- Pk
-
1 def pk(ref, hyp, k=None, boundary='1'): 2 """ 3 Compute the Pk metric for a pair of segmentations A segmentation 4 is any sequence over a vocabulary of two items (e.g. "0", "1"), 5 where the specified boundary value is used to mark the edge of a 6 segmentation. 7 8 >>> '%.2f' % pk('0100'*100, '1'*400, 2) 9 '0.50' 10 >>> '%.2f' % pk('0100'*100, '0'*400, 2) 11 '0.50' 12 >>> '%.2f' % pk('0100'*100, '0100'*100, 2) 13 '0.00' 14 15 :param ref: the reference segmentation 16 :type ref: str or list 17 :param hyp: the segmentation to evaluate 18 :type hyp: str or list 19 :param k: window size, if None, set to half of the average reference segment length 20 :type boundary: str or int or bool 21 :param boundary: boundary value 22 :type boundary: str or int or bool 23 :rtype: float 24 """ 25 26 if k is None: 27 k = int(round(len(ref) / (ref.count(boundary) * 2.))) 28 29 err = 0 30 for i in range(len(ref)-k +1): 31 r = ref[i:i+k].count(boundary) > 0 32 h = hyp[i:i+k].count(boundary) > 0 33 if r != h: 34 err += 1 35 return err / (len(ref)-k +1.)
-
- WindowDiff
-
1 def windowdiff(seg1, seg2, k, boundary="1", weighted=False): 2 """ 3 Compute the windowdiff score for a pair of segmentations. A 4 segmentation is any sequence over a vocabulary of two items 5 (e.g. "0", "1"), where the specified boundary value is used to 6 mark the edge of a segmentation. 7 8 >>> s1 = "000100000010" 9 >>> s2 = "000010000100" 10 >>> s3 = "100000010000" 11 >>> '%.2f' % windowdiff(s1, s1, 3) 12 '0.00' 13 >>> '%.2f' % windowdiff(s1, s2, 3) 14 '0.30' 15 >>> '%.2f' % windowdiff(s2, s3, 3) 16 '0.80' 17 18 :param seg1: a segmentation 19 :type seg1: str or list 20 :param seg2: a segmentation 21 :type seg2: str or list 22 :param k: window width 23 :type k: int 24 :param boundary: boundary value 25 :type boundary: str or int or bool 26 :param weighted: use the weighted variant of windowdiff 27 :type weighted: boolean 28 :rtype: float 29 """ 30 31 if len(seg1) != len(seg2): 32 raise ValueError("Segmentations have unequal length") 33 if k > len(seg1): 34 raise ValueError("Window width k should be smaller or equal than segmentation lengths") 35 wd = 0 36 for i in range(len(seg1) - k + 1): 37 ndiff = abs(seg1[i:i + k].count(boundary) - seg2[i:i + k].count(boundary)) 38 if weighted: 39 wd += ndiff 40 else: 41 wd += min(1, ndiff) 42 return wd / (len(seg1) - k + 1.)
这两个指标观看文献，还真是有点玄学！还好，找到了nltk中对应的实现，极其简单明了！
-