從所有可能的變量組合中生成虛擬變量

Question

我有 5 個可以present (=1) 或not (=0) 的條件：

set.seed(101)
df <- data.frame(
alfa = sample(c(0, 1), 30, replace = TRUE),
beta = sample(c(0, 1), 30, replace = TRUE),
gamma = sample(c(0, 1), 30, replace = TRUE),
delta = sample(c(0, 1), 30, replace = TRUE),
epsilon = sample(c(0, 1), 30, replace = TRUE)
)

我想從這些條件存在的所有可能組合 (2 ⁵ ) 中生成一組虛擬變量。 具體來說，我想驗證以下條件的伴隨存在：

• 1） alfa + beta ；
• 2） alfa + gamma ；
• 3） alfa + delta ；
• 4) alfa + epsilon ;
• 5) alfa + beta + gamma ;
• [...]
• 27) alfa + beta + gamma + delta + epsilon;

生成所有可能組合的矩陣

v <- as.matrix(expand.grid(rep(list(c(FALSE, TRUE)), ncol(df))))

所有組合：

 head(v)
      Var1  Var2  Var3  Var4  Var5
[1,]  TRUE FALSE FALSE FALSE FALSE
[2,] FALSE  TRUE FALSE FALSE FALSE
[3,]  TRUE  TRUE FALSE FALSE FALSE
[4,] FALSE FALSE  TRUE FALSE FALSE
[5,]  TRUE FALSE  TRUE FALSE FALSE
[6,] FALSE  TRUE  TRUE FALSE FALSE

將矩陣轉換為列索引列表

indexes <- lapply(seq_len(nrow(v)), function(x) v[x, ])
names(indexes) <- apply(v, 1, function(x) paste(names(df)[x], collapse="."))

不幸的是我被困在這里。
我需要根據上述組合生成 27 個虛擬變量（32-5）。

EDT：我用這種骯臟的方式解決了這個問題：

# my df
set.seed(101)
df <- data.frame(
alfa = sample(c(0, 1), 30, replace = TRUE),
beta = sample(c(0, 1), 30, replace = TRUE),
gamma = sample(c(0, 1), 30, replace = TRUE),
delta = sample(c(0, 1), 30, replace = TRUE),
epsilon = sample(c(0, 1), 30, replace = TRUE)
)

# count the numebr of coesistent conditions:
df$n <- rowSums(df[1:5], na.rm = TRUE)

# Dirty way to compute multiple combinations:
df$alfa.beta <- ifelse (df$alfa == 1 & df$beta == 1 & df$gamma == 0 & df$delta == 0 & df$epsilon == 0 , 1, 0)
df$alfa.gamma <- ifelse (df$alfa == 1 & df$beta == 0 & df$gamma == 1 & df$delta == 0 & df$epsilon == 0 , 1, 0)
df$beta.gamma <- ifelse (df$alfa == 0 & df$beta == 1 & df$gamma == 1 & df$delta == 0 & df$epsilon == 0 , 1, 0)
df$alfa.beta.gamma <- ifelse (df$alfa == 1 & df$beta == 1 & df$gamma == 1 & df$delta == 0 & df$epsilon == 0 , 1, 0)
df$alfa.delta <- ifelse (df$alfa == 1 & df$beta == 0 & df$gamma == 0 & df$delta == 1 & df$epsilon == 0 , 1, 0)
df$beta.delta <- ifelse (df$alfa == 0 & df$beta == 1 & df$gamma == 0 & df$delta == 1 & df$epsilon == 0 , 1, 0)
df$alfa.beta.delta <- ifelse (df$alfa == 1 & df$beta == 1 & df$gamma == 0 & df$delta == 1 & df$epsilon == 0 , 1, 0)
df$gamma.delta <- ifelse (df$alfa == 0 & df$beta == 0 & df$gamma == 1 & df$delta == 1 & df$epsilon == 0 , 1, 0)
df$alfa.gamma.delta <- ifelse (df$alfa == 1 & df$beta == 0 & df$gamma == 1 & df$delta == 1 & df$epsilon == 0 , 1, 0)
df$beta.gamma.delta <- ifelse (df$alfa == 0 & df$beta == 1 & df$gamma == 1 & df$delta == 1 & df$epsilon == 0 , 1, 0)
df$alfa.beta.gamma.delta <- ifelse (df$alfa == 1 & df$beta == 1 & df$gamma == 1 & df$delta == 1 & df$epsilon == 0 , 1, 0)
df$alfa.epsilon <- ifelse (df$alfa == 1 & df$beta == 0 & df$gamma == 0 & df$delta == 0 & df$epsilon == 1 , 1, 0)
df$beta.epsilon <- ifelse (df$alfa == 0 & df$beta == 1 & df$gamma == 0 & df$delta == 0 & df$epsilon == 1 , 1, 0)
df$alfa.beta.epsilon <- ifelse (df$alfa == 1 & df$beta == 1 & df$gamma == 0 & df$delta == 0 & df$epsilon == 1 , 1, 0)
df$gamma.epsilon <- ifelse (df$alfa == 0 & df$beta == 0 & df$gamma == 1 & df$delta == 0 & df$epsilon == 1 , 1, 0)
df$alfa.gamma.epsilon <- ifelse (df$alfa == 1 & df$beta == 0 & df$gamma == 1 & df$delta == 0 & df$epsilon == 1 , 1, 0)
df$beta.gamma.epsilon <- ifelse (df$alfa == 0 & df$beta == 1 & df$gamma == 1 & df$delta == 0 & df$epsilon == 1 , 1, 0)
df$alfa.beta.gamma.epsilon <- ifelse (df$alfa == 1 & df$beta == 1 & df$gamma == 1 & df$delta == 0 & df$epsilon == 1 , 1, 0)
df$delta.epsilon <- ifelse (df$alfa == 0 & df$beta == 0 & df$gamma == 0 & df$delta == 1 & df$epsilon == 1 , 1, 0)
df$alfa.delta.epsilon <- ifelse (df$alfa == 1 & df$beta == 0 & df$gamma == 0 & df$delta == 1 & df$epsilon == 1 , 1, 0)
df$beta.delta.epsilon <- ifelse (df$alfa == 0 & df$beta == 1 & df$gamma == 0 & df$delta == 1 & df$epsilon == 1 , 1, 0)
df$alfa.beta.delta.epsilon <- ifelse (df$alfa == 1 & df$beta == 1 & df$gamma == 0 & df$delta == 1 & df$epsilon == 1 , 1, 0)
df$gamma.delta.epsilon <- ifelse (df$alfa == 0 & df$beta == 0 & df$gamma == 1 & df$delta == 1 & df$epsilon == 1 , 1, 0)
df$alfa.gamma.delta.epsilon <- ifelse (df$alfa == 1 & df$beta == 0 & df$gamma == 1 & df$delta == 1 & df$epsilon == 1 , 1, 0)
df$beta.gamma.delta.epsilon <- ifelse (df$alfa == 0 & df$beta == 1 & df$gamma == 1 & df$delta == 1 & df$epsilon == 1 , 1, 0)
df$alfa.beta.gamma.delta.epsilon <- ifelse (df$alfa == 1 & df$beta == 1 & df$gamma == 1 & df$delta == 1 & df$epsilon == 1 , 1, 0)

