def compareMeasureNG2(edges,sims,ratio,names,proms,wName=None,ciss=None,link_func=maxSim):
precs=dict.fromkeys(names)
recalls=dict.fromkeys(names)
ss=dict.fromkeys(names)
ee=flatenDictList(edges)#ee is true edges
e=mdf.global_remove(edges,ratio)
for name in names:
ss[name]=flatenDict(netAlignInfer\
(link_func,e,sims[name]))
tss=getTS2(edges,ciss,proms,ss[name],0.1)
factors=getAssoc2(*tss,min_c=0.9)
for name in names:
precs[name]=[]
recalls[name]=[]
for thresh in np.arange(0,1.0,0.1):
for key in ss[name].keys():
if key[1] in factors.keys():
if key[0]+str(ciss[key[1]].slen) == tss[1][key[1]]:
#print 'BEFORE',ss[name][key]
ss[name][key]=1
#print 'AFTER',ss[name][key]
(p,r)=prEval(ee,ss[name],thresh)
precs[name].append(p)
recalls[name].append(r)
if not wName==None:
(precs[wName],recalls[wName])=doEntropyWeights(ee,e,ciss,\
link_func=link_func)
return (precs,recalls,ss)
def compareMeasureNG(edges,sims,ratio,names,wName=None,ciss=None,link_func=maxSim):
'''
NG means this experiment is not using the grouping
of cis-element
'''
precs=dict.fromkeys(names)
recalls=dict.fromkeys(names)
ss=dict.fromkeys(names)
ee=flatenDictList(edges)#ee is true edges
e=mdf.global_remove(edges,ratio)
for name in names:
ss[name]=flatenDict(netAlignInfer\
(link_func,e,sims[name]))
for name in names:
precs[name]=[]
recalls[name]=[]
for thresh in np.arange(0,1.0,0.1):
(p,r)=prEval(ee,ss[name],thresh)
precs[name].append(p)
recalls[name].append(r)
if not wName==None:
(precs[wName],recalls[wName])=doEntropyWeights(ee,e,ciss,\
link_func=link_func)
return (precs,recalls,ss)
def doEntropyWeights(ee,e,ciss,link_func=maxSim,proms=None):
precs=[]
recalls=[]
weights=getEntropyWeights(e,ciss)
cis_keys=ciss.keys()
sims=dict()
for x in cis_keys:
sims[x]=dict()
for y in cis_keys:
sims[x][y]=dmSim(ciss[x].seq,ciss[y].seq\
,w1=weights[x],w2=weights[y]\
,useLength=True)
ss=flatenDict(netAlignInfer(link_func,e,sims))
for thresh in np.arange(0,1,0.1):
(p,r)=prEval(ee,ss,thresh)
precs.append(p)
recalls.append(r)
return (precs,recalls)
x2=[]
y2=[]
x3=[]
y3=[]
ee=flatenDictList(edges)
for exp_i in range(N):
e=mdf.global_remove(edges,0.3)
scores1=netAlignInfer(maxSim,e,nwSims)
scores2=netAlignInfer(maxSim,e,nwSimsL)
scores3=netAlignInfer(maxSim,e,dmSimsL)
ss1=flatenDict(scores1)
ss2=flatenDict(scores2)
ss3=flatenDict(scores3)
for thresh in np.arange(0,1,0.1):
result=prEval(ee,ss1,thresh)
result2=prEval(ee,ss2,thresh)
result3=prEval(ee,ss3,thresh)
x.append(result[0])
y.append(result[1])
x2.append(result2[0])
y2.append(result2[1])
x3.append(result3[0])
y3.append(result3[1])
plt.figure(1)
plt.scatter(x,y)
plt.figure(2)
plt.scatter(x2,y2)
# Create the filter list of the hidden edges
# so that the evaluation only focus on these edges
for exp_i in range(N):
e=mdf.global_remove(edges,0.3)
# hid_e is a list of real edges hidden
entire_keys=edges.keys()
subset_keys=e.keys()
tmp_e=flatenDictList(e)
hid_e=set(ee.keys())-set(tmp_e.keys())
M=len(hid_e) # number of the hidden edges
print "start inferring"
scores1=netAlignInfer(maxSim,e,nwSims)
scores2=netAlignInfer(maxSim,e,nwSimsL)
scores3=netAlignInfer(maxSim,e,dmSimsL)
ss1=flatenDict(scores1)
ss2=flatenDict(scores2)
ss3=flatenDict(scores3)
for i in range(len(threshs)):
print "thresh is ", threshs[i]
thresh=threshs[i]
(precs[0][i],ph)=prEval(ee,ss1,thresh)
(precs[1][i],ph)=prEval(ee,ss2,thresh)
(precs[2][i],ph)=prEval(ee,ss3,thresh)
recalls[0][i]=getRecall(ee,ss1,hid_e,thresh)
recalls[1][i]=getRecall(ee,ss2,hid_e,thresh)
recalls[2][i]=getRecall(ee,ss3,hid_e,thresh)
print "end of experiement", exp_i
