def process_count_topic(topic,name):
counter = Counter();
for section in topic:
sz = len(section)
print (section[0])
for i in range(1,sz):
print ("Problem ",abs(section[i]))
# Find
tmp_set = []
num = abs(section[i])
input_max = 0
if(num < 800):
continue
url = url_conv(num)
content = TextPre.convert_and_filter(url)
global amount_words
amount_words += 1
array = \
content.split()
#print array
for element in array:
if len(element) < 3 or element in remove_word or element in tmp_set:
continue;
counter[element]+=1
tmp_set.append(element)
return counter
def download(url,num,path): content = TextPre.convert_and_filter(url) fo = open(path+"/"+str(num)+".txt","w+") fo.write(content) fo.close()
def matrix_constructor_topic():
f = open('info.in','r+')
a = f.readline()
f.close()
print a
if(len(a) == 0):
print "NO INFO"
tmp = a.split()
a_s = int(tmp[0])
f_s = int(tmp[1])
ref = {}
idx = 0;
f = open("dict.txt","r+")
a = f.readline()
while a != "":
tmp = a.split()
ref[tmp[0]] = idx
print (tmp[0]," ",idx)
idx += 1
a = f.readline()
X = [[0 for c in range(0,f_s)] for r in range(0,a_s)]
Y = [0 for r in range(0,a_s)]
lab_idx = 0
smp_idx = 0
for topic in all_topic:
for section in topic:
sz = len(section)
print (section[0])
for i in range(1,sz):
#print "Problem ",abs(section[i])
num = abs(section[i])
if(num < 800):
continue
global amount_samples
amount_samples+=1
url = url_conv(num)
content = TextPre.convert_and_filter(url)
input_num,input_length,des_length = TextPre.max_input_num(content)
input_max.append(int(input_num)) # Fetch the input max value
input_size.append(int(input_length))
des_size.append(int(des_length))
#print input_max
array = \
content.split()
#print array
for element in array:
print (element)
if element in ref:
print smp_idx," ",ref[element]
if X[smp_idx][ref[element]] == 0:
X[smp_idx][ref[element]] = 1
#X[smp_idx][ref[element]] += 1
Y[smp_idx] = lab_idx
smp_idx += 1
lab_idx += 1
f = open('info.in','a+')
f.write("%d" % int(amount_samples)) # Number of samples
f.close()
return X,Y