Answer 1

也許您可以通過在模型公式中使用stats::model.matrix和^運算符來返回所有（高階）變量交互來實現您的目標：

library(stats)

df <- data.frame(
    alfa = sample(c(TRUE, FALSE), 30, replace = TRUE),
    beta = sample(c(TRUE, FALSE), 30, replace = TRUE),
    gamma = sample(c(TRUE, FALSE), 30, replace = TRUE),
    delta = sample(c(TRUE, FALSE), 30, replace = TRUE),
    epsilon = sample(c(TRUE, FALSE), 30, replace = TRUE)
)

df_dummy <- model.matrix(~ .^5, data = df)

colnames(df_dummy)
#>  [1] "(Intercept)"                                      
#>  [2] "alfaTRUE"                                         
#>  [3] "betaTRUE"                                         
#>  [4] "gammaTRUE"                                        
#>  [5] "deltaTRUE"                                        
#>  [6] "epsilonTRUE"                                      
#>  [7] "alfaTRUE:betaTRUE"                                
#>  [8] "alfaTRUE:gammaTRUE"                               
#>  [9] "alfaTRUE:deltaTRUE"                               
#> [10] "alfaTRUE:epsilonTRUE"                             
#> [11] "betaTRUE:gammaTRUE"                               
#> [12] "betaTRUE:deltaTRUE"                               
#> [13] "betaTRUE:epsilonTRUE"                             
#> [14] "gammaTRUE:deltaTRUE"                              
#> [15] "gammaTRUE:epsilonTRUE"                            
#> [16] "deltaTRUE:epsilonTRUE"                            
#> [17] "alfaTRUE:betaTRUE:gammaTRUE"                      
#> [18] "alfaTRUE:betaTRUE:deltaTRUE"                      
#> [19] "alfaTRUE:betaTRUE:epsilonTRUE"                    
#> [20] "alfaTRUE:gammaTRUE:deltaTRUE"                     
#> [21] "alfaTRUE:gammaTRUE:epsilonTRUE"                   
#> [22] "alfaTRUE:deltaTRUE:epsilonTRUE"                   
#> [23] "betaTRUE:gammaTRUE:deltaTRUE"                     
#> [24] "betaTRUE:gammaTRUE:epsilonTRUE"                   
#> [25] "betaTRUE:deltaTRUE:epsilonTRUE"                   
#> [26] "gammaTRUE:deltaTRUE:epsilonTRUE"                  
#> [27] "alfaTRUE:betaTRUE:gammaTRUE:deltaTRUE"            
#> [28] "alfaTRUE:betaTRUE:gammaTRUE:epsilonTRUE"          
#> [29] "alfaTRUE:betaTRUE:deltaTRUE:epsilonTRUE"          
#> [30] "alfaTRUE:gammaTRUE:deltaTRUE:epsilonTRUE"         
#> [31] "betaTRUE:gammaTRUE:deltaTRUE:epsilonTRUE"         
#> [32] "alfaTRUE:betaTRUE:gammaTRUE:deltaTRUE:epsilonTRUE"

