diff --git a/R/ons_uk_population_2023.R b/R/ons_uk_population_2023.R
index 52769e4..7a006c6 100644
--- a/R/ons_uk_population_2023.R
+++ b/R/ons_uk_population_2023.R
@@ -35,14 +35,14 @@
 #'
 #' # create a dataset that has total population by age groups for England
 #' ons_uk_population_2023 |>
-#' filter(Name=="ENGLAND") |>
-#'   mutate(age_group = case_when(as.numeric(age)<=17 ~ "0-17",
-#'                               as.numeric(age)>=18 & as.numeric(age)<=64 ~ "18-64",
-#'                               as.numeric(age)>=65 ~ "65+",
-#'                               age=="90+" ~ "65+")) |>
-#'  group_by(age_group) |>
-#'  summarise(count=sum(count))
-#'
-#'
+#'   filter(Name == "ENGLAND") |>
+#'   mutate(age_group = case_when(
+#'     as.numeric(age) <= 17 ~ "0-17",
+#'     as.numeric(age) >= 18 & as.numeric(age) <= 64 ~ "18-64",
+#'     as.numeric(age) >= 65 ~ "65+",
+#'     age == "90+" ~ "65+"
+#'   )) |>
+#'   group_by(age_group) |>
+#'   summarise(count = sum(count))
 #'
 "ons_uk_population_2023"
diff --git a/data-raw/ons_uk_population_2023.R b/data-raw/ons_uk_population_2023.R
new file mode 100644
index 0000000..7d00665
--- /dev/null
+++ b/data-raw/ons_uk_population_2023.R
@@ -0,0 +1,34 @@
+# Source: https://www.ons.gov.uk/peoplepopulationandcommunity/populationandmigration/populationestimates/datasets/populationestimatesforukenglandandwalesscotlandandnorthernireland
+
+library(readxl)
+library(tidyverse)
+library(tidyr)
+
+# Load the data in
+population_data_2023_f <- read_excel(
+  "mye23tablesuk.xlsx", # add full file path here before file name
+  sheet = "MYE2 - Females",
+  skip = 7
+)
+
+population_data_2023_m <- read_excel(
+  "mye23tablesuk.xlsx", # add full file path here before file name
+  sheet = "MYE2 - Males",
+  skip = 7
+)
+
+
+# pivot longer
+population_data_2023_f <- population_data_2023_f |>
+  select(!`All ages`) |>
+  pivot_longer(`0`:`90+`, names_to = "age", values_to = "count")
+
+population_data_2023_m <- population_data_2023_m |>
+  select(!`All ages`) |>
+  pivot_longer(`0`:`90+`, names_to = "age", values_to = "count")
+
+population_data_combined <- bind_rows(
+  females = population_data_2023_f,
+  males = population_data_2023_m,
+  .id = "sex"
+)