Update app.py

app.py

@@ -1,3 +1,4 @@
+
 import gradio as gr
 import cv2
 import numpy as np
@@ -6,10 +7,6 @@ from sklearn.linear_model import LinearRegression
 import random
 import base64
 import joblib
-import pandas as pd
-from reportlab.lib.pagesizes import letter
-from reportlab.pdfgen import canvas
-from io import BytesIO
 
 # Initialize the face mesh model
 mp_face_mesh = mp.solutions.face_mesh
@@ -18,6 +15,7 @@ face_mesh = mp_face_mesh.FaceMesh(static_image_mode=True,
                                   refine_landmarks=True,
                                   min_detection_confidence=0.5)
 
+
 # Functions for feature extraction
 def extract_features(image, landmarks):
     red_channel = image[:, :, 2]
@@ -52,7 +50,8 @@ try:
     spo2_model = joblib.load("spo2_model_simulated.pkl")
     hr_model = joblib.load("heart_rate_model.pkl")
 except FileNotFoundError:
-    print("Error: One or more .pkl model files are missing. Please upload them.")
+    print(
+        "Error: One or more .pkl model files are missing. Please upload them.")
     exit(1)
 
 models = {
@@ -196,23 +195,8 @@ def build_health_card(profile_image, test_results, summary, patient_name="", pat
     return html
 
 
-# Function to generate PDF from HTML content using reportlab
-def generate_pdf(html_content):
-    buffer = BytesIO()
-    c = canvas.Canvas(buffer, pagesize=letter)
-    
-    # Adding basic content to PDF (you can modify this to match your layout)
-    text = c.beginText(40, 750)
-    text.setFont("Helvetica", 12)
-    text.textLines(html_content)  # Add the content
-
-    c.drawText(text)
-    c.showPage()
-    c.save()
-
-    buffer.seek(0)
-    return buffer
-
+# Initialize global variable for patient details
+current_patient_details = {'name': '', 'age': '', 'gender': '', 'id': ''}
 
 # Modified analyze_face function
 def analyze_face(input_data):
@@ -239,16 +223,12 @@ def analyze_face(input_data):
     landmarks = result.multi_face_landmarks[
         0].landmark  # Fixed: Use integer index
     features = extract_features(frame_rgb, landmarks)
-    
-    # Convert features to pandas DataFrame with correct column names (matching the training phase)
-    features_df = pd.DataFrame([features], columns=["%red pixel", "%green pixel", "%blue pixel"])  # Ensure lowercase column names
-    
     test_values = {}
     r2_scores = {}
 
     for label in models:
         if label == "Hemoglobin":
-            prediction = models[label].predict(features_df)[0]
+            prediction = models[label].predict([features])[0]
             test_values[label] = prediction
             r2_scores[label] = 0.385
         else:
@@ -319,10 +299,7 @@ def analyze_face(input_data):
         current_patient_details['gender'],
         current_patient_details['id']
     )
-
-    # Generate PDF from the HTML content
-    pdf_file = generate_pdf(health_card_html)
-    return health_card_html, pdf_file
+    return health_card_html, frame_rgb
 
 
 # Modified route_inputs function
@@ -341,9 +318,8 @@ def route_inputs(mode, image, video, patient_name, patient_age, patient_gender,
         'id': patient_id
     }
     
-    health_card_html, pdf_file = analyze_face(image if mode == "Image" else video)
-    
-    return health_card_html, pdf_file
+    health_card_html, frame_rgb = analyze_face(image if mode == "Image" else video)
+    return health_card_html, frame_rgb
 
 
 # Create Gradio interface
@@ -368,11 +344,10 @@ with gr.Blocks() as demo:
         with gr.Column():
             result_html = gr.HTML(label="🧪 Health Report Table")
             result_image = gr.Image(label="📷 Key Frame Snapshot")
-            download_btn = gr.Button("📥 Download PDF")
-            
+
     submit_btn.click(fn=route_inputs,
                      inputs=[mode_selector, image_input, video_input, patient_name, patient_age, patient_gender, patient_id],
                      outputs=[result_html, result_image])
 
 # Launch Gradio for Replit
-demo.launch(server_name="0.0.0.0", server_port=7860)
+demo.launch(server_name="0.0.0.0", server_port=7860)