In IsaacVerm/marriage: exploratory analysis marriage in Belgium

library(knitr)

opts_chunk$set(echo=TRUE,
               warning=FALSE,
               message=FALSE,
               cache=FALSE)

devtools::load_all(here::here())

Tidy data

At what age do people marry?

The first question we want to investigate is at what age people marry. This data is available in the year_of_birth tab of the marriage files.

We'd like to have a single dataframe indicating for each age how many people marry. However, when loading the data isn't coded in the way we want.

select_worksheet(worksheet = "year_of_birth",
                 year = "2013",
                 type = "divorce")[1:20, ]

There are several issues:

the name of the analysis is repeated as header
there's a total row at the top
at the bottom the source of the data is mentioned
we have the data by year while we want a single dataframe
regions are separate variables while we want a single variable region with the regions as values
distinction is made between first and second spouses while we don't care about this distinction
people with the same ages can be born in two different years
the year in which the data were gathered isn't mentioned explicitly
the type of data (divorce or marriage) isn't mentioned explicitly
variables are coded as character instead of factors (e.g. region)

We create a function to solve each issue, apply these to each dataframe and then bind all dataframes for each year together. Small note: additional data on gender is provided from 2015 on. Making a modification to incorporate this hasn't been done yet so for the moment the focus is on the data 2013-2014.

types <- c("divorce","marriage")
years <- paste0("201", 3:4)

rep_years <- rep(years, times = length(types))
rep_types <- rep(types, each = length(years))

worksheets <- map2(.x = rep_years,
                   .y = rep_types,
                   .f = ~select_worksheet(worksheet = "year_of_birth",
                                          year = .x,
                                          type = .y)
                   )

tidy_args <- list(worksheet = worksheets,
                  year = rep_years,
                  type = rep_types)
tidy_dfs <- pmap(tidy_args,
                 function(worksheet, year, type) tidy_year_of_birth(worksheet, year, type)
                 )

year_of_birth <- bind_together(tidy_dfs)

save(year_of_birth,
     file = paste(data_path, "year_of_birth.RData", sep = "/")
     ) # data_path is object in tidy-year_of_birth.R