Upload 4 files

DockerFile

@@ -0,0 +1,17 @@
+FROM python:3.10
+
+# Set working directory
+WORKDIR /code
+
+# Install dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy all files
+COPY . .
+
+# Expose API port
+EXPOSE 7860
+
+# Start FastAPI app
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

main.py

@@ -0,0 +1,67 @@
+from fastapi import FastAPI
+from fastapi.responses import JSONResponse
+from pydantic import BaseModel, Field, computed_field
+from typing import Literal, Annotated
+import pickle
+import pandas as pd
+import joblib
+import traceback
+
+from fastapi.middleware.cors import CORSMiddleware
+
+# Path to your saved pickle file
+model_path = "xgb_model_reg.pkl"  
+
+# Load the model
+model = joblib.load(model_path)
+
+app=FastAPI()
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],  # In production, use specific domains
+    allow_methods=["GET", "POST"],
+    allow_headers=["*"],
+)
+
+#pydantic Model to validate data
+class UserInput(BaseModel):
+    age: Annotated[int, Field(gt=0,description='Age of the Patient')]
+    albumin_gL: Annotated[float, Field(gt=0,description='Quantity of Albumin in gL')]
+    creat_umol: Annotated[float, Field(gt=0,description='Quantity of Creatnine in umol')]
+    glucose_mmol: Annotated[float, Field(gt=0,description='Qunatity of Glucose in mmol')]
+    lncrp:Annotated[float, Field(gt=0,description='Log of Crp')]
+    lymph: Annotated[float, Field(gt=0,description='lym ph')]
+    mcv: Annotated[float, Field(gt=0,description='mcv')]
+    rdw: Annotated[float, Field(gt=0,description='rdw')]
+    alp: Annotated[float, Field(gt=0,description='alp')]
+    wbc: Annotated[float, Field(gt=0,description='white blood cell')]
+
+@app.post('/predict')
+def predict_premium(data: UserInput):
+    try:
+        input_df = pd.DataFrame(
+            [
+                {
+                    'age': data.age,
+                    'albumin_gL': data.albumin_gL,
+                    'creat_umol': data.creat_umol,
+                    'glucose_mmol': data.glucose_mmol,
+                    'lncrp': data.lncrp,
+                    'lymph': data.lymph,
+                    'mcv': data.mcv,
+                    'rdw': data.rdw,
+                    'alp': data.alp,
+                    'wbc': data.wbc
+                }
+            ]
+        )
+
+        prediction_value = float(model.predict(input_df)[0])  # <-- FIXED HERE
+
+        return JSONResponse(
+            status_code=200,
+            content={"Predicted Biological Age of Patient": prediction_value}
+        )
+    except Exception as e:
+        return JSONResponse(status_code=500, content={"error": str(e)})

requirements.txt

@@ -0,0 +1,7 @@
+fastapi
+uvicorn
+pydantic
+pandas
+joblib
+scikit-learn
+xgboost

xgb_model_reg.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c5645af0edb995d8d995921a3454e9ffa1df735d8c60c89d4d5075afea3f200
+size 4417070