nltkor 1.2.14__cp311-cp311-macosx_13_0_x86_64.whl

nltkor/cider/__init__.py

@@ -0,0 +1,2 @@
+
+__all__=['Cider']

nltkor/cider/cider.py

@@ -0,0 +1,55 @@
+#-*-coding:utf8-*-
+# Filename: cider.py
+#
+# Description: Describes the class to compute the CIDEr (Consensus-Based Image Description Evaluation) Metric
+#               by Vedantam, Zitnick, and Parikh (http://arxiv.org/abs/1411.5726)
+#
+# Creation Date: Sun Feb  8 14:16:54 2015
+#
+# Authors: Ramakrishna Vedantam <vrama91@vt.edu> and Tsung-Yi Lin <tl483@cornell.edu>
+
+from nltkor.cider.cider_scorer import CiderScorer
+
+class Cider:
+    """
+    Main Class to compute the CIDEr metric
+
+    """
+    def __init__(self, test=None, refs=None, n=4, sigma=6.0):
+        # set cider to sum over 1 to 4-grams
+        self._n = n
+        # set the standard deviation parameter for gaussian penalty
+        self._sigma = sigma
+
+    def compute_score(self, gts, res):
+        """
+        Main function to compute CIDEr score
+        :param  hypo_for_image (dict) : dictionary with key <image> and value <tokenized hypothesis / candidate sentence>
+                ref_for_image (dict)  : dictionary with key <image> and value <tokenized reference sentence>
+        :return: cider (float) : computed CIDEr score for the corpus
+        """
+        '''
+        gts={0:['안 녕 하 세 요 홍성태입니다.','안 녕 해 요 홍성태입니다']}
+        res={0:['a b ']}
+        '''
+        assert(gts.keys() == res.keys())
+        imgIds = gts.keys()
+
+        cider_scorer = CiderScorer(n=self._n, sigma=self._sigma)
+
+        for id in imgIds:
+
+            hypo = res[id]
+            ref = gts[id]
+
+            # Sanity check.
+            assert(type(hypo) is list)
+            assert(len(hypo) == 1)
+            assert(type(ref) is list)
+            assert(len(ref) > 0)
+
+            cider_scorer += (hypo[0], ref)
+
+        score = cider_scorer.compute_score()
+
+        return format(score,".7f")

