DarkNeuron-AI/darkneuron-spamdex-v1

🧠 SpamDex - Spam Detection Model (v1.0)

A lightweight Naive Bayes + TF-IDF based spam detection model developed by DarkNeuronAI.
It classifies emails as Spam (1) or Ham (0) with high accuracy and fast performance — ideal for simple text classification tasks.

---

🚀 Features

• Fast and efficient — works on low-end systems
• Trained with real-world email dataset
• Perfect for text classification and spam filtering projects
• Easy to use and integrate

---

🚀 Model Overview

• Algorithm: Naive Bayes (MultinomialNB)
• Vectorization: TF-IDF (Term Frequency - Inverse Document Frequency)
• Goal: Classify email/text messages as Spam or Ham
• Performance: High accuracy on real-world datasets

---

🧩 Files Included

• spam_detection_model.pkl → Trained Naive Bayes model
• spam_detection_vectorizer.pkl → TF-IDF vectorizer for text preprocessing
• example_usage.py → Example code to use the model
• requirements.txt → Dependencies list

---

🏷️ Prediction Labels(Binary)

• 0: Represent Ham(Not Spam) Prediction
• 1: Represent Spam Prediction

💡 How to Use(Example Code)

from huggingface_hub import hf_hub_download
import joblib
import string 
import re

# Download and load the vectorizer
vectorizer_path = hf_hub_download("DarkNeuron-AI/darkneuron-spamdex-v1", "spam_detection_vectorizer.pkl")
vectorizer = joblib.load(vectorizer_path)

# Download and load the trained model
model_path = hf_hub_download("DarkNeuron-AI/darkneuron-spamdex-v1", "spam_detection_model.pkl")
model = joblib.load(model_path)

# Text cleaning function
def clean_text(text):
    text = text.lower()  # lowercase
    text = re.sub(r'\d+', '', text)  # remove digits
    text = text.translate(str.maketrans('', '', string.punctuation))  # remove punctuation
    return text.strip()  # remove extra spaces

# Example usage
email_text = "Congratulations! You are the topper!"
cleaned_email = clean_text(email_text)

# Wrap text in a list for vectorizer
email_vector = vectorizer.transform([cleaned_email])

# Predict
prediction = model.predict(email_vector)

print("Prediction:", "🚨 Spam" if prediction[0] == 1 else "✅ Not Spam")

Developed With ❤️ By DarkNeuronAI