pandas notebook

In [5]:

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

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

Listas, dicionários e vetores¶

In [6]:

lista_01 = [1,5,13,4,6,8] # lista
dict_01 = {"valor x": 1, "valor y": 32, "valor z": 3.5} # dicionário
array_01 = np.array([1,2.3,2.4])

lista_01 = [1,5,13,4,6,8] # lista dict_01 = {"valor x": 1, "valor y": 32, "valor z": 3.5} # dicionário array_01 = np.array([1,2.3,2.4])

In [3]:

lista_01[1]

lista_01[1]

Out[3]:

5

In [4]:

dict_01['valor y']

dict_01['valor y']

Out[4]:

32

In [7]:

array_01[2]

array_01[2]

Out[7]:

2.4

In [12]:

lista_01.append('3.0')
lista_01

lista_01.append('3.0') lista_01

Out[12]:

[1, 5, 13, 4, 6, 8, '3']

In [11]:

array_01 = np.append(array_01, 3.)
array_01

array_01 = np.append(array_01, 3.) array_01

Out[11]:

array([1. , 2.3, 2.4, 3. ])

In [ ]:

dict_01['valor i'] = 4
dict_01.update({'valor j': 4, 'valor k': 5})

dict_01['valor i'] = 4 dict_01.update({'valor j': 4, 'valor k': 5})

Dataframes¶

In [17]:

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

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

Out[17]:

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

In [18]:

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

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

In [14]:

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

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

Out[14]:

	Nome	idade
0	Joelande	14
1	Jociara	18
2	Basilio	15
3	Mahysa	13
4	Carlos	19

Carregando um dataframe de um arquivo¶

In [33]:

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

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[33]:

	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 [ ]:

In [42]:

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

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

Out[42]:

	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 [41]:

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

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

Out[41]:

	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 [43]:

df_female_mut['Weight'].mean()

df_female_mut['Weight'].mean()

Out[43]:

41.0

In [48]:

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

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

Out[48]:

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

arquivo IBGE 2010- Bahia básico¶

arquivo IBGE 2010- Bahia Domicílio renda¶