Create app.py

app.py

@@ -0,0 +1,140 @@
+import os
+import gradio as gr
+from transformers import pipeline
+import spacy
+import lib.read_pdf
+# Initialize spaCy model
+nlp = spacy.load('en_core_web_sm')
+nlp.add_pipe('sentencizer')
+
+def split_in_sentences(text):
+    doc = nlp(text)
+    return [str(sent).strip() for sent in doc.sents]
+
+def make_spans(text, results):
+    results_list = [res['label'] for res in results]
+    facts_spans = list(zip(split_in_sentences(text), results_list))
+    return facts_spans
+
+# 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')
+
+def summarize_text(text):
+    resp = summarizer(text)
+    return resp[0]['summary_text']
+
+def text_to_sentiment(text):
+    sentiment = fin_model(text)[0]["label"]
+    return sentiment
+
+def fin_ext(text):
+    results = fin_model(split_in_sentences(text))
+    return make_spans(text, results)
+
+def extract_and_summarize(pdf1, pdf2):
+    if not pdf1 or not pdf2:
+        return [], []
+
+    pdf1_path = os.path.join(PDF_FOLDER, pdf1)
+    pdf2_path = os.path.join(PDF_FOLDER, pdf2)
+
+    # Extract and format paragraphs
+    paragraphs_1 = lib.read_pdf.extract_and_format_paragraphs(pdf1_path)
+    paragraphs_2 = lib.read_pdf.extract_and_format_paragraphs(pdf2_path)
+
+    start_keyword = "Main risks to"
+    end_keywords = ["4. Appendix", "Annex:", "4. Annex", "Detailed tables", "ACKNOWLEDGEMENTS", "STATISTICAL ANNEX", "PROSPECTS BY MEMBER STATES"]
+
+    start_index1, end_index1 = lib.read_pdf.find_text_range(paragraphs_1, start_keyword, end_keywords)
+    start_index2, end_index2 = lib.read_pdf.find_text_range(paragraphs_2, start_keyword, end_keywords)
+
+    paragraphs_1 = lib.read_pdf.extract_relevant_text(paragraphs_1, start_index1, end_index1)
+    paragraphs_2 = lib.read_pdf.extract_relevant_text(paragraphs_2, start_index2, end_index2)
+
+    paragraphs_1 = lib.read_pdf.split_text_into_paragraphs(paragraphs_1, 0)
+    paragraphs_2 = lib.read_pdf.split_text_into_paragraphs(paragraphs_2, 0)
+
+    return paragraphs_1, paragraphs_2
+
+# Gradio interface setup
+PDF_FOLDER = "data"
+
+def get_pdf_files(folder):
+    return [f for f in os.listdir(folder) if f.endswith('.pdf')]
+
+stored_paragraphs_1 = []
+stored_paragraphs_2 = []
+
+with gr.Blocks() as demo:
+    gr.Markdown("## Financial Report Paragraph Selection and Analysis")
+
+    with gr.Row():
+        # Upload PDFs
+        with gr.Column():
+            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")
+
+        with gr.Column():
+            b1 = gr.Button("Extract and Display Paragraphs")
+            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_summarize(pdf1, pdf2)
+                updated_dropdown_1 = gr.Dropdown.update(choices=[f"Paragraph {i+1}: {p[:100]}..." for i, p in enumerate(stored_paragraphs_1)], label="Select Paragraph from PDF 1")
+                updated_dropdown_2 = gr.Dropdown.update(choices=[f"Paragraph {i+1}: {p[:100]}..." for i, p in enumerate(stored_paragraphs_2)], label="Select Paragraph from PDF 2")
+                return updated_dropdown_1, updated_dropdown_2
+
+            b1.click(fn=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():
+            selected_paragraph_1 = gr.Textbox(label="Selected Paragraph 1 Content")
+            summarize_btn1 = gr.Button("Summarize Text from PDF 1")
+            sentiment_btn1 = gr.Button("Classify Financial Tone from PDF 1")
+            fin_spans_1 = gr.HighlightedText(label="Financial Tone Analysis for PDF 1")
+
+            def process_paragraph_1(paragraph):
+                try:
+                    paragraph_index = int(paragraph.split(':')[0].replace('Paragraph ', '')) - 1
+                    selected_paragraph = stored_paragraphs_1[paragraph_index]
+                    summary = summarize_text(selected_paragraph)
+                    sentiment = text_to_sentiment(selected_paragraph)
+                    fin_spans = fin_ext(selected_paragraph)
+                    return selected_paragraph, summary, sentiment, fin_spans
+                except (IndexError, ValueError):
+                    return "Invalid selection", "Error", "Error", []
+
+            summarize_btn1.click(fn=lambda p: process_paragraph_1(p)[1], inputs=paragraph_1_dropdown, outputs=selected_paragraph_1)
+            sentiment_btn1.click(fn=lambda p: process_paragraph_1(p)[2], inputs=paragraph_1_dropdown, outputs=selected_paragraph_1)
+            b5 = gr.Button("Analyze Financial Tone and FLS")
+            b5.click(fn=lambda p: process_paragraph_1(p)[3], inputs=paragraph_1_dropdown, outputs=fin_spans_1)
+
+    with gr.Row():
+        # Process the selected paragraph from PDF 2
+        with gr.Column():
+            selected_paragraph_2 = gr.Textbox(label="Selected Paragraph 2 Content")
+            summarize_btn2 = gr.Button("Summarize Text from PDF 2")
+            sentiment_btn2 = gr.Button("Classify Financial Tone from PDF 2")
+            fin_spans_2 = gr.HighlightedText(label="Financial Tone Analysis for PDF 2")
+
+            def process_paragraph_2(paragraph):
+                try:
+                    paragraph_index = int(paragraph.split(':')[0].replace('Paragraph ', '')) - 1
+                    selected_paragraph = stored_paragraphs_2[paragraph_index]
+                    summary = summarize_text(selected_paragraph)
+                    sentiment = text_to_sentiment(selected_paragraph)
+                    fin_spans = fin_ext(selected_paragraph)
+                    return selected_paragraph, summary, sentiment, fin_spans
+                except (IndexError, ValueError):
+                    return "Invalid selection", "Error", "Error", []
+
+            summarize_btn2.click(fn=lambda p: process_paragraph_2(p)[1], inputs=paragraph_2_dropdown, outputs=selected_paragraph_2)
+            sentiment_btn2.click(fn=lambda p: process_paragraph_2(p)[2], inputs=paragraph_2_dropdown, outputs=selected_paragraph_2)
+            b6 = gr.Button("Analyze Financial Tone and FLS")
+            b6.click(fn=lambda p: process_paragraph_2(p)[3], inputs=paragraph_2_dropdown, outputs=fin_spans_2)
+
+demo.launch()