implemented model deployment using fast api and docker

Dockerfile

@@ -0,0 +1,18 @@
+# Use Python 3.9 slim image
+FROM python:3.9-slim
+
+# Set working directory
+WORKDIR /app
+
+# Copy requirements and install
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy source code
+COPY src/ ./src/
+
+# Expose port
+EXPOSE 8000
+
+# Run the application
+CMD ["uvicorn", "src.api.main:app", "--host", "0.0.0.0", "--port", "8000"]

docker-compose.yml

@@ -0,0 +1,11 @@
+version: '3.8'
+
+services:
+  api:
+    build: .
+    ports:
+      - "8000:8000"
+    volumes:
+      - ./mlruns:/app/mlruns  # If MLflow uses local storage
+    environment:
+      - MLFLOW_TRACKING_URI=http://localhost:5000  # If running MLflow server separately

src/api/main.py

@@ -0,0 +1,31 @@
+from fastapi import FastAPI
+import mlflow.sklearn
+import pandas as pd
+from .pydantic_models import TransactionData, PredictionResponse
+
+app = FastAPI(title="Credit Risk Prediction API", version="1.0.0")
+
+# Load the model from MLflow registry
+model_name = "CreditRiskLogisticRegression"
+model_version = "latest"  # or specify version
+model = mlflow.sklearn.load_model(f"models:/{model_name}/{model_version}")
+
+@app.post("/predict", response_model=PredictionResponse)
+def predict_risk(transaction: TransactionData):
+    # Convert to DataFrame
+    data = pd.DataFrame([transaction.dict()])
+
+    # Predict probability
+    proba = model.predict_proba(data)[:, 1][0]
+
+    # Predict class
+    prediction = model.predict(data)[0]
+
+    return PredictionResponse(
+        risk_probability=float(proba),
+        is_high_risk=bool(prediction)
+    )
+
+@app.get("/")
+def read_root():
+    return {"message": "Credit Risk Prediction API"}

src/api/pydantic_models.py

@@ -0,0 +1,17 @@
+from pydantic import BaseModel
+from typing import Optional
+
+class TransactionData(BaseModel):
+    CurrencyCode: str
+    CountryCode: int
+    ProviderId: str
+    ProductId: str
+    ProductCategory: str
+    ChannelId: str
+    Amount: float
+    Value: int
+    PricingStrategy: int
+
+class PredictionResponse(BaseModel):
+    risk_probability: float
+    is_high_risk: bool