nltkor/cider/cider_scorer.py

@@ -0,0 +1,207 @@
+#!/usr/bin/env python
+#-*-coding:utf8-*-
+# Tsung-Yi Lin <tl483@cornell.edu>
+# Ramakrishna Vedantam <vrama91@vt.edu>
+
+import copy
+from collections import defaultdict
+import math
+import statistics 
+
+def precook(s, n=4, out=False):
+    """
+    Takes a string as input and returns an object that can be given to
+    either cook_refs or cook_test. This is optional: cook_refs and cook_test
+    can take string arguments as well.
+    :param s: string : sentence to be converted into ngrams
+    :param n: int    : number of ngrams for which representation is calculated
+    :return: term frequency vector for occuring ngrams
+    """
+    words = s.split()
+    counts = defaultdict(int)
+    for k in range(1,n+1):
+        for i in range(len(words)-k+1):
+            ngram = tuple(words[i:i+k])
+            counts[ngram] += 1
+    return counts
+
+def cook_refs(refs, n=4): ## lhuang: oracle will call with "average"
+    '''Takes a list of reference sentences for a single segment
+    and returns an object that encapsulates everything that BLEU
+    needs to know about them.
+    :param refs: list of string : reference sentences for some image
+    :param n: int : number of ngrams for which (ngram) representation is calculated
+    :return: result (list of dict)
+    '''
+    return [precook(ref, n) for ref in refs]
+
+def cook_test(test, n=4):
+    '''Takes a test sentence and returns an object that
+    encapsulates everything that BLEU needs to know about it.
+    :param test: list of string : hypothesis sentence for some image
+    :param n: int : number of ngrams for which (ngram) representation is calculated
+    :return: result (dict)
+    '''
+    return precook(test, n, True)
+
+class CiderScorer(object):
+    """CIDEr scorer.
+    """
+
+    def copy(self):
+        ''' copy the refs.'''
+        new = CiderScorer(n=self.n)
+        new.ctest = copy.copy(self.ctest)
+        new.crefs = copy.copy(self.crefs)
+        return new
+
+    def __init__(self, test=None, refs=None, n=4, sigma=6.0):
+        ''' singular instance '''
+
+        self.n = n
+        self.sigma = sigma
+        
+        #요기서 ~₩
+        self.crefs = []
+        self.ctest = []
+        self.document_frequency = defaultdict(float)
+        self.cook_append(test, refs)
+        self.ref_len = None
+
+    def cook_append(self, test, refs):
+        '''called by constructor and __iadd__ to avoid creating new instances.'''
+        
+        if refs is not None:
+            self.crefs.append(cook_refs(refs))
+            if test is not None:
+                self.ctest.append(cook_test(test)) ## N.B.: -1
+            else:
+                self.ctest.append(None) # lens of crefs and ctest have to match
+
+
+    def size(self):
+        assert len(self.crefs) == len(self.ctest), "refs/test mismatch! %d<>%d" % (len(self.crefs), len(self.ctest))
+        return len(self.crefs)
+
+    def __iadd__(self, other):
+        '''add an instance (e.g., from another sentence).'''
+
+        if type(other) is tuple:
+            ## avoid creating new CiderScorer instances
+
+            self.cook_append(other[0], other[1])
+        else:
+            self.ctest.extend(other.ctest)
+            self.crefs.extend(other.crefs)
+
+        return self
+    def compute_doc_freq(self):
+        '''
+        Compute term frequency for reference data.
+        This will be used to compute idf (inverse document frequency later)
+        The term frequency is stored in the object
+        :return: None
+        '''
+        for refs in self.crefs:
+            # refs, k ref captions of one image
+            for ngram in set([ngram for ref in refs for (ngram,count) in ref.items()]):
+                self.document_frequency[ngram] += 1
+            # maxcounts[ngram] = max(maxcounts.get(ngram,0), count)
+
+    def compute_cider(self):
+        def counts2vec(cnts):
+            """
+            Function maps counts of ngram to vector of tfidf weights.
+            The function returns vec, an array of dictionary that store mapping of n-gram and tf-idf weights.
+            The n-th entry of array denotes length of n-grams.
+            :param cnts:
+            :return: vec (array of dict), norm (array of float), length (int)
+            """
+
+            vec = [defaultdict(float) for _ in range(self.n)]
+            length = 0
+            norm = [0.0 for _ in range(self.n)]
+            for (ngram,term_freq) in cnts.items():
+                # give word count 1 if it doesn't appear in reference corpus
+                df = math.log(max(1.0, self.document_frequency[ngram]))
+                # ngram index
+                n = len(ngram)-1
+                # tf (term_freq) * idf (precomputed idf) for n-grams
+                vec[n][ngram] = float(term_freq)*(self.ref_len - df)
+                
+                if vec[n][ngram]== 0:
+                    vec[n][ngram]=1
+
+                # compute norm for the vector.  the norm will be used for computing similarity
+                norm[n] += pow(vec[n][ngram], 2)
+
+                if n == 1:
+                    length += term_freq
+
+            norm = [math.sqrt(n) for n in norm]
+            return vec, norm, length
+
+        def sim(vec_hyp, vec_ref, norm_hyp, norm_ref, length_hyp, length_ref):
+            '''
+            Compute the cosine similarity of two vectors.
+            :param vec_hyp: array of dictionary for vector corresponding to hypothesis
+            :param vec_ref: array of dictionary for vector corresponding to reference
+            :param norm_hyp: array of float for vector corresponding to hypothesis
+            :param norm_ref: array of float for vector corresponding to reference
+            :param length_hyp: int containing length of hypothesis
+            :param length_ref: int containing length of reference
+            :return: array of score for each n-grams cosine similarity
+            '''
+            delta = float(length_hyp - length_ref)
+            # measure consine similarity
+            val = [0.0 for _ in range(self.n)]
+            for n in range(self.n):
+                # ngram
+                for (ngram,count) in vec_hyp[n].items():
+                    # vrama91 : added clipping
+                    val[n] += min(vec_hyp[n][ngram], vec_ref[n][ngram]) * vec_ref[n][ngram]
+
+                if (norm_hyp[n] != 0) and (norm_ref[n] != 0):
+                    val[n] /= (norm_hyp[n]*norm_ref[n])
+
+                assert(not math.isnan(val[n]))
+                # vrama91: added a length based gaussian penalty
+                val[n] *= math.exp((-(delta**2))/(2*self.sigma**2))
+            return val
+
+        # compute log reference length
+        self.ref_len = math.log(float(len(self.crefs)))  
+
+        scores = []
+        for test, refs in zip(self.ctest, self.crefs):
+            # compute vector for test captions
+
+            vec, norm, length = counts2vec(test)
+            # compute vector for ref captions
+            score = [0.0 for _ in range(self.n)]
+            for ref in refs:
+                vec_ref, norm_ref, length_ref = counts2vec(ref)
+                ret_list=sim(vec, vec_ref, norm, norm_ref, length, length_ref)
+                for num,val in zip(range(self.n),ret_list):
+                    score[num]+=val
+                #score += sim(vec, vec_ref, norm, norm_ref, length, length_ref)
+            # change by vrama91 - mean of ngram scores, instead of sum
+            score_avg = statistics.mean(score)
+            # divide by number of references
+            score_avg /= len(refs)
+            # multiply score by 10
+            #score_avg *= 10.0
+            # append score of an image to the score list
+            scores.append(score_avg)
+        return scores
+
+    def compute_score(self, option=None, verbose=0):
+        # compute idf
+        self.compute_doc_freq()
+        # assert to check document frequency
+        assert(len(self.ctest) >= max(self.document_frequency.values()))
+        # compute cider score
+        score = self.compute_cider()
+        # debug
+        # print score
+        return statistics.mean(score)