Pandas introduction pt1¶

In [1]:

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

In [2]:

idade= np.random.randint(low=12, high=20, size=14)
idade

Out[2]:

array([12, 18, 13, 14, 16, 18, 19, 14, 19, 18, 16, 17, 19, 12])

In [3]:

dados = {'Nome': ['Joelande','Jociara', 'Basilio', 'Mahysa', 'Carlos', 'João Paulo', 'Nilton', 'Ana Paula', 'Hermilino Danilo', 'Paulo Tadeu', 'Evaldo', 'Fernando' , 'Lorena', 'Jailza'],
        'Idade': idade
}

In [9]:

df = pd.DataFrame(dados)
df.head(10)

Out[9]:

	Nome	Idade
0	Joelande	12
1	Jociara	18
2	Basilio	13
3	Mahysa	14
4	Carlos	16
5	João Paulo	18
6	Nilton	19
7	Ana Paula	14
8	Hermilino Danilo	19
9	Paulo Tadeu	18

In [16]:

df['Nome'].values

Out[16]:

array(['Joelande', 'Jociara', 'Basilio', 'Mahysa', 'Carlos', 'João Paulo',
       'Nilton', 'Ana Paula', 'Hermilino Danilo', 'Paulo Tadeu', 'Evaldo',
       'Fernando', 'Lorena', 'Jailza'], dtype=object)

In [19]:

df = pd.read_csv('https://raw.githubusercontent.com/255ribeiro/curso_python_gis/master/docs/dados_py/heroes_information.csv')
print(df.shape)
df.head()

(734, 11)

Out[19]:

	Unnamed: 0	name	Gender	Eye color	Race	Hair color	Height	Publisher	Skin color	Alignment	Weight
0	0	A-Bomb	Male	yellow	Human	No Hair	203.0	Marvel Comics	-	good	441.0
1	1	Abe Sapien	Male	blue	Icthyo Sapien	No Hair	191.0	Dark Horse Comics	blue	good	65.0
2	2	Abin Sur	Male	blue	Ungaran	No Hair	185.0	DC Comics	red	good	90.0
3	3	Abomination	Male	green	Human / Radiation	No Hair	203.0	Marvel Comics	-	bad	441.0
4	4	Abraxas	Male	blue	Cosmic Entity	Black	-99.0	Marvel Comics	-	bad	-99.0

In [21]:

fltr = df['Gender'] == 'Female'
#print(fltr)
df_female = df[fltr]
df_female.head()

Out[21]:

	Unnamed: 0	name	Gender	Eye color	Race	Hair color	Height	Publisher	Skin color	Alignment	Weight
8	8	Agent 13	Female	blue	-	Blond	173.0	Marvel Comics	-	good	61.0
24	24	Angel Dust	Female	yellow	Mutant	Black	165.0	Marvel Comics	-	good	57.0
25	25	Angel Salvadore	Female	brown	-	Black	163.0	Marvel Comics	-	good	54.0
26	26	Angela	Female	-	-	-	-99.0	Image Comics	-	bad	-99.0
38	38	Arachne	Female	blue	Human	Blond	175.0	Marvel Comics	-	good	63.0

In [22]:

fltr =  (df['Gender'] == 'Female') & (df['Race'] == 'Mutant')
df_female_mut = df[fltr]
df_female_mut.head()

Out[22]:

	Unnamed: 0	name	Gender	Eye color	Race	Hair color	Height	Publisher	Skin color	Alignment	Weight
24	24	Angel Dust	Female	yellow	Mutant	Black	165.0	Marvel Comics	-	good	57.0
55	55	Aurora	Female	blue	Mutant	Black	180.0	Marvel Comics	-	good	63.0
114	114	Blink	Female	green	Mutant	Magenta	165.0	Marvel Comics	pink	good	56.0
129	129	Boom-Boom	Female	blue	Mutant	Blond	165.0	Marvel Comics	-	good	55.0
167	167	Cerebra	Female	-	Mutant	-	-99.0	Marvel Comics	-	good	-99.0

In [27]:

df_female_mut['Weight'].median()

Out[27]:

55.5

In [32]:

df_gb = df_female_mut.groupby('Alignment')
df_gb['Weight'].mean()

Out[32]:

Alignment
bad        56.500000
good       37.647059
neutral    67.000000
Name: Weight, dtype: float64

In [35]:

import pandas as pd

import numpy as np

from matplotlib import pyplot as plt

from scipy.optimize import curve_fit

In [37]:

dic1 = {'c1': [1,2,3], 'c2': [4,5,6]}

df1 = pd.DataFrame(dic1)

df1.head()

Out[37]:

	c1	c2
0	1	4
1	2	5
2	3	6

In [38]:

df1.c2

Out[38]:

0    4
1    5
2    6
Name: c2, dtype: int64

In [39]:

df1['c2']

Out[39]:

0    4
1    5
2    6
Name: c2, dtype: int64

In [43]:

df2 = pd.DataFrame({'c1': [7,8,9], 'c3': [10,11,12]})

Concat dataframes¶

In [44]:

df3 = pd.concat([df1, df2]).reset_index()

df3.head(7)

Out[44]:

	index	c1	c2	c3
0	0	1	4.0	NaN
1	1	2	5.0	NaN
2	2	3	6.0	NaN
3	0	7	NaN	10.0
4	1	8	NaN	11.0
5	2	9	NaN	12.0

arquivo IBGE 2010- Bahia básico¶

arquivo IBGE 2010- Bahia Domicílio renda¶