Update app.py

app.py

@@ -2,7 +2,44 @@ import gradio as gr
 import pandas as pd
 import numpy as np
 import pickle
-from steps.transform import transformer_fn
+from sklearn.compose import ColumnTransformer
+from sklearn.preprocessing import StandardScaler, OneHotEncoder
+from sklearn.pipeline import Pipeline
+from sklearn.impute import SimpleImputer
+
+def transformer_fn():
+    """
+    Returns a preprocessing pipeline that matches the training approach.
+    """
+    # Define numeric and categorical features
+    numeric_features = ['age', 'avg_glucose_level', 'bmi']
+    categorical_features = [
+        'gender', 'hypertension', 'heart_disease', 'ever_married',
+        'work_type', 'Residence_type', 'smoking_status'
+    ]
+    
+    # Create numeric pipeline
+    numeric_transformer = Pipeline(steps=[
+        ('imputer', SimpleImputer(strategy='median')),
+        ('scaler', StandardScaler())
+    ])
+    
+    # Create categorical pipeline
+    categorical_transformer = Pipeline(steps=[
+        ('imputer', SimpleImputer(strategy='constant', fill_value='missing')),
+        ('onehot', OneHotEncoder(drop='first', sparse=False))
+    ])
+    
+    # Combine preprocessing steps
+    preprocessor = ColumnTransformer(
+        transformers=[
+            ('num', numeric_transformer, numeric_features),
+            ('cat', categorical_transformer, categorical_features)
+        ],
+        remainder='drop'  # Drop any other columns
+    )
+    
+    return preprocessor
 
 # Load the model
 with open('model.pkl', 'rb') as f:
@@ -31,7 +68,7 @@ def predict(gender, age, hypertension, ever_married, work_type, heart_disease, a
 
     # Transform the input using the same transformer used during training
     try:
-        X_transformed = transformer.transform(input_df)
+        X_transformed = transformer.fit_transform(input_df)  # Using fit_transform since it's a new transformer instance
         prediction = model.predict_proba(X_transformed)[0][1]
         return f"The probability of stroke is {prediction:.2%}"
     except Exception as e: