Created
October 10, 2020 19:04
-
-
Save kumeS/db75fdb0389f9a84846c58f5dcf302c1 to your computer and use it in GitHub Desktop.
Japanese Morphological Analysis using SudachiPy in R
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
SudachiTokenizerR <- function(text='国家公務員', mode=SplitA, N=100){ | |
try(for(n in 0:N){ | |
#n <- 0 | |
if(n == 0){ m <- array(NA, dim=(7)) } | |
try(a <- tokenizer_obj$tokenize(text=text, mode=mode)[n], silent=T) | |
m[1] <- as.character(a) | |
m[2:7] <- a$part_of_speech() | |
if(n == 0){ | |
sudachipyResults <- m | |
}else{ | |
if(n == 1){ | |
sudachipyResults <- abind::abind(sudachipyResults, m, along=0) | |
}else{ | |
sudachipyResults <- abind::abind(sudachipyResults, m, along=1) | |
} | |
} | |
}, silent=T) | |
if(length(dim(sudachipyResults)) == 1){ | |
sudachipyResults <- t(data.frame(sudachipyResults)) | |
}else{ | |
sudachipyResults <- data.frame(sudachipyResults) | |
} | |
rownames(sudachipyResults) <- 1:nrow(sudachipyResults) | |
colnames(sudachipyResults) <- c("語彙", "品詞タグ01", "品詞タグ02", "品詞タグ03", "品詞タグ04", "品詞タグ05", "品詞タグ06") | |
return(sudachipyResults) | |
} | |
#実行例 | |
#SudachiTokenizerR(text='国家公務員') | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment