Update app.py

app.py

@@ -1,50 +1,33 @@
+import os
 import streamlit as st
-from transformers import pipeline
+from transformers import pipeline, AutoTokenizer, AutoModelForSeq2SeqLM
 
 def analyze_financial_news():
-    access = "hf_"
-    token = "hhbFNpjKohezoexWMlyPUpvJQLWlaFhJaa"
-
-    # Load the text classification model pipeline
-    analysis = pipeline("text-classification", model='ZephyruSalsify/FinNews_SentimentAnalysis')
-    classification = pipeline("text-classification", model="nickmuchi/finbert-tone-finetuned-finance-topic-classification", token=access+token)
-
-    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 input for user to enter the financial news
     text = st.text_area("Enter the Financial News", "")
 
-    label_1 = ""
-    score_1 = 0.0
-    label_2 = ""
-    score_2 = 0.0
+    # Load the summarization pipeline
+    summarization_pipe = pipeline("summarization", model="facebook/bart-large-cnn")
 
-    analyze_clicked = st.button("Analyze")
+    # Use pipeline as a high-level helper
+    summary = summarization_pipe(text)[0]['summary_text']
 
-    if analyze_clicked:
-        # Perform text analysis on the input text
-        results_1 = analysis(text)[0]
-        results_2 = classification(text)[0]
-
-        label_1 = results_1["label"]
-        score_1 = results_1["score"]
-        label_2 = results_2["label"]
-        score_2 = results_2["score"]
+    # Perform sentiment analysis on the summarized text
+    sentiment_pipe = pipeline("sentiment-analysis")
+    sentiment_results = sentiment_pipe(summary)[0]
 
     # Display the results
     st.write("Financial Text:", text)
-    st.write("Trend:", label_1)
-    st.write("Trend_Score:", score_1)
-
-    st.write("Finance Topic:", label_2)
-    st.write("Topic_Score:", score_2)
+    st.write("Summary:", summary)
+    st.write("Sentiment:", sentiment_results["label"])
+    st.write("Sentiment Score:", sentiment_results["score"])
 
 def main():
+    st.set_page_config(page_title="Financial News Analysis", page_icon="♕")
     analyze_financial_news()
 
 if __name__ == "__main__":