Update app.py

app.py

@@ -302,7 +302,7 @@ stored_df1 = []
 stored_df2 = []
 
 with gr.Blocks() as demo:
-    with gr.Tab("Contents"):
+    with gr.Tab("Methodology"):
         gr.Markdown("""
         ## Macro-economy Adverse Scenario Comparison from EBA Reports
         
@@ -322,108 +322,72 @@ with gr.Blocks() as demo:
         - Select two Excel files and a sheet name.
         - For the two selected tables, compute the difference of the cumulative adverse growth rate over their respective three years for the selected sheet name (topic).
         - For the selected topic (sheet name), find related sentences in the associated PDF text that mention the topic, and classify them by sentiment.
-        - For a selected country and topic, describe the adverse growth rate trend over three years using the [**google/flan-t5-base** model](https://huggingface.co/google/flan-t5-base).
+        - For a selected country and topic, describe the adverse growth rate trend over three years using the [**google/flan-t5-base**](https://huggingface.co/google/flan-t5-base).
         """)
     with gr.Tab("Financial Report Text Analysis"):
-        gr.Markdown("## Financial Report Paragraph Selection and Analysis on adverse macro-economy scenario")
+        gr.Markdown("## Paragraph Extraction and Analysis on Adverse Macro-Economy Scenarios")
 
         with gr.Row():
-            # Upload PDFs
             with gr.Column():
+                gr.Markdown("### Step 1: Upload and Extract Paragraphs")
                 pdf1 = gr.Dropdown(choices=get_pdf_files(PDF_FOLDER), label="Select PDF 1")
                 pdf2 = gr.Dropdown(choices=get_pdf_files(PDF_FOLDER), label="Select PDF 2")
-
+                extract_button = gr.Button("Extract Paragraphs")
+                
             with gr.Column():
-                b1 = gr.Button("Extract and Display Paragraphs")
+                gr.Markdown("### Step 2: Select Paragraphs for Analysis")
                 paragraph_1_dropdown = gr.Dropdown(label="Select Paragraph from PDF 1")
                 paragraph_2_dropdown = gr.Dropdown(label="Select Paragraph from PDF 2")
 
                 def update_paragraphs(pdf1, pdf2):
-                    global stored_paragraphs_1, stored_paragraphs_2
                     stored_paragraphs_1, stored_paragraphs_2 = extract_and_paragraph(pdf1, pdf2, True)
-                    updated_dropdown_1 = [f"Paragraph {i+1}: {p[:100]}..." for i, p in enumerate(stored_paragraphs_1)]
-                    updated_dropdown_2 = [f"Paragraph {i+1}: {p[:100]}..." for i, p in enumerate(stored_paragraphs_2)]
-                    return gr.update(choices=updated_dropdown_1), gr.update(choices=updated_dropdown_2)
+                    return [f"Paragraph {i+1}: {p[:100]}..." for i, p in enumerate(stored_paragraphs_1)], \
+                           [f"Paragraph {i+1}: {p[:100]}..." for i, p in enumerate(stored_paragraphs_2)]
 
-                b1.click(fn=update_paragraphs, inputs=[pdf1, pdf2], outputs=[paragraph_1_dropdown, paragraph_2_dropdown])
+                extract_button.click(update_paragraphs, inputs=[pdf1, pdf2], outputs=[paragraph_1_dropdown, paragraph_2_dropdown])
 
         with gr.Row():
-            # Process the selected paragraph from PDF 1
             with gr.Column():
                 gr.Markdown("### PDF 1 Analysis")
-                selected_paragraph_1 = gr.Textbox(label="Selected Paragraph 1 Content", lines=4)
                 summarize_btn1 = gr.Button("Summarize Text from PDF 1")
                 summary_textbox_1 = gr.Textbox(label="Summary for PDF 1", lines=2)
-                summarize_btn1.click(fn=lambda p: process_paragraph_1_sum(p), inputs=paragraph_1_dropdown, outputs=summary_textbox_1)
                 sentiment_btn1 = gr.Button("Classify Financial Tone from PDF 1")
-                sentiment_textbox_1 = gr.Textbox(label="Classification for PDF 1", lines=1)
-                sentiment_btn1.click(fn=lambda p: process_paragraph_1_sent(p), inputs=paragraph_1_dropdown, outputs=sentiment_textbox_1)
-                analyze_btn1 = gr.Button("Analyze Financial Tone on each sentence with yiyanghkust/finbert-tone")
-                fin_spans_1 = gr.HighlightedText(label="Financial Tone Analysis for PDF 1")
-                analyze_btn1.click(fn=lambda p: process_paragraph_1_sent_tone(p), inputs=paragraph_1_dropdown, outputs=fin_spans_1)
-                analyze_btn1_ = gr.Button("Analyze Financial Tone on each sentence with ProsusAI/finbert")
-                fin_spans_1_ = gr.HighlightedText(label="Financial Tone Analysis for PDF 1 bis")
-                analyze_btn1_.click(fn=lambda p: process_paragraph_1_sent_tone_bis(p), inputs=paragraph_1_dropdown, outputs=fin_spans_1_)
-
-            # Process the selected paragraph from PDF 2
+                sentiment_textbox_1 = gr.Textbox(label="Tone Classification for PDF 1", lines=1)
+
+                summarize_btn1.click(process_paragraph_1_sum, inputs=paragraph_1_dropdown, outputs=summary_textbox_1)
+                sentiment_btn1.click(process_paragraph_1_sent, inputs=paragraph_1_dropdown, outputs=sentiment_textbox_1)
+
             with gr.Column():
                 gr.Markdown("### PDF 2 Analysis")
-                selected_paragraph_2 = gr.Textbox(label="Selected Paragraph 2 Content", lines=4)
-                selected_paragraph_2.change(show, paragraph_2_dropdown, selected_paragraph_2)
                 summarize_btn2 = gr.Button("Summarize Text from PDF 2")
                 summary_textbox_2 = gr.Textbox(label="Summary for PDF 2", lines=2)
-                summarize_btn2.click(fn=lambda p: process_paragraph_2_sum(p), inputs=paragraph_2_dropdown, outputs=summary_textbox_2)
                 sentiment_btn2 = gr.Button("Classify Financial Tone from PDF 2")
-                sentiment_textbox_2 = gr.Textbox(label="Classification for PDF 2", lines=1)
-                sentiment_btn2.click(fn=lambda p: process_paragraph_2_sent(p), inputs=paragraph_2_dropdown, outputs=sentiment_textbox_2)
-                analyze_btn2 = gr.Button("Analyze Financial Tone on each sentence with yiyanghkust/finbert-tone")
-                fin_spans_2 = gr.HighlightedText(label="Financial Tone Analysis for PDF 2")
-                analyze_btn2.click(fn=lambda p: process_paragraph_2_sent_tone(p), inputs=paragraph_2_dropdown, outputs=fin_spans_2)
-                analyze_btn2_ = gr.Button("Analyze Financial Tone on each sentence with ProsusAI/finbert")
-                fin_spans_2_ = gr.HighlightedText(label="Financial Tone Analysis for PDF 2 bis")
-                analyze_btn2_.click(fn=lambda p: process_paragraph_2_sent_tone_bis(p), inputs=paragraph_2_dropdown, outputs=fin_spans_2_)
+                sentiment_textbox_2 = gr.Textbox(label="Tone Classification for PDF 2", lines=1)
+
+                summarize_btn2.click(process_paragraph_2_sum, inputs=paragraph_2_dropdown, outputs=summary_textbox_2)
+                sentiment_btn2.click(process_paragraph_2_sent, inputs=paragraph_2_dropdown, outputs=sentiment_textbox_2)
 
