Upload 2 files

app.py

@@ -0,0 +1,72 @@
+# Import necessary libraries
+from flask import Flask, render_template, request, jsonify
+from utils import model_predict, get_available_models
+
+# Initialize Flask app
+app = Flask(__name__)
+
+@app.route("/")
+def home():
+    models = get_available_models()
+    return render_template("ZAHRAAZNOUR.html", models=models)
+
+@app.route('/predict', methods=["POST"])
+def predict():
+    """
+    Handles form submission and returns prediction.
+    """
+    email = request.form.get('email')
+    model_name = request.form.get('model')
+    
+    if not email:
+        return render_template("ZAHRAAZNOUR.html", 
+                             error="Please provide an email",
+                             models=get_available_models())
+
+    if not model_name:
+        return render_template("ZAHRAAZNOUR.html", 
+                             error="Please select a model",
+                             models=get_available_models())
+
+    try:
+        prediction = model_predict(email, model_name)
+        result = "Spam" if prediction == 1 else "Not Spam"
+        return render_template("ZAHRAAZNOUR.html", 
+                             prediction=result,
+                             email=email,
+                             selected_model=model_name,
+                             models=get_available_models())
+    except Exception as e:
+        return render_template("ZAHRAAZNOUR.html", 
+                             error=f"Error: {str(e)}",
+                             models=get_available_models())
+
+@app.route('/api/predict', methods=["POST"])
+def predict_api():
+    """
+    API endpoint that accepts a JSON payload and returns a prediction.
+    """
+    try:
+        data = request.get_json()
+        email = data.get("email")
+        model_name = data.get("model")
+        
+        if not email:
+            return jsonify({'error': 'No email provided'}), 400
+
+        if not model_name:
+            return jsonify({'error': 'No model selected'}), 400
+
+        prediction = model_predict(email, model_name)
+        result = "Spam" if prediction == 1 else "Not Spam"
+        return jsonify({
+            'email': email,
+            'model': model_name,
+            'prediction': result
+        })
+
+    except Exception as e:
+        return jsonify({'error': str(e)}), 400
+
+if __name__ == "__main__":
+    app.run(host="0.0.0.0", port=5000, debug=True)

utils.py

@@ -0,0 +1,49 @@
+# utils.py (Helper Functions)
+import pickle
+import os
+from pathlib import Path
+
+MODELS = {
+    'Support Vector Machine': 'Models/svm_model.pkl',
+    'Random Forest': 'Models/rf_model.pkl',
+    'K-Nearest Neighbors': 'Models/knn_model.pkl',
+    'Naive Bayes': 'Models/clf_NaiveBaised.pkl',
+    'Decision Tree': 'Models/DT_model.pkl'
+}
+
+
+def get_available_models():
+    """
+    Returns a list of available models
+    """
+    return list(MODELS.keys())
+
+
+def load_model(model_name):
+    """
+    Loads the specified model from file.
+    """
+    if model_name not in MODELS:
+        raise ValueError(f"Model {model_name} not found")
+
+    model_file = MODELS[model_name]
+    try:
+        with open(model_file, "rb") as file:
+            model = pickle.load(file)
+        return model
+    except FileNotFoundError:
+        raise FileNotFoundError(f"Model file {model_file} not found")
+    except Exception as e:
+        raise Exception(f"Error loading model: {str(e)}")
+
+
+def model_predict(email, model_name):
+    """
+    Predicts using the specified model.
+    """
+    try:
+        model = load_model(model_name)
+        prediction = model.predict([email])
+        return 1 if prediction[0] == 1 else -1
+    except Exception as e:
+        raise Exception(f"Prediction error: {str(e)}")