I have a input file which are all floating point numbers to 4 decimal place.
i.e. 13359 0.0000 0.0000 0.0001 0.0001 0.0002` 0.0003 0.0007 ...
(the first is the id).
My class uses the loadVectorsFromFile method which multiplies it by 10000 and then int() these numbers. On top of that, I also loop through each vector to ensure that there are no
negative values inside. However, when I perform _hclustering, I am continually seeing the error, "Linkage Z contains negative values".
I seriously think this is a bug because:
I checked my values,
the values are no where small enough or big enough to approach the limits of the floating point numbers and
the formula that I used to derive the values in the file uses absolute value (my input is DEFINITELY right).
Can someone enligten me as to why I am seeing this weird error? What is going on that is causing this negative distance error?
=====
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()):
