10/25/24, 4:57 PM HW 4

HW 4
Enter your name and EID here: Jiaqi Guo (jg76446)

For all questions, include the R commands/functions that you used to find your answer (show R chunk). Answers
without supporting code will not receive credit. Write full sentences to describe your findings.

Part 1
world_bank_pop tidyverse

Question 1: (2 pts)
world_bank_pop

# pivot years 2000 to 2017 into a 'year' variable, and population values into 'indicator
_value'
world_bank_pop_tidy <- world_bank_pop %>%
pivot_longer(
cols = `2000`:`2017`, # Columns for each year from 2000 to 2017
names_to = "year", # New column to hold year values
values_to = "indicator_value" # New column to hold values for each year
) %>%
mutate(year = as.numeric(year)) # Ensure 'year' is a numeric variable

pivot world_bank_pop
year
indicator_value year
world_bank_pop pivot indicator
myworld

# further tidying to make each indicator category its own column

myworld <- world_bank_pop_tidy %>%
pivot_wider(
names_from = indicator,
values_from = indicator_value
)
myworld

file:///Users/jiaqiguo/Downloads/R studio/SDS322E/HW4.html 1/12

10/25/24, 4:57 PM HW 4

## # A tibble: 4,788 × 6
## country year SP.URB.TOTL SP.URB.GROW SP.POP.TOTL SP.POP.GROW
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 ABW 2000 41625 1.66 89101 2.54
## 2 ABW 2001 42025 0.956 90691 1.77
## 3 ABW 2002 42194 0.401 91781 1.19
## 4 ABW 2003 42277 0.197 92701 0.997
## 5 ABW 2004 42317 0.0946 93540 0.901
## 6 ABW 2005 42399 0.194 94483 1.00
## 7 ABW 2006 42555 0.367 95606 1.18
## 8 ABW 2007 42729 0.408 96787 1.23
## 9 ABW 2008 42906 0.413 97996 1.24
## 10 ABW 2009 43079 0.402 99212 1.23
## # ℹ 4,778 more rows

Question 2: (2 pts)
ggplot Note: the
country code WLD represents the entire world.

# Filter the data to include only the world population growth data (country code "WLD")
world_growth <- myworld %>%
filter(country == "WLD")

# Plot urban population growth over the years

ggplot(world_growth, aes(x = year, y = SP.URB.GROW)) +
geom_line(color = "blue") +
labs(
title = "World Urban Population Growth Over the Years",
x = "Year",
y = "Urban Population Growth (%)"
)

file:///Users/jiaqiguo/Downloads/R studio/SDS322E/HW4.html 2/12

10/25/24, 4:57 PM HW 4

myworld

# Filter data for the year 2017 and find the country with the highest population growth
highest_growth_2017 <- myworld %>%
filter(year == 2017) %>%
filter(SP.POP.GROW == max(SP.POP.GROW, na.rm = TRUE))

highest_growth_2017

## # A tibble: 1 × 6
## country year SP.URB.TOTL SP.URB.GROW SP.POP.TOTL SP.POP.GROW
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl>
## 1 QAT 2017 2686753 4.46 2711755 4.39

file:///Users/jiaqiguo/Downloads/R studio/SDS322E/HW4.html 3/12

10/25/24, 4:57 PM HW 4

Question 3: (2 pts)

countrycode

# Install the package (only needed once)

install.packages("countrycode")

codelist

# Call the countrycode package

library(countrycode)

# Take a look at the dataset

head(codelist)

continent wb
country.name.en wb
continent mycodes

# Create `mycodes` by selecting necessary columns and removing rows with missing data
mycodes <- codelist %>%
select(continent, wb, country.name.en) %>%
filter(!is.na(wb) & !is.na(continent))
mycodes

## # A tibble: 216 × 3
## continent wb country.name.en
## <chr> <chr> <chr>
## 1 Asia AFG Afghanistan
## 2 Europe ALB Albania
## 3 Africa DZA Algeria
## 4 Oceania ASM American Samoa
## 5 Europe AND Andorra
## 6 Africa AGO Angola
## 7 Americas ATG Antigua & Barbuda
## 8 Americas ARG Argentina
## 9 Asia ARM Armenia
## 10 Americas ABW Aruba
## # ℹ 206 more rows

mycodes

# Count distinct country codes

num_country_codes <- mycodes %>%
summarise(distinct_codes = n_distinct(wb))

num_country_codes

file:///Users/jiaqiguo/Downloads/R studio/SDS322E/HW4.html 4/12

10/25/24, 4:57 PM HW 4

## # A tibble: 1 × 1
## distinct_codes
## <int>
## 1 216

Question 4: (2 pts)
myworld mycodes

# your code goes below (replace this comment with something meaningful)
num_country_codes <- myworld %>%
summarise(distinct_codes = n_distinct(country))
num_country_codes

## # A tibble: 1 × 1
## distinct_codes
## <int>
## 1 266

inner_join() myworld
mycountries

# combining dataset using innerjoin

mycountries <- inner_join(myworld, mycodes, by = c("country" = "wb"))
mycountries

## # A tibble: 3,870 × 8
## country year SP.URB.TOTL SP.URB.GROW SP.POP.TOTL SP.POP.GROW continent
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 ABW 2000 41625 1.66 89101 2.54 Americas
## 2 ABW 2001 42025 0.956 90691 1.77 Americas
## 3 ABW 2002 42194 0.401 91781 1.19 Americas
## 4 ABW 2003 42277 0.197 92701 0.997 Americas
## 5 ABW 2004 42317 0.0946 93540 0.901 Americas
## 6 ABW 2005 42399 0.194 94483 1.00 Americas
## 7 ABW 2006 42555 0.367 95606 1.18 Americas
## 8 ABW 2007 42729 0.408 96787 1.23 Americas
## 9 ABW 2008 42906 0.413 97996 1.24 Americas
## 10 ABW 2009 43079 0.402 99212 1.23 Americas
## # ℹ 3,860 more rows
## # ℹ 1 more variable: country.name.en <chr>

mycountries

file:///Users/jiaqiguo/Downloads/R studio/SDS322E/HW4.html 5/12

10/25/24, 4:57 PM HW 4

# Find the country code with the highest population growth in 2017
highest_growth_country <- mycountries %>%
filter(year == 2017) %>%
slice_max(order_by = SP.POP.GROW)

highest_growth_country

## # A tibble: 1 × 8
## country year SP.URB.TOTL SP.URB.GROW SP.POP.TOTL SP.POP.GROW continent
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 QAT 2017 2686753 4.46 2711755 4.39 Asia
## # ℹ 1 more variable: country.name.en <chr>

Question 5: (2 pts)
continent mycountries

# Group by continent and calculate the average urban population growth

average_growth_by_continent <- mycountries %>%
group_by(continent) %>%
summarize(average_growth = mean(SP.URB.GROW, na.rm = TRUE)) %>%
ungroup()

# Identify the continent with the highest and lowest average growth
highest_growth_continent <- average_growth_by_continent %>%
filter(average_growth == max(average_growth, na.rm = TRUE))

lowest_growth_continent <- average_growth_by_continent %>%

filter(average_growth == min(average_growth, na.rm = TRUE))

# Output the results

highest_growth_continent

## # A tibble: 1 × 2
## continent average_growth
## <chr> <dbl>
## 1 Africa 3.59

lowest_growth_continent

## # A tibble: 1 × 2
## continent average_growth
## <chr> <dbl>
## 1 Europe 0.499

file:///Users/jiaqiguo/Downloads/R studio/SDS322E/HW4.html 6/12

10/25/24, 4:57 PM HW 4

myafrica2017

# creating new dataset for focusing on Africa Countries for year of 2017
myafrica2017 <- mycountries %>%
filter(year == 2017, continent == "Africa")
myafrica2017

