update app.py using joblib.load

app.py

@@ -1,115 +1,77 @@
 import gradio as gr
+import dill
 import pandas as pd
+import xgboost as xgb
 import numpy as np
 import pickle
-from sklearn.preprocessing import StandardScaler
-import sklearn
-
-print(f"Prediction environment scikit-learn version: {sklearn.__version__}")
-
-def preprocess_input(data_dict):
-    """Preprocess input data to match the training format"""
-    df = pd.DataFrame([data_dict])
-    
-    # Numeric features - add prefix 'num__'
-    numeric_features = ['age', 'avg_glucose_level', 'bmi']
-    for feat in numeric_features:
-        df[f'num__{feat}'] = df[feat]
-    
-    # Scale numeric features
-    scaler = StandardScaler()
-    for feat in numeric_features:
-        df[f'num__{feat}'] = scaler.fit_transform(df[[feat]])
-    
-    # Create categorical features with proper prefixes
-    # gender
-    df['cat__gender_Male'] = (df['gender'] == 'Male').astype(float)
-    df['cat__gender_Other'] = 0.0  # Assuming no 'Other' gender in our interface
-    
-    # hypertension
-    df['cat__hypertension_1'] = df['hypertension'].astype(float)
-    
-    # heart_disease
-    df['cat__heart_disease_1'] = df['heart_disease'].astype(float)
-    
-    # ever_married
-    df['cat__ever_married_Yes'] = (df['ever_married'] == 'Yes').astype(float)
-    
-    # work_type
-    df['cat__work_type_Never_worked'] = (df['work_type'] == 'Never_worked').astype(float)
-    df['cat__work_type_Private'] = (df['work_type'] == 'Private').astype(float)
-    df['cat__work_type_Self-employed'] = (df['work_type'] == 'Self-employed').astype(float)
-    df['cat__work_type_children'] = (df['work_type'] == 'children').astype(float)
-    
-    # Residence_type
-    df['cat__Residence_type_Urban'] = (df['Residence_type'] == 'Urban').astype(float)
-    
-    # smoking_status
-    df['cat__smoking_status_formerly smoked'] = (df['smoking_status'] == 'formerly smoked').astype(float)
-    df['cat__smoking_status_never smoked'] = (df['smoking_status'] == 'never smoked').astype(float)
-    df['cat__smoking_status_smokes'] = (df['smoking_status'] == 'smokes').astype(float)
-    
-    # Select only the transformed columns in the correct order
-    expected_columns = [
-        'num__age', 'num__avg_glucose_level', 'num__bmi',
-        'cat__gender_Male', 'cat__gender_Other', 'cat__hypertension_1',
-        'cat__heart_disease_1', 'cat__ever_married_Yes',
-        'cat__work_type_Never_worked', 'cat__work_type_Private',
-        'cat__work_type_Self-employed', 'cat__work_type_children',
-        'cat__Residence_type_Urban', 'cat__smoking_status_formerly smoked',
-        'cat__smoking_status_never smoked', 'cat__smoking_status_smokes'
-    ]
-    
-    return df[expected_columns]
-
-def predict(gender, age, hypertension, ever_married, work_type, heart_disease, 
-           avg_glucose_level, bmi, smoking_status, Residence_type):
-    """Make prediction using the loaded model"""
-    # Create input dictionary
-    input_data = {
-        'gender': gender,
-        'age': age,
-        'hypertension': 1 if hypertension == 'Yes' else 0,
-        'heart_disease': 1 if heart_disease == 'Yes' else 0,
-        'ever_married': ever_married,
-        'work_type': work_type,
-        'Residence_type': Residence_type,
-        'avg_glucose_level': avg_glucose_level,
-        'bmi': bmi,
-        'smoking_status': smoking_status
-    }
-    
-    # Preprocess the input
-    processed_input = preprocess_input(input_data)
-    
-    # Load and use the model
-    try:
-        with open('model.pkl', 'rb') as file:
-            model = pickle.load(file)
-        prediction = model.predict_proba(processed_input)[0][1]
-        return f"The probability of stroke is {prediction:.2%}"
-    except Exception as e:
-        return f"Error making prediction: {str(e)}"
 
