Update app.py

app.py

@@ -1,6 +1,7 @@
 import streamlit as st
 import requests
 import pandas as pd
+import numpy as np
 
 def load_preprocessing_components():
     with open("encoder.pkl", "rb") as f:
@@ -9,6 +10,21 @@ def load_preprocessing_components():
         scaler = dill.load(f)
     return encoder, scaler
 
+
+class InferenceData(BaseModel):
+    Age: float
+    Sex: str
+    ChestPainType: str
+    RestingBP: float
+    Cholesterol: float
+    FastingBS: int
+    RestingECG: str
+    MaxHR: float
+    ExerciseAngina: str
+    Oldpeak: float
+    ST_Slope: str
+
+
 def preprocess_data(df: pd.DataFrame) -> np.ndarray:
     # Encode categorical variables
     encoded = encoder.transform(df[encoder.feature_names_in_])
@@ -25,10 +41,11 @@ def preprocess_data(df: pd.DataFrame) -> np.ndarray:
 
     return df
 
-def predict(data: Dict()):
+
+def predict(data: InferenceData):
     try:
         # Convert input data to DataFrame
-        df = pd.DataFrame([data.model_dump()])
+        df = pd.DataFrame(data.dict())
 
         # Preprocess data
         processed_data = preprocess_data(df)
@@ -59,22 +76,20 @@ exercise_angina = st.selectbox("Exercise-Induced Angina", ["Y", "N"])
 oldpeak = st.number_input("Oldpeak", min_value=0.0, max_value=10.0, step=0.1)
 st_slope = st.selectbox("ST Slope", ["Up", "Flat", "Down"])
 
-# Button to submit the form
 if st.button("Predict"):
-    # Prepare the data payload
-    data = {
-        "Age": age,
-        "Sex": sex,
-        "ChestPainType": chest_pain_type,
-        "RestingBP": resting_bp,
-        "Cholesterol": cholesterol,
-        "FastingBS": fasting_bs,
-        "RestingECG": resting_ecg,
-        "MaxHR": max_hr,
-        "ExerciseAngina": exercise_angina,
-        "Oldpeak": oldpeak,
-        "ST_Slope": st_slope
-    }
+    data = InferenceData(
+        Age=age,
+        Sex=sex,
+        ChestPainType=chest_pain_type,
+        RestingBP=resting_bp,
+        Cholesterol=cholesterol,
+        FastingBS=fasting_bs,
+        RestingECG=resting_ecg,
+        MaxHR=max_hr,
+        ExerciseAngina=exercise_angina,
+        Oldpeak=oldpeak,
+        ST_Slope=st_slope
+    )
     
     # Send a request to the FastAPI server
     response = predict(data)
@@ -87,7 +102,7 @@ if st.button("Predict"):
     else:
         st.error("Error: Unable to get prediction from API. Please try again later.")
 
-# Batch Prediction Section
+
 st.subheader("Batch Prediction")
 uploaded_file = st.file_uploader("Upload CSV for batch prediction", type="csv")