FilesExpand file tree

 master

/

data_preprocessing.py

Copy path

Blame

More file actions

Blame

More file actions

Latest commit

 

History

History

History

35 lines (29 loc) · 1.13 KB

 master

/

data_preprocessing.py

Copy path

Top

File metadata and controls

• Code
• Blame

35 lines (29 loc) · 1.13 KB

Raw

Copy raw file

Download raw file

Open symbols panel

Edit and raw actions

1

2

3

4

5

6

7

8

9

10

11

12

13

14

15

16

17

18

19

20

21

22

23

24

25

26

27

28

29

30

31

32

33

34

35

# Import the libraries

import numpy as np

import matplotlib.pyplot as plt

import pandas as pd

# Import 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

imputer=Imputer(missing_values='NaN', strategy='mean', axis=0)

imputer=imputer.fit(X[:, 1:3])

X[:, 1:3] = imputer.transform(X[:, 1:3])

# Encoding categorical data

from sklearn.preprocessing import LabelEncoder, OneHotEncoder

labelencoder_X = LabelEncoder()

X[:,0] = labelencoder_X.fit_transform(X[:,0])

onehotencoder = OneHotEncoder(categorical_features = [0])

X = onehotencoder.fit_transform(X).toarray()

labelencoder_y = LabelEncoder()

y = labelencoder_y.fit_transform(y)

# Splitting the dataset into the training set and test set

from sklearn.cross_validation import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2,random_state=42)

# 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)