Create main.py

main.py

@@ -1,83 +1,64 @@
-from fastapi import FastAPI
-from fastapi.responses import HTMLResponse
+# main.py
+from fastapi import FastAPI, Query, Request, HTTPException
+from fastapi.responses import JSONResponse, HTMLResponse
 from fastapi.templating import Jinja2Templates
-from fastapi import FastAPI, Query, Request
-
-from pydantic import BaseModel
-from transformers import pipeline 
-from typing import Union
-import pickle 
-import joblib 
+import xgboost as xgb
+import joblib
+import pandas as pd
+from pydantic import BaseModel  # Import Pydantic's BaseModel
 
+app = FastAPI()
+templates = Jinja2Templates(directory="templates")
 
 # Load the pickled XGBoost model
 xgb_model = joblib.load("xgb_model.joblib")
 
-
-app = FastAPI()
-templates = Jinja2Templates(directory="templates")
-
-@app.get("/display")
-def display_params(
+class InputFeatures(BaseModel):
+    prg: float
+    pl: float
+    pr: float
+    sk: float
+    ts: float
+    m11: float
+    bd2: float
+    age: int
+
+@app.get("/")
+async def read_root():
+    return {"message": "Welcome to the XGBoost Diabetes Prediction API"}
+
+@app.get("/form/")
+async def show_form():
+    return templates.TemplateResponse("input_form.html", {"request": None})
+
+@app.post("/predict/")
+async def predict_diabetes(
     request: Request,
-    prg: float = Query(..., description="Plasma glucose"),
-    pl: float = Query(..., description="Blood Work Result-1 (mu U/ml)"),
-    pr: float = Query(..., description="Blood Pressure (mm Hg)"),
-    sk: float = Query(..., description="Blood Work Result-2 (mm)"),
-    ts: float = Query(..., description="Blood Work Result-3 (mu U/ml)"),
-    m11: float = Query(..., description="Body mass index (weight in kg/(height in m)^2"),
-    bd2: float = Query(..., description="Blood Work Result-4 (mu U/ml)"),
-    age: int = Query(..., description="Patient's age (years)")
+    input_data: InputFeatures  # Use the Pydantic model for input validation
 ):
-    #prepare input features for prediction
-    input_features = [prg,pl,pr,sk,ts,m11,bd2,age]
-
-    #Make predictions using the loaded model 
-    prediction = xgb_model.predict([input_features])[0]
-
-    return templates.TemplateResponse(
-        "display_params.html",
-        {
-            "request": request,
-            "prg": prg,
-            "pl": pl,
-            "pr": pr,
-            "sk": sk,
-            "ts": ts,
-            "m11": m11,
-            "bd2": bd2,
-            "age": age
-            "prediction": prediction  # Include the prediction in the response
+    try:
+        # Convert Pydantic model to a DataFrame for prediction
+        input_df = pd.DataFrame([input_data.dict()])
+
+        # Make predictions using the loaded XGBoost model
+        prediction = xgb_model.predict_proba(xgb.DMatrix(input_df))
+
+        # Create a JSON response
+        response = {
+            "input_features": input_data,
+            "prediction": {
+                "class_0_probability": prediction[0],
+                "class_1_probability": prediction[1]
+            }
         }
-    )
-
-
-
-
-
-
-
-
-# class Item(BaseModel):
-#     name: str
-#     price: float
-#     is_offer: Union[bool, None] = None
-
-
-# @app.get("/")
-# def read_root():
-#     return {"Hello": "World"}
-
-
-# @app.get("/items/{item_id}")
-# def read_item(item_id: int, q: Union[str, None] = None):
-#     return {"item_id": item_id, "q": q}
-
-
-# @app.put("/items/{item_id}")
-# def update_item(item_id: int, item: Item):
-#     return {"item_name": item.name, "item_id": item_id}
 
-# @app.get("/display")
-# def display_params(request: Request, item_id: int, q: Union[str, None] = None):
-#     return templates.TemplateResponse("display_params.html", {"request": request, "item_id": item_id, "q": q})
+        return templates.TemplateResponse(
+            "display_params.html",
+            {
+                "request": request,
+                "input_features": response["input_features"],
+                "prediction": response["prediction"]
+            }
+        )
+    except Exception as e:
+        raise HTTPException(status_code=500, detail="An error occurred while processing the request.")