Dplyr exercises from Sept 24

Solutions

library(gapminder)
library(ggplot2)
library(dplyr)

# 1. Calculate the mean gdpPercap for each country.

gapminder %>% 
  group_by(country) %>%
    summarise(mean_gdpPercap = mean(gdpPercap))

## Source: local data frame [142 x 2]
## 
##        country mean_gdpPercap
## 1  Afghanistan       802.6746
## 2      Albania      3255.3666
## 3      Algeria      4426.0260
## 4       Angola      3607.1005
## 5    Argentina      8955.5538
## 6    Australia     19980.5956
## 7      Austria     20411.9163
## 8      Bahrain     18077.6639
## 9   Bangladesh       817.5588
## 10     Belgium     19900.7581
## ..         ...            ...

# 2. Calculate the mean gdp for each country.

gapminder %>% 
  mutate(gdp = gdpPercap * pop) %>%
  group_by(country) %>%
  summarise(mean_gdp = mean(gdp))

## Source: local data frame [142 x 2]
## 
##        country     mean_gdp
## 1  Afghanistan  12709647583
## 2      Albania   9094669267
## 3      Algeria  96735171261
## 4       Angola  25532681843
## 5    Argentina 266754123835
## 6    Australia 320253755823
## 7      Austria 158579002935
## 8      Bahrain   7694793798
## 9   Bangladesh  80648494456
## 10     Belgium 197371599665
## ..         ...          ...

# 3. Create a graph of the total population of each continent over time.

gapminder %>%
  group_by(continent) %>%
  summarise(total_pop = sum(pop)) %>%
ggplot(data = ., aes(x = continent, y = total_pop)) + 
    geom_bar(stat = "identity")

# Note - read the error message if you have difficulties! We can talk about why 
# we do this in class if you are curious. 

# Alternatively you could plot points: 
gapminder %>%
    group_by(continent) %>%
    summarise(total_pop = sum(pop)) %>%

ggplot(data = ., aes(x = continent, y = total_pop)) + 
    geom_point()

# 4. For each continent, what country had the smallest population in 1952, 1972, 
#    and 2002? (google for help if you need to!)

gapminder %>% 
  filter(year %in% c(1952, 1972, 2002)) %>%
  group_by(continent, year) %>% 
  slice(which.min(pop))

## Source: local data frame [15 x 6]
## Groups: continent, year
## 
##                  country continent year lifeExp     pop  gdpPercap
## 1  Sao Tome and Principe    Africa 1952  46.471   60011   879.5836
## 2  Sao Tome and Principe    Africa 1972  56.480   76595  1532.9853
## 3  Sao Tome and Principe    Africa 2002  64.337  170372  1353.0924
## 4    Trinidad and Tobago  Americas 1952  59.100  662850  3023.2719
## 5    Trinidad and Tobago  Americas 1972  65.900  975199  6619.5514
## 6    Trinidad and Tobago  Americas 2002  68.976 1101832 11460.6002
## 7                Bahrain      Asia 1952  50.939  120447  9867.0848
## 8                Bahrain      Asia 1972  63.300  230800 18268.6584
## 9                Bahrain      Asia 2002  74.795  656397 23403.5593
## 10               Iceland    Europe 1952  72.490  147962  7267.6884
## 11               Iceland    Europe 1972  74.460  209275 15798.0636
## 12               Iceland    Europe 2002  80.500  288030 31163.2020
## 13           New Zealand   Oceania 1952  69.390 1994794 10556.5757
## 14           New Zealand   Oceania 1972  71.890 2929100 16046.0373
## 15           New Zealand   Oceania 2002  79.110 3908037 23189.8014

Dplyr exercises from Sept 24

Exercises

Solutions