Module 6: Apply 5

Import data

# excel file
data <- read_csv("../00_data/myData.csv")
data

## # A tibble: 20,755 × 4
##    Entity      Code   Year LifeExpectancy
##    <chr>       <chr> <dbl>          <dbl>
##  1 Afghanistan AFG    1950           27.7
##  2 Afghanistan AFG    1951           28.0
##  3 Afghanistan AFG    1952           28.4
##  4 Afghanistan AFG    1953           28.9
##  5 Afghanistan AFG    1954           29.2
##  6 Afghanistan AFG    1955           29.9
##  7 Afghanistan AFG    1956           30.4
##  8 Afghanistan AFG    1957           30.9
##  9 Afghanistan AFG    1958           31.5
## 10 Afghanistan AFG    1959           32.0
## # ℹ 20,745 more rows

Apply the following dplyr verbs to your data

Filter rows

filter(data, Year == 2021, LifeExpectancy == 21)

## # A tibble: 0 × 4
## # ℹ 4 variables: Entity <chr>, Code <chr>, Year <dbl>, LifeExpectancy <dbl>

Arrange rows

arrange(data, Entity, Year, LifeExpectancy)

## # A tibble: 20,755 × 4
##    Entity      Code   Year LifeExpectancy
##    <chr>       <chr> <dbl>          <dbl>
##  1 Afghanistan AFG    1950           27.7
##  2 Afghanistan AFG    1951           28.0
##  3 Afghanistan AFG    1952           28.4
##  4 Afghanistan AFG    1953           28.9
##  5 Afghanistan AFG    1954           29.2
##  6 Afghanistan AFG    1955           29.9
##  7 Afghanistan AFG    1956           30.4
##  8 Afghanistan AFG    1957           30.9
##  9 Afghanistan AFG    1958           31.5
## 10 Afghanistan AFG    1959           32.0
## # ℹ 20,745 more rows

Select columns

select(data, Year, LifeExpectancy)

## # A tibble: 20,755 × 2
##     Year LifeExpectancy
##    <dbl>          <dbl>
##  1  1950           27.7
##  2  1951           28.0
##  3  1952           28.4
##  4  1953           28.9
##  5  1954           29.2
##  6  1955           29.9
##  7  1956           30.4
##  8  1957           30.9
##  9  1958           31.5
## 10  1959           32.0
## # ℹ 20,745 more rows

Add columns

mutate(data, Decade = Year %/% 10 * 10)

## # A tibble: 20,755 × 5
##    Entity      Code   Year LifeExpectancy Decade
##    <chr>       <chr> <dbl>          <dbl>  <dbl>
##  1 Afghanistan AFG    1950           27.7   1950
##  2 Afghanistan AFG    1951           28.0   1950
##  3 Afghanistan AFG    1952           28.4   1950
##  4 Afghanistan AFG    1953           28.9   1950
##  5 Afghanistan AFG    1954           29.2   1950
##  6 Afghanistan AFG    1955           29.9   1950
##  7 Afghanistan AFG    1956           30.4   1950
##  8 Afghanistan AFG    1957           30.9   1950
##  9 Afghanistan AFG    1958           31.5   1950
## 10 Afghanistan AFG    1959           32.0   1950
## # ℹ 20,745 more rows

Summarize by groups

summarise(data, Year = mean(LifeExpectancy, na.rm = TRUE))

## # A tibble: 1 × 1
##    Year
##   <dbl>
## 1  61.6