load the text classification model pipeline
    classification = pipeline("text-classification", model="nickmuchi/finbert-tone-finetuned-finance-topic-classification", token=access+token)
    sentiment_analysis = pipeline("sentiment-analysis")

    st.set_page_config(page_title="Financial News Analysis", page_icon="♕")

    # Streamlit application layout
    st.title("Financial News Analysis")
    st.write("Analyze corresponding Topic and Trend for Financial News!")
    st.image("./Fin.jpg", use_column_width=True)

    # Text input for user to enter the text
    text = st.text_area("Enter the Financial News", "")

    analyze_clicked = st.button("Analyze")

    if analyze_clicked:
        # Perform text classification on the input text
        results = classification(text)

        # Filter only the news related to "Energy | Oil"
        energy_oil_news = [news for news in results if news["label"] == "Energy | Oil"]
        
        st.write("Energy | Oil News:", energy_oil_news)  # Debug statement to check the Energy | Oil news list
        
        if energy_oil_news:
            # If there are news related to "Energy | Oil", perform sentiment analysis for each news
            for idx, news in enumerate(energy_oil_news, start=1):
                # Print the structure of each news to find the correct key for the news text
                st.write(f"News {idx} structure:")
                st.write(news)
                
                # Uncomment the following line once you identify the correct key for the news text
                # sentiment_results = sentiment_analysis(news["<correct_key_for_text>"])[0]
        else:
            st.write("No news relevant to Energy | Oil.")

def main():
    analyze_financial_news()

if __name__ == "__main__":
    main()