# all summer guests
sommargaester <- readr::read_csv("data/p1sommar.csv", col_names = FALSE, 
                                 locale = readr::locale(encoding = "latin1"))
knitr::kable(sommargaester[1:10,])

# get their names
sommargaester_names <- unique(sommargaester$X1)

# for putting names in the right order for later queries
transform_name <- function(name){
  paste(stringr::str_split(name, ",",
                           simplify = TRUE)[2],
        stringr::str_split(name, ",",
                           simplify = TRUE)[1])
}

pretty_sommargaester_names <- purrr::map_chr(sommargaester_names, transform_name)
sommargaester_names <- tibble::tibble(name = pretty_sommargaester_names,
                                      X1 = sommargaester_names)
sommargaester <- dplyr::left_join(sommargaester, sommargaester_names,
                                  by = "X1")

sommargaester <- dplyr::select(sommargaester, - X1)
# transform the date
sommargaester <- tidyr::gather(sommargaester, "rep", "date", X2:X7)
sommargaester <- dplyr::group_by(sommargaester, name)
sommargaester <- dplyr::mutate(sommargaester, rep = 1:n())
sommargaester <- dplyr::ungroup(sommargaester)

sommargaester <- dplyr::filter(sommargaester, !is.na(date))
# remove winter
sommargaester <- dplyr::filter(sommargaester, !stringr::str_detect(date, "V"))
# remove repeat episodes
sommargaester <- dplyr::filter(sommargaester, !stringr::str_detect(date, "R"))


# transform the date to a format with a non ambiguous year
sommargaester <- dplyr::mutate(sommargaester, date = as.numeric(date))
sommargaester <- dplyr::mutate(sommargaester, date = ifelse(date > 180000, paste0("19", date),
                                                            ifelse(date < 100000,
                                                                   paste0("200", date),
                                                                   paste0("20", date))))
sommargaester <- dplyr::mutate(sommargaester, pretty_date = lubridate::ymd(date))

knitr::kable(sommargaester[1:10,])

# function for getting someone's data
get_someone_data <- function(name, pb = NULL){
  if (!is.null(pb)) pb$tick()$print()
  Sys.sleep(1)
  item <- WikidataR::find_item(name, language = "sv")
  # sometimes people have no Wikidata entry so I need this condition
  if(length(item) > 0){
    entity_code <- item[[1]]$id
    query <-  paste0("PREFIX entity: <http://www.wikidata.org/entity/>
                     #partial results
                     
                     SELECT ?propUrl ?propLabel ?valUrl ?valLabel ?picture
                     WHERE
                     {
                     hint:Query hint:optimizer 'None' .
                     {	BIND(entity:",entity_code," AS ?valUrl) .
                     BIND(\"N/A\" AS ?propUrl ) .
                     BIND(\"identity\"@sv AS ?propLabel ) .
                     }
                     UNION
                     {	entity:", entity_code," ?propUrl ?valUrl .
                     ?property ?ref ?propUrl .
                     ?property rdf:type wikibase:Property .
                     ?property rdfs:label ?propLabel
                     }
                     
                     ?valUrl rdfs:label ?valLabel
                     FILTER (LANG(?valLabel) = 'sv') .
                     OPTIONAL{ ?valUrl wdt:P18 ?picture .}
                     FILTER (lang(?propLabel) = 'sv' )
                     }
                     ORDER BY ?propUrl ?valUrl
                     LIMIT 200")
    results <- WikidataQueryServiceR::query_wikidata(query)
    results$name<- name
    results
  }else{
    NULL
  }
   
  }

pb <- dplyr::progress_estimated(length(unique(sommargaester$name)))
sommargaester_wiki <- purrr::map_df(unique(sommargaester$name),
                                    get_someone_data, pb=pb)

sommargaester <- dplyr::left_join(sommargaester, sommargaester_wiki, by = "name")

readr::write_csv(sommargaester, path = "data/p1_wiki_data.csv")

knitr::kable(sommargaester[1:10,])

occupation <- dplyr::filter(sommargaester, propLabel == "sysselsättning")
occupations <- unique(occupation$valLabel)
translate_occupation <- function(occupation){
  job <- WikidataR::find_item(occupation, language = "sv")[[1]]$label
  if(is.null(job)){
    job <- ""
  }
  return(job)
}
english_occupations <- purrr::map_chr(occupations, translate_occupation)
translations <- data.frame(sysselsaettning = occupations,
                           occupation = english_occupations)
occupation <- dplyr::left_join(occupation, translations, by = c("valLabel" = "sysselsaettning"))

withoccupation <- dplyr::filter(sommargaester, !is.na(propLabel))
withoccupation <- dplyr::group_by(withoccupation, name)
withoccupation <- dplyr::summarise(withoccupation, withoccupation = any(propLabel == "sysselsättning"))

invites <- dplyr::select(sommargaester, name, rep)
invites <- dplyr::group_by(invites, name)
invites <- dplyr::summarize(invites, no_invites = max(rep))
invites <- unique(invites)
library("ggplot2")
 theme_set(theme_gray(base_size = 18))
ggplot(invites) +
  geom_histogram(aes(no_invites)) +
  xlab("Number of invitations per P1 summer guest")

jobs <- dplyr::select(occupation, name, occupation) 
jobs <- unique(jobs)
invites <- dplyr::left_join(invites, occupation, by = "name")
invites <- dplyr::select(invites, name, no_invites, occupation)
invites <- unique(invites)
invites <- dplyr::group_by(invites, name, no_invites)
invites <- dplyr::summarise(invites, occupation = toString(occupation))
invites <- dplyr::ungroup(invites)
invites <- dplyr::arrange(invites, desc(no_invites))
knitr::kable(invites[1:20,])

everything <- dplyr::group_by(occupation, occupation)
everything <- dplyr::summarize(everything, n = n())
everything <- dplyr::filter(everything, n > 50)
library("magrittr")
everything %>%
  dplyr::arrange(n) %>%
  dplyr::mutate(occupation = factor(occupation, ordered = TRUE, levels = unique(occupation))) %>%
ggplot() +
  geom_col(aes(occupation, n)) +
  theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
  ggtitle("Number of episodes by occupation",
subtitle = "for occupations represented more than 50 times")

everything <- dplyr::select(occupation, name, occupation)
everything <- unique(everything)
everything <- dplyr::group_by(everything, occupation)
everything <- dplyr::summarize(everything, n = n())
everything <- dplyr::filter(everything, n > 20)
library("magrittr")
everything %>%
  dplyr::arrange(n) %>%
  dplyr::mutate(occupation = factor(occupation, ordered = TRUE, levels = unique(occupation))) %>%
ggplot() +
  geom_col(aes(occupation, n)) +
  theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
  ggtitle("Number of guests by occupation",
subtitle = "for occupations represented more than 20 times")