Update app.py

app.py

@@ -20,6 +20,7 @@ def make_spans(text, results):
 # Initialize pipelines
 summarizer = pipeline("summarization", model="human-centered-summarization/financial-summarization-pegasus")
 fin_model = pipeline("sentiment-analysis", model='yiyanghkust/finbert-tone', tokenizer='yiyanghkust/finbert-tone')
+fin_model_bis = pipeline("sentiment-analysis", model='ProsusAI/finbert', tokenizer='ProsusAI/finbert')
 
 def summarize_text(text):
     resp = summarizer(text)
@@ -32,6 +33,9 @@ def text_to_sentiment(text):
 def fin_ext(text):
     results = fin_model(split_in_sentences(text))
     return make_spans(text, results)
+def fin_ext_bis(text):
+    results = fin_model_bis(split_in_sentences(text))
+    return make_spans(text, results)
 
 def extract_and_summarize(pdf1, pdf2):
     if not pdf1 or not pdf2:
@@ -97,51 +101,103 @@ with gr.Blocks() as demo:
         # Process the selected paragraph from PDF 1
         with gr.Column():
             gr.Markdown("### PDF 1 Analysis")
-            def process_paragraph_1(paragraph):
+            def process_paragraph_1_sum(paragraph):
                 try:
                     paragraph_index = int(paragraph.split(':')[0].replace('Paragraph ', '')) - 1
                     selected_paragraph = stored_paragraphs_1[paragraph_index]
                     summary = summarize_text(selected_paragraph)
+                    return summary
+                except (IndexError, ValueError):
+                    return "Error"
+            def process_paragraph_1_sent(paragraph):
+                try:
+                    paragraph_index = int(paragraph.split(':')[0].replace('Paragraph ', '')) - 1
+                    selected_paragraph = stored_paragraphs_1[paragraph_index]
                     sentiment = text_to_sentiment(selected_paragraph)
+
+                    return sentiment
+                except (IndexError, ValueError):
+                    return "Error"
+            def process_paragraph_1_sent_tone(paragraph):
+                try:
+                    paragraph_index = int(paragraph.split(':')[0].replace('Paragraph ', '')) - 1
+                    selected_paragraph = stored_paragraphs_1[paragraph_index]
                     fin_spans = fin_ext(selected_paragraph)
-                    return selected_paragraph, summary, sentiment, fin_spans
+                    return fin_spans
                 except (IndexError, ValueError):
-                    return "Invalid selection", "Error", "Error", []
+                    return []
+            def process_paragraph_1_sent_tone_bis(paragraph):
+                try:
+                    paragraph_index = int(paragraph.split(':')[0].replace('Paragraph ', '')) - 1
+                    selected_paragraph = stored_paragraphs_1[paragraph_index]
+                    fin_spans = fin_ext_bis(selected_paragraph)
+                    return fin_spans
+                except (IndexError, ValueError):
+                    return []
             selected_paragraph_1 = gr.Textbox(label="Selected Paragraph 1 Content", lines=4)
             selected_paragraph_1.change(show, paragraph_1_dropdown, selected_paragraph_1)
             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(p)[1], inputs=paragraph_1_dropdown, outputs=summary_textbox_1)
+            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(p)[2], inputs=paragraph_1_dropdown, outputs=sentiment_textbox_1)
-            analyze_btn1 = gr.Button("Analyze Financial Tone on each sentence")
+            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(p)[3], inputs=paragraph_1_dropdown, outputs=fin_spans_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)[3], inputs=paragraph_1_dropdown, outputs=fin_spans_1_)
 
         # Process the selected paragraph from PDF 2
         with gr.Column():
             gr.Markdown("### PDF 2 Analysis")
-            def process_paragraph_2(paragraph):
+            def process_paragraph_2_sum(paragraph):
                 try:
                     paragraph_index = int(paragraph.split(':')[0].replace('Paragraph ', '')) - 1
-                    selected_paragraph = stored_paragraphs_2[paragraph_index]
+                    selected_paragraph = stored_paragraphs_1[paragraph_index]
                     summary = summarize_text(selected_paragraph)
+                    return summary
+                except (IndexError, ValueError):
+                    return "Error"
+            def process_paragraph_2_sent(paragraph):
+                try:
+                    paragraph_index = int(paragraph.split(':')[0].replace('Paragraph ', '')) - 1
+                    selected_paragraph = stored_paragraphs_1[paragraph_index]
                     sentiment = text_to_sentiment(selected_paragraph)
+
+                    return sentiment
+                except (IndexError, ValueError):
+                    return "Error"
+            def process_paragraph_2_sent_tone(paragraph):
+                try:
+                    paragraph_index = int(paragraph.split(':')[0].replace('Paragraph ', '')) - 1
+                    selected_paragraph = stored_paragraphs_1[paragraph_index]
                     fin_spans = fin_ext(selected_paragraph)
-                    return selected_paragraph, summary, sentiment, fin_spans
+                    return fin_spans
+                except (IndexError, ValueError):
+                    return []
+            def process_paragraph_2_sent_tone_bis(paragraph):
+                try:
+                    paragraph_index = int(paragraph.split(':')[0].replace('Paragraph ', '')) - 1
+                    selected_paragraph = stored_paragraphs_2[paragraph_index]
+                    fin_spans = fin_ext_bis(selected_paragraph)
+                    return fin_spans
                 except (IndexError, ValueError):
-                    return "Invalid selection", "Error", "Error", []
+                    return []
             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(p)[1], inputs=paragraph_2_dropdown, outputs=summary_textbox_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(p)[2], inputs=paragraph_2_dropdown, outputs=sentiment_textbox_2)
-            analyze_btn2 = gr.Button("Analyze Financial Tone on each sentence")
+            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(p)[3], inputs=paragraph_2_dropdown, outputs=fin_spans_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)[3], inputs=paragraph_2_dropdown, outputs=fin_spans_2_)
 
 demo.launch()