toxic-comment-classifier 0.1.8

A Python library for classifying toxic comments using deep learning.

---

# Toxic Comment Classifier

A Python library for classifying toxic comments using deep learning. It supports detecting multiple types of toxicity including obscene language, threats, and identity hate.

---

## 📦 Installation

```python
pip install toxic-comment-classifier

---

🚀 Usage

🔹 Import and Initialize the Model

from toxic_classifier.model import ToxicCommentClassifier

# Load the classifier
model = ToxicCommentClassifier()

---

🔹 Classify a Single Comment

text = "You are so dumb and stupid!"
scores = model.classify(text)

print("Toxicity Scores:", scores)

Example Output:

{'toxic': 0.5003802180290222,
 'severe_toxic': 0.4986536502838135,
 'obscene': 0.4989285469055176,
 'threat': 0.5020793676376343,
 'insult': 0.49787813425064087,
 'identity_hate': 0.5006254315376282}

---

🔹 Get Overall Toxicity Score

toxicity = model.predict(text)
print(f"Overall Toxicity Score: {toxicity:.4f}")

Overall Toxicity Score: 0.4998

---

🔹 Classify Multiple Comments

texts = [
    "I hate this!",
    "You're amazing!",
    "This is the worst thing ever!"
]

scores = model.predict_batch(texts)

for txt, score in zip(texts, scores):
    print(f"Text: {txt} --> Toxicity Score: {score:.4f}")

Text: I hate this! --> Toxicity Score: 0.5002
Text: You're amazing! --> Toxicity Score: 0.5000
Text: This is the worst thing ever! --> Toxicity Score: 0.5008

---

📄 License

This project is licensed under the MIT License.