SC/data_prepare/utils.py", line 135, in load_inputs_twitter y.append(lines[i + 2].strip().split()[0]) IndexError: list index out of range

[monajalal]

So I give the following parameters to lcr but still it uses restaurant parameters

jalal@goku ASC]$ python model/lcr.py --train_file_path data/absa/twitter/1train_new.txt --test_file_path data/absa/twitter/test.txt --embedding_file_path data/absa/twitter/twitter_word_embedding_partial_300_42b.txt --learning_rate 0.1 --batch_size 25 --n_iter 50 --random_base 0.1 --l2_reg 0.00001 --keep_prob1 0.5 --keep_prob2 0.5

Parameters:
aspect_id_file_path=data/restaurant/aspect_id_new.txt
batch_size=25
display_step=4
embedding_dim=300
embedding_file_path=data/absa/twitter/twitter_word_embedding_partial_300_42b.txt
is_r=1
keep_prob1=0.5
keep_prob2=0.5
l2_reg=1e-05
learning_rate=0.1
max_doc_len=20
max_sentence_len=80
max_target_len=10
method=AE
model_num=100
n_class=3
n_hidden=300
n_iter=50
n_layer=3
prob_file=prob1.txt
random_base=0.1
saver_file=prob1.txt
t1=last
t2=last
test_file_path=data/absa/twitter/test.txt
test_file_path_r=data/restaurant/rest_2014_lstm_test_new.txt
train_file_path=data/absa/twitter/1train_new.txt
train_file_path_r=data/restaurant/rest_2014_lstm_train_new.txt
validate_file_path=data/restaurant/rest_2014_lstm_test_new.txt
validate_file_path_r=data/restaurant/rest_2014_lstm_test_new.txt
word_id_file_path=data/restaurant/word_id_new.txt

a bad word embedding: 10213
(10215, 300)
10215 10215
I am lcr_rot.
2018-04-20 02:04:54.459445: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2018-04-20 02:04:54.459480: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2018-04-20 02:04:54.459493: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
2018-04-20 02:04:54.459538: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX2 instructions, but these are available on your machine and could speed up CPU computations.
2018-04-20 02:04:54.459550: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use FMA instructions, but these are available on your machine and could speed up CPU computations.
load word-to-id done!
Traceback (most recent call last):
  File "model/lcr.py", line 255, in <module>
    tf.app.run()
  File "/scratch/sjn-p2/anaconda/anaconda2/lib/python2.7/site-packages/tensorflow/python/platform/app.py", line 48, in run
    _sys.exit(main(_sys.argv[:1] + flags_passthrough))
  File "model/lcr.py", line 143, in main
    FLAGS.max_target_len
  File "/scratch2/debate_tweets/sentiment/ASC/data_prepare/utils.py", line 135, in load_inputs_twitter
    y.append(lines[i + 2].strip().split()[0])
IndexError: list index out of range
[jalal@goku ASC]$ 

How should I fix it?

Also in twitter data there is couple of files for train and embedding. Can you please explain the difference among them? thanks Like what is the difference between 1train.txt, 1train_new.txt and train_new.txt? same about various twitter word embedding txt files.

[jalal@goku ASC]$ ls data/absa/twitter/
1test.txt   1train_new.txt  all.txt     test.txt   train_new.txt                           twitter_word_embedding_partial_200.txt      validate.txt
1train.txt  1validate.txt   process.py  train.txt  twitter_word_embedding_partial_100.txt  twitter_word_embedding_partial_300_42b.txt  word_id.txt