Spaces:
Sleeping
Sleeping
Upload Manual ML Indobert
Browse files- .dockerignore +91 -0
- .gitignore +61 -0
- Dockerfile +33 -0
- README.md +90 -11
- app.py +218 -0
- requirements.txt +17 -0
.dockerignore
ADDED
|
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# .dockerignore - Exclude file yang tidak diperlukan dari Docker build
|
| 2 |
+
# Ini memastikan hanya file yang terpakai yang masuk ke Docker image
|
| 3 |
+
|
| 4 |
+
# Model checkpoints dan versions yang tidak terpakai
|
| 5 |
+
models/indobert_versions/
|
| 6 |
+
models/indobert/checkpoint-*/
|
| 7 |
+
**/checkpoint-*/
|
| 8 |
+
**/checkpoints/
|
| 9 |
+
**/*.ckpt
|
| 10 |
+
|
| 11 |
+
# Training artifacts yang tidak perlu
|
| 12 |
+
*.pth.tar
|
| 13 |
+
*.pt
|
| 14 |
+
trainer_state.json
|
| 15 |
+
training_args.bin
|
| 16 |
+
|
| 17 |
+
# Data dan dataset (tidak perlu di Space)
|
| 18 |
+
data/
|
| 19 |
+
datasets/
|
| 20 |
+
*.csv
|
| 21 |
+
*.json
|
| 22 |
+
*.jsonl
|
| 23 |
+
!config.json
|
| 24 |
+
!tokenizer.json
|
| 25 |
+
!tokenizer_config.json
|
| 26 |
+
!special_tokens_map.json
|
| 27 |
+
|
| 28 |
+
# Python cache
|
| 29 |
+
__pycache__/
|
| 30 |
+
*.py[cod]
|
| 31 |
+
*$py.class
|
| 32 |
+
*.so
|
| 33 |
+
.Python
|
| 34 |
+
*.egg-info/
|
| 35 |
+
.pytest_cache/
|
| 36 |
+
.mypy_cache/
|
| 37 |
+
|
| 38 |
+
# Virtual environments
|
| 39 |
+
venv/
|
| 40 |
+
env/
|
| 41 |
+
ENV/
|
| 42 |
+
|
| 43 |
+
# IDE
|
| 44 |
+
.vscode/
|
| 45 |
+
.idea/
|
| 46 |
+
*.swp
|
| 47 |
+
*.swo
|
| 48 |
+
*~
|
| 49 |
+
.DS_Store
|
| 50 |
+
Thumbs.db
|
| 51 |
+
|
| 52 |
+
# Git
|
| 53 |
+
.git/
|
| 54 |
+
.gitignore
|
| 55 |
+
.gitattributes
|
| 56 |
+
|
| 57 |
+
# Documentation yang tidak perlu di runtime
|
| 58 |
+
DEPLOYMENT.md
|
| 59 |
+
QUICKSTART.md
|
| 60 |
+
*.md
|
| 61 |
+
!README.md
|
| 62 |
+
|
| 63 |
+
# Test files
|
| 64 |
+
test_*.py
|
| 65 |
+
tests/
|
| 66 |
+
*_test.py
|
| 67 |
+
|
| 68 |
+
# Scripts yang tidak perlu di runtime
|
| 69 |
+
upload_model_to_hub.py
|
| 70 |
+
quick_deploy.sh
|
| 71 |
+
quick_deploy.ps1
|
| 72 |
+
|
| 73 |
+
# Logs
|
| 74 |
+
*.log
|
| 75 |
+
logs/
|
| 76 |
+
|
| 77 |
+
# Temporary files
|
| 78 |
+
*.tmp
|
| 79 |
+
tmp/
|
| 80 |
+
temp/
|
| 81 |
+
.cache/
|
| 82 |
+
|
| 83 |
+
# Large files yang tidak perlu
|
| 84 |
+
*.zip
|
| 85 |
+
*.tar
|
| 86 |
+
*.gz
|
| 87 |
+
*.rar
|
| 88 |
+
|
| 89 |
+
# Notebook checkpoints
|
| 90 |
+
.ipynb_checkpoints/
|
| 91 |
+
*.ipynb
|
.gitignore
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# .gitignore untuk Hugging Face Space
|
| 2 |
+
|
| 3 |
+
# Python
|
| 4 |
+
__pycache__/
|
| 5 |
+
*.py[cod]
|
| 6 |
+
*$py.class
|
| 7 |
+
*.so
|
| 8 |
+
.Python
|
| 9 |
+
build/
|
| 10 |
+
develop-eggs/
|
| 11 |
+
dist/
|
| 12 |
+
downloads/
|
| 13 |
+
eggs/
|
| 14 |
+
.eggs/
|
| 15 |
+
lib/
|
| 16 |
+
lib64/
|
| 17 |
+
parts/
|
| 18 |
+
sdist/
|
| 19 |
+
var/
|
| 20 |
+
wheels/
|
| 21 |
+
*.egg-info/
|
| 22 |
+
