In skvrnami/listr: Package for processing candidate lists data

This vignette gives examples how to use the listr package.

Let's load some data first.

data <- structure(list(list_no = c(1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 
1L, 2L, 3L, 4L, 5L, 6L, 7L, 8L, 9L, 10L, 11L, 12L, 13L, 14L, 
15L, 16L, 17L, 18L, 19L, 20L, 21L, 22L, 23L, 24L, 25L, 26L, 27L, 
28L, 29L, 30L, 31L, 32L, 33L, 34L, 35L, 36L, 37L, 38L, 39L, 40L, 
41L), name = c("Jiskra Jan", "Kopecká Iva", "Truhlářová Dana", 
"Kalvasová Iveta", "Paulus Přemysl", "Kalvas Martin", "Hassman Jaroslav", 
"Paulusová Marta", "Vondra Jaroslav", "Bernard Daniel", "Zikmund Roman", 
"Jindrák Miroslav JUDr.", "Schautová Dita JUDr.", "Breburda Lubomír", 
"Kucharczyková Ilona MVDr.", "Michal Karel Ing.", "Picka Emil JUDr.", 
"Mamula Petr Ing. CSc.", "Bosák Belo Ing.", "Kunst Ivan Ing.", 
"Baloun Jiří", "Čermák Lubomír", "Nádeník Robert", "Rezek Miloš Ing.", 
"Jarolímek Josef", "Bahník Radomír", "Vamberský Ivo", "Honka Karel", 
"Šafařík Bohumil", "Sankot David", "Novák Jaroslav Ing.", 
"Jaroš Ladislav", "Novotný Petr", "Vaňková Blanka", "Hudeček Jan", 
"Hájek Tomáš", "Veselý Zdeněk Ing.", "Jaroš Petr", "Nováková Vanda", 
"Hájková Renáta", "Kysučan Pavel", "Platil Jaroslav", "Sankotová Helena", 
"Zelenková Adolfa", "Hrušková Jiřina", "Podhajský Pavel", 
"Spolková Jaroslava", "Novák Zbyněk", "Čermák Jan Ing.", 
"Votruba Jan"), age = c(40L, 27L, 42L, 23L, 56L, 31L, 32L, 58L, 
44L, 49L, 40L, 56L, 37L, 50L, 48L, 61L, 72L, 62L, 68L, 54L, 58L, 
70L, 51L, 61L, 51L, 33L, 44L, 51L, 39L, 36L, 58L, 70L, 40L, 46L, 
56L, 40L, 67L, 25L, 45L, 42L, 38L, 40L, 34L, 70L, 33L, 36L, 45L, 
42L, 66L, 31L), nominate_party = c("ČP", "ČP", "ČP", "ČP", 
"ČP", "ČP", "ČP", "ČP", "ČP", "NEZ/DEM", "NEZ/DEM", "NEZ/DEM", 
"NEZ/DEM", "NEZ/DEM", "NEZ/DEM", "NEZ/DEM", "NEZ/DEM", "NEZ/DEM", 
"NEZ/DEM", "NEZ/DEM", "NEZ/DEM", "NEZ/DEM", "NEZ/DEM", "NEZ/DEM", 
"NEZ/DEM", "NEZ/DEM", "NEZ/DEM", "NEZ/DEM", "NEZ/DEM", "NEZ/DEM", 
"NEZ/DEM", "NEZ/DEM", "NEZ/DEM", "NEZ/DEM", "NEZ/DEM", "NEZ/DEM", 
"NEZ/DEM", "NEZ/DEM", "NEZ/DEM", "NEZ/DEM", "NEZ/DEM", "NEZ/DEM", 
"NEZ/DEM", "NEZ/DEM", "NEZ/DEM", "NEZ/DEM", "NEZ/DEM", "NEZ/DEM", 
"NEZ/DEM", "NEZ/DEM")), .Names = c("list_no", "name", "age", 
"nominate_party"), row.names = c(NA, 50L), class = "data.frame")

head(data)

Then extract full name from column which contain names mixed with academic titles. The function extract_text_before_titles assumes that titles are located after the academic titles so it extracts the part of the string before the titles.

data$full_name <- unlist(purrr::map(data$name, listr::extract_text_before_titles))
data[data$name != data$full_name, c("name", "full_name")]

Then you can extract titles and put them in a separate column.

data$titles <- unlist(purrr::map(data$name, listr::extract_titles))
data[data$titles != "", c("name", "full_name", "titles")]

You can recode the column with titles so that it reflects the highest attained title. The recoded column contains ordered factor with levels "No title", "Bachelor", "Master", "Doctor", "Associate Professor (docent)", and "Professor".

data$highest_titles <- listr::recode_titles(data$titles)
data[10:25, c("name", "full_name", "titles", "highest_titles")]

Then you can split full names into first and last names.

data <- listr::add_names_to_df(data, "full_name")
head(data[, c("name", "first_name", "last_name")])

Based on the first and last names we can estimate gender of the person.

data <- listr::parse_gender(data, "first_name", "last_name")
head(data[, c("first_name", "last_name", "gender")])

skvrnami/listr documentation built on June 21, 2020, 4:13 a.m.