Dropping rows and columns

In [16]:
import numpy as np
import pandas as pd 

df = pd.read_csv("bank.csv", sep=';') 

# Showing first 5 rows
df[:5]
Out[16]:
age job marital education default balance housing loan contact day month duration campaign pdays previous poutcome y
0 30 unemployed married primary no 1787 no no cellular 19 oct 79 1 -1 0 unknown no
1 33 services NaN secondary no 4789 yes yes cellular 11 may 220 1 339 4 failure no
2 35 management single tertiary no 1350 yes no cellular 16 apr 185 1 330 1 failure no
3 30 management married tertiary no 1476 yes yes unknown 3 jun 199 4 -1 0 unknown no
4 59 blue-collar married secondary no 0 yes no unknown 5 may 226 1 -1 0 unknown no

Drop a row

In [9]:
# Drop row with index 2 : 2	35	management	single	tertiary	no	1350	yes	no	cellular	16	apr	185	1	330	1	failure	no

df.drop(2)[:5]
Out[9]:
age job marital education default balance housing loan contact day month duration campaign pdays previous poutcome y
0 30 unemployed married primary no 1787 no no cellular 19 oct 79 1 -1 0 unknown no
1 33 services NaN secondary no 4789 yes yes cellular 11 may 220 1 339 4 failure no
3 30 management married tertiary no 1476 yes yes unknown 3 jun 199 4 -1 0 unknown no
4 59 blue-collar married secondary no 0 yes no unknown 5 may 226 1 -1 0 unknown no
5 35 management single tertiary no 747 no no cellular 23 feb 141 2 176 3 failure no

Drop a column

In [15]:
# Drop column -> job

df.drop('job', axis=1)[:5]
Out[15]:
age marital education default balance housing loan contact day month duration campaign pdays previous poutcome y
0 30 married primary no 1787 no no cellular 19 oct 79 1 -1 0 unknown no
1 33 NaN secondary no 4789 yes yes cellular 11 may 220 1 339 4 failure no
2 35 single tertiary no 1350 yes no cellular 16 apr 185 1 330 1 failure no
3 30 married tertiary no 1476 yes yes unknown 3 jun 199 4 -1 0 unknown no
4 59 married secondary no 0 yes no unknown 5 may 226 1 -1 0 unknown no