## # A tibble: 54 × 8
## country year SP.URB.TOTL SP.URB.GROW SP.POP.TOTL SP.POP.GROW continent
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 AGO 2017 19586972 4.62 30208628 3.55 Africa
## 2 BDI 2017 1417430 4.82 11155593 2.29 Africa
## 3 BEN 2017 5423582 4.11 11596779 2.95 Africa
## 4 BFA 2017 5701421 5.01 19835858 2.87 Africa
## 5 BWA 2017 1650064 3.20 2401840 2.08 Africa
## 6 CAF 2017 2047664 2.76 4996741 1.87 Africa
## 7 CIV 2017 12505013 3.47 24848016 2.59 Africa
## 8 CMR 2017 13605785 3.91 24393181 2.83 Africa
## 9 COD 2017 36983500 4.76 84283273 3.44 Africa
## 10 COG 2017 3530528 3.08 5312340 2.39 Africa
## # ℹ 44 more rows
## # ℹ 1 more variable: country.name.en <chr>

Question 6: (2 pts)

map_data()
maps

# Install package (only needed once)

install.packages("maps")

mapWorld

# Geographic coordinates about countries in the world

mapWorld <- map_data("world")

# Take a quick look

head(mapWorld)

file:///Users/jiaqiguo/Downloads/R studio/SDS322E/HW4.html 7/12

10/25/24, 4:57 PM HW 4

## long lat group order region subregion

## 1 -69.89912 12.45200 1 1 Aruba <NA>
## 2 -69.89571 12.42300 1 2 Aruba <NA>
## 3 -69.94219 12.43853 1 3 Aruba <NA>
## 4 -70.00415 12.50049 1 4 Aruba <NA>
## 5 -70.06612 12.54697 1 5 Aruba <NA>
## 6 -70.05088 12.59707 1 6 Aruba <NA>

mapWorld myafrica2017 Note: the

variables do not have the same name for each dataset but they contain the same information.
mymap

# checking column names of both dataset

mapWorld

## long lat group order region subregion

## 1 -69.89912 12.45200 1 1 Aruba <NA>
## 2 -69.89571 12.42300 1 2 Aruba <NA>
## 3 -69.94219 12.43853 1 3 Aruba <NA>
## 4 -70.00415 12.50049 1 4 Aruba <NA>
## 5 -70.06612 12.54697 1 5 Aruba <NA>
## 6 -70.05088 12.59707 1 6 Aruba <NA>
## 7 -70.03511 12.61411 1 7 Aruba <NA>
## 8 -69.97314 12.56763 1 8 Aruba <NA>
## 9 -69.91181 12.48047 1 9 Aruba <NA>
## 10 -69.89912 12.45200 1 10 Aruba <NA>
## 12 74.89131 37.23164 2 12 Afghanistan <NA>
## 13 74.84023 37.22505 2 13 Afghanistan <NA>
## 14 74.76738 37.24917 2 14 Afghanistan <NA>
## 15 74.73896 37.28564 2 15 Afghanistan <NA>
## 16 74.72666 37.29072 2 16 Afghanistan <NA>
## 17 74.66895 37.26670 2 17 Afghanistan <NA>
## [ reached 'max' / getOption("max.print") -- omitted 99322 rows ]

myafrica2017

file:///Users/jiaqiguo/Downloads/R studio/SDS322E/HW4.html 8/12

10/25/24, 4:57 PM HW 4

## # A tibble: 54 × 8
## country year SP.URB.TOTL SP.URB.GROW SP.POP.TOTL SP.POP.GROW continent
## <chr> <dbl> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 AGO 2017 19586972 4.62 30208628 3.55 Africa
## 2 BDI 2017 1417430 4.82 11155593 2.29 Africa
## 3 BEN 2017 5423582 4.11 11596779 2.95 Africa
## 4 BFA 2017 5701421 5.01 19835858 2.87 Africa
## 5 BWA 2017 1650064 3.20 2401840 2.08 Africa
## 6 CAF 2017 2047664 2.76 4996741 1.87 Africa
## 7 CIV 2017 12505013 3.47 24848016 2.59 Africa
## 8 CMR 2017 13605785 3.91 24393181 2.83 Africa
## 9 COD 2017 36983500 4.76 84283273 3.44 Africa
## 10 COG 2017 3530528 3.08 5312340 2.39 Africa
## # ℹ 44 more rows
## # ℹ 1 more variable: country.name.en <chr>