+import joblib
+
+model = joblib.load('model.pkl')
+print(model)
+
+
+
+def predict(gender, age, hypertension, ever_married, work_type, heart_disease, avg_glucose_level, bmi, smoking_status, Residence_type):
+    # Mapping for categorical variables
+    gender_mapping = {'Male': 1, 'Female': 0}
+    hypertension_mapping = {'Yes': 1, 'No': 0}
+    ever_married_mapping = {'Yes': 1, 'No': 0}
+    work_type_mapping = {'Private': 2, 'Self-employed': 4, 'Govt_job': 3, 'children': 1, 'Never_worked': 0}
+    heart_disease_mapping = {'Yes': 1, 'No': 0}
+    smoking_status_mapping = {'formerly smoked': 3, 'smokes': 1, 'never smoked': 2, 'Unknown': 0}
+    Residence_type_mapping = {'Urban': 1, 'Rural': 0}
+
+    # Map categorical variables to their corresponding numerical values
+    gender = gender_mapping[gender]
+    hypertension = hypertension_mapping[hypertension]
+    ever_married = ever_married_mapping[ever_married]
+    work_type = work_type_mapping[work_type]
+    heart_disease = heart_disease_mapping[heart_disease]
+    smoking_status = smoking_status_mapping[smoking_status]
+    Residence_type = Residence_type_mapping[Residence_type]
+
+    inputs = [gender, age, hypertension, ever_married, work_type, heart_disease, avg_glucose_level, bmi, smoking_status, Residence_type]
+    input_labels = ['gender', 'age', 'hypertension', 'ever_married', 'work_type', 'heart_disease', 'avg_glucose_level', 'bmi', 'smoking_status', 'Residence_type']
+
+    # Convert the input into a pandas DataFrame
+    input_df = pd.DataFrame([inputs], columns=input_labels)
+
+    # Predict the stroke probability
+    prediction = model.predict_proba(input_df)[0][1]
+
+    # Return the prediction
+    result = "The probability of stroke is {:.2f}%".format(prediction * 100)  # to give a percentage
+    return result
+
+
+
+
+
+
+input_labels = [
+    'gender', 'age', 'hypertension', 'ever_married', 'work_type', 
+    'heart_disease', 'avg_glucose_level', 'bmi', 'smoking_status', 'Residence_type'
+]
 # Create the Gradio interface
 iface = gr.Interface(
     fn=predict,
     inputs=[
-        gr.Radio(choices=['Female', 'Male'], label="Gender"),
-        gr.Slider(minimum=0, maximum=100, label="Age"),
-        gr.Radio(choices=['Yes', 'No'], label="Hypertension"),
-        gr.Radio(choices=['Yes', 'No'], label="Ever Married"),
-        gr.Radio(choices=['Private', 'Self-employed', 'Govt_job', 'children', 'Never_worked'], label="Work Type"),
-        gr.Radio(choices=['Yes', 'No'], label="Heart Disease"),
-        gr.Number(label="Average Glucose Level"),
-        gr.Slider(minimum=10, maximum=50, label="BMI"),
-        gr.Radio(choices=['formerly smoked', 'never smoked', 'smokes', 'Unknown'], label="Smoking Status"),
-        gr.Radio(choices=['Urban', 'Rural'], label="Residence Type")
+        gr.components.Radio(choices=['Female', 'Male'], label="Gender"),
+        gr.components.Slider(label="Age"),
+        gr.components.Radio(choices=['Yes', 'No'], label="Hypertension"),
+        gr.components.Radio(choices=['Yes', 'No'], label="Ever Married"),
+        gr.components.Radio(choices=['Private', 'Self-employed', 'Govt_job', 'children', 'Never_worked'], label="Work Type"),
+        gr.components.Radio(choices=['Yes', 'No'], label="Heart Disease"),
+        gr.components.Number(label="Average Glucose Level"),
+        gr.components.Slider(label="BMI"),
+        gr.components.Radio(choices=['formerly smoked', 'never smoked', 'smokes', 'Unknown'], label="Smoking Status"),
+        gr.components.Radio(choices=['Urban', 'Rural'], label="Residence Type")
     ],
     outputs='text',
     title='Stroke Probability Predictor',
     description='Predicts the probability of having a stroke based on input features.'
 )
 
-if __name__ == "__main__":
-    iface.launch()
+
+iface.launch()