data_preprocessing.py

# -*- coding: utf-8 -*-
#importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd

#Importing the Dataset
dataset = pd.read_csv('Data.csv')
X = dataset.iloc[:, :-1].values
Y = dataset.iloc[:,3].values

# Taking care of missing data
#from sklearn.preprocessing import Imputer
from sklearn.impute import SimpleImputer
imputer = SimpleImputer(missing_values = np.nan, strategy = 'mean', verbose = 0)
imputer = imputer.fit(X[:, 1:3])
X[:, 1:3] = imputer.transform(X[:, 1:3])

#Encoding categorial data
from sklearn.preprocessing import LabelEncoder
labelencoder_X = LabelEncoder()
X[:, 0] = labelencoder_X.fit_transform(X[:, 0])

from sklearn.preprocessing import OneHotEncoder
onehotencoder = OneHotEncoder(categories= 'auto')
X = onehotencoder.fit_transform(X).toarray()

labelencoder_Y = LabelEncoder()
Y = labelencoder_Y.fit_transform(Y)

#Splitting the dataset into train and test test
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)

#Scaling if you want the data to be in the same format
#from sklearn.preprocessing import StandardScaler
#sc_X = StandardScaler()
#X_train = sc_X.fit_transform(X_train)
#X_test = sc_X.transform(X_test)