Update app.py

app.py

@@ -1,5 +1,4 @@
 
-
 import gradio as gr
 import fitz  # PyMuPDF
 import docx
@@ -57,15 +56,6 @@ def content_change_score(text1, text2):
     except:
         return 100.0
 
-def structure_score(text):
-    toc_score = 5 if "table of contents" in text.lower() else 0
-    bullet_score = 5 if len(re.findall(r"\n\s*[-•*]", text)) > 10 else 0
-    return toc_score + bullet_score
-
-def calculate_weighted_score(content_diff, improved_los, total_los, struct_score=10):
-    lo_component = (improved_los / total_los) * 100 if total_los > 0 else 0
-    return round(0.6 * lo_component + 0.3 * content_diff + 0.1 * struct_score, 2)
-
 def compare_handouts(old_pdf, new_pdf, lo_file):
     old_text = extract_text_from_pdf(old_pdf)
     new_text = extract_text_from_pdf(new_pdf)
@@ -80,23 +70,22 @@ def compare_handouts(old_pdf, new_pdf, lo_file):
     old_scores = semantic_match(lo_list, old_text)
     new_scores = semantic_match(lo_list, new_text)
 
-    content_diff = content_change_score(old_text, new_text)
-    improved_count = sum([n > o for n, o in zip(new_scores, old_scores)])
-    matched_los = sum([n >= o for n, o in zip(new_scores, old_scores)])
-    struct_score = structure_score(new_text)
-
-    weighted_score = calculate_weighted_score(content_diff, improved_count, len(lo_list), struct_score)
+    content_diff_percent = content_change_score(old_text, new_text)
+    lo_improvements = [round(new - old, 2) for new, old in zip(new_scores, old_scores)]
+    improved_count = sum([diff > 0.01 for diff in lo_improvements])
+    improved_total = sum([diff for diff in lo_improvements if diff > 0])
 
-    summary = f"🧠 Improved LOs: {improved_count} / {len(lo_list)}\n"
-    summary += f"📄 Content Change Estimate: {content_diff}%\n"
-    summary += f"🏗️ Structure Score: {struct_score}/10\n"
-    summary += f"🔢 Final Weighted Score: {weighted_score}%\n"
+    lo_change_percent = round((improved_total / len(lo_list)) * 100, 2)
 
+    summary = f"🧠 Improved LOs: {improved_count} / {len(lo_list)} (Total improvement score: {improved_total})\n"
+    summary += f"📄 Content Change Estimate: {content_diff_percent}%\n"
+    summary += f"🎯 LO Change Estimate: {lo_change_percent}%\n"
     if improved_count > 0:
-        summary += "\n🟢 Summary: New handout better aligns with LOs and has improved clarity."
+        summary += "🟢 Summary: New handout better aligns with LOs and has improved clarity."
     else:
-        summary += "\n⚠️ Summary: No significant LO improvement detected."
+        summary += "⚠️ Summary: No significant improvement in LO alignment."
 
+    # Plot
     x = np.arange(len(lo_list))
     width = 0.35
     fig, ax = plt.subplots()
@@ -112,8 +101,8 @@ def compare_handouts(old_pdf, new_pdf, lo_file):
     return summary, fig
 
 with gr.Blocks() as demo:
-    gr.Markdown("📘 **Educational Content Comparator - Weighted Analysis**")
-    gr.Markdown("Upload old & new handouts + Learning Outcomes (.docx) to evaluate change & alignment.")
+    gr.Markdown("📘 **Educational Content Comparator**")
+    gr.Markdown("Upload 2 handouts and a .docx file of Learning Outcomes to compare changes and alignment.")
 
     with gr.Row():
         old_pdf = gr.File(label="📂 Upload Old PDF", file_types=[".pdf"], type="binary")
@@ -124,7 +113,7 @@ with gr.Blocks() as demo:
         btn = gr.Button("Submit")
         clear_btn = gr.Button("Clear")
 
-    output_text = gr.Textbox(label="📋 Summary", lines=6)
+    output_text = gr.Textbox(label="📋 Summary", lines=6, interactive=False)
     output_plot = gr.Plot(label="📊 LO Match Chart")
 
     btn.click(fn=compare_handouts, inputs=[old_pdf, new_pdf, lo_file], outputs=[output_text, output_plot])