Download app.py from Pfe-Spam-Detection/api_spam_detectionv2: direct link, hf CLI and curl.
- Browser
- Download file 2.48 kB
-
https://huggingface.co/spaces/Pfe-Spam-Detection/api_spam_detectionv2/resolve/main/app.py
- Command line
-
hf download hf://spaces/Pfe-Spam-Detection/api_spam_detectionv2/app.py
-
curl -L -o app.py https://huggingface.co/spaces/Pfe-Spam-Detection/api_spam_detectionv2/resolve/main/app.py
2.48 kB
| import os | |
| import torch | |
| import torch.nn.functional as F | |
| import re | |
| from fastapi import FastAPI | |
| from fastapi.middleware.cors import CORSMiddleware | |
| from pydantic import BaseModel | |
| from transformers import BertTokenizerFast, BertForSequenceClassification | |
| from collections import Counter | |
| app = FastAPI() | |
| # Autorise tout le monde (CORS) | |
| app.add_middleware( | |
| CORSMiddleware, | |
| allow_origins=["*"], | |
| allow_methods=["*"], | |
| allow_headers=["*"], | |
| ) | |
| # Chargement du modèle (Public) | |
| MODEL_NAME = "Aitouaouch/bert_model_for_spam_detection" | |
| print("Chargement du modèle BERT...") | |
| tokenizer = BertTokenizerFast.from_pretrained(MODEL_NAME) | |
| model = BertForSequenceClassification.from_pretrained(MODEL_NAME) | |
| model.eval() | |
| print("Modèle prêt !") | |
| STOPWORDS = {"the","a","an","is","it","in","on","at","to","for","of","and","or","but","be","are","was","were","this","that","with","from","have","has","you","your","we","our","i","my","he","she","they","their","its","will","can","not","no","so","do","if","as","by","up","all","more","about","just"} | |
| class EmailRequest(BaseModel): | |
| subject: str | |
| body: str | |
| domain: str | |
| def extract_keywords(text: str, top_n: int = 8) -> list[str]: | |
| words = re.findall(r'\b[a-zA-Z]{4,}\b', text.lower()) | |
| filtered = [w for w in words if w not in STOPWORDS] | |
| freq = Counter(filtered) | |
| return [word for word, _ in freq.most_common(top_n)] | |
| def health(): | |
| return {"message": "Serveur de détection de Spam actif"} | |
| async def predict(request: EmailRequest): | |
| try: | |
| # Préparation du texte | |
| text = f"[DOMAIN] {request.domain} [BODY] {request.subject} {request.body}" | |
| inputs = tokenizer(text, return_tensors="pt", truncation=True, padding=True, max_length=256) | |
| with torch.no_grad(): | |
| outputs = model(**inputs) | |
| probs = F.softmax(outputs.logits, dim=1) | |
| prediction_idx = torch.argmax(probs, dim=1).item() | |
| confidence = probs[0][prediction_idx].item() * 100 | |
| prediction = "spam" if prediction_idx == 1 else "safe" | |
| keywords = extract_keywords(f"{request.subject} {request.body}") | |
| return { | |
| "prediction": prediction, | |
| "confidence": round(confidence, 2), | |
| "keywords": keywords | |
| } | |
| except Exception as e: | |
| return {"error": str(e)} | |
| if __name__ == "__main__": | |
| import uvicorn | |
| uvicorn.run(app, host="0.0.0.0", port=7860) |