In [218]:
# -*- encoding: utf-8 -*-
import numpy as np
import pandas as pd
import matplotlib
from matplotlib import pyplot as plt
import xlrd #sudo pip3 install xlrd (para usar o metodo to_excel()do pandas )
import xlwt
%matplotlib inline
In [226]:
fis = pd.read('fi.csv')
fis.head()
In [228]:
#?pd.read_csv
#df = pd.read_csv('meteorologia.csv', encoding='utf-8', index_col=0)
df = pd.read_csv('meteorologia.csv', encoding='utf-8')
del(df['TOTAL_AVALIADOS'])
In [50]:
#Busca por linhas, as que possuem como indice o valor idx. sintaxe: df.loc[idx]
#df.loc[1.1]
In [229]:
grupos = df.groupby(['ORDEM','EIXO', 'ALTERNATIVA']).sum()
#grupos.to_html('curso-131-statis.html')
#grupos.to_excel('curso-131-statis.xls', sheet_name='Sheet1')
grupos
#df.select(lambda x: x == 'ORDEM', axis=1).groupby('ORDEM').sum()
Out[229]:
In [116]:
df.ALTERNATIVA[ df.ORDEM == 1.1 ].count()
Out[116]:
In [93]:
plt.figure(figsize=(16,8))
df['ALTERNATIVA'].plot(kind='hist', stacked=True, bins=100)
Out[93]:
In [ ]: