add CI/CD pipeline

Author: msaad-dot

.github/workflows/deploy.yml

@@ -0,0 +1,27 @@
+name: CI/CD Pipeline
+
+on:
+  push:
+    branches:
+      - main
+
+jobs:
+  build-and-push:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          push: true
+          tags: saaddot/fraud-detection-api:latest

Dockerfile

@@ -0,0 +1,12 @@
+FROM python:3.11-slim
+
+WORKDIR /api
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
+
+EXPOSE 8000
+
+CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]

app/.ipynb_checkpoints/config-checkpoint.py

@@ -0,0 +1,28 @@
+from pathlib import Path
+
+# ------------------------
+# Project paths
+# ------------------------
+BASE_DIR = Path(__file__).resolve().parent.parent
+
+MODEL_PATH = BASE_DIR / "models" / "xgboost.pkl"
+SCALER_PATH = BASE_DIR / "artifacts" / "standard_scaler.pkl"
+
+# ------------------------
+# Model metadata
+# ------------------------
+MODEL_NAME = "xgboost_fraud_detector"
+MODEL_VERSION = "1.0.0"
+
+# ------------------------
+# Inference configuration
+# ------------------------
+THRESHOLD = 0.5
+
+FEATURE_ORDER = [
+    "Time",
+    "V1", "V2", "V3", "V4", "V5", "V6", "V7", "V8", "V9",
+    "V10", "V11", "V12", "V13", "V14", "V15", "V16", "V17", "V18", "V19",
+    "V20", "V21", "V22", "V23", "V24", "V25", "V26", "V27", "V28",
+    "Amount"
+]

app/.ipynb_checkpoints/inference-checkpoint.py

@@ -0,0 +1,31 @@
+import joblib # type: ignore
+import pandas as pd  # pyright: ignore[reportMissingModuleSource]
+from pathlib import Path
+from .config import (
+    MODEL_PATH,
+    SCALER_PATH,
+    THRESHOLD,
+    FEATURE_ORDER
+)
+
+model = joblib.load(MODEL_PATH)
+scaler = joblib.load(SCALER_PATH)
+
+def predict_fraud(features: dict) -> dict:
+    data = pd.DataFrame([features])
+
+    # 2. Scale ONLY Time and Amount
+    data[["Time", "Amount"]] = scaler.transform(
+        data[["Time", "Amount"]]
+    )
+
+    # Reorder columns to match training schema
+    data = data[FEATURE_ORDER]
+
+    probability = model.predict_proba(data)[0][1]
+
+    return {
+        "fraud_probability": float(probability),
+        "threshold": THRESHOLD,
+        "is_fraud": bool(probability >= THRESHOLD)
+    }

app/.ipynb_checkpoints/main-checkpoint.py

@@ -0,0 +1,52 @@
+from fastapi import FastAPI, HTTPException
+from .schemas import Transaction
+from .inference import predict_fraud
+
+from .config import (
+    MODEL_NAME,
+    MODEL_VERSION,
+    THRESHOLD,
+    FEATURE_ORDER
+)
+
+app = FastAPI(
+    title="Fraud Detection API",
+    version="1.0.0"
+)
+
+@app.get("/health")
+def health_check():
+    return {"status": "ok"}
+
+@app.post("/predict")
+def predict(transaction: Transaction):
+    try:
+        return predict_fraud(transaction.model_dump())
+
+    except KeyError as e:
+        raise HTTPException(
+            status_code=400,
+            detail=f"Missing required feature: {str(e)}"
+        )
+
+    except ValueError as e:
+        raise HTTPException(
+            status_code=400,
+            detail=str(e)
+        )
+
+    except Exception:
+        raise HTTPException(
+            status_code=500,
+            detail="Internal model inference error"
+        )
+
+@app.get("/model-info")
+def model_info():
+    return {
+        "model_name": MODEL_NAME,
+        "model_version": MODEL_VERSION,
+        "threshold": THRESHOLD,
+        "num_features": len(FEATURE_ORDER)
+    }
+