Upload New File

untitled4.py

+import re
+import numpy as np
+from sklearn.preprocessing import StandardScaler
+import joblib
+
+# Function to extract features
+def extract_features(url):
+    url_length = len(url)
+    special_chars = len(re.findall(r'[!@#$%^&*(),.?":{}|<>]', url))
+    return [url_length, special_chars]
+
+# Load the best-trained text and engineered feature classifiers
+best_text_classifier = joblib.load('best_text_classifier.joblib')
+best_engineered_classifier = joblib.load('best_engineered_classifier.joblib')
+
+# Create a StandardScaler instance and fit it to a placeholder example
+scaler = StandardScaler()
+
+# Placeholder example (replace with actual training data if available)
+placeholder_example = np.array([[100, 5], [120, 8], [90, 3]])
+
+# Fit the scaler to the placeholder example
+scaler.fit(placeholder_example)
+
+# Input URL from the console
+new_url = input("Enter the URL to predict: ")
+
+# Feature extraction for the new URL
+new_text_features = extract_features(new_url)
+# Standardize the new features using the fitted scaler
+new_text_features = scaler.transform([new_text_features])
+
+# Make predictions using the text-based classifier
+text_prediction = best_text_classifier.predict([new_url])
+
+# Make predictions using the engineered feature-based classifier
+engineered_prediction = best_engineered_classifier.predict(new_text_features)
+
+# Print predictions
+print("Text-Based Prediction:", text_prediction[0])
+print("Engineered Feature-Based Prediction:", engineered_prediction[0])