data_preprocessing_tools.py

# -*- coding: utf-8 -*-
"""
Created on Wed May 13 07:38:37 2020

@author: matix
"""

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

dataset = pd.read_csv('Pre-processing\Data.csv')

X = dataset.iloc[:, :-1].values
y = dataset.iloc[:, -1].values


"""Taking care of missing data"""

from sklearn.impute import SimpleImputer
imputer = SimpleImputer(missing_values=np.nan, strategy='mean')
imputer.fit(X[:, 1:3])
X[:, 1:3] = imputer.transform(X[:, 1:3])

"""Encoding the Independent Variable"""

from sklearn.compose import ColumnTransformer
from sklearn.preprocessing import OneHotEncoder
ct = ColumnTransformer(transformers=[('encoder', OneHotEncoder(), [0])], remainder='passthrough')
X = np.array(ct.fit_transform(X))

"""Encoding the Dependent Variable"""

from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()
y = le.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 = 1)

"""Feature Scaling"""

from sklearn.preprocessing import StandardScaler
sc = StandardScaler()
X_train[:, 3:] = sc.fit_transform(X_train[:, 3:])
X_test[:, 3:] = sc.transform(X_test[:, 3:])