def main(size_of_test_set, articles, max_sentences):
path = r'C:\Users\Adam\workspace\Wiki Pi NLP\Test_Set_Files_BIONLP09\dot_a1_files'
count = 0
for dir_entry in os.listdir(path):
count += 1
if count > size_of_test_set:
break
dir_entry_path = os.path.join(path, dir_entry)
if os.path.isfile(dir_entry_path):
with open(dir_entry_path, 'r') as my_file:
reader=csv.reader(my_file,delimiter='\t')
rows = []
for row in reader:
rows.append(row)
first_two_proteins = []
for lst in rows[:2]:
first_two_proteins.append(lst[2])
if len(first_two_proteins) != 2:
continue
first_two_proteins = [x.lower() for x in first_two_proteins]
#first_two_proteins = [x.replace('-',' ') for x in first_two_proteins]
if first_two_proteins[0] == first_two_proteins[1]:
continue
a1_file = make_a1_file_object(my_file, dir_entry,first_two_proteins)
print a1_file.proteins, count
PPI_cite_main.index(a1_file, articles, max_sentences)
def main(q1, q2, articles, max_sentences):
q1= q1.lower()
q2 = q2.lower()
first_two_proteins = [q1, q2]
a1_file = make_a1_file_object(first_two_proteins)
print a1_file.proteins
PPI_cite_main.index(a1_file, articles, max_sentences)
def main(q1, q2, articles, max_sentences):
q1 = q1.lower()
q2 = q2.lower()
first_two_proteins = [q1, q2]
a1_file = make_a1_file_object(first_two_proteins)
print a1_file.proteins
PPI_cite_main.index(a1_file, articles, max_sentences)
def main(size_of_test_set, articles, max_sentences):
path = r'C:\Users\Adam\workspace\Wiki Pi NLP\Test_Set_Files_BIONLP09\dot_a1_files'
count = 0
for dir_entry in os.listdir(path):
count += 1
if count > size_of_test_set:
break
dir_entry_path = os.path.join(path, dir_entry)
if os.path.isfile(dir_entry_path):
with open(dir_entry_path, 'r') as my_file:
reader = csv.reader(my_file, delimiter='\t')
rows = []
for row in reader:
rows.append(row)
first_two_proteins = []
for lst in rows[:2]:
first_two_proteins.append(lst[2])
if len(first_two_proteins) != 2:
continue
first_two_proteins = [x.lower() for x in first_two_proteins]
#first_two_proteins = [x.replace('-',' ') for x in first_two_proteins]
if first_two_proteins[0] == first_two_proteins[1]:
continue
a1_file = make_a1_file_object(my_file, dir_entry,
first_two_proteins)
print a1_file.proteins, count
PPI_cite_main.index(a1_file, articles, max_sentences)
