Update app.py

app.py

@@ -41,6 +41,13 @@ def semantic_match(lo_list, content):
     scores = [cosine_similarity([content_vec], [vec])[0][0] for vec in vectors[1:]]
     return scores
 
+def compute_change_percentage(old_text, new_text):
+    vectorizer = TfidfVectorizer()
+    vectors = vectorizer.fit_transform([old_text, new_text])
+    cos_sim = cosine_similarity(vectors[0], vectors[1])[0][0]
+    change_percentage = round((1 - cos_sim) * 100, 2)
+    return change_percentage
+
 def compare_all(old_pdf, new_pdf, lo_file):
     try:
         los = lo_file.decode("utf-8", errors="ignore").splitlines()
@@ -57,7 +64,6 @@ def compare_all(old_pdf, new_pdf, lo_file):
     old_scores = semantic_match(los, old_text)
     new_scores = semantic_match(los, new_text)
 
-    # Create bar plot
     labels = [f"LO{i+1}" for i in range(len(los))]
     x = range(len(labels))
     fig, ax = plt.subplots()
@@ -69,7 +75,6 @@ def compare_all(old_pdf, new_pdf, lo_file):
     ax.set_title("Learning Outcomes Comparison")
     ax.legend()
 
-    # Table
     data = {
         "Learning Outcome": labels,
         "Old Match": [round(s*100, 2) for s in old_scores],
@@ -78,8 +83,11 @@ def compare_all(old_pdf, new_pdf, lo_file):
     }
     df = pd.DataFrame(data)
 
-    summary = f"📈 Overall Content Change: {round(cosine_similarity([TfidfVectorizer().fit_transform([old_text, new_text]).toarray()[0]], [TfidfVectorizer().fit_transform([old_text, new_text]).toarray()[1]])[0][0] * 100, 2)}%"
-    summary += f"🎯 Matched LOs: {sum(1 for s in new_scores if s >= 0.5)} of {len(los)}"
+    change_percentage = compute_change_percentage(old_text, new_text)
+    matched_los = sum(1 for s in new_scores if s >= 0.5)
+
+    summary = f"📈 Overall Content Change: {change_percentage}%\n"
+    summary += f"🎯 Matched LOs: {matched_los} of {len(los)}\n"
     summary += f"🟢 New content appears {'more' if sum(new_scores) > sum(old_scores) else 'less'} aligned with outcomes."
 
     return summary, df, fig