.installed.cfg
|
| 23 |
+
*.egg
|
| 24 |
+
|
| 25 |
+
# Virtual Environment
|
| 26 |
+
venv/
|
| 27 |
+
env/
|
| 28 |
+
ENV/
|
| 29 |
+
|
| 30 |
+
# IDE
|
| 31 |
+
.vscode/
|
| 32 |
+
.idea/
|
| 33 |
+
*.swp
|
| 34 |
+
*.swo
|
| 35 |
+
*~
|
| 36 |
+
|
| 37 |
+
# OS
|
| 38 |
+
.DS_Store
|
| 39 |
+
Thumbs.db
|
| 40 |
+
|
| 41 |
+
# Model files (jika sudah di-upload ke HF Hub)
|
| 42 |
+
models/indobert/*.bin
|
| 43 |
+
models/indobert/*.safetensors
|
| 44 |
+
models/indobert/pytorch_model.bin
|
| 45 |
+
|
| 46 |
+
# Logs
|
| 47 |
+
*.log
|
| 48 |
+
logs/
|
| 49 |
+
|
| 50 |
+
# Environment variables
|
| 51 |
+
.env
|
| 52 |
+
.env.local
|
| 53 |
+
|
| 54 |
+
# Test files
|
| 55 |
+
test_*.py
|
| 56 |
+
tests/
|
| 57 |
+
|
| 58 |
+
# Temporary files
|
| 59 |
+
*.tmp
|
| 60 |
+
tmp/
|
| 61 |
+
temp/
|
Dockerfile
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Hugging Face Space - IndoBERT Fake News Detection
|
| 2 |
+
# Base image dengan Python 3.10
|
| 3 |
+
FROM python:3.10-slim
|
| 4 |
+
|
| 5 |
+
# Set working directory
|
| 6 |
+
WORKDIR /app
|
| 7 |
+
|
| 8 |
+
# Install system dependencies
|
| 9 |
+
RUN apt-get update && apt-get install -y \
|
| 10 |
+
git \
|
| 11 |
+
build-essential \
|
| 12 |
+
&& rm -rf /var/lib/apt/lists/*
|
| 13 |
+
|
| 14 |
+
# Copy requirements first untuk caching
|
| 15 |
+
COPY requirements.txt .
|
| 16 |
+
RUN pip install --no-cache-dir -r requirements.txt
|
| 17 |
+
|
| 18 |
+
# Copy application code (hanya file yang diperlukan)
|
| 19 |
+
COPY app.py .
|
| 20 |
+
|
| 21 |
+
# Model akan di-load dari HuggingFace Hub, tidak perlu copy lokal
|
| 22 |
+
# Environment variable HF_MODEL_REPO akan di-set di Space settings
|
| 23 |
+
|
| 24 |
+
# Expose port 7860 (default untuk HF Spaces)
|
| 25 |
+
EXPOSE 7860
|
| 26 |
+
|
| 27 |
+
# Set environment variables
|
| 28 |
+
ENV GRADIO_SERVER_NAME="0.0.0.0"
|
| 29 |
+
ENV GRADIO_SERVER_PORT=7860
|
| 30 |
+
ENV HF_MODEL_REPO="Davidbio/fakenewsdetection"
|
| 31 |
+
|
| 32 |
+
# Run the application
|
| 33 |
+
CMD ["python", "app.py"]
|
README.md
CHANGED
|
@@ -1,11 +1,90 @@
|
|
| 1 |
-
---
|
| 2 |
-
title:
|
| 3 |
-
emoji:
|
| 4 |
-
colorFrom:
|
| 5 |
-
colorTo:
|
| 6 |
-
sdk: docker
|
| 7 |
-
pinned: false
|
| 8 |
-
license: mit
|
| 9 |
-
|
| 10 |
-
|
| 11 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
title: IndoBERT Fake News Detection
|
| 3 |
+
emoji: 🔍
|
| 4 |
+
colorFrom: red
|
| 5 |
+
colorTo: yellow
|
| 6 |
+
sdk: docker
|
| 7 |
+
pinned: false
|
| 8 |
+
license: mit
|
| 9 |
+
app_port: 7860
|
| 10 |
+
tags:
|
| 11 |
+
- indonesian
|
| 12 |
+
- fake-news
|
| 13 |
+
- bert
|
| 14 |
+
- classification
|
| 15 |
+
- nlp
|
| 16 |
+
- text-classification
|
| 17 |
+
models:
|
| 18 |
+
- Davidbio/fakenewsdetection
|
| 19 |
+
---
|
| 20 |
+
|
| 21 |
+
# 🔍 IndoBERT Fake News Detection
|
| 22 |
+
|
| 23 |
+
Aplikasi deteksi berita hoax berbahasa Indonesia menggunakan model IndoBERT.
