README.md

<!--
================================================================================
Text Classification Dataset - Models Directory
================================================================================
Author: Molla Samser
Website: https://rskworld.in
Copyright (c) 2026 RSK World - All Rights Reserved
================================================================================
-->

# Models Directory

This directory stores trained machine learning models for text classification.

## Supported Model Files

| File | Description |
|------|-------------|
| `tfidf_vectorizer.pkl` | TF-IDF vectorizer (fitted) |
| `naive_bayes_model.pkl` | Multinomial Naive Bayes classifier |
| `logistic_regression_model.pkl` | Logistic Regression classifier |
| `svm_model.pkl` | Linear SVM classifier |
| `random_forest_model.pkl` | Random Forest classifier |
| `bert_model/` | Fine-tuned BERT model directory |

## Saving Models

```python
import joblib
from sklearn.linear_model import LogisticRegression
from sklearn.feature_extraction.text import TfidfVectorizer

# Save vectorizer
joblib.dump(vectorizer, 'models/tfidf_vectorizer.pkl')

# Save model
joblib.dump(model, 'models/logistic_regression_model.pkl')
```

## Loading Models

```python
import joblib

# Load vectorizer and model
vectorizer = joblib.load('models/tfidf_vectorizer.pkl')
model = joblib.load('models/logistic_regression_model.pkl')

# Make prediction
text = "Your text here"
features = vectorizer.transform([text])
prediction = model.predict(features)
```

## Model Training

Run the training script to generate models:

```bash
python scripts/train_classifier.py
```

---

**Author:** Molla Samser | **Website:** [rskworld.in](https://rskworld.in)

**Copyright (c) 2026 RSK World - All Rights Reserved**