py7. Adding Mean Column and Row to a DataFrame in Python

DataFrames in pandas are similar to data.frame in R and can hold tabular data.

Every column is a specific type, such as integer or float. This is similar to R in which each column is a class such as integer or numeric.

The means function is a method of the DataFrame and the period is important here. In R, the periods are mostly treated as parts of name.

A dictionary d is created, of the 3 samples, and next a DataFrame is created based on the dictionary.

# ex7.py
from __future__ import division, print_function
from pandas import DataFrame
from numpy.random import choice
x1 = choice(10, size = 10, replace = False)
x2 = choice(10, size = 10, replace = False)
x3 = choice(10, size = 10, replace = False)
d = {'x1':x1,'x2':x2,'x3':x3}
df = DataFrame(d)
print('\nDataFrame df =\n%s' % df)
print('\nFirst Column =\n%s' % df['x1'])
print('\nFirst Row =\n%s' % df.ix[0])
print('\nFirst Column, First Row = %s' % df.loc[0,'x1'])
print('\nAdding ave column')
df['ave'] = df.mean(axis=1)
print('\ndf =\n%s' % df)
print('\nAdding ave row')
df.ix['ave_row'] = df.mean(axis=0)
print('\ndf =\n%s' % df)
#DataFrame df =
#   x1  x2  x3
#0   6   9   8
#1   3   1   6
#2   9   5   5
#3   0   3   3
#4   5   2   9
#5   2   8   7
#6   7   7   4
#7   4   0   1
#8   1   6   0
#9   8   4   2
#
#First Column =
#0    6
#1    3
#2    9
#3    0
#4    5
#5    2
#6    7
#7    4
#8    1
#9    8
#Name: x1, dtype: int32
#
#First Row =
#x1    6
#x2    9
#x3    8
#Name: 0, dtype: int32
#
#First Column, First Row = 6
#
#Adding ave column
#
#df =
#   x1  x2  x3       ave
#0   6   9   8  7.666667
#1   3   1   6  3.333333
#2   9   5   5  6.333333
#3   0   3   3  2.000000
#4   5   2   9  5.333333
#5   2   8   7  5.666667
#6   7   7   4  6.000000
#7   4   0   1  1.666667
#8   1   6   0  2.333333
#9   8   4   2  4.666667
#
#Adding ave row
#
#df =
#          x1   x2   x3       ave
#0        6.0  9.0  8.0  7.666667
#1        3.0  1.0  6.0  3.333333
#2        9.0  5.0  5.0  6.333333
#3        0.0  3.0  3.0  2.000000
#4        5.0  2.0  9.0  5.333333
#5        2.0  8.0  7.0  5.666667
#6        7.0  7.0  4.0  6.000000
#7        4.0  0.0  1.0  1.666667
#8        1.0  6.0  0.0  2.333333
#9        8.0  4.0  2.0  4.666667
#ave_row  4.5  4.5  4.5  4.500000