# Beeferman's Pk text segmentation evaluation metric
[docs]def pk(ref, hyp, k=None, boundary='1'):
"""
Compute the Pk metric for a pair of segmentations A segmentation
is any sequence over a vocabulary of two items (e.g. "0", "1"),
where the specified boundary value is used to mark the edge of a
segmentation.
>>> s1 = "00000010000000001000000"
>>> s2 = "00000001000000010000000"
>>> s3 = "00010000000000000001000"
>>> pk(s1, s1, 3)
0.0
>>> pk(s1, s2, 3)
0.095238...
>>> pk(s2, s3, 3)
0.190476...
:param ref: the reference segmentation
:type ref: str or list
:param hyp: the segmentation to evaluate
:type hyp: str or list
:param k: window size, if None, set to half of the average reference segment length
:type boundary: str or int or bool
:param boundary: boundary value
:type boundary: str or int or bool
:rtype: float
"""
if k is None:
k = int(round(len(ref) / (ref.count(boundary) * 2.)))
n_considered_seg = len(ref) - k + 1
n_same_ref = 0.0
n_false_alarm = 0.0
n_miss = 0.0
for i in xrange(n_considered_seg):
bsame_ref_seg = False
bsame_hyp_seg = False
if boundary not in ref[(i+1):(i+k)]:
n_same_ref += 1.0
bsame_ref_seg = True
if boundary not in hyp[(i+1):(i+k)]:
bsame_hyp_seg = True
if bsame_hyp_seg and not bsame_ref_seg:
n_miss += 1
if bsame_ref_seg and not bsame_hyp_seg:
n_false_alarm += 1
prob_same_ref = n_same_ref / n_considered_seg
prob_diff_ref = 1 - prob_same_ref
prob_miss = n_miss / n_considered_seg
prob_false_alarm = n_false_alarm / n_considered_seg
return prob_miss * prob_diff_ref + prob_false_alarm * prob_same_ref