.

app.py

@@ -9,17 +9,6 @@ s = setup(healthcare_stroke_data, target = 'stroke', normalize = True, normalize
 
 best = compare_models(sort = 'AUC', n_select = 15)
 compare_model_results = pull()
-
-def predict(model, gender, age, hypertension, heart_disease, ever_married, work_type, Residence_type, avg_glucose_level, bmi, smoking_status):
-  
-    df = pd.DataFrame.from_dict({'gender': [gender], 'age': [age], 'hypertension': [hypertension], 'heart_disease':[heart_disease], 'ever_married':[ever_married],
-                                 'work_type': [work_type], 'Residence_type': [Residence_type], 'avg_glucose_level': [avg_glucose_level], 'bmi':[bmi],'smoking_status':[smoking_status]})
-    model_index = list(compare_model_results['Model']).index(model)
-    model = best[model_index]
-    pred = predict_model(model, df, raw_score=True)
-    return {'Yes': pred['Score_Yes'][0].astype('float64'), 
-            'No': pred['Score_No'][0].astype('float64' )}
-            
             
 model = gr.inputs.Dropdown(list(compare_model_results['Model']),label="Model")
 gender = gr.inputs.Dropdown(choices=["Male", "Female"],label = 'gender')