##---- Should be DIRECTLY executable !! ----
##-- ==> Define data, use random,
##-- or do help(data=index) for the standard data sets.
## The function is currently defined as
function (data, members = members, col_name, congresses = unique(data$congress))
{
data %<>% mutate(string = data[[col_name]])
if ("chamber" %in% names(data)) {
data %<>% mutate(string = ifelse(!is.na(chamber), paste(chamber,
string) %>% str_replace("House", "Represenative") %>%
str_replace("Senate", "Senator"), string))
data %<>% select(-chamber)
}
if ("state" %in% names(data)) {
data %<>% mutate(string = ifelse(!is.na(state), paste(string,
"-", stateFromFull(state)), string))
data %<>% select(-state)
}
t <- Sys.time()
if (!"data_id" %in% names(data)) {
data$data_id <- 1:nrow(data)
}
data$data_id %<>% str_squish() %>% as.numeric()
data$ID <- 1:nrow(data)
data %<>% mutate(data_id = coalesce(data_id, ID) %>% as.numeric())
data$data_id %<>% formatC(width = 6, flag = "0", format = "fg")
data$congress %<>% replace_na(0) %>% as.numeric() %>% replace_na(0) %>%
as.numeric()
data %<>% mutate(last_name = NA, first_name = NA, pattern = NA) %>%
select(-first_name, -last_name, -pattern)
data$string %<>% cleanFROMcolumn()
data$string %<>% ocr.errors()
data$string %<>% tolower() %>% str_replace("senator senator",
"senator") %>% str_replace("represenative representative",
"representative")
data$string %<>% str_replace("na politano", "napolitano")
data$string %<>% str_remove("^na ")
data$string %<>% str_remove("^na ")
data$string %<>% str_replace("han na\b", "hanna")
data$string %<>% str_remove_all("\bna\b")
data$string %<>% str_squish()
data$string %<>% str_replace(" ,", ", ")
data$string %<>% str_squish()
data$string %<>% replace_na("")
for (i in 1:dim(typos)[1]) {
r <- typos$correct[i]
p <- typos$typos[i]
data %<>% mutate(string = string %>% purrr::map_chr(str_replace,
pattern = p, replacement = r %>% paste("")))
}
data$string %<>% str_replace(" ,", ", ") %>% str_squish()
base::message(paste("Typos fixed in", round(Sys.time() -
t), "seconds"))
t <- Sys.time()
data <- map_dfr(congresses, extractNamesPerCongress, data = data,
members = members)
base::message(paste("Names matched in", round(Sys.time() -
t), "seconds"))
data %<>% distinct()
data$ID <- 1:nrow(data) %>% formatC(width = 6, flag = "0")
data %<>% left_join(members %>% select(icpsr, pattern, bioname,
first_name, last_name, congress, chamber, state) %>%
distinct()) %>% distinct()
data$icpsr %<>% as.numeric()
data %<>% select(data_row_id = data_id, match_id = ID, icpsr,
bioname, string, pattern, chamber, congress, everything())
return(data)
}
#> function (data, members = members, col_name, congresses = unique(data$congress))
#> {
#> data %<>% mutate(string = data[[col_name]])
#> if ("chamber" %in% names(data)) {
#> data %<>% mutate(string = ifelse(!is.na(chamber), paste(chamber,
#> string) %>% str_replace("House", "Represenative") %>%
#> str_replace("Senate", "Senator"), string))
#> data %<>% select(-chamber)
#> }
#> if ("state" %in% names(data)) {
#> data %<>% mutate(string = ifelse(!is.na(state), paste(string,
#> "-", stateFromFull(state)), string))
#> data %<>% select(-state)
#> }
#> t <- Sys.time()
#> if (!"data_id" %in% names(data)) {
#> data$data_id <- 1:nrow(data)
#> }
#> data$data_id %<>% str_squish() %>% as.numeric()
#> data$ID <- 1:nrow(data)
#> data %<>% mutate(data_id = coalesce(data_id, ID) %>% as.numeric())
#> data$data_id %<>% formatC(width = 6, flag = "0", format = "fg")
#> data$congress %<>% replace_na(0) %>% as.numeric() %>% replace_na(0) %>%
#> as.numeric()
#> data %<>% mutate(last_name = NA, first_name = NA, pattern = NA) %>%
#> select(-first_name, -last_name, -pattern)
#> data$string %<>% cleanFROMcolumn()
#> data$string %<>% ocr.errors()
#> data$string %<>% tolower() %>% str_replace("senator senator",
#> "senator") %>% str_replace("represenative representative",
#> "representative")
#> data$string %<>% str_replace("na politano", "napolitano")
#> data$string %<>% str_remove("^na ")
#> data$string %<>% str_remove("^na ")
#> data$string %<>% str_replace("han na\b", "hanna")
#> data$string %<>% str_remove_all("\bna\b")
#> data$string %<>% str_squish()
#> data$string %<>% str_replace(" ,", ", ")
#> data$string %<>% str_squish()
#> data$string %<>% replace_na("")
#> for (i in 1:dim(typos)[1]) {
#> r <- typos$correct[i]
#> p <- typos$typos[i]
#> data %<>% mutate(string = string %>% purrr::map_chr(str_replace,
#> pattern = p, replacement = r %>% paste("")))
#> }
#> data$string %<>% str_replace(" ,", ", ") %>% str_squish()
#> base::message(paste("Typos fixed in", round(Sys.time() -
#> t), "seconds"))
#> t <- Sys.time()
#> data <- map_dfr(congresses, extractNamesPerCongress, data = data,
#> members = members)
#> base::message(paste("Names matched in", round(Sys.time() -
#> t), "seconds"))
#> data %<>% distinct()
#> data$ID <- 1:nrow(data) %>% formatC(width = 6, flag = "0")
#> data %<>% left_join(members %>% select(icpsr, pattern, bioname,
#> first_name, last_name, congress, chamber, state) %>%
#> distinct()) %>% distinct()
#> data$icpsr %<>% as.numeric()
#> data %<>% select(data_row_id = data_id, match_id = ID, icpsr,
#> bioname, string, pattern, chamber, congress, everything())
#> return(data)
#> }
#> <environment: 0x12113bf90>
