Update app.py

app.py

@@ -69,9 +69,62 @@ user_data = user_report()
 st.header("Customer Data")
 st.write(user_data)
 
+
+def prediction(user_data):
+    # Importing data from csv
+
+        df = pd.read_csv('health_insurance.csv')
+
+        from sklearn.preprocessing import LabelEncoder
+
+        le_gender  = LabelEncoder() 
+        df['Gender'] = le_gender.fit_transform(df['Gender'])
+
+        le_vAge =  LabelEncoder()
+        df['Vehicle_Age'] = le_vAge.fit_transform(df['Vehicle_Age'])
+
+        le_vDamage = LabelEncoder()
+        df['Vehicle_Damage'] = le_vDamage.fit_transform(df['Vehicle_Damage'])
+
+        x = df.drop('Response', axis = 1)
+        y = df['Response']
+
+        #balancing the data for Target column
+        from imblearn.over_sampling import SMOTE
+
+        smt = SMOTE(k_neighbors=8, random_state=10)
+        x_new, y_new = smt.fit_resample(x, y)
+        #x_new.shape, y_new.shape
+
+        #Splitting the data into train and test datasets
+
+        from sklearn.model_selection import train_test_split
+
+        xtrain, xtest, ytrain, ytest = train_test_split(x_new, y_new, test_size =.30, random_state = 0)
+        #xtrain.shape, xtest.shape, ytrain.shape, ytest.shape
+
+
+        from sklearn.preprocessing import StandardScaler
+
+        scaler = StandardScaler()
+        xtrain = scaler.fit_transform(xtrain)
+        xtest = scaler.transform(xtest)
+
+
+        from xgboost import XGBClassifier
+
+        model_xgb = XGBClassifier()
+        model_xgb.fit(xtrain, ytrain)
+
+        response = model_xgb.predict(user_data)
+        if response==1:
+            st.subheader('This customer willing to buy a vehicle insurance')
+        else:
+            st.subheader('This customer will not buy a vehicle insurance')
+
 y_pred = cross_sell(user_data)
 
-st.subheader(y_pred)
+