You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
29 lines
800 B
29 lines
800 B
import os
|
|
from utils.csv import read_csv_file
|
|
|
|
project_root = os.path.dirname(os.path.dirname(os.path.abspath(__file__)))
|
|
|
|
train_file_path = project_root+'/data/tsv/train.tsv'
|
|
test_file_path = project_root+'/data/tsv/test.tsv'
|
|
|
|
print(train_file_path)
|
|
|
|
data = read_csv_file(csv_file_path=train_file_path, delimiter='\t')
|
|
|
|
i = 0
|
|
for inst in data:
|
|
if len(inst.features) <= 0:
|
|
inst.print()
|
|
i += 1
|
|
print('Data Points without Features :: ', i)
|
|
|
|
# tokens = inst.text.split()
|
|
# for token in tokens:
|
|
# if token not in feature_dict:
|
|
# feature_dict[token] = 1
|
|
# continue
|
|
# feature_dict[token] += 1
|
|
#
|
|
# for key in sorted(feature_dict, key=feature_dict.get, reverse=True):
|
|
# print(key, ' -> ', feature_dict.get(key))
|