|
| 24 |
+
|
| 25 |
+
## 📖 Deskripsi
|
| 26 |
+
|
| 27 |
+
Model ini menggunakan **IndoBERT** (Indonesian BERT) yang telah di-fine-tune pada dataset berita Indonesia untuk mengklasifikasikan berita sebagai **Real** atau **Hoax (Fake News)**.
|
| 28 |
+
|
| 29 |
+
### ✨ Fitur
|
| 30 |
+
|
| 31 |
+
- 🤖 Deteksi otomatis berita hoax menggunakan deep learning
|
| 32 |
+
- 📊 Menampilkan confidence score dan probabilitas detail
|
| 33 |
+
- 🇮🇩 Dioptimalkan untuk teks berbahasa Indonesia
|
| 34 |
+
- ⚡ Interface yang mudah digunakan dengan Gradio
|
| 35 |
+
|
| 36 |
+
## 🚀 Cara Penggunaan
|
| 37 |
+
|
| 38 |
+
1. Masukkan teks berita pada kotak input
|
| 39 |
+
2. Klik tombol "🔍 Deteksi Berita"
|
| 40 |
+
3. Lihat hasil analisis:
|
| 41 |
+
- Label prediksi (Real/Hoax)
|
| 42 |
+
- Confidence score
|
| 43 |
+
- Distribusi probabilitas
|
| 44 |
+
|
| 45 |
+
## 🎯 Model Information
|
| 46 |
+
|
| 47 |
+
- **Base Model:** indobenchmark/indobert-base-p1
|
| 48 |
+
- **Task:** Binary Text Classification
|
| 49 |
+
- **Classes:**
|
| 50 |
+
- 0: Real News
|
| 51 |
+
- 1: Fake News (Hoax)
|
| 52 |
+
- **Max Sequence Length:** 256 tokens
|
| 53 |
+
- **Framework:** PyTorch + Transformers
|
| 54 |
+
|
| 55 |
+
## ⚠️ Disclaimer
|
| 56 |
+
|
| 57 |
+
Model ini adalah **alat bantu** dan tidak menjamin akurasi 100%. Selalu verifikasi informasi dari sumber terpercaya sebelum menyimpulkan sebuah berita sebagai hoax.
|
| 58 |
+
|
| 59 |
+
## 📚 Dataset
|
| 60 |
+
|
| 61 |
+
Model dilatih menggunakan dataset berita Indonesia yang telah dilabeli sebagai real atau hoax.
|
| 62 |
+
|
| 63 |
+
## 🛠️ Technology Stack
|
| 64 |
+
|
| 65 |
+
- **Framework:** Gradio
|
| 66 |
+
- **Model:** IndoBERT (Transformers)
|
| 67 |
+
- **Backend:** PyTorch
|
| 68 |
+
- **Deployment:** Hugging Face Spaces (Docker)
|
| 69 |
+
|
| 70 |
+
## 📝 Citation
|
| 71 |
+
|
| 72 |
+
Jika menggunakan model ini, mohon cantumkan:
|
| 73 |
+
|
| 74 |
+
```bibtex
|
| 75 |
+
@misc{indobert-fakenews,
|
| 76 |
+
title={IndoBERT Fake News Detection},
|
| 77 |
+
author={Your Name},
|
| 78 |
+
year={2025},
|
| 79 |
+
publisher={Hugging Face},
|
| 80 |
+
howpublished={\url{https://huggingface.co/spaces/your-username/indobert-fakenews}}
|
| 81 |
+
}
|
| 82 |
+
```
|
| 83 |
+
|
| 84 |
+
## 📄 License
|
| 85 |
+
|
| 86 |
+
MIT License
|
| 87 |
+
|
| 88 |
+
---
|
| 89 |
+
|
| 90 |
+
**Developed with ❤️ for Indonesian NLP Community**
|
app.py
ADDED
|
@@ -0,0 +1,218 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
"""
|
| 2 |
+
Hugging Face Space Application - IndoBERT Fake News Detection
|
| 3 |
+
Menggunakan Gradio untuk interface yang user-friendly
|
| 4 |
+
"""
|
| 5 |
+
|
| 6 |
+
import gradio as gr
|
| 7 |
+
import torch
|
| 8 |
+
from transformers import AutoTokenizer, AutoModelForSequenceClassification
|
| 9 |
+
import numpy as np
|
| 10 |
+
from pathlib import Path
|
| 11 |
+
import os
|
| 12 |
+
import logging
|
| 13 |
+
|
| 14 |
+
logging.basicConfig(level=logging.INFO)
|
| 15 |
+
logger = logging.getLogger(__name__)
|
| 16 |
+
|
| 17 |
+
# Konfigurasi - Model dari HuggingFace Hub
|
| 18 |
+
MODEL_REPO = "Davidbio/fakenewsdetection" # Model yang sudah di-upload
|
| 19 |
+
MODEL_DIR = Path(__file__).parent / "models" / "indobert" # Fallback lokal
|
| 20 |
+
|
| 21 |
+
|
| 22 |
+
class FakeNewsDetector:
|
| 23 |
+
def __init__(self):
|
| 24 |
+
self.tokenizer = None
|
| 25 |
+
self.model = None
|
| 26 |
+
self.device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
|
| 27 |
+
self.load_model()
|
| 28 |
+
|
| 29 |
+
def load_model(self):
|
| 30 |
+
"""Load model dari HuggingFace Hub atau lokal"""
|
| 31 |
+
try:
|
| 32 |
+
# Load dari HuggingFace Hub (prioritas utama)
|
| 33 |
+
hf_repo = os.environ.get("HF_MODEL_REPO", MODEL_REPO)
|
| 34 |
+
logger.info(f"Loading model dari HuggingFace Hub: {hf_repo}")
|
| 35 |
+
|
| 36 |
+
try:
|
| 37 |
+
self.tokenizer = AutoTokenizer.from_pretrained(hf_repo)
|
| 38 |
+
self.model = AutoModelForSequenceClassification.from_pretrained(hf_repo)
|
| 39 |
+
logger.info("✅ Model loaded dari HuggingFace Hub")
|
| 40 |
+
except Exception as hub_error:
|
| 41 |
+
# Fallback ke lokal jika HF Hub gagal
|
| 42 |
+
if MODEL_DIR.exists() and any(MODEL_DIR.iterdir()):
|
| 43 |
+
logger.warning(f"HF Hub failed, loading from local: {hub_error}")
|
| 44 |
+
self.tokenizer = AutoTokenizer.from_pretrained(MODEL_DIR)
|
| 45 |
+
self.model = AutoModelForSequenceClassification.from_pretrained(
|
| 46 |
+
MODEL_DIR
|
| 47 |
+
)
|
| 48 |
+
logger.info("✅ Model loaded dari lokal")
|
| 49 |
+
else:
|
| 50 |
+
raise hub_error
|
| 51 |
+
|
| 52 |
+
self.model.eval()
|
| 53 |
+
self.model.to(self.device)
|
| 54 |
+
logger.info(f"Model berhasil dimuat di {self.device}")
|
| 55 |
+
except Exception as e:
|
| 56 |
+
logger.error(f"Error loading model: {e}")
|
| 57 |
+
raise
|
| 58 |
+
|
| 59 |
+
def predict(self, text: str):
|
| 60 |
+
"""
|
| 61 |
+
Prediksi apakah berita adalah hoax atau bukan
|
| 62 |
+
Returns: (label, confidence, probabilities)
