R Notebook

Reading the data Named d1

d1<-read.delim("https://raw.githubusercontent.com/tuyenhavan/Statistics/master/conditii_test_VN4_SORTATE_GC%20(3).txt",col.names = c("ID","Code","Trash"),sep = ",")

# Convert Code to factor

d1$Code<-as.factor(d1$Code)

# Remove the first letter of Code column 

library(stringr)
library(tidyr)
library(dplyr)

df<-str_split_fixed(d1$Code,"",2) %>% data.frame() %>% select(Code=X2) %>% data.frame(cbind(d1[,-2])) %>% select(ID,Code,Trash) 

df$Code<-as.factor(df$Code)

head(df)

NA

Data named d2

d2<-read.delim("https://raw.githubusercontent.com/tuyenhavan/Statistics/master/SUTDS_Shapefie-FCODE%20(3).txt",sep = ";",col.names = c("Code","Address"))

# Convert Code to factor 
d2$Code<-as.factor(d2$Code)

head(d2)

Join two datasets by Code

Final_result<-inner_join(df,d2,by="Code") %>% select(ID, Code, Address, Trash)

Column `Code` joining factors with different levels, coercing to character vector

head(Final_result)

dim(Final_result)

[1] 6270    4