     with gr.Tab("Financial Report Table Analysis"):
-        # New tab content goes here
-        gr.Markdown("## Excel Data Comparison")
+        gr.Markdown("## Excel Data Comparison and Topic Analysis")
 
         with gr.Row():
             with gr.Column():
+                gr.Markdown("### Step 1: Upload Excel Files")
                 file1 = gr.Dropdown(choices=get_excel_files(PDF_FOLDER), label="Select Excel File 1")
                 file2 = gr.Dropdown(choices=get_excel_files(PDF_FOLDER), label="Select Excel File 2")
-                sheet = gr.Dropdown(choices=["GDP", "HICP", "RRE prices", "Unemployment", "CRE prices"], label="Select Sheet for File 1 and 2")
-            
-            with gr.Column():
-                result = gr.Image(label="Comparison pLot")
-        
-        def update_sheets(file):
-            return get_sheet_names(file)
-        
-        
-        b1 = gr.Button("Compare Data")
-        b2 = gr.Button("Extract text information")
-        
-        with gr.Row():
+                sheet = gr.Dropdown(choices=["GDP", "HICP", "RRE prices", "Unemployment", "CRE prices"], label="Select Sheet")
+
             with gr.Column():
-                sentiment_results_pdf1 = gr.HighlightedText(label="Sentiment Analysis - PDF 1")
+                gr.Markdown("### Step 2: Select a Country for Adverse Growth Analysis")
                 country_1_dropdown = gr.Dropdown(label="Select Country from Excel File 1")
-                summarize_btn1_country = gr.Button("Summary for the selected country")
-                text_result_df1 = gr.Textbox(label="Sentence for excel file 1", lines=2)
-                summarize_btn1_country.click(fn=lambda country, theme: generate_text(stored_df1, country, theme),
-                             inputs=[country_1_dropdown, sheet],
-                             outputs=text_result_df1)
-            with gr.Column():
-                sentiment_results_pdf2 = gr.HighlightedText(label="Sentiment Analysis - PDF 2")
                 country_2_dropdown = gr.Dropdown(label="Select Country from Excel File 2")
-                summarize_btn2_country = gr.Button("Summary for the selected country")
-                text_result_df2 = gr.Textbox(label="Sentence for excel file 2", lines=2)
-                summarize_btn2_country.click(fn=lambda country, theme: generate_text(stored_df2, country, theme),
-                             inputs=[country_2_dropdown, sheet],
-                             outputs=text_result_df2)
-    
-        # Button to extract text from PDFs and perform sentiment analysis
-        b1.click(fn=process_and_compare, inputs=[file1, sheet, file2, sheet], outputs=[result,country_1_dropdown, country_2_dropdown])
-        b2.click(fn=process_pdfs_and_analyze_sentiment, inputs=[file1, file2, sheet], outputs=[sentiment_results_pdf1, sentiment_results_pdf2])
 
+        with gr.Row():
+            gr.Markdown("### Step 3: Compare Data and Generate Reports")
+            comparison_button = gr.Button("Compare Data")
+            text_result_df1 = gr.Textbox(label="Adverse Growth Report for Excel File 1", lines=4)
+            text_result_df2 = gr.Textbox(label="Adverse Growth Report for Excel File 2", lines=4)
+
+            comparison_button.click(fn=process_and_compare, inputs=[file1, sheet, file2], outputs=[text_result_df1, text_result_df2])
 
 demo.launch()