def agreementRates(clf,valLabels,uLabels,plot=False):
'''
This function gets a classifiers dictionary generated from clfsEval
and calculates the agreement of the classifiers and
generate a list of accuracy, f1_scores and other performance metrics
so that we can figure out the thold that can maximize performance
'''
clfsLabels=[i for i in clf['pred_val']]
clfsLabels=np.array(clfsLabels)
agmnt=[]
mvLabels=[]
#Calculation of the majority vote labels
for i in range(len(clfsLabels[1])):
temp=clfsLabels[:,i]
mx=len(temp)
cts=dS.counts(temp)
oCts=sorted(cts['counts'])
temp=dS.expSmooth(oCts,0.95)/mx
agmnt.append(temp)
tmax=max(cts['counts'])
tind=np.argwhere(np.array(cts['counts'])==tmax)
#Check whether there is a tie in the number of counts
#if there is one simply throw the dies
if len(tind)==1:
tind=np.argmax(cts['counts'])
mvLabels.append(cts['vals'][tind])
else:
tind=np.random.permutation(tind)[0]
mvLabels.append(cts['vals'][tind])
sAgmnt=np.sort(np.unique(agmnt))
clf['agmntLevels']=sAgmnt
#In this section is calculated the f1_score for the ground truth and
#the predicted values filtering by the agreement rate
f1_scores=[]
for i in sAgmnt:
inds2=np.argwhere(agmnt>=i)
temp=[]
for cnum in range(len(clf['pred_val'])):
try:
temp.append(f1_score(valLabels[inds2],clf['pred_val'][cnum][inds2],labels=uLabels))
except:
print('problem at funcs agreement rates')
# print(f1_score(valLabels[inds2],clf['pred_val'][cnum][inds2],labels=uLabels))
f1_scores.append(temp)
if plot==True:
plt.plot(sAgmnt,f1_scores)
plt.show()
clf['f1_score_val_predval_agmnt']=f1_scores
return mvLabels,agmnt
def majorityVote(clfs,testingData,ignore=[]):
'''
This function takes a set of previously built classifiers and calculates the
majority vote for a given testing data set as well some performance measures related with
the majority vote itself
ignore is a list of the indexes of the classifiers to be ignored
'''
votes=[]
mV=[]
agmnt=[]
for i in range(len(clfs)):
if i not in ignore:
temp=clfs[i]['classifier'][0].predict(testingData)
votes.append(temp)
votes=np.array(votes)
for i in range(np.shape(votes)[1]):
temp=votes[:,i]
mx=len(temp)
cts=dS.counts(temp)
oCts=sorted(cts['counts'])
temp=dS.expSmooth(oCts,0.95)/mx
agmnt.append(temp)
tmax=max(cts['counts'])
tind=np.argwhere(np.array(cts['counts'])==tmax)
#Check whether there is a tie in the number of counts
#if there is one simply throw the dies
if len(tind)==1:
tind=np.argmax(cts['counts'])
mV.append(cts['vals'][tind])
else:
tind=np.random.permutation(tind)[0]
mV.append(cts['vals'][tind])
#Check the agreement and majority vote values
#I should be done with this section if it is
#working correctly
return mV,agmnt,votes