Create main.py

main.py

@@ -0,0 +1,55 @@
+# import all the required libraries
+
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns 
+
+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)
+    return response