R 中的嵌套 if else 语句 - 即使“if”语句为 TRUE 也会执行“else”语句

Question

I have a dataframe with 2 columns: df$a and df$b . I need to calculate the values for column df$c based on the values of df$b using 2 seperate sets of conditions. Which set of conditions should be applied depends on the value of df$a .

I tried to solve this by writing a nested if else statement.

# A subset of my data
    a <- c(4211L, 2660L, 2839L, 3967L, 3167L, 2755L, 1680L, 2400L, 1173L, 1301L, 2370L, 2366L, 411L, 615L, 1382L, 826L, 717L, 401L, 177L, 82L, 579L, 246L)
    b <- c(0.213, 0.102, 0.092, 0.121, 0.093, 0.0918, 0.0241, 0.060, 0.008, 0.003, 0.0385, 0.0368, -0.0529, -0.0697, 0.0192, -0.0346, -0.053, NA, -0.098, -0.139, -0.137, -0.0697)
    df <- data.frame(a,b)

I want to use the first set of conditions when df$a <1000 , and the second set of conditions when df$a>=1000 . This is my code:

df$c <- if (df$a < 1000) {
          ifelse(df$b <= -0.2, '1',
                 ifelse(df$b > -0.2 & df$b <= -0.1, '2',
                        ifelse(df$b > -0.1 & df$b <= 0.0, '3',
                               ifelse(df$b > 0.0 & df$b <= 0.1, '4',
                                      '5'))))
        } else {
          ifelse(df$b <= 0.0, '1',
                 ifelse(df$b > 0.0 & df$b <= 0.1, '2',
                        ifelse(df$b > 0.1 & df$b <= 0.2, '3',
                               ifelse(df$b > 0.2 & df$b <= 0.3, '4',
                                      '5'))))
        }

However, the code calculates all df$c values based on conditions in the else statement, even when (df$a < 1000) is TRUE . Does anyone know what is causing this mistake? I get the following warning message:

Warning message:
In if (df$a < 1000) { :
  the condition has length > 1 and only the first element will be used

Answer 1

You could use ifelse as well, because if is non vectorized. And I would use a function like cut to simplify the code:

a <- c(4211L, 2660L, 2839L, 3967L, 3167L, 2755L, 1680L, 2400L, 1173L, 1301L, 2370L, 2366L, 411L, 615L, 1382L, 826L, 717L, 401L, 177L, 82L, 579L, 246L)
b <- c(0.213, 0.102, 0.092, 0.121, 0.093, 0.0918, 0.0241, 0.060, 0.008, 0.003, 0.0385, 0.0368, -0.0529, -0.0697, 0.0192, -0.0346, -0.053, NA, -0.098, -0.139, -0.137, -0.0697)
df <- data.frame(a,b)

df$c <- ifelse(df$a < 1000,
               cut(df$b, breaks = c(-Inf, -0.2, -0.1, 0.0, 0.1, +Inf), 
                   labels = as.character(1:5)),
               cut(df$b, c(-Inf, 0, 0.1, 0.2, 0.3, +Inf), 
                   as.character(1:5)))
df

# a       b  c
# 1  4211  0.2130  4
# 2  2660  0.1020  3
# 3  2839  0.0920  2
# 4  3967  0.1210  3
# 5  3167  0.0930  2
# 6  2755  0.0918  2
# 7  1680  0.0241  2
# ....

Answer 2

We can use findInterval :

df$c <- with(df, ifelse(a < 1000, findInterval(b, seq(-0.2, 0.1, 0.1)), 
                                  findInterval(b, seq(0, 0.3, 0.1))) + 1)
df$c
# [1]  4  3  2  3  2  2  2  2  2  2  2  2  3  3  2  3  3 NA  3  2  2  3