(주)빌트온 동남아 유사도 Check

rm(list=ls())
library(stringr)
library(dplyr)
input <- read.csv("C:\\Users\\이해리\\Desktop\\multi\\TH_facial_cleanser.csv")

1step 대문자를 소문자로 치환

input$aa<- tolower(input$top_title)

2step 문자열에서 문자 분리

input$bb <- strsplit(input$aa, split="")

3step dataframe 생성

rows <- input
cols <- input
mat <- matrix(nrow=235, ncol=235)
rownames(mat) <- input$top_title
colnames(mat) <- input$top_title
mat <- as.data.frame(mat)
mat_70 <- mat
class(mat)

4step 값 삽입

for (n in 1:235){
	a <- input$bb[[n]]
for (m in 1:235){
	b <- input$bb[[m]]
x <- a %in% b
x1 <- (length(which(x=="TRUE"))/length(a))

    mat[n,m] <- x1

  }

}

70% 이상 값 추출

for (n in 1:235){

  a <- input$bb[[n]]

  for (m in 1:235){

    b <- input$bb[[m]]

    x <- a %in% b

    x1 <- (length(which(x=="TRUE"))/length(a))

    if (x1 >= 0.7){

      mat_70[n,m] <- x1

    }else {

      mat_70[n,m] <- 0

    }

  }

}

write.csv(mat_70,"C:\\Users\\이해리\\Desktop\\multi\\TH_facial_cleanser_check.csv", row.names=TRUE )