Update Sniffer_AI.py

Sniffer_AI.py

@@ -1,69 +1,99 @@
-import gradio as gr
+import pandas as pd
+import numpy as np
 import joblib
-import requests
+import gradio as gr
 import os
+import tempfile
 
-from sklearn.ensemble import RandomForestClassifier
+# Set a custom directory for Gradio's temporary files
+os.environ["GRADIO_TEMP"] = tempfile.mkdtemp()
 
-# Load the saved models
-rf_model = joblib.load('rf_model.pkl')
+# Load the saved Random Forest model
+rf_model = joblib.load('rf_model.pkl')  # Ensure the correct model path
 
-# Define the feature names (excluding the target column 'type')
-feature_names = [
-    "date", "time", "door_state", "sphone_signal", "label"
+# Define required numeric features
+numeric_features = [
+    "date_numeric", "total_minutes", "seconds",
+    "door_state", "sphone_signal", "label"
 ]
 
+# Class labels for attack types
 class_labels = {
-    0: "normal",
-    1: "backdoor",
-    2: "ddos",
-    3: "injection",
-    4: "password",
-    5: "ransomware",
-    6: "scanning",
-    7: "xss",
+    0: "Normal",
+    1: "Backdoor",
+    2: "DDoS",
+    3: "Injection",
+    4: "Password Attack",
+    5: "Ransomware",
+    6: "Scanning",
+    7: "XSS",
 }
 
-# Placeholder model (replace with actual Random Forest model object)
-rf_model = None  # Load the actual trained Random Forest model here
+def convert_datetime_features(log_data):
+    """Convert date and time into numeric values."""
+    try:
+        log_data['date'] = pd.to_datetime(log_data['date'], format='%d-%m-%y', errors='coerce')
+        log_data['date_numeric'] = log_data['date'].astype(np.int64) // 10**9  
+
+        time_parsed = pd.to_datetime(log_data['time'], format='%H:%M:%S', errors='coerce')
+        log_data['total_minutes'] = (time_parsed.dt.hour * 60) + time_parsed.dt.minute
+        log_data['seconds'] = time_parsed.dt.second
+    except Exception as e:
+        return f"Error processing date/time: {str(e)}"
+    
+    return log_data
 
 def detect_intrusion(file):
-    # Read the uploaded log file as a CSV or structured data
+    """Process log file and predict attack type."""
     try:
-        log_data = pd.read_csv(file.name)  # Use file.name to get the path for reading
+        log_data = pd.read_csv(file.name)
     except Exception as e:
         return f"Error reading file: {str(e)}"
 
-    # Check if all required feature columns are in the log file
-    missing_features = [feature for feature in feature_names if feature not in log_data.columns]
+    log_data = convert_datetime_features(log_data)
+
+    missing_features = [feature for feature in numeric_features if feature not in log_data.columns]
     if missing_features:
         return f"Missing features in file: {', '.join(missing_features)}"
-    
-    # Extract the feature values (excluding the 'type' column which is the target)
-    feature_values = log_data[feature_names].astype(float).values
 
-    # Predict the class (multi-class classification) for each row in the log file
-    predictions = rf_model.predict(feature_values)
+    try:
+        log_data['door_state'] = log_data['door_state'].astype(str).str.strip().replace({'closed': 0, 'open': 1})
+        log_data['sphone_signal'] = pd.to_numeric(log_data['sphone_signal'], errors='coerce')
+
+        feature_values = log_data[numeric_features].astype(float).values
+        predictions = rf_model.predict(feature_values)
+    except Exception as e:
+        return f"Error during prediction: {str(e)}"
+
+    # Map predictions to specific attack types
+    log_data['Prediction'] = [class_labels.get(pred, 'Unknown Attack') for pred in predictions]
+
+    # Format date for output
+    log_data['date'] = log_data['date'].dt.strftime('%Y-%m-%d')
+
+    # Select final output columns
+    output_df = log_data[['date', 'time', 'Prediction']]
+
+    # Save the output to a CSV file for download
+    output_file = "intrusion_results.csv"
+    output_df.to_csv(output_file, index=False)
 
-    # Return only the 'Prediction' and 'label' columns
-    return log_data[['Prediction']].head().to_string()
+    return output_df, output_file
 
-# Create a Gradio interface
+# Create Gradio interface
 iface = gr.Interface(
     fn=detect_intrusion,
-    inputs=[
-        gr.File(label="Upload Log File (CSV format)")  # File input
-    ],  
-    outputs="text", 
+    inputs=[gr.File(label="Upload Log File (CSV format)")],
+    outputs=[gr.Dataframe(label="Intrusion Detection Results"), gr.File(label="Download Predictions CSV")],
     title="Intrusion Detection System",
-    description=("""
-        Upload a CSV log file containing the following features: 
-        date, time, door_state, sphone_signal, label (without the 'type' column).
-        Example file structure:
+    description=(
+        """
+        Upload a CSV log file with the following features:
         date,time,door_state,sphone_signal,label
-        2025-03-12,10:45:00,1,-85,normal
-    """)
+        Example:
+        26-04-19,13:59:20,1,-85,normal
+        """
+    )
 )
 
-# Launch the interface locally for testing
 iface.launch()