Skip to content
Snippets Groups Projects
Commit 1533b7d8 authored by LE DURAND Matteo's avatar LE DURAND Matteo
Browse files

ajout de l'annuaire au donnée + prefix des fonctions

parent cb9c9492
No related branches found
No related tags found
No related merge requests found
......@@ -27,23 +27,23 @@ load("github.RData")
load("gitlab_forge.RData")
load("gitlab.RData")
load("date_MAJ.RData")
load("path_annuaire.RData")
annuaire <- read_csv(path_annuaire,col_types = "c")
annuaire <- readr::read_csv(path_annuaire,col_types = "c")
annuaire$Messagerie <- tolower(annuaire$Messagerie)
annuaire <- annuaire %>% rename( mail = Messagerie)
annuaire <- annuaire %>% filter( str_detect(Unité,"CSD" ) )
annuaire <- annuaire %>% mutate(auteur = paste(Prénom, Nom),
mail_clean = str_remove(mail, "@.*") )%>% select(mail_clean, auteur)
annuaire <- annuaire %>% dplyr::rename( mail = Messagerie)
annuaire <- annuaire %>% dplyr::filter( stringr::str_detect(Unité,"CSD" ) )
annuaire <- annuaire %>% dplyr::mutate(auteur = paste(Prénom, Nom),
mail_clean = stringr::str_remove(mail, "@.*") )%>% dplyr::select(mail_clean, auteur)
all_data <- bind_rows(all_data_gitlab, all_data_forge, combined_data)
all_data <- dplyr::bind_rows(all_data_gitlab, all_data_forge, combined_data)
all_data$updated_at <- as.POSIXct(all_data$updated_at, format = ("%Y-%m-%dT%H:%M:%S"))
all_data <- all_data %>% mutate(email_clean = str_remove(author, "@.*"))
all_data <- all_data %>% stringdist_left_join(annuaire,by = c("email_clean" = "mail_clean"), method = "jw", max_dist = 0.265) # ajout de auteur des membre du SCTE via l'annuaire, 75% des auteurs sont du csd
all_data <- all_data %>% dplyr::mutate(email_clean = stringr::str_remove(author, "@.*"))
all_data <- all_data %>% fuzzyjoin::stringdist_left_join(annuaire,by = c("email_clean" = "mail_clean"), method = "jw", max_dist = 0.265) # ajout de auteur des membre du SCTE via l'annuaire, 75% des auteurs sont du csd
all_data <- all_data %>% dplyr::mutate(etiquette = paste(groupe,topics,sep = ","))
all_data <- all_data %>% mutate(message = paste(type,sep = " : ",message,auteur),
auteur = replace_na(auteur,"autre"))
all_data <- all_data %>% dplyr::mutate(message = paste(type,sep = " : ",message,auteur),
auteur = tidyr::replace_na(auteur,"autre"))
# transformation re_code ----
traduction <- c(
......@@ -64,4 +64,4 @@ all_data <- all_data %>% dplyr::rename(project_name = name)
#transformation message
all_data$message <- all_data$message %>% tolower()
min_all_data <- all_data %>% filter(str_detect(message,'commit : initial commit'))
min_all_data <- all_data %>% dplyr::filter(stringr::str_detect(message,'commit : initial commit'))
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment