def median_approach(llimit,ulimit,isphrase,pathname):
posmedlist=[]
negmedlist=[]
medians=[]
lpcount=0
totalcount=ulimit-llimit
cnt_var=0
print '\nNo of +ve reviews trained : '
for fid in movie_reviews.fileids(categories=['pos'])[llimit:ulimit]:
testmed=proximity_tagger.medianlist(movie_reviews.abspath(fid),isphrase,cnt_var,0,pathname)
posmedlist.append(testmed)
lpcount=lpcount+1
cnt_var+=1
print 'Training +ve review ',lpcount,'.'*10,(float(lpcount)*100/float(totalcount)),'%'
lpcount=0
cnt_var=0
print '\nNo of -ve reviews trained : '
for fid in movie_reviews.fileids(categories=['neg'])[llimit:ulimit]:
testmed=proximity_tagger.medianlist(movie_reviews.abspath(fid),isphrase,cnt_var,1,pathname)
negmedlist.append(testmed)
lpcount=lpcount+1
cnt_var+=1
print 'Training -ve review ',lpcount,'.'*10,(float(lpcount)*100/float(totalcount)),'%'
medians.append([numpy.median(x) for x in itertools.izip(*posmedlist)])
medians.append([numpy.median(x) for x in itertools.izip(*negmedlist)])
f = open('train_result\proximity_median_train_result_'+str(isphrase),'w')
json.dump(medians,f)
f.close()
def median_result(file_to_test,isphrase):
median_testset=[]
f = open('train_result/proximity_median_train_result_'+str(isphrase),'r')
median_testset=json.load(f)
f.close()
median_test = proximity_tagger.medianlist(file_to_test,isphrase)
med_pos_val = median_testset[0][0]-median_test[0]
med_neg_val = median_testset[1][1]-median_test[1]
if(med_pos_val<med_neg_val):
return 1
return -1
def median_result(file_to_test,isphrase):
alpha=0.4
beta =0.4
gamma=0.2
median_testset=[]
f = open('train_result/proximity_median_train_result_'+str(isphrase),'r')
median_testset=json.load(f)
#print '\nMedian Test Set : ', median_testset
f.close()
median_test = proximity_tagger.medianlist(file_to_test,isphrase)
#print '\nMedian Test : ', median_test
med_pos_val = median_testset[0][0]-median_test[0]
med_neg_val = median_testset[1][1]-median_test[1]
#print 'Values : ', med_pos_val, med_neg_val
if(med_pos_val<med_neg_val):
return 1
return -1
