import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

# Importing the dataset
dataset = pd.read_csv('../input/churn-predictions-personal/Churn_Predictions.csv')
X = dataset.iloc[:, 3:13]
y = dataset.iloc[:, 13]

#Create dummy variables
geography=pd.get_dummies(X["Geography"],drop_first=True)
gender=pd.get_dummies(X['Gender'],drop_first=True)
## Concatenate the Data Frames
X=pd.concat([X,geography,gender],axis=1)
## Drop Unnecessary columns
X=X.drop(['Geography','Gender'],axis=1)

# Splitting the dataset into the Training set and Test set
from sklearn.model_selection import train_test_split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 0)

# Feature Scaling
from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train = sc.fit_transform(X_train)
X_test = sc.transform(X_test)