inference_example.py

# Simple Inference Example
from transformers import AutoTokenizer, AutoModelForSequenceClassification
import torch
import re

# Load model
tokenizer = AutoTokenizer.from_pretrained("junaid1993/distilroberta-bot-detection")
model = AutoModelForSequenceClassification.from_pretrained("junaid1993/distilroberta-bot-detection")

def preprocess_text(text):
    if not isinstance(text, str):
        return ""
    text = re.sub(r'http\S+|www\.\S+', '', text)
    text = re.sub(r'[@#]', '', text)
    text = re.sub(r'[^\w\s]', '', text)
    text = re.sub(r'\d+', '', text)
    text = re.sub(r'\s+', ' ', text).strip()
    return text.lower()

def predict_bot(text):
    clean_text = preprocess_text(text)
    inputs = tokenizer(clean_text, return_tensors="pt", truncation=True, max_length=512)
    
    with torch.no_grad():
        outputs = model(**inputs)
        probabilities = torch.nn.functional.softmax(outputs.logits, dim=-1)
    
    bot_prob = probabilities[0][1].item()
    prediction = "Bot" if bot_prob > 0.5 else "Human"
    
    return {"prediction": prediction, "bot_probability": bot_prob}

# Example usage
examples = [
    "🔥 AMAZING DEAL! Get 90% OFF now!",
    "Just finished reading a great book about AI."
]

for text in examples:
    result = predict_bot(text)
    print(f"Text: {text}")
    print(f"Prediction: {result['prediction']} ({result['bot_probability']:.3f})")
    print("-" * 50)