Week 8: Apply it to your data 7

Import your data

library(tidyverse)

data <- read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/refs/heads/main/data/2022/2022-03-22/babynames.csv")

## Rows: 1924665 Columns: 5
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (2): sex, name
## dbl (3): year, n, prop
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

names(data)

## [1] "year" "sex"  "name" "n"    "prop"

data_small <- data %>%
  select(year, sex, name, n) %>%
  filter(name %in% c("James", "Mary"))

Pivoting

long to wide form

data_wide <- data_small %>%
  pivot_wider(
    names_from = name,
    values_from = n
  )

wide to long form

data_long <- data_wide %>%
  pivot_longer(
    cols = c(James, Mary),
    names_to = "name",
    values_to = "n"
  )

Separating and Uniting

babynames_sep <- data %>%
  unite("year_sex", year, sex, sep = "_")

babynames_sep %>%
  separate(
    col = year_sex,
    into = c("year", "sex"),
    sep = "_"
  )

## # A tibble: 1,924,665 × 5
##    year  sex   name          n   prop
##    <chr> <chr> <chr>     <dbl>  <dbl>
##  1 1880  F     Mary       7065 0.0724
##  2 1880  F     Anna       2604 0.0267
##  3 1880  F     Emma       2003 0.0205
##  4 1880  F     Elizabeth  1939 0.0199
##  5 1880  F     Minnie     1746 0.0179
##  6 1880  F     Margaret   1578 0.0162
##  7 1880  F     Ida        1472 0.0151
##  8 1880  F     Alice      1414 0.0145
##  9 1880  F     Bertha     1320 0.0135
## 10 1880  F     Sarah      1288 0.0132
## # ℹ 1,924,655 more rows

Separate a column

NA

Unite two columns

data %>%
  unite(
    col = "year_sex",
    year,
    sex,
    sep = "_"
  )

## # A tibble: 1,924,665 × 4
##    year_sex name          n   prop
##    <chr>    <chr>     <dbl>  <dbl>
##  1 1880_F   Mary       7065 0.0724
##  2 1880_F   Anna       2604 0.0267
##  3 1880_F   Emma       2003 0.0205
##  4 1880_F   Elizabeth  1939 0.0199
##  5 1880_F   Minnie     1746 0.0179
##  6 1880_F   Margaret   1578 0.0162
##  7 1880_F   Ida        1472 0.0151
##  8 1880_F   Alice      1414 0.0145
##  9 1880_F   Bertha     1320 0.0135
## 10 1880_F   Sarah      1288 0.0132
## # ℹ 1,924,655 more rows

Missing Values

babynames_na <- data %>%
  mutate(
    n = ifelse(n < 10, NA, n)
  )