Update app.py

app.py

@@ -47,7 +47,6 @@ def train_model(output_range):
     model = LinearRegression().fit(X, y)
     return model
 
-
 # Load models
 try:
     hemoglobin_model = joblib.load("hemoglobin_model_from_anemia_dataset.pkl")
@@ -160,10 +159,13 @@ def save_results_to_pdf(test_results, filename):
         return f"Error saving PDF: {str(e)}", None
 
 # Build health card layout
-def build_health_card(profile_image, test_results, summary, patient_name="", patient_age="", patient_gender="", patient_id=""):
+def build_health_card(profile_image, test_results, summary, pdf_filepath, patient_name="", patient_age="", patient_gender="", patient_id=""):
     from datetime import datetime
     current_date = datetime.now().strftime("%B %d, %Y")
     
+    # Use a relative path for the download link to work in Gradio
+    pdf_filename = os.path.basename(pdf_filepath) if pdf_filepath else "health_report.pdf"
+    
     html = f"""
     <div id="health-card" style="font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif; max-width: 700px; margin: 20px auto; border-radius: 16px; background: linear-gradient(135deg, #e3f2fd 0%, #f3e5f5 100%); border: 2px solid #ddd; box-shadow: 0 8px 32px rgba(0, 0, 0, 0.15); padding: 30px; color: #1a1a1a;">
         
@@ -203,22 +205,14 @@ def build_health_card(profile_image, test_results, summary, patient_name="", pat
         </div>
 
         <div style="display: flex; gap: 15px; justify-content: center; flex-wrap: wrap;">
-            <button onclick="window.print()" style="padding: 12px 24px; background: linear-gradient(135deg, #4caf50, #45a049); color: white; border: none; border-radius: 8px; cursor: pointer; font-weight: 600; font-size: 14px; box-shadow: 0 4px 12px rgba(76, 175, 80, 0.3); transition: all 0.3s;">
+            <a href="/file=/tmp/{pdf_filename}" download="{pdf_filename}" style="padding: 12px 24px; background: linear-gradient(135deg, #4caf50, #45a049); color: white; border: none; border-radius: 8px; cursor: pointer; font-weight: 600; font-size: 14px; box-shadow: 0 4px 12px rgba(76, 175, 80, 0.3); transition: all 0.3s; text-decoration: none;">
                 📥 Download Report
-            </button>
+            </a>
             <button style="padding: 12px 24px; background: linear-gradient(135deg, #2196f3, #1976d2); color: white; border: none; border-radius: 8px; cursor: pointer; font-weight: 600; font-size: 14px; box-shadow: 0 4px 12px rgba(33, 150, 243, 0.3);">
                 📞 Find Labs Near Me
             </button>
         </div>
     </div>
-    <style>
-    @media print {{
-        /* Hide input sections during print */
-        .gradio-container {{ display: block; }}
-        /* Keep only the health card visible */
-        #health-card {{ display: block; }}
-    }}
-    </style>
     """
     return html
 
@@ -246,7 +240,7 @@ def analyze_face(input_data):
     result = face_mesh.process(frame_rgb)
     if not result.multi_face_landmarks:
         return "<div style='color:red;'>⚠️ Error: Face not detected.</div>", None
-    landmarks = result.multi_face_landmarks[0].landmark  # Fixed: Use integer index
+    landmarks = result.multi_face_landmarks[0].landmark
     features = extract_features(frame_rgb, landmarks)
     test_values = {}
     r2_scores = {}
@@ -264,14 +258,12 @@ def analyze_face(input_data):
     gray = cv2.cvtColor(frame_rgb, cv2.COLOR_RGB2GRAY)
     green_std = np.std(frame_rgb[:, :, 1]) / 255
     brightness_std = np.std(gray) / 255
-    tone_index = np.mean(frame_rgb[100:150, 100:150]) / 255 if frame_rgb[
-        100:150, 100:150].size else 0.5
+    tone_index = np.mean(frame_rgb[100:150, 100:150]) / 255 if frame_rgb[100:150, 100:150].size else 0.5
     hr_features = [brightness_std, green_std, tone_index]
     heart_rate = float(np.clip(hr_model.predict([hr_features])[0], 60, 100))
     skin_patch = frame_rgb[100:150, 100:150]
     skin_tone_index = np.mean(skin_patch) / 255 if skin_patch.size else 0.5
-    brightness_variation = np.std(cv2.cvtColor(frame_rgb,
-                                               cv2.COLOR_RGB2GRAY)) / 255
+    brightness_variation = np.std(cv2.cvtColor(frame_rgb, cv2.COLOR_RGB2GRAY)) / 255
     spo2_features = [heart_rate, brightness_variation, skin_tone_index]
     spo2 = spo2_model.predict([spo2_features])[0]
     rr = int(12 + abs(heart_rate % 5 - 2))
@@ -281,8 +273,7 @@ def analyze_face(input_data):
         build_table("🩸 Hematology",
                     [("Hemoglobin", test_values["Hemoglobin"], (13.5, 17.5)),
                      ("WBC Count", test_values["WBC Count"], (4.0, 11.0)),
-                     ("Platelet Count", test_values["Platelet Count"],
-                      (150, 450))]),
+                     ("Platelet Count", test_values["Platelet Count"], (150, 450))]),
         "Iron Panel":
         build_table("🧬 Iron Panel",
                     [("Iron", test_values["Iron"], (60, 170)),
@@ -312,18 +303,6 @@ def analyze_face(input_data):
     _, buffer = cv2.imencode('.png', frame_rgb)
     profile_image_base64 = base64.b64encode(buffer).decode('utf-8')
 
-    # Use global patient details
-    global current_patient_details
-    health_card_html = build_health_card(
-        profile_image_base64, 
-        test_results,
-        summary, 
-        current_patient_details['name'],
-        current_patient_details['age'],
-        current_patient_details['gender'],
-        current_patient_details['id']
-    )
-    
     # Generate PDF and return for download
     pdf_filename = f"Health_Report_{datetime.now().strftime('%Y-%m-%d_%H-%M-%S')}.pdf"
     pdf_result, pdf_filepath = save_results_to_pdf(test_results, pdf_filename)
@@ -333,9 +312,20 @@ def analyze_face(input_data):
         temp_pdf_path = "/tmp/" + os.path.basename(pdf_filepath)
         shutil.copy(pdf_filepath, temp_pdf_path)
         
+        # Pass pdf_filepath to build_health_card
+        health_card_html = build_health_card(
+            profile_image_base64, 
+            test_results,
+            summary, 
+            temp_pdf_path,  # Pass the PDF path
+            current_patient_details['name'],
+            current_patient_details['age'],
+            current_patient_details['gender'],
+            current_patient_details['id']
+        )
+        
         return health_card_html, temp_pdf_path
 
-
 # Modified route_inputs function
 def route_inputs(mode, image, video, patient_name, patient_age, patient_gender, patient_id):
     if mode == "Image" and image is None:
@@ -355,7 +345,6 @@ def route_inputs(mode, image, video, patient_name, patient_age, patient_gender,
     health_card_html, pdf_file_path = analyze_face(image if mode == "Image" else video)
     return health_card_html, pdf_file_path
 
-
 # Create Gradio interface
 with gr.Blocks() as demo:
     gr.Markdown("""# 🧠 Face-Based Lab Test AI Report (Video Mode)""")