Evaluate different logical conditions from string

问题:

I have a data.frame like this:

  value     condition
1  0.46   value > 0.5
2  0.96 value == 0.79
3  0.45 value <= 0.65
4  0.68 value == 0.88
5  0.57   value < 0.9
6  0.10  value > 0.01
7  0.90  value >= 0.6
8  0.25  value < 0.91
9  0.04   value > 0.2

structure(list(value = c(0.46, 0.96, 0.45, 0.68, 0.57, 0.1, 0.9, 
0.25, 0.04), condition = c("value > 0.5", "value == 0.79", "value <= 0.65", 
"value == 0.88", "value < 0.9", "value > 0.01", "value >= 0.6", 
"value < 0.91", "value > 0.2")), class = "data.frame", row.names = c(NA, 
-9L))

I would like to evaluate the strings in the condition column for every row.

So the result would look like this.

  value     condition  goal
1  0.46   value > 0.5 FALSE
2  0.96 value == 0.79 FALSE
3  0.45 value <= 0.65  TRUE
4  0.68 value == 0.88 FALSE
5  0.57   value < 0.9  TRUE
6  0.10  value > 0.01  TRUE
7  0.90  value >= 0.6  TRUE
8  0.25  value < 0.91  TRUE
9  0.04   value > 0.2 FALSE

I suppose there is a handy NSE solution within the dplyr framework. I have experimented with !! and expr() and others. I got some promising results when trying to subset by condition using

result <- df[0,]
for(i in 1:nrow(df)) { 
  result <- rbind(result, filter_(df[i,], bquote(.(df$condition[i]))))
}

But I don't like the solution and it's not exactly what I'm after.

I hope someone can help.

UPDATE: I'm trying to avoid eval(parse(..)).

回答1:

Not entirely sure whether you are looking for something like this, however, you can also use lazy_eval() from lazyeval:

df %>%
 rowwise() %>%
 mutate(res = lazy_eval(sub("value", value, condition)))

  value condition     res  
  <dbl> <chr>         <lgl>
1 0.46  value > 0.5   FALSE
2 0.96  value == 0.79 FALSE
3 0.45  value <= 0.65 TRUE 
4 0.68  value == 0.88 FALSE
5 0.570 value < 0.9   TRUE 
6 0.1   value > 0.01  TRUE 
7 0.9   value >= 0.6  TRUE 
8 0.25  value < 0.91  TRUE 
9 0.04  value > 0.2   FALSE

And even though it is very close to eval(parse(...)), a possibility is also using parse_expr() from rlang:

df %>%
 rowwise() %>%
 mutate(res = eval(rlang::parse_expr(condition)))

回答2:

One straightforward and easy solution would be using eval(parse...

library(dplyr)

df %>%
  rowwise() %>%
  mutate(goal = eval(parse(text = condition)))

# A tibble: 9 x 3
#  value condition     goal 
#  <dbl> <chr>         <lgl>
#1 0.46  value > 0.5   FALSE
#2 0.96  value == 0.79 FALSE
#3 0.45  value <= 0.65 TRUE 
#4 0.68  value == 0.88 FALSE
#5 0.570 value < 0.9   TRUE 
#6 0.1   value > 0.01  TRUE 
#7 0.9   value >= 0.6  TRUE 
#8 0.25  value < 0.91  TRUE 
#9 0.04  value > 0.2   FALSE

However, I would recommend reading some posts before using it.

回答3:

Using match.fun:

# get function, and the value
myFun <- lapply(strsplit(df1$condition, " "), function(i){
  list(f = match.fun(i[ 2 ]), 
       v = as.numeric(i[ 3 ]))
})

df1$goal <- mapply(function(x, y){ 
  x[[ "f" ]](y, x[ "v" ])
  }, x = myFun, y = df1$value)

#   value     condition  goal
# 1  0.46   value > 0.5 FALSE
# 2  0.96 value == 0.79 FALSE
# 3  0.45 value <= 0.65  TRUE
# 4  0.68 value == 0.88 FALSE
# 5  0.57   value < 0.9  TRUE
# 6  0.10  value > 0.01  TRUE
# 7  0.90  value >= 0.6  TRUE
# 8  0.25  value < 0.91  TRUE
# 9  0.04   value > 0.2 FALSE

回答4:

If you want to avoid eval(parse... you can try this:

library(tidyverse)
df %>% mutate(bound = as.numeric(str_extract(condition, "[0-9 \\.]*$")),
              goal = case_when(grepl("==", condition) ~ value == bound,
                               grepl(">=", condition) ~ value >= bound,
                               grepl("<=", condition) ~ value <= bound,
                               grepl(">", condition) ~ value > bound,
                               grepl("<", condition) ~ value < bound,
                               T ~ NA))

  value     condition bound  goal
1  0.46   value > 0.5  0.50 FALSE
2  0.96 value == 0.79  0.79 FALSE
3  0.45 value <= 0.65  0.65  TRUE
4  0.68 value == 0.88  0.88 FALSE
5  0.57   value < 0.9  0.90  TRUE
6  0.10  value > 0.01  0.01  TRUE
7  0.90  value >= 0.6  0.60  TRUE
8  0.25  value < 0.91  0.91  TRUE
9  0.04   value > 0.2  0.20 FALSE