split_line_breaks.r

#create new (empty) data frame for output
df <- data.frame()
#read source dataframe
sourceData <- read.csv("originals/rentBoard-clean.csv", stringsAsFactors = F)

#get max rows
maxRows <- nrow(sourceData)
  
for(i in 1:maxRows){
    #subset row
    row <- sourceData[i,]
    #subset scell
    name_cell <- row[,"Landlord.Name"]    
    
    if(str_detect(name_cell, "\n") ){
        #split column into list of character vectors
        names <- suppressWarnings(strsplit(name_cell, '\n'))
        #for each in character vector
        for(name in names[[1]]){
            #duplicate source row, replacing ['column'] value with each
            row$Landlord.Name = name
            #write this row to the new dataframe
            df <- rbind(df, row)
        }
    }
    #else write original row to empty data frame
    else df <- rbind(df, row)
    print(i)
}

#write new data frame to output
write.csv(df, "output/rent_board_split.csv", row.names=FALSE)
print("DUNZO")