guotong1988/nl2sql

Bidirectional Attention for SQL Generation

Hi! My name is Tong Guo.

Reviewer of ACL-2023, NAACL-2022/2024, EMNLP-2022/2023 Industry Track.

Another email: [email protected]

Never Give Up. Learn From Failure.

---

Print is the best debugging method.

nl2sql's Issues

KeyError: 'query_tok'

mldl@ub1604:/ub16_prj/NL2SQL$ python train.py --ca
Loading from original dataset
Loading data from data/train.jsonl
Loading data from data/train.tables.jsonl
Loading data from data/dev.jsonl
Loading data from data/dev.tables.jsonl
Loading data from data/test.jsonl
Loading data from data/test.tables.jsonl
Loading word embedding from glove/glove.42B.300d.txt
Using fixed embedding
Using column attention on aggregator predicting
Using column attention on selection predicting
Using column attention on where predicting
Traceback (most recent call last):
File "train.py", line 103, in
val_sql_data, val_table_data, TRAIN_ENTRY)
File "/home/mldl/ub16_prj/NL2SQL/sqlnet/utils.py", line 200, in epoch_acc
q_seq, col_seq, col_num, ans_seq, query_seq, gt_cond_seq, raw_data = to_batch_seq(sql_data, table_data, perm, st, ed, ret_vis_data=True)
File "/home/mldl/ub16_prj/NL2SQL/sqlnet/utils.py", line 113, in to_batch_seq
query_seq.append(sql['query_tok'])
KeyError: 'query_tok'
mldl@ub1604:/ub16_prj/NL2SQL$

IndexError: too many indices for array

ub16hp@UB16HP:/ub16_prj/NL2SQL$ python train.py
Loading from original dataset
Loading data from data/train_tok.jsonl
Loading data from data/train_tok.tables.jsonl
Loading data from data/dev_tok.jsonl
Loading data from data/dev_tok.tables.jsonl
Loading data from data/test_tok.jsonl
Loading data from data/test_tok.tables.jsonl
Loading word embedding from glove/glove.42B.300d.txt
Using fixed embedding
Not using column attention on aggregator predicting
Not using column attention on selection predicting
Not using column attention on where predicting
/home/ub16hp/ub16_prj/NL2SQL/sqlnet/model/modules/aggregator_predict.py:55: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
att = self.softmax(att_val)
/home/ub16hp/ub16_prj/NL2SQL/sqlnet/model/modules/selection_predict.py:55: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
att = self.softmax(att_val)
/home/ub16hp/ub16_prj/NL2SQL/sqlnet/model/modules/sqlnet_condition_predict.py:123: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
num_col_att = self.softmax(num_col_att_val)
/home/ub16hp/ub16_prj/NL2SQL/sqlnet/model/modules/sqlnet_condition_predict.py:138: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
num_att = self.softmax(num_att_val)
/home/ub16hp/ub16_prj/NL2SQL/sqlnet/model/modules/sqlnet_condition_predict.py:163: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
col_att = self.softmax(col_att_val)
/home/ub16hp/ub16_prj/NL2SQL/sqlnet/model/modules/sqlnet_condition_predict.py:209: UserWarning: Implicit dimension choice for softmax has been deprecated. Change the call to include dim=X as an argument.
op_att = self.softmax(op_att_val)
Init dev acc_qm: 0.0
breakdown on (agg, sel, where): [0.05498159 0.16363852 0. ]
Epoch 1 @ 2018-10-01 12:27:07.696338
Traceback (most recent call last):
File "train.py", line 128, in
sql_data, table_data, TRAIN_ENTRY)
File "/home/ub16hp/ub16_prj/NL2SQL/sqlnet/utils.py", line 145, in epoch_train
cum_loss += loss.data.cpu().numpy()[0]*(ed - st)
IndexError: too many indices for array
ub16hp@UB16HP:/ub16_prj/NL2SQL$