def calculateCorrelation(cogDist, taxDist):
corrList = []
for dir, cogDirDist in cogDist.iteritems():
taxDirDist = taxDist[dir]
corrList.append(calculateWeightedKendall( \
[taxDirDist[x] for x in cogDirDist.keys()], cogDirDist.values()))
mean = np.mean(corrList)
std = np.std(corrList, ddof = 1.)
print("Result: mean %f std %f" % (mean, std))
return(mean, std)
# Now find optimal reclassified TaxaTypes, and dump them into a file
print("Build reclassification...")
reclassObjList = []
dumpDirNodeCostDict = {}
for dir in dirTaxaTypeDictDict.keys():
nodeCostDict = taxaTypeTree.bldCostDict(dirTaxaTypeDictDict[dir])
dumpDirNodeCostDict[dir] = taxaTypeTree.utilJsonDump(
nodeAttribDict = nodeCostDict)
taxaType, cost = taxaTypeTree.optimal(nodeCostDict)
dist = taxaDict[dir].type.distance(taxaType)
reclassObjList.append(UtilObject(dir = dir, cogCorr = dirCorrDict[dir],
oldClassif = taxaDict[dir].type, newClassif = taxaType,
taxaDist = dist, cogDist=cost, taxaDistCnts = taxaDistCntDict[dir]))
UtilStore(dumpDirNodeCostDict, DIR_NODE_COST_DICT())
reclassObjList = sorted(reclassObjList, key = lambda x: x.cogCorr)
UtilStore([x for x in reclassObjList if x.taxaDist > 0],
HIER_RECLASSIFIED_LIST())
distList = [0] * (TaxaType.maxDistance() + 1)
for obj in reclassObjList:
distList[obj.taxaDist] += 1
print("Out of %d genomes, reclassification dist distribution %s" %
(len(dirTaxaTypeDictDict), repr(distList)))
# Calculate Kendal correlation between taxaDist and cogCorr
corr = calculateWeightedKendall([x.taxaDist for x in reclassObjList],
[x.cogCorr for x in reclassObjList])
print "taxaDist / cogCorr correlation", corr
def calculateOrderCorrelation(l):
"""
:param l - list of pairs
:return: Kendal Tau correlation
"""
return calculateWeightedKendall(*(zip(*l)))
