def generate_interval():
train = DataSet('cf/Test/test_rand1.csv')
columns = ['id','content_id','class_name','start','end','timespan','user_id']
user_dict = to_dict_byUser(train, columns, -1)
timespliter = TimeSpliter(user_dict)
time_tag = timespliter.tag_all_user()
myPickle.save(time_tag, 'test_user_time_all.pkl')
def main():
i = 0
during_dict = {}
for line in open('VideoInfo.csv', 'r'):
if i <= 2:
i += 1
continue
if len(line.split(',')) < 26:
continue
content_name = line.split(',')[1]
during = line.split(',')[8]
during_dict.setdefault(content_name, during)
during_dict['V0001008060161'] = 2659
during_dict['V0001008060159'] = 2615
during_dict['V0001008060162'] = 2688
during_dict['V0001008060163'] = 2666
during_dict['V0001008060165'] = 2608
during_dict['V0001008060166'] = 2672
during_dict['V0001008100071'] = 2627
during_dict['V0001008100072'] = 2642
during_dict['V1401003030026'] = 2767
myPickle.save(during_dict, 'video.pkl')
for p in range(1,nprocs):
(DNTP_p,dsA_p,LV_p,LVP_p,TPS_p)=comm.recv(source=p)
dsAr.append(dsA_p)
DNTP.extend(DNTP_p)
LV.extend(LV_p)
LVP.extend(LVP_p)
TPS.extend(TPS_p)
dsA=mergeDicts(dsAr)
print 'Number of complexes',len(dsA)
#print 'Complex wise AUC = ',np.mean(dA.values())
p12=map(list,zip(*dsA.values()));pa=p12[0];p1=p12[1];p2=p12[2];ps=p1;ps.extend(p2);
print 'Complex Wise AUC =',np.mean(pa),'Protein Wise AUC =',np.mean(ps)
if not auconly:
(fplv,tplv,auclv)=roc.roc_VA(LV)
(fplvp,tplvp,auclvp)=roc.roc_VA(LVP)
mkl.save(ofname,((fplv,tplv,auclv),(fplvp,tplvp,auclvp)))
print "AUC = ",auclv
"""
plt.hist(np.array(DNTP).flatten(),[0,1,2,3,4,5,6,1000],cumulative=True);plt.grid();plt.xlabel('sequence distance');plt.ylabel('counts');plt.title('Number of top 200 predictions vs. sequence distance from nearest true positive');plt.show()
[np.sum(dn<2.0) for dn in DNTP]
cids=[getFileParts(getFileParts(ifile)[1])[1] for ifile in fs]
[dsA[cid] for cid in cids]
[dAo[cid] for cid in cids]
"""
#DISTRIBUTION PLOT
dthresh=[0,1,2,3,4] # sequence distance threshold
XX=calcRFPP(np.array(TPS)[:,1]+1,DNTP,dthresh=dthresh)
if doplot:
plt.figure();plt.plot(fplv,tplv);plt.xlabel('FP');plt.ylabel('TP');plt.grid();plt.title('ROC Curve: AUC = %1.2f' % (auclv*100))
plt.figure();plt.boxplot(tuple(XX),bootstrap=1000,positions=dthresh);plt.xlabel('Sequence Distance (D) from a TP'); plt.ylabel('Minimum rank of a prediction within distance D of a TP' );plt.title('Results of soft sequence distance threshold');plt.grid();plt.yticks(range(0,201,10));
plt.show()
TPS.extend(TPS_p)
dsA = mergeDicts(dsAr)
print 'Number of complexes', len(dsA)
#print 'Complex wise AUC = ',np.mean(dA.values())
p12 = map(list, zip(*dsA.values()))
pa = p12[0]
p1 = p12[1]
p2 = p12[2]
ps = p1
ps.extend(p2)
print 'Complex Wise AUC =', np.mean(pa), 'Protein Wise AUC =', np.mean(
ps)
if not auconly:
(fplv, tplv, auclv) = roc.roc_VA(LV)
(fplvp, tplvp, auclvp) = roc.roc_VA(LVP)
mkl.save(ofname, ((fplv, tplv, auclv), (fplvp, tplvp, auclvp)))
print "AUC = ", auclv
"""
plt.hist(np.array(DNTP).flatten(),[0,1,2,3,4,5,6,1000],cumulative=True);plt.grid();plt.xlabel('sequence distance');plt.ylabel('counts');plt.title('Number of top 200 predictions vs. sequence distance from nearest true positive');plt.show()
[np.sum(dn<2.0) for dn in DNTP]
cids=[getFileParts(getFileParts(ifile)[1])[1] for ifile in fs]
[dsA[cid] for cid in cids]
[dAo[cid] for cid in cids]
"""
#DISTRIBUTION PLOT
dthresh = [0, 1, 2, 3, 4] # sequence distance threshold
XX = calcRFPP(np.array(TPS)[:, 1] + 1, DNTP, dthresh=dthresh)
if doplot:
plt.figure()
plt.plot(fplv, tplv)
plt.xlabel('FP')