R中的標籤編碼器功能？

Question

在python中，scikit有一個很好的功能叫做LabelEncoder，它將分類層次（字符串）映射爲整型表示。

有沒有什麼在R做這個？例如，如果有一個名爲色用值{「藍」，「紅」，「綠」}可變編碼器將轉變：

Blue => 1 
Green => 2 
Red => 3 

，並用此映射，以再用於轉化新的數據使用創建一個對象以類似的方式。

地址： 似乎不只是因素會起作用，因爲沒有持續的映射。如果新數據與訓練數據有一個看不見的級別，則整個結構會發生變化。理想情況下，我希望以某種方式標記失蹤或「其他」的新級別。

sample_dat <- data.frame(a_str=c('Red','Blue','Blue','Red','Green')) 
sample_dat$a_int<-as.integer(as.factor(sample_dat$a_str)) 
sample_dat$a_int 
#[1] 3 1 1 3 2 
sample_dat2 <- data.frame(a_str=c('Red','Blue','Blue','Red','Green','Azure')) 
sample_dat2$a_int<-as.integer(as.factor(sample_dat2$a_str)) 
sample_dat2$a_int 
# [1] 4 2 2 4 3 1 

Answer 1

我寫的，我認爲作品;下面，和/或如何將規模尚未被測試的效率

str2Int.fit_transform<-function(df, plug_missing=TRUE){ 

    list_of_levels=list() #empty list 

    #loop through the columns 
    for (i in 1: ncol(df)) 
    { 

    #only 
    if (is.character(df[,i]) || is.factor(df[,i])){ 

     #deal with missing 
     if(plug_missing){ 

     #if factor 
     if (is.factor(df[,i])){ 
      df[,i] = factor(df[,i], levels=c(levels(df[,i]), 'MISSING')) 
      df[,i][is.na(df[,i])] = 'MISSING' 


     }else{ #if character 

      df[,i][is.na(df[,i])] = 'MISSING' 

     } 
     }#end missing IF 

     levels<-unique(df[,i]) #distinct levels 
     list_of_levels[[colnames(df)[i]]] <- levels #set list with name of the columns to the levels 
     df[,i] <- as.numeric(factor(df[,i], levels = levels)) 

    }#end if character/factor IF 


    }#end loop 

    return (list(list_of_levels,df)) #return the list of levels and the new DF 

}#end of function 



str2Int.transform<-function(df,list_of_levels,plug_missing=TRUE) 
{ 
    #loop through the columns 
    for (i in 1: ncol(df)) 
    { 

    #only 
    if (is.character(df[,i]) || is.factor(df[,i])){ 


     #deal with missing 
     if(plug_missing){ 

     #if factor 
     if (is.factor(df[,i])){ 
      df[,i] = factor(df[,i], levels=c(levels(df[,i]), 'MISSING')) 
      df[,i][is.na(df[,i])] = 'MISSING' 


     }else{ #if character 

      df[,i][is.na(df[,i])] = 'MISSING' 

     } 
     }#end missing IF 

     levels=list_of_levels[[colnames(df)[i]]] 

     if (! is.null(levels)){ 
     df[,i] <- as.numeric(factor(df[,i], levels = levels)) 
     } 

    }# character or factor 

    }#end of loop 

    return(df) 

}#end of function 




###################################################### 
# Test the functions 
###################################################### 



###Test fit transform 

# as strings 
sample_dat <- data.frame(a_fact=c('Red','Blue','Blue',NA,'Green'), a_int=c(1,2,3,4,5), a_str=c('a','b','c','a','v'),stringsAsFactors=FALSE) 

result<-str2Int.fit_transform(sample_dat) 
result[[1]] #list of levels 
result[[2]] #transformed df 

#as factors 
sample_dat <- data.frame(a_fact=c('Red','Blue','Blue',NA,'Green'), a_int=c(1,2,3,4,5), a_str=c('a','b','c','a','v'),stringsAsFactors=TRUE) 

result<-str2Int.fit_transform(sample_dat) 
result[[1]] #list of levels 
result[[2]] #transformed df 



###Test transform 
str2Int.transform(sample_dat,result[[1]]) 

Answer 2

創建數據的載體：

colors <- c("red", "red", "blue", "green") 

創建一個因素：

factors <- factor(colors) 

轉換系數爲數字：

as.numeric(factors) 

輸出：（注意，這按字母順序排列）

# [1] 3 3 1 2 

您還可以設置自定義編號系統：（注意，現在輸出遵循「彩虹色序」我定義的）

rainbow <- c("red","orange","yellow","green","blue","purple") 
ordered <- factor(colors, levels = rainbow) 
as.numeric(ordered) 
# [1] 1 1 5 4 

見?factor。

Answer 3

如果我正確理解你想要什麼：

# function which returns function which will encode vectors with values of 'vec' 
label_encoder = function(vec){ 
    levels = sort(unique(vec)) 
    function(x){ 
     match(x, levels) 
    } 
} 

colors = c("red", "red", "blue", "green") 

color_encoder = label_encoder(colors) # create encoder 

encoded_colors = color_encoder(colors) # encode colors 
encoded_colors 

new_colors = c("blue", "green", "green") # new vector 
encoded_new_colors = color_encoder(new_colors) 
encoded_new_colors 

other_colors = c("blue", "green", "green", "yellow") 
color_encoder(other_colors) # NA's are introduced 

# save and restore to disk 
saveRDS(color_encoder, "color_encoder.RDS") 
c_encoder = readRDS("color_encoder.RDS") 
c_encoder(colors) # same result 

# dealing with multiple columns 

# create data.frame 
set.seed(123) # make result reproducible 
color_dataframe = as.data.frame(
    matrix(
     sample(c("red", "blue", "green", "yellow"), 12, replace = TRUE), 
     ncol = 3) 
) 
color_dataframe 

# encode each column 
for (column in colnames(color_dataframe)){ 
    color_dataframe[[column]] = color_encoder(color_dataframe[[column]]) 
} 
color_dataframe