Use pandas dot function on Series and DataFrames

Pandas dot

In [1]:

import pandas as pd

In [2]:

# create list of column names
columns = ['bronze', 'country_name', 'gold', 'silver']

In [3]:

# dictionary values
countries = ['Russian Fed.', 'Norway', 'Canada', 'United States',
             'Netherlands', 'Germany', 'Switzerland', 'Belarus',
             'Austria', 'France', 'Poland', 'China', 'Korea', 
             'Sweden', 'Czech Republic', 'Slovenia', 'Japan',
             'Finland', 'Great Britain', 'Ukraine', 'Slovakia',
             'Italy', 'Latvia', 'Australia', 'Croatia', 'Kazakhstan']

gold = [13, 11, 10, 9, 8, 8, 6, 5, 4, 4, 4, 3, 3, 2, 2, 2, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0]
silver = [11, 5, 10, 7, 7, 6, 3, 0, 8, 4, 1, 4, 3, 7, 4, 2, 4, 3, 1, 0, 0, 2, 2, 2, 1, 0]
bronze = [9, 10, 5, 12, 9, 5, 2, 1, 5, 7, 1, 2, 2, 6, 2, 4, 3, 1, 2, 1, 0, 6, 2, 1, 0, 1]

In [4]:

# create dictionary (key-value pairs)
# key: object
# value: lists 

ex_dict = {
    'country_name': countries,
    'gold': gold,
    'silver': silver,
    'bronze': bronze
}

In [5]:

# create DataFrame called 'olympic_medal_counts_df'

df = pd.DataFrame(ex_dict, columns=columns)

In [6]:

df.head()

Out[6]:

	bronze	country_name	gold	silver
0	9	Russian Fed.	13	11
1	10	Norway	11	5
2	5	Canada	10	10
3	12	United States	9	7
4	9	Netherlands	8	7

In [7]:

df.shape

Out[7]:

(26, 4)

In [8]:

# we need 26 x 3 dot 3 x 1 
# this would give a 26 x 1 series which we can concatenate with the 26 x 1 country_name's series

lst = ['gold', 'silver', 'bronze']
v_medals = df.loc[:, lst]
v_medals.head()

Out[8]:

	gold	silver	bronze
0	13	11	9
1	11	5	10
2	10	10	5
3	9	7	12
4	8	7	9

In [9]:

v_medals.shape

Out[9]:

(26, 3)

In [10]:

type(v_medals)

Out[10]:

pandas.core.frame.DataFrame

In [11]:

lst_points = [4, 2, 1]
lst_points

Out[11]:

[4, 2, 1]

In [12]:

# create series
v_points = pd.Series(lst_points)
v_points

Out[12]:

0    4
1    2
2    1
dtype: int64

In [13]:

v_points.shape

Out[13]:

(3,)

In [14]:

import numpy as np
np.dot(v_medals, v_points)

Out[14]:

array([83, 64, 65, 62, 55, 49, 32, 21, 37, 31, 19, 22, 20, 28, 18, 16, 15,
       11,  8,  5,  4, 10,  6,  5,  2,  1])

In [16]:

# store results in an array
arr = np.dot(v_medals, v_points)

In [17]:

# create a pandas series from array
v_all_points = pd.Series(arr)
v_all_points

Out[17]:

0     83
1     64
2     65
3     62
4     55
5     49
6     32
7     21
8     37
9     31
10    19
11    22
12    20
13    28
14    18
15    16
16    15
17    11
18     8
19     5
20     4
21    10
22     6
23     5
24     2
25     1
dtype: int64

In [18]:

v_country = df.loc[:, 'country_name']
country_scores = pd.concat([v_country, v_all_points], axis=1)

In [19]:

country_scores.head()

Out[19]:

	0	1
0	Russian Fed.	83
1	Norway	64
2	Canada	65
3	United States	62
4	Netherlands	55

In [20]:

# rename columns
cols = ['country_name', 'points']
country_scores.columns = cols

In [21]:

country_scores.head()

Out[21]:

	country_name	points
0	Russian Fed.	83
1	Norway	64
2	Canada	65
3	United States	62
4	Netherlands	55

Tags: pandas