# joining dataset 'mapWorld' and 'myafrica2017'

mymap <- inner_join(mapWorld, myafrica2017, by = c("region" = "country.name.en"))
mymap

## long lat group order region subregion country year SP.URB.TOTL

## 1 23.96650 -10.87178 3 423 Angola <NA> AGO 2017 19586972
## 2 23.98828 -11.00283 3 424 Angola <NA> AGO 2017 19586972
## 3 24.01006 -11.18477 3 425 Angola <NA> AGO 2017 19586972
## 4 24.02559 -11.31563 3 426 Angola <NA> AGO 2017 19586972
## 5 24.04141 -11.37412 3 427 Angola <NA> AGO 2017 19586972
## 6 24.04668 -11.40537 3 428 Angola <NA> AGO 2017 19586972
## 7 24.02930 -11.43916 3 429 Angola <NA> AGO 2017 19586972
## SP.URB.GROW SP.POP.TOTL SP.POP.GROW continent
## 1 4.620862 30208628 3.550987 Africa
## 2 4.620862 30208628 3.550987 Africa
## 3 4.620862 30208628 3.550987 Africa
## 4 4.620862 30208628 3.550987 Africa
## 5 4.620862 30208628 3.550987 Africa
## 6 4.620862 30208628 3.550987 Africa
## 7 4.620862 30208628 3.550987 Africa
## [ reached 'max' / getOption("max.print") -- omitted 11472 rows ]

Question 7: (2 pts)
ggmap

# Install package (only needed once)

install.packages("ggmap")

#
Note: it would be a good idea to run the code piece by piece to see what each layer adds to
the plot. eval=FALSE

file:///Users/jiaqiguo/Downloads/R studio/SDS322E/HW4.html 9/12

10/25/24, 4:57 PM HW 4

# Upload the ggmap package

library(ggmap)

# Build a map!
mymap |>
#
ggplot(aes(x = long, y = lat, group = group, fill = SP.URB.GROW)) +
#
geom_polygon(colour = "black") +
#
scale_fill_gradient(low = "red", high = "blue") +
#
labs(fill = "Urban Growth",
title = "Urban Growth in Africa in 2017",
x ="Longitude",
y ="Latitude")

Question 8: (1 pt)

myafrica2017 mapWorld
mapWorld myafrica2017

myafrica2017 |>
anti_join(mapWorld, by =c("country.name.en" = "region")) |>
select(country.name.en)

## # A tibble: 5 × 1
## country.name.en
## <chr>
## 1 Côte d’Ivoire
## 2 Congo - Kinshasa
## 3 Congo - Brazzaville
## 4 São Tomé & Príncipe
## 5 Eswatini

Note: This question

can be challenging! You will have to do some research about each of these countries: this is pretty typical for a
data scientist though! We need to get more knowledge about the context to make sense of the data.

file:///Users/jiaqiguo/Downloads/R studio/SDS322E/HW4.html 10/12

10/25/24, 4:57 PM HW 4

str_detect() mapWorld
myafrica2017

# distinct country names in mapWorld that could match

mapWorld |>
distinct(region) |>
filter(str_detect(region, "Ivor") |
str_detect(region, "Congo") |
str_detect(region, "Sao") |
str_detect(region, "Swaziland")
)

## region
## 1 Ivory Coast
## 2 Democratic Republic of the Congo
## 3 Republic of Congo
## 4 Sao Tome and Principe
## 5 Swaziland

myafrica2017
Hint: use recode() inside mutate() as described in our WS10 or in this article
https://www.statology.org/recode-dplyr/ (https://www.statology.org/recode-dplyr/).
mapWorld myafrica2017

# your code goes below (replace this comment with something meaningful)

Part 2

Question 9: (2 pts)

file:///Users/jiaqiguo/Downloads/R studio/SDS322E/HW4.html 11/12

10/25/24, 4:57 PM HW 4

Question 10: (2 pts)

Formatting: (1 pt)
Open in Browser

file:///Users/jiaqiguo/Downloads/R studio/SDS322E/HW4.html 12/12