python - Scipy 负距离？什么？

Question

我有一个包含小数点后 4 位 float 的输入文件:

i.e. 13359    0.0000    0.0000    0.0001    0.0001    0.0002`    0.0003    0.0007    ... 

(第一个是id)。我的类使用 loadVectorsFromFile 方法将其乘以 10000，然后使用 int() 这些数字。最重要的是，我还循环遍历每个向量以确保内部没有负值。但是，当我执行 _hclustering 时，我不断看到错误，“LinkageZcontains negative values”。

我真的认为这是一个错误，因为:

1. 我检查了我的值(value)观，
2. 这些值没有足够小或足够大以接近 float 的限制，并且
3. 我用来导出文件中值的公式使用绝对值(我的输入绝对正确)。

有人可以启发我为什么会看到这个奇怪的错误吗？是什么导致了这种负距离误差？

=====

def loadVectorsFromFile(self, limit, loc, assertAllPositive=True, inflate=True):
    """Inflate to prevent "negative" distance, we use 4 decimal points, so *10000
    """
    vectors = {}
    self.winfo("Each vector is set to have %d limit in length" % limit)
    with open( loc ) as inf:
        for line in filter(None, inf.read().split('\n')):
            l = line.split('\t')
            if limit:
                scores = map(float, l[1:limit+1])
            else:
                scores = map(float, l[1:])

            if inflate:        
                vectors[ l[0]] = map( lambda x: int(x*10000), scores)     #int might save space
            else:
                vectors[ l[0]] = scores                           

    if assertAllPositive:
        #Assert that it has no negative value
        for dirID, l in vectors.iteritems():
            if reduce(operator.or_, map( lambda x: x < 0, l)):
                self.werror( "Vector %s has negative values!" % dirID)
    return vectors

def main( self, inputDir, outputDir, limit=0,
        inFname="data.vectors.all", mappingFname='all.id.features.group.intermediate'):
    """
    Loads vector from a file and start clustering
    INPUT
        vectors is { featureID: tfidfVector (list), }
    """
    IDFeatureDic = loadIdFeatureGroupDicFromIntermediate( pjoin(self.configDir, mappingFname))
    if not os.path.exists(outputDir):
        os.makedirs(outputDir)

    vectors = self.loadVectorsFromFile( limit, pjoin( inputDir, inFname))
    for threshold in map( lambda x:float(x)/30, range(20,30)):
        clusters = self._hclustering(threshold, vectors)
        if clusters:
            outputLoc = pjoin(outputDir, "threshold.%s.result" % str(threshold))
            with open(outputLoc, 'w') as outf:
                for clusterNo, cluster in clusters.iteritems():
                    outf.write('%s\n' % str(clusterNo))
                    for featureID in cluster:
                        feature, group = IDFeatureDic[featureID]
                        outline = "%s\t%s\n" % (feature, group)
                        outf.write(outline.encode('utf-8'))
                    outf.write("\n")
        else:
            continue

def _hclustering(self, threshold, vectors):
    """function which you should call to vary the threshold
    vectors:    { featureID:    [ tfidf scores, tfidf score, .. ]
    """
    clusters = defaultdict(list)
    if len(vectors) > 1:
        try:
            results = hierarchy.fclusterdata( vectors.values(), threshold, metric='cosine')
        except ValueError, e:
            self.werror("_hclustering: %s" % str(e))
            return False

        for i, featureID in enumerate( vectors.keys()):

Answer 1

这是因为 float 不准确，所以向量之间的某些距离不是 0，而是例如 -0.000000000000000002。使用scipy.clip() 函数来修正问题。如果您的距离矩阵是 dmatr，请使用 numpy.clip(dmatr,0,1,dmatr)，您应该没问题。