51 Groupby In numpy

In [1]:

import pandas as pd

In [4]:

dmc = {'Company':['Hyderabad','Hyderabad','Pune','Pune','Chennai','Chennai'],
       'Person':['ramesh','Venkat','Praveen','Prasad','Nani','Kiran'],
       'Sales':[500,1520,440,334,273,850]}

In [5]:

dmc

Out[5]:

{'Company': ['Hyderabad', 'Hyderabad', 'Pune', 'Pune', 'Chennai', 'Chennai'],
 'Person': ['ramesh', 'Venkat', 'Praveen', 'Prasad', 'Nani', 'Kiran'],
 'Sales': [500, 1520, 440, 334, 273, 850]}

In [6]:

df=pd.DataFrame(dmc)

In [7]:

df

Out[7]:

	Company	Person	Sales
0	Hyderabad	ramesh	500
1	Hyderabad	Venkat	1520
2	Pune	Praveen	440
3	Pune	Prasad	334
4	Chennai	Nani	273
5	Chennai	Kiran	850

In [8]:

df.groupby('Company').mean()

Out[8]:

	Sales
Company
Chennai	561.5
Hyderabad	1010.0
Pune	387.0

In [9]:

df.groupby('Company')

Out[9]:

<pandas.core.groupby.DataFrameGroupBy object at 0x0000000007F7AF28>

In [10]:

gr=df.groupby('Company')

In [11]:

gr.mean()

Out[11]:

	Sales
Company
Chennai	561.5
Hyderabad	1010.0
Pune	387.0

In [12]:

gr.max()

Out[12]:

	Person	Sales
Company
Chennai	Nani	850
Hyderabad	ramesh	1520
Pune	Praveen	440

In [13]:

gr.min()

Out[13]:

	Person	Sales
Company
Chennai	Kiran	273
Hyderabad	Venkat	500
Pune	Prasad	334

In [14]:

gr.count()

Out[14]:

	Person	Sales
Company
Chennai	2	2
Hyderabad	2	2
Pune	2	2

In [22]:

gr.describe()

Out[22]:

	Sales
	count	mean	std	min	25%	50%	75%	max
Company
Chennai	2.0	561.5	408.000613	273.0	417.25	561.5	705.75	850.0
Hyderabad	2.0	1010.0	721.248917	500.0	755.00	1010.0	1265.00	1520.0
Pune	2.0	387.0	74.953319	334.0	360.50	387.0	413.50	440.0

In [16]:

gr.describe().transpose()

Out[16]:

	Company	Chennai	Hyderabad	Pune
Sales	count	2.000000	2.000000	2.000000
	mean	561.500000	1010.000000	387.000000
	std	408.000613	721.248917	74.953319
	min	273.000000	500.000000	334.000000
	25%	417.250000	755.000000	360.500000
	50%	561.500000	1010.000000	387.000000
	75%	705.750000	1265.000000	413.500000
	max	850.000000	1520.000000	440.000000

In [23]:

gr.describe().transpose()

Out[23]:

	Company	Chennai	Hyderabad	Pune
Sales	count	2.000000	2.000000	2.000000
	mean	561.500000	1010.000000	387.000000
	std	408.000613	721.248917	74.953319
	min	273.000000	500.000000	334.000000
	25%	417.250000	755.000000	360.500000
	50%	561.500000	1010.000000	387.000000
	75%	705.750000	1265.000000	413.500000
	max	850.000000	1520.000000	440.000000

https://www.tutorialspoint.com/python_pandas/python_pandas_groupby.htm

In [3]:

import pandas as pd

ipl_data = {'Team': ['Riders', 'Riders', 'Devils', 'Devils', 'Kings',
         'kings', 'Kings', 'Kings', 'Riders', 'Royals', 'Royals', 'Riders'],
         'Rank': [1, 2, 2, 3, 3,4 ,1 ,1,2 , 4,1,2],
         'Year': [2014,2015,2014,2015,2014,2015,2016,2017,2016,2014,2015,2017],
         'Points':[876,789,863,673,741,812,756,788,694,701,804,690]}
df = pd.DataFrame(ipl_data)

print (df)

    Points  Rank    Team  Year
0      876     1  Riders  2014
1      789     2  Riders  2015
2      863     2  Devils  2014
3      673     3  Devils  2015
4      741     3   Kings  2014
5      812     4   kings  2015
6      756     1   Kings  2016
7      788     1   Kings  2017
8      694     2  Riders  2016
9      701     4  Royals  2014
10     804     1  Royals  2015
11     690     2  Riders  2017

In [4]:

df

Out[4]:

	Points	Rank	Team	Year
0	876	1	Riders	2014
1	789	2	Riders	2015
2	863	2	Devils	2014
3	673	3	Devils	2015
4	741	3	Kings	2014
5	812	4	kings	2015
6	756	1	Kings	2016
7	788	1	Kings	2017
8	694	2	Riders	2016
9	701	4	Royals	2014
10	804	1	Royals	2015
11	690	2	Riders	2017

In [5]:

df.groupby('Team')

Out[5]:

<pandas.core.groupby.DataFrameGroupBy object at 0x0000000005AFF400>

In [6]:

 df.groupby('Team').groups

Out[6]:

{'Devils': Int64Index([2, 3], dtype='int64'),
 'Kings': Int64Index([4, 6, 7], dtype='int64'),
 'Riders': Int64Index([0, 1, 8, 11], dtype='int64'),
 'Royals': Int64Index([9, 10], dtype='int64'),
 'kings': Int64Index([5], dtype='int64')}