Lesson 04: Last Three Wrangling Verbs

Learning group_by(), summarise(), and arrange()

Before we do any exercises, make sure to run this code:

library(tidyverse)
dat <- read_csv("https://raw.githubusercontent.com/BrighamEaquinto/brighameaquinto.github.io/master/datasets/insurance.csv")

This is our dataset for this practice:

age sex bmi children smoker region charges
19 female 27.900 0 yes southwest 16884.924
18 male 33.770 1 no southeast 1725.552
28 male 33.000 3 no southeast 4449.462
33 male 22.705 0 no northwest 21984.471
32 male 28.880 0 no northwest 3866.855


Let’s learn about group_by() & summarise()

What if we want to learn:

  • the average BMI by gender
  • the total sum of charges by region in the US
  • min & max of children by age

All of these are examples uses for group_by() and summarise() statements.


Examples

Examples 1: Average BMI by Gender

dat %>% 
    group_by(sex) %>%
    summarise(Average_Age = mean(age))
sex Average_Age
female 39.50302
male 38.91716

Examples 2: Average BMI by Age

dat %>% 
    group_by(age) %>% 
    summarise(mean(bmi)) %>% 
    head()
age mean(bmi)
18 31.32616
19 28.59691
20 30.63276
21 28.18571
22 31.08768
23 31.45446

Practice Exercises

Exercise 1: Sum of Charges by Region

Use the code below to get you started. Find the sum of the charges by region.

Starter Code:

dat %>% 
    group_by(______) %>% 
    summarise(_____________ = ___(_______))

Attempt the code above then use this dropdown for help

Answer 
dat %>% 
    group_by(region) %>% 
    summarise(Total_Charges = sum(charges))

This is the correct output:

region Total_Charges
northeast 4343669
northwest 4035712
southeast 5363690
southwest 4012755

Exercise 2: Min & Max of Children by Age

Use the code below to get you started. Find the minimum and maximum amount of children by age.

Starter Code:

dat %>% 
    group_by(___) %>%
    summarise(
        Min = ___(________),
        Max = ___(________)
        ) %>% 
    head()
Answer 
dat %>% 
    group_by(age) %>%
    summarise(
        Min = min(children),
        Max = max(children)
        ) %>% 
    head()

This is the correct output:

age Min Max
18 0 4
19 0 5
20 0 5
21 0 4

Exercise 3: Average Charges by Sex and by Smoker

Here no starter code is given. If you need to, look back at previous code chunks for guidence.

Try as best as possible to mimic the results below.

Only use the dropdown answer when you’ve tried as much as possible.

Answer 
dat %>% 
    group_by(sex, smoker) %>% 
    summarise(
        Average_Charges = mean(charges), 
        Total_Charges = sum(charges))

This is the correct output:

sex smoker Average_Charges Total_Charges
female no 8762.297 4792977
female yes 30678.996 3528085
male no 8087.205 4181085
male yes 33042.006 5253679

Exercise 4: Storm Dataset - Wind and Air Pressure

This dataset is bult into R so you already have it. It is called storms. This is a new dataset so you may want to either view() it or use the head() method on it.

Find the average and standard deviation of the wind speed and air pressure by storm category.

Answer 
storms %>% 
    group_by(category) %>% 
    summarise(
        mean(wind),
        sd(wind), 
        mean(pressure), 
        sd(pressure)
        ) %>% knitr::kable()

This is the correct output:

category mean(wind) sd(wind) mean(pressure) sd(pressure)
-1 27.49482 3.702448 1007.5390 3.900209
0 45.66392 8.231625 999.2910 6.837831
1 70.95140 5.454009 981.1887 9.125784
2 89.41923 3.873391 966.9359 9.018024
3 104.48157 4.246545 953.9124 9.168259
4 122.10462 6.383000 939.3942 9.788015
5 145.58140 5.862072 917.4070 12.732892

Exercise 5: Summarizing by Month

Find the mean, median, and standard deviation of wind speed by month.

Only use the dropdown answer when you’ve tried as much as possible.

Answer 
storms %>% 
    group_by(month) %>% 
    summarise(
        Mean_Wind = mean(wind), 
        Median = median(wind), 
        St_Dev = sd(wind)
        )

This is the correct output:

month Mean_Wind Median St_Dev
1 50.33333 50 12.312969
4 44.61538 45 5.937711
5 36.27778 35 9.011887
6 37.55348 35 12.676257
7 41.74973 40 18.711162
8 51.75471 45 25.584917
9 57.54597 50 28.192273
10 56.49272 50 25.795906
11 53.30986 50 22.702523
12 47.88000 45 14.608659

Exercise 6: Airquality Dataset - Summarising by Month

This example is very similar to the previous example. This is a new datset and hopefully doing the same thing with another dataset will solidify the concept.

This dataset is bult into R so you already have it. It is called airquality. This is a new dataset so you may want to either view() it or use the head() method on it.

Answer 
airquality %>% 
    group_by(Month) %>% 
    summarise(
        Mean_Wind = mean(Wind), 
        Median = median(Wind), 
        St_Dev = sd(Wind)
        )

This is the correct output:

Month Mean_Wind Median St_Dev
5 11.622581 11.5 3.531450
6 10.266667 9.7 3.769234
7 8.941935 8.6 3.035981
8 8.793548 8.6 3.225930
9 10.180000 10.3 3.461254