In [1]:
import numpy as np
import pandas as pd
In [2]:
data = {'Company':['GOOG','GOOG','MSFT','MSFT','FB','FB'],
'Person':['Sam','Charlie','Amy','Vanessa','Carl','Sarah'],
'Sales':[200,120,340,124,243,350]}
In [4]:
df = pd.DataFrame(data)
In [5]:
df
Out[5]:
In [6]:
df.groupby('Company')
Out[6]:
In [7]:
by_comp = df.groupby('Company')
In [9]:
by_comp.mean()
Out[9]:
In [10]:
by_comp.std()
Out[10]:
In [13]:
by_comp.sum().loc['FB']
Out[13]:
In [15]:
df.groupby('Company').sum().loc['FB'] # the one-liner
Out[15]:
In [16]:
df.groupby('Company').count()
Out[16]:
In [18]:
df.groupby('Company').max() # Note that this does not work for strings. Data is mixed up now
Out[18]:
In [19]:
df.groupby('Company').describe()
Out[19]:
In [20]:
df.groupby('Company').describe().transpose()['FB']
Out[20]:
In [ ]: