Updated Backend

.gitattributes

@@ -1,35 +0,0 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,26 @@
+# Use official Python 3.10 slim image
+FROM python:3.10-slim
+
+# Set working directory to /app
+WORKDIR /app
+
+# Copy requirements (relative to backend/ folder)
+COPY requirements.txt requirements.txt
+
+# Install dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the current directory contents (backend code) into /app
+COPY . .
+
+# Set permissions for Hugging Face (User 1000)
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+# Expose port 7860
+EXPOSE 7860
+
+# Run uvicorn (module is main:app since we are inside the folder)
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -1,10 +1,25 @@
 ---
 title: NavAI Guard Backend
-emoji: 📉
-colorFrom: indigo
-colorTo: pink
+emoji: 🚢
+colorFrom: blue
+colorTo: cyan
 sdk: docker
 pinned: false
+app_port: 7860
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Nav-AI Guard Backend
+
+This repository is configured to deploy the **Nav-AI Guard Backend** to Hugging Face Spaces using Docker.
+
+## Configuration
+
+*   **SDK**: Docker
+*   **App Port**: 7860
+*   **Docker Path**: This repo contains the `Dockerfile` in the `backend/` directory.
+
+## How to Deploy
+
+1.  **Create a Space**: Select **Docker** SDK.
+2.  **Connect Repo**: Point to this repository.
+3.  **Context**: Ensure the Space build context is set to the `backend/` subdirectory if possible, OR if syncing only the backend folder, this `README.md` at the root will auto-configure it.

main.py

@@ -0,0 +1,106 @@
+import os
+import joblib
+import numpy as np
+import pandas as pd
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+from tensorflow.keras.models import load_model
+from fastapi.middleware.cors import CORSMiddleware
+
+app = FastAPI(title="NavAI-Guard API", description="Maritime Anomaly Detection API")
+
+# Enable CORS for frontend
+# In production, you might want to restrict this to your Vercel domain
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"], # Allows all origins
+    allow_credentials=True,
+    allow_methods=["*"], # Allows all methods
+    allow_headers=["*"], # Allows all headers
+)
+
+# Global variables to hold model and scaler
+model = None
+scaler = None
+THRESHOLD = 0.1
+
+class AISData(BaseModel):
+    timestamp_str: str = "27/02/2024 03:42:19"
+    mmsi: float
+    latitude: float
+    longitude: float
+    sog: float
+    cog: float
+    heading: float
+
+@app.on_event("startup")
+def load_assets():
+    global model, scaler
+    try:
+        base_path = os.path.dirname(os.path.abspath(__file__))
+        model_path = os.path.join(base_path, "models", "autoencoder_model.keras")
+        scaler_path = os.path.join(base_path, "models", "scaler.pkl")
+        
+        print(f"Loading model from {model_path}...")
+        model = load_model(model_path)
+        print(f"Loading scaler from {scaler_path}...")
+        scaler = joblib.load(scaler_path)
+        print("Assets loaded successfully.")
+    except Exception as e:
+        print(f"Error loading assets: {e}")
+        raise RuntimeError(f"Could not load model or scaler: {e}")
+
+@app.get("/")
+def health_check():
+    return {"status": "active", "system": "NavAI-Guard"}
+
+@app.post("/predict")
+def predict_anomaly(data: AISData):
+    if model is None or scaler is None:
+        raise HTTPException(status_code=503, detail="Model/Scaler not loaded")
+
+    try:
+        # 1. Process Timestamp
+        # Format: DD/MM/YYYY HH:MM:SS
+        timestamp_sec = pd.to_datetime(data.timestamp_str, format="%d/%m/%Y %H:%M:%S").value / 1e9
+    except Exception as e:
+        raise HTTPException(status_code=400, detail=f"Invalid Timestamp Format: {e}")
+
+    # 2. Prepare Input Vector
+    # Order matches app.py: [timestamp_sec, mmsi, latitude, longitude, sog, cog, heading]
+    input_features = np.array([[
+        timestamp_sec,
+        data.mmsi,
+        data.latitude,
+        data.longitude,
+        data.sog,
+        data.cog,
+        data.heading
+    ]])
+
+    try:
+        # 3. Scale
+        input_scaled = scaler.transform(input_features)
+
+        # 4. Reconstruct
+        reconstructed = model.predict(input_scaled)
+
+        # 5. Calculate Error (MSE)
+        reconstruction_error = np.mean(np.square(input_scaled - reconstructed))
+
+        # 6. Determine Anomaly
+        is_anomaly = float(reconstruction_error) > THRESHOLD
+
+        return {
+            "anomaly": is_anomaly,
+            "score": float(reconstruction_error),
+            "threshold": THRESHOLD,
+            "status": "Anomalous" if is_anomaly else "Normal"
+        }
+
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Prediction error: {e}")
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8000)

requirements.txt

@@ -0,0 +1,8 @@
+fastapi
+uvicorn
+pandas
+numpy
+scikit-learn
+tensorflow
+joblib
+python-multipart