import pandas as pd
import numpy as np
dict_data = {
'CL': [100,800,200],
'CO': [100,200,300],
'MX': [300,500,400]
}
dict_data
df = pd.DataFrame(dict_data)
df
CLint64
COint64
0
100
100
1
800
200
2
200
300
dict_data = {
'edad' : [ 10, 9, 13, 14, 12, 11, 12],
'cm' : [ 115, 110, 130, 155, 125, 120, 125],
'pais' : [ 'co', 'mx', 'co', 'mx', 'mx', 'ch', 'ch'],
'genero' : [ 'M', 'F', 'F', 'M', 'M', 'M', 'F'],
'Q1' : [ 5, 10, 8, np.nan, 7, 8, 3],
'Q2' : [ 7, 9, 9, 8, 8, 8, 9.]
}
dict_data
df = pd.DataFrame(dict_data, index = ['ana','benito','camilo','daniel','erika','fabian','gabriela'])
df
edadint64
cmint64
ana
10
115
benito
9
110
camilo
13
130
daniel
14
155
erika
12
125
fabian
11
120
gabriela
12
125
df.index
df.columns
df.values
df[['edad','cm','Q1']]
edadint64
cmint64
ana
10
115
benito
9
110
camilo
13
130
daniel
14
155
erika
12
125
fabian
11
120
gabriela
12
125
df.loc[['ana','erika'],['edad','cm','Q1']]
edadint64
cmint64
ana
10
115
erika
12
125
df.loc['daniel','Q1']
df.iloc[:,[1,3]]
cmint64
generoobject
ana
115
M
benito
110
F
camilo
130
F
daniel
155
M
erika
125
M
fabian
120
M
gabriela
125
F
df[(df['edad'] >= 12) & (df['pais'] == 'mx')]
edadint64
cmint64
daniel
14
155
erika
12
125
df.query('edad > 12')
edadint64
cmint64
camilo
13
130
daniel
14
155
df[df['Q2']>=df['Q1']]
edadint64
cmint64
ana
10
115
camilo
13
130
erika
12
125
fabian
11
120
gabriela
12
125