^{由reprex 包(v0.3.0) 於 2019 年 6 月 16 日創建}

擴展的 data.frame df_dummy為所有 31 種可能的交互組合（除了攔截）返回單熱編碼列。 要失去截距，請將模型公式替換為~ .^5 + 0或~.^5 - 1 。 請注意，通過將5替換為df的列數，這很容易擴展到更多變量。

---

編輯：上面的代碼不會給你一個變量組合的唯一存在（類似於你編輯的問題中的手動編碼）。 要實現這一點，您可以嘗試：

df_dummy <- model.matrix(~ .^5 - .^4 - 1, data = df)

colnames(df_dummy)
#>  [1] "alfaFALSE:betaFALSE:gammaFALSE:deltaFALSE:epsilonFALSE"
#>  [2] "alfaTRUE:betaFALSE:gammaFALSE:deltaFALSE:epsilonFALSE" 
#>  [3] "alfaFALSE:betaTRUE:gammaFALSE:deltaFALSE:epsilonFALSE" 
#>  [4] "alfaTRUE:betaTRUE:gammaFALSE:deltaFALSE:epsilonFALSE"  
#>  [5] "alfaFALSE:betaFALSE:gammaTRUE:deltaFALSE:epsilonFALSE" 
#>  [6] "alfaTRUE:betaFALSE:gammaTRUE:deltaFALSE:epsilonFALSE"  
#>  [7] "alfaFALSE:betaTRUE:gammaTRUE:deltaFALSE:epsilonFALSE"  
#>  [8] "alfaTRUE:betaTRUE:gammaTRUE:deltaFALSE:epsilonFALSE"   
#>  [9] "alfaFALSE:betaFALSE:gammaFALSE:deltaTRUE:epsilonFALSE" 
#> [10] "alfaTRUE:betaFALSE:gammaFALSE:deltaTRUE:epsilonFALSE"  
#> [11] "alfaFALSE:betaTRUE:gammaFALSE:deltaTRUE:epsilonFALSE"  
#> [12] "alfaTRUE:betaTRUE:gammaFALSE:deltaTRUE:epsilonFALSE"   
#> [13] "alfaFALSE:betaFALSE:gammaTRUE:deltaTRUE:epsilonFALSE"  
#> [14] "alfaTRUE:betaFALSE:gammaTRUE:deltaTRUE:epsilonFALSE"   
#> [15] "alfaFALSE:betaTRUE:gammaTRUE:deltaTRUE:epsilonFALSE"   
#> [16] "alfaTRUE:betaTRUE:gammaTRUE:deltaTRUE:epsilonFALSE"    
#> [17] "alfaFALSE:betaFALSE:gammaFALSE:deltaFALSE:epsilonTRUE" 
#> [18] "alfaTRUE:betaFALSE:gammaFALSE:deltaFALSE:epsilonTRUE"  
#> [19] "alfaFALSE:betaTRUE:gammaFALSE:deltaFALSE:epsilonTRUE"  
#> [20] "alfaTRUE:betaTRUE:gammaFALSE:deltaFALSE:epsilonTRUE"   
#> [21] "alfaFALSE:betaFALSE:gammaTRUE:deltaFALSE:epsilonTRUE"  
#> [22] "alfaTRUE:betaFALSE:gammaTRUE:deltaFALSE:epsilonTRUE"   
#> [23] "alfaFALSE:betaTRUE:gammaTRUE:deltaFALSE:epsilonTRUE"   
#> [24] "alfaTRUE:betaTRUE:gammaTRUE:deltaFALSE:epsilonTRUE"    
#> [25] "alfaFALSE:betaFALSE:gammaFALSE:deltaTRUE:epsilonTRUE"  
#> [26] "alfaTRUE:betaFALSE:gammaFALSE:deltaTRUE:epsilonTRUE"   
#> [27] "alfaFALSE:betaTRUE:gammaFALSE:deltaTRUE:epsilonTRUE"   
#> [28] "alfaTRUE:betaTRUE:gammaFALSE:deltaTRUE:epsilonTRUE"    
#> [29] "alfaFALSE:betaFALSE:gammaTRUE:deltaTRUE:epsilonTRUE"   
#> [30] "alfaTRUE:betaFALSE:gammaTRUE:deltaTRUE:epsilonTRUE"    
#> [31] "alfaFALSE:betaTRUE:gammaTRUE:deltaTRUE:epsilonTRUE"    
#> [32] "alfaTRUE:betaTRUE:gammaTRUE:deltaTRUE:epsilonTRUE"

^{由reprex 包(v0.3.0) 於 2019 年 6 月 16 日創建}