data_preprocessing_template.py

# DATA PREPROCESSING

# importing 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.impute import SimpleImputer
imputer=SimpleImputer(missing_values=np.nan,strategy="mean")
imputer=imputer.fit(X[:,1:3]) 
X[:,1:3]=imputer.transform(X[:,1:3])

#encoding categorical data
from sklearn.preprocessing import OneHotEncoder
from sklearn.compose import ColumnTransformer
ct = ColumnTransformer([('encoder', OneHotEncoder(), [0])], remainder='passthrough')
X = np.array(ct.fit_transform(X), dtype=np.float)
# Encoding Y data
from sklearn.preprocessing import LabelEncoder
Y = LabelEncoder().fit_transform(Y)

# 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_X = StandardScaler()
X_train = sc_X.fit_transform(X_train)
X_test = sc_X.transform(X_test)
sc_Y = StandardScaler()
Y_train = sc_Y.fit_transform(Y_train.reshape(-1,1))