Week 8: Apply it to your data 7

Import your data

mydata. <- read.csv("00_data/mydata.")

Pivoting

long to wide form

#I Do not think I can fill this out.

wide to long form

mydata_long <- mydata. %>%
  pivot_longer(
    cols = c(`Population.2025`, `Yearly.Change`, `Net.Change`),
    names_to = "measure",
    values_to = "value",
    values_transform = list(
      value = as.character))
head(mydata_long)

## # A tibble: 6 × 11
##      id Country..or.dependency. Density..P.Km.. Land.Area..Km.. Migrants..net.
##   <int> <chr>                             <int>           <int> <chr>         
## 1     1 India                               492         2973190 −495,753      
## 2     1 India                               492         2973190 −495,753      
## 3     1 India                               492         2973190 −495,753      
## 4     2 China                               151         9388211 −268,126      
## 5     2 China                               151         9388211 −268,126      
## 6     2 China                               151         9388211 −268,126      
## # ℹ 6 more variables: Fert..Rate <dbl>, Median.Age <dbl>, Urban.Pop.. <chr>,
## #   World.Share <chr>, measure <chr>, value <chr>

Separating and Uniting

Separate a column

mydata_sep <- mydata. %>%
  separate(col   = Fert..Rate, into  = c("whole.Fret#", "Decimal#"), convert = TRUE ) 

## Warning: Expected 2 pieces. Missing pieces filled with `NA` in 4 rows [40, 59, 222,
## 233].

head(mydata_sep)

##   id Country..or.dependency. Population.2025 Yearly.Change Net.Change
## 1  1                   India      1463865525         0.89%   12929734
## 2  2                   China      1416096094        −0.23% −3,225,184
## 3  3           United States       347275807         0.54%    1849236
## 4  4               Indonesia       285721236         0.79%    2233305
## 5  5                Pakistan       255219554         1.57%    3950390
## 6  6                 Nigeria       237527782         2.08%    4848304
##   Density..P.Km.. Land.Area..Km.. Migrants..net. whole.Fret# Decimal#
## 1             492         2973190       −495,753           1       94
## 2             151         9388211       −268,126           1        2
## 3              38         9147420        1230663           1       62
## 4             158         1811570        −39,509           2        1
## 5             331          770880     −1,235,336           3        5
## 6             261          910770        −15,258           4        3
##   Median.Age Urban.Pop.. World.Share
## 1       28.8       37.1%      17.78%
## 2       40.1       67.5%      17.20%
## 3       38.5       82.8%       4.22%
## 4       30.4       59.6%       3.47%
## 5       20.6       34.4%       3.10%
## 6       18.1       54.9%       2.89%

Unite two columns

mydata_united <- mydata. %>%
  unite(col = "Population.2025","World.Share",
    sep    = "_",
    remove = TRUE  
  )

head(mydata_united)

##   id Country..or.dependency. Yearly.Change Net.Change Density..P.Km..
## 1  1                   India         0.89%   12929734             492
## 2  2                   China        −0.23% −3,225,184             151
## 3  3           United States         0.54%    1849236              38
## 4  4               Indonesia         0.79%    2233305             158
## 5  5                Pakistan         1.57%    3950390             331
## 6  6                 Nigeria         2.08%    4848304             261
##   Land.Area..Km.. Migrants..net. Fert..Rate Median.Age Urban.Pop..
## 1         2973190       −495,753       1.94       28.8       37.1%
## 2         9388211       −268,126       1.02       40.1       67.5%
## 3         9147420        1230663       1.62       38.5       82.8%
## 4         1811570        −39,509       2.10       30.4       59.6%
## 5          770880     −1,235,336       3.50       20.6       34.4%
## 6          910770        −15,258       4.30       18.1       54.9%
##   Population.2025
## 1          17.78%
## 2          17.20%
## 3           4.22%
## 4           3.47%
## 5           3.10%
## 6           2.89%

Missing Values

mydata. %>% 
  filter(Land.Area..Km.. == 0)

##    id Country..or.dependency. Population.2025 Yearly.Change Net.Change
## 1 233                Holy See             501         1.01%          5
##   Density..P.Km.. Land.Area..Km.. Migrants..net. Fert..Rate Median.Age
## 1            1253               0             13          1       57.4
##   Urban.Pop.. World.Share
## 1        <NA>  0.0000061%

mydata_missing <- mydata. %>%
  mutate(
    Land.Area..Km.. = ifelse(Land.Area..Km.. == 0, NA, Land.Area..Km..))

colSums(is.na(mydata_missing))

##                      id Country..or.dependency.         Population.2025 
##                       0                       0                       0 
##           Yearly.Change              Net.Change         Density..P.Km.. 
##                       0                       0                       0 
##         Land.Area..Km..          Migrants..net.              Fert..Rate 
##                       1                       0                       0 
##              Median.Age             Urban.Pop..             World.Share 
##                       0                      23                       0