|
| 63 |
+
"""
|
| 64 |
+
if not text or len(text.strip()) < 10:
|
| 65 |
+
return (
|
| 66 |
+
"Error",
|
| 67 |
+
0.0,
|
| 68 |
+
{"Real": 0.0, "Hoax": 0.0},
|
| 69 |
+
"⚠️ Teks terlalu pendek. Minimal 10 karakter.",
|
| 70 |
+
)
|
| 71 |
+
|
| 72 |
+
try:
|
| 73 |
+
# Tokenisasi
|
| 74 |
+
encoded = self.tokenizer(
|
| 75 |
+
text, truncation=True, max_length=256, return_tensors="pt"
|
| 76 |
+
).to(self.device)
|
| 77 |
+
|
| 78 |
+
# Prediksi
|
| 79 |
+
with torch.no_grad():
|
| 80 |
+
logits = self.model(**encoded).logits
|
| 81 |
+
probs = torch.softmax(logits, dim=-1).cpu().numpy()[0]
|
| 82 |
+
|
| 83 |
+
# Ekstrak hasil
|
| 84 |
+
prob_real = float(probs[0])
|
| 85 |
+
prob_hoax = float(probs[1])
|
| 86 |
+
predicted_label = int(np.argmax(probs))
|
| 87 |
+
confidence = float(probs[predicted_label])
|
| 88 |
+
|
| 89 |
+
# Label dan warning
|
| 90 |
+
label_text = "🚨 HOAX" if predicted_label == 1 else "✅ REAL"
|
| 91 |
+
|
| 92 |
+
# Confidence level
|
| 93 |
+
if confidence >= 0.9:
|
| 94 |
+
confidence_level = "Sangat Tinggi"
|
| 95 |
+
elif confidence >= 0.75:
|
| 96 |
+
confidence_level = "Tinggi"
|
| 97 |
+
elif confidence >= 0.6:
|
| 98 |
+
confidence_level = "Sedang"
|
| 99 |
+
else:
|
| 100 |
+
confidence_level = "Rendah"
|
| 101 |
+
|
| 102 |
+
# Warning message
|
| 103 |
+
warning = ""
|
| 104 |
+
if confidence < 0.6:
|
| 105 |
+
warning = "⚠️ Confidence rendah. Hasil mungkin tidak akurat. Silakan verifikasi secara manual."
|
| 106 |
+
|
| 107 |
+
# Format hasil
|
| 108 |
+
result_text = f"""
|
| 109 |
+
### Hasil Deteksi: {label_text}
|
| 110 |
+
|
| 111 |
+
**Confidence:** {confidence:.2%} ({confidence_level})
|
| 112 |
+
|
| 113 |
+
**Probabilitas Detail:**
|
| 114 |
+
- Real News: {prob_real:.2%}
|
| 115 |
+
- Fake News (Hoax): {prob_hoax:.2%}
|
| 116 |
+
|
| 117 |
+
{warning}
|
| 118 |
+
"""
|
| 119 |
+
|
| 120 |
+
return (
|
| 121 |
+
result_text,
|
| 122 |
+
confidence,
|
| 123 |
+
{"Real News": prob_real, "Fake News (Hoax)": prob_hoax},
|
| 124 |
+
warning,
|
| 125 |
+
)
|
| 126 |
+
|
| 127 |
+
except Exception as e:
|
| 128 |
+
logger.error(f"Error during prediction: {e}")
|
| 129 |
+
return f"❌ Error: {str(e)}", 0.0, {"Real": 0.0, "Hoax": 0.0}, ""
|
| 130 |
+
|
| 131 |
+
|
| 132 |
+
# Inisialisasi detector
|
| 133 |
+
detector = FakeNewsDetector()
|
| 134 |
+
|
| 135 |
+
|
| 136 |
+
def predict_news(text: str):
|
| 137 |
+
"""Wrapper function untuk Gradio"""
|
| 138 |
+
result_text, confidence, probs, warning = detector.predict(text)
|
| 139 |
+
return result_text, probs
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
# Contoh teks untuk demo
|
| 143 |
+
examples = [
|
| 144 |
+
[
|
| 145 |
+
"Pemerintah mengumumkan kebijakan baru untuk meningkatkan ekonomi rakyat dengan subsidi langsung kepada UMKM."
|
| 146 |
+
],
|
| 147 |
+
["BREAKING: Alien mendarat di Jakarta dan bertemu dengan presiden!"],
|
| 148 |
+
[
|
| 149 |
+
"Menteri Kesehatan mengimbau masyarakat untuk tetap menjaga protokol kesehatan di tengah musim hujan."
|
| 150 |
+
],
|
| 151 |
+
]
|
| 152 |
+
|
| 153 |
+
# Buat Gradio Interface
|
| 154 |
+
with gr.Blocks(title="IndoBERT Fake News Detection", theme=gr.themes.Soft()) as demo:
|
| 155 |
+
gr.Markdown("""
|
| 156 |
+
# 🔍 IndoBERT Fake News Detection
|
| 157 |
+
|
| 158 |
+
Deteksi berita hoax menggunakan model IndoBERT yang telah dilatih pada dataset berita Indonesia.
