Temporary variables in list comprehensions

Tue Jan 10 09:32:31 EST 2017

On Monday, 9 January 2017 03:53:37 UTC, Steven D'Aprano wrote:
> Suppose you have an expensive calculation that gets used two or more times
> in a loop.

[...]
> [(tmp, tmp + 1) for x in data for tmp in [expensive_calculation(x)]]
>> I can't decide whether that's an awesome trick or a horrible hack...

My immediate reaction is that it depends on the constraints that made it important for you to use a comprehension rather than an explicit loop in the first place.
For a toy example like this it's obviously a horrible hack, and you should simply make an explicit loop:
 result = []
 for x in data:
 # Don't recalculate this value, as it's expensive!
 val = expensive_calculation(x)
 result.append((val, val+1))
In a real world case, maybe there's a good reason why you'd prefer to stick with a comprehension. In that case, you look at trade-offs like
 def intermediate_tuple(val): return val, val+1
 [intermediate_tuple(x) for x in data]
or
 [(lambda val: (val, val+1))(x) for x in data]
or your version.
All have their own unique uglinesses, as does the explicit loop. Personally my preferences would be the explicit loop, then the intermediate_tuple function, in that order.
Paul