Question

我有550 242个观测数据和9个变量的数据集

str(train) 

'data.frame':   550242 obs. of  9 variables:
 $ State.Name       : chr  "ANDHRA PRADESH" "ANDHRA PRADESH" "ANDHRA PRADESH" "ANDHRA PRADESH" ...
 $ District.Name    : chr  "EAST GODAVARI(04)" "EAST GODAVARI(04)" "EAST GODAVARI(04)" "EAST GODAVARI(04)" ...
 $ Block.Name       : chr  "PRATHIPADU(10)" "PRATHIPADU(10)" "PRATHIPADU(10)" "PRATHIPADU(10)" ...
 $ Panchayat.Name   : chr  "GOKAVARAM(04)" "GOKAVARAM(04)" "GAJJANAPUDI(06)" "GAJJANAPUDI(06)" ...
 $ Village.Name     : chr  "VANTHADA(014 )" "PANDAVULAPALEM(022 )" "G. KOTHURU(023 )" "GAJJANAPUDI(029 )" ...
 $ Habitation.Name  : chr  "VANTHADA(0404410014010400)" "PANDAVULAPALEM(0404410022010400)" "G. KOTHURU(0404410023010600)" "GAJJANAPUDI(0404410029010600)" ...
 $ Quality.Parameter: chr  "Salinity" "Fluoride" "Salinity" "Salinity" ...
 $ Year             : chr  "1/4/2009" "1/4/2009" "1/4/2009" "1/4/2009" ...
 $ newdate          : Date, format: "2009-04-01" "2009-04-01" "2009-04-01" ...

head(unique(train$District.Name))
[1] "EAST GODAVARI(04)" "WEST GODAVARI(05)" "KRISHNA(06)"           "GUNTUR(07)"        "ADILABAD(19)"     
[6] "KARIMNAGAR(20)"

在列名train$District.Name中，我只想保留字符串并清理其余部分，所以这是我的代码。：

state_1$District.Name <- gsub("("," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub(")"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("1"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("0"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("29"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("8"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("16"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("3"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("5"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("8"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("14"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("24"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("22"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("25"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("21"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("20"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("9"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub(")"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("1"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("0"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("29"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("8"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("16"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("3"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("5"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("8"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("14"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("24"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("22"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("25"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("2"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("6"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("4"," ",fixed=TRUE,state_1$District.Name)
state_1$District.Name <- gsub("7"," ",fixed=TRUE,state_1$District.Name)

由于存在所有这些字符，但我可以使用循环执行相同的操作（更少的代码来处理）：

vector<-c("      `(",")","1","0","29","8","16","3","5","8","14","21","22","23","24","25","2","6","4","7","9","14")`

for (i in 1:length(state_1$District.Name)) {
  for(j in 1:length(vector))
    {
      train$District.Name <- gsub(vector[j],new.vector[j],fixed=TRUE,train$District.Name)
    }
}

此代码完成了工作，但需要花费太多时间。作为顶级代码，它可以在几秒钟内完成所有500k变量（但更多行代码）的工作。

我可以用更少的代码和更快的执行来获得大量观察的两全其美吗？

Answer 1

如果我清楚地理解，对于state_1 $ District.Name你只想保留字符串。您可以使用reg exp：state_1$District.Name <- gsub(pattern = "\\(.*","",state_1$District.Name)

使用这样的一行来完成

除了循环之外的任何有效的方法来清理大型观察？

1 个答案: