Chapter 2 - Data Preparation Basics
Segment 5 - Grouping and data aggregation
import numpy as np
import pandas as pd
from pandas import Series, DataFrame
Grouping data by column index
address = '~/Data/mtcars.csv'
cars = pd.read_csv(address)
cars.columns = ['car_names', 'mpg', 'cyl', 'disp', 'hp', 'drat', 'wt', 'qsec', 'vs', 'am', 'gear', 'carb']
cars.head()
|
car_names |
mpg |
cyl |
disp |
hp |
drat |
wt |
qsec |
vs |
am |
gear |
carb |
| 0 |
Mazda RX4 |
21.0 |
6 |
160.0 |
110 |
3.90 |
2.620 |
16.46 |
0 |
1 |
4 |
4 |
| 1 |
Mazda RX4 Wag |
21.0 |
6 |
160.0 |
110 |
3.90 |
2.875 |
17.02 |
0 |
1 |
4 |
4 |
| 2 |
Datsun 710 |
22.8 |
4 |
108.0 |
93 |
3.85 |
2.320 |
18.61 |
1 |
1 |
4 |
1 |
| 3 |
Hornet 4 Drive |
21.4 |
6 |
258.0 |
110 |
3.08 |
3.215 |
19.44 |
1 |
0 |
3 |
1 |
| 4 |
Hornet Sportabout |
18.7 |
8 |
360.0 |
175 |
3.15 |
3.440 |
17.02 |
0 |
0 |
3 |
2 |
cars_groups = cars.groupby(cars['cyl'])
cars_groups.mean()
|
mpg |
disp |
hp |
drat |
wt |
qsec |
vs |
am |
gear |
carb |
| cyl |
|
|
|
|
|
|
|
|
|
|
| 4 |
26.663636 |
105.136364 |
82.636364 |
4.070909 |
2.285727 |
19.137273 |
0.909091 |
0.727273 |
4.090909 |
1.545455 |
| 6 |
19.742857 |
183.314286 |
122.285714 |
3.585714 |
3.117143 |
17.977143 |
0.571429 |
0.428571 |
3.857143 |
3.428571 |
| 8 |
15.100000 |
353.100000 |
209.214286 |
3.229286 |
3.999214 |
16.772143 |
0.000000 |
0.142857 |
3.285714 |
3.500000 |