Update app.py

app.py

@@ -5,19 +5,21 @@ import numpy as np
 import os
 import cv2
 import tensorflow as tf
-import firebase_admin
-from firebase_admin import credentials, db
 from datetime import datetime
+import psycopg2
+from psycopg2.extras import DictCursor
 
 app = Flask(__name__)
 
-# ✅ 1. Initialize Firebase
-cred = credentials.Certificate("glaucoma-4b682-firebase-adminsdk-fbsvc-cd31fbe99d.json")  # Path to your service account JSON
+# ✅ 1. Connect to PostgreSQL (Supabase)
+POSTGRES_URL = "postgresql://postgres.otihqjwfqjwccsipzroy:Dhruvagr%40123@aws-0-us-east-2.pooler.supabase.com:5432/postgres"
 
-firebase_admin.initialize_app(cred)
- # Will save results here
+def get_db_connection():
+    """Get a new database connection."""
+    conn = psycopg2.connect(POSTGRES_URL)
+    return conn
 
-# ✅ 2. Load the Model
+# ✅ 2. Load Model
 model = load_model('mobilenet_glaucoma_model.h5', compile=False)
 
 # ✅ 3. Preprocess Image
@@ -39,8 +41,8 @@ def make_gradcam(img_array, model, last_conv_layer_name='Conv_1_bn'):
     grads = tape.gradient(loss, conv_outputs)
 
     pooled_grads = tf.reduce_mean(grads, axis=(0, 1, 2))
-    conv_outputs = conv_outputs[0].numpy()  # ✅ IMPORTANT
-    pooled_grads = pooled_grads.numpy() 
+    conv_outputs = conv_outputs[0].numpy()
+    pooled_grads = pooled_grads.numpy()
 
     for i in range(conv_outputs.shape[-1]):
         conv_outputs[..., i] *= pooled_grads[i]
@@ -75,16 +77,16 @@ def home():
 
 @app.route("/test_file")
 def test_file():
-    """Check if the Firebase service account JSON is present and readable."""
-    filepath = "glaucoma-4b682-firebase-adminsdk-fbsvc-cd31fbe99d.json"
+    """Check if the model file is present and readable."""
+    filepath = "mobilenet_glaucoma_model.h5"
     if os.path.exists(filepath):
-        return f"✅ Service account file found at: {filepath}"
+        return f"✅ Model file found at: {filepath}"
     else:
-        return "❌ Service account JSON NOT found."
+        return "❌ Model file NOT found."
 
 @app.route('/predict', methods=['POST'])
 def predict():
-    """Perform prediction and save results to Firebase."""
+    """Perform prediction and save results to PostgreSQL (Supabase)."""
     if 'file' not in request.files:
         return jsonify({'error': 'No file uploaded'}), 400
 
@@ -107,14 +109,16 @@ def predict():
         gradcam_filename = f"gradcam_{int(datetime.now().timestamp())}.png"
         save_gradcam_image(img, heatmap, filename=gradcam_filename)
 
-        # Save to Firebase
-        results_ref.push({
-            'image_filename': file.filename,
-            'prediction': result,
-            'confidence': confidence,
-            'gradcam_filename': gradcam_filename,
-            'timestamp': datetime.now().isoformat()
-        })
+        # Save results to PostgreSQL
+        conn = get_db_connection()
+        cursor = conn.cursor()
+        cursor.execute("""
+            INSERT INTO results (image_filename, prediction, confidence, gradcam_filename, timestamp) 
+            VALUES (%s, %s, %s, %s, %s)
+        """, (file.filename, result, confidence, gradcam_filename, datetime.now().isoformat()))
+        conn.commit()
+        cursor.close()
+        conn.close()
 
         return jsonify({
             'prediction': result,
@@ -129,11 +133,26 @@ def predict():
 
 @app.route('/results', methods=['GET'])
 def results():
-    """List all results from the Firebase database."""
-    results_data = results_ref.get()
-    if not results_data:
-        results_data = []
-    return jsonify(results_data)
+    """List all results from the PostgreSQL database."""
+    conn = get_db_connection()
+    cursor = conn.cursor(cursor_factory=DictCursor)
+    cursor.execute("SELECT * FROM results ORDER BY timestamp DESC")
+    results_data = cursor.fetchall()
+    cursor.close()
+    conn.close()
+
+    results_list = []
+    for record in results_data:
+        results_list.append({
+            'id': record['id'],  # Assumes 'id' is your primary key column
+            'image_filename': record['image_filename'],
+            'prediction': record['prediction'],
+            'confidence': record['confidence'],
+            'gradcam_filename': record['gradcam_filename'],
+            'timestamp': record['timestamp']
+        })
+
+    return jsonify(results_list)
 
 @app.route('/gradcam/<filename>')
 def get_gradcam(filename):