|
| 159 |
+
|
| 160 |
+
**Cara Penggunaan:**
|
| 161 |
+
1. Masukkan teks berita pada kotak di bawah
|
| 162 |
+
2. Klik tombol "🔍 Deteksi Berita"
|
| 163 |
+
3. Lihat hasil analisis dan tingkat confidence
|
| 164 |
+
|
| 165 |
+
⚠️ **Catatan:** Model ini adalah alat bantu dan tidak 100% akurat. Selalu verifikasi dari sumber terpercaya.
|
| 166 |
+
""")
|
| 167 |
+
|
| 168 |
+
with gr.Row():
|
| 169 |
+
with gr.Column(scale=2):
|
| 170 |
+
input_text = gr.Textbox(
|
| 171 |
+
label="📝 Masukkan Teks Berita",
|
| 172 |
+
placeholder="Ketik atau paste teks berita di sini...",
|
| 173 |
+
lines=8,
|
| 174 |
+
max_lines=15,
|
| 175 |
+
)
|
| 176 |
+
|
| 177 |
+
with gr.Row():
|
| 178 |
+
clear_btn = gr.Button("🗑️ Clear", variant="secondary")
|
| 179 |
+
submit_btn = gr.Button("🔍 Deteksi Berita", variant="primary")
|
| 180 |
+
|
| 181 |
+
with gr.Column(scale=1):
|
| 182 |
+
output_text = gr.Markdown(label="Hasil Deteksi")
|
| 183 |
+
output_plot = gr.Label(label="Distribusi Probabilitas", num_top_classes=2)
|
| 184 |
+
|
| 185 |
+
# Examples
|
| 186 |
+
gr.Markdown("### 📋 Contoh Teks")
|
| 187 |
+
gr.Examples(examples=examples, inputs=input_text, label="Klik untuk mencoba contoh")
|
| 188 |
+
|
| 189 |
+
# Event handlers
|
| 190 |
+
submit_btn.click(
|
| 191 |
+
fn=predict_news, inputs=input_text, outputs=[output_text, output_plot]
|
| 192 |
+
)
|
| 193 |
+
|
| 194 |
+
clear_btn.click(
|
| 195 |
+
fn=lambda: ("", "", {}),
|
| 196 |
+
inputs=None,
|
| 197 |
+
outputs=[input_text, output_text, output_plot],
|
| 198 |
+
)
|
| 199 |
+
|
| 200 |
+
gr.Markdown("""
|
| 201 |
+
---
|
| 202 |
+
### ℹ️ Tentang Model
|
| 203 |
+
|
| 204 |
+
Model ini menggunakan **IndoBERT** (Indonesian BERT) yang telah di-fine-tune pada dataset berita Indonesia
|
| 205 |
+
untuk klasifikasi berita real vs hoax.
|
| 206 |
+
|
| 207 |
+
- **Base Model:** indobenchmark/indobert-base-p1
|
| 208 |
+
- **Task:** Binary Classification (Real/Hoax)
|
| 209 |
+
- **Max Length:** 256 tokens
|
| 210 |
+
|
| 211 |
+
### 🤝 Kontribusi & Feedback
|
| 212 |
+
|
| 213 |
+
Jika menemukan hasil yang kurang akurat, silakan laporkan untuk membantu meningkatkan model ini.
|
| 214 |
+
""")
|
| 215 |
+
|
| 216 |
+
# Launch app
|
| 217 |
+
if __name__ == "__main__":
|
| 218 |
+
demo.launch(server_name="0.0.0.0", server_port=7860, share=False)
|
requirements.txt
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Hugging Face Space Requirements
|
| 2 |
+
# Python 3.10+
|
| 3 |
+
|
| 4 |
+
# Web Framework - Gradio untuk HF Spaces
|
| 5 |
+
gradio>=4.0.0
|
| 6 |
+
|
| 7 |
+
# Model & ML Dependencies
|
| 8 |
+
torch>=2.0.0
|
| 9 |
+
transformers>=4.30.0
|
| 10 |
+
huggingface-hub>=0.18.0
|
| 11 |
+
|
| 12 |
+
# Data Processing
|
| 13 |
+
numpy>=1.24.0
|
| 14 |
+
pandas>=2.0.0
|
| 15 |
+
|
| 16 |
+
# Utilities
|
| 17 |
+
python-dotenv>=1.0.0
|