Closed HugoSousa closed 7 years ago
I realize that if the code is changed to
from bratutils import agreement as a
__author__ = 'Aleksandar Savkov'
doc = '796'
gold = a.Document('../res/ht_gold/' + doc + '.ann')
extension = a.Document('../res/ht_extension/' + doc + '.ann')
#gold.make_gold()
statistics = gold.compare_to_gold(extension)
print statistics
it outputs the result I just said.
I just realize now that in your sample you also comment the make_gold
function and the order in which the documents appear in the compare_to_gold
was confusing to me too, as it is not referred which one is the gold document in the sample (actually in the collections comparison, the gold collection is the function parameter).
So, I guess this is not an issue, just a bad usage from myself.
Can you confirm this is the correct way to execute it?
Thanks, Hugo
Hi, this is long overdue but I think the answer is yes :)
I'm closing this issue. Thanks for your feedback!
Sasho
Hello again,
I have two .ann files.
The gold
And the candidate set
For the comparison I'm running the following code
This should produce as result: 0 correct, 12 missing and 3 spurious tags. Right?
The produced result is 3 missing tags and 0 correct/partial/spurious. I think the spurious tags are not being correctly handled.
Is my thinking right, or this is actually the desired output?
Hugo