data preprocessing

github

In [2]:

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

In [3]:

data = pd.read_csv("data.csv")
data.head(2)

Out[3]:

	Country	Age	Salary	Purchased
0	France	44.0	72000.0	No
1	Spain	27.0	48000.0	Yes

In [8]:

x = data.iloc[:,[0,1,2]]
y = data.iloc[:,3]
x

Out[8]:

	Country	Age	Salary
0	France	44.0	72000.0
1	Spain	27.0	48000.0
2	Germany	30.0	54000.0
3	Spain	38.0	61000.0
4	Germany	40.0	NaN
5	France	35.0	58000.0
6	Spain	NaN	52000.0
7	France	48.0	79000.0
8	Germany	50.0	83000.0
9	France	37.0	67000.0

In [10]:

x.iloc[:,2].fillna(np.mean(x.iloc[:,2]),inplace = True)
x.iloc[:,1].fillna(np.mean(x.iloc[:,1]),inplace = True)
x

Out[10]:

	Country	Age	Salary
0	France	44.000000	72000.000000
1	Spain	27.000000	48000.000000
2	Germany	30.000000	54000.000000
3	Spain	38.000000	61000.000000
4	Germany	40.000000	63777.777778
5	France	35.000000	58000.000000
6	Spain	38.777778	52000.000000
7	France	48.000000	79000.000000
8	Germany	50.000000	83000.000000
9	France	37.000000	67000.000000

In [84]:

from sklearn.preprocessing import LabelEncoder
from sklearn.preprocessing import OneHotEncoder

In [12]:

x = pd.get_dummies(x)
x

Out[12]:

	Age	Salary	Country_France	Country_Germany	Country_Spain
0	44.000000	72000.000000	1	0	0
1	27.000000	48000.000000	0	0	1
2	30.000000	54000.000000	0	1	0
3	38.000000	61000.000000	0	0	1
4	40.000000	63777.777778	0	1	0
5	35.000000	58000.000000	1	0	0
6	38.777778	52000.000000	0	0	1
7	48.000000	79000.000000	1	0	0
8	50.000000	83000.000000	0	1	0
9	37.000000	67000.000000	1	0	0

In [ ]:

In [ ]: