def __init__(self, word_emb, N_word, N_h=100, N_depth=2,
gpu=False, trainable_emb=False):
super(Seq2SQL, self).__init__()
self.trainable_emb = trainable_emb
self.gpu = gpu
self.N_h = N_h
self.N_depth = N_depth
self.max_col_num = 45
self.max_tok_num = 200
self.SQL_TOK = ['<UNK>', '<END>', 'WHERE', 'AND',
'EQL', 'GT', 'LT', '<BEG>']
self.COND_OPS = ['EQL', 'GT', 'LT']
#Word embedding
if trainable_emb:
self.agg_embed_layer = WordEmbedding(word_emb, N_word, gpu,
self.SQL_TOK, our_model=False,
trainable=trainable_emb)
self.sel_embed_layer = WordEmbedding(word_emb, N_word, gpu,
self.SQL_TOK, our_model=False,
trainable=trainable_emb)
self.cond_embed_layer = WordEmbedding(word_emb, N_word, gpu,
self.SQL_TOK, our_model=False,
trainable=trainable_emb)
else:
self.embed_layer = WordEmbedding(word_emb, N_word, gpu,
self.SQL_TOK, our_model=False,
trainable=trainable_emb)
#Predict aggregator
self.agg_pred = AggPredictor(N_word, N_h, N_depth, use_ca=False)
#Predict selected column
self.sel_pred = SelPredictor(N_word, N_h, N_depth, self.max_tok_num,
use_ca=False)
#Predict number of cond
self.cond_pred = Seq2SQLCondPredictor(
N_word, N_h, N_depth, self.max_col_num, self.max_tok_num, gpu)
self.CE = nn.CrossEntropyLoss()
self.softmax = nn.Softmax()
self.log_softmax = nn.LogSoftmax()
self.bce_logit = nn.BCEWithLogitsLoss()
if gpu:
self.cuda()
def __init__(self, word_emb, N_word, N_h=120, N_depth=2,
gpu=False, trainable_emb=False, db_content=0):
super(SQLNet, self).__init__()
self.trainable_emb = trainable_emb
self.db_content = db_content
self.gpu = gpu
self.N_h = N_h
self.N_depth = N_depth
self.max_col_num = 45
self.max_tok_num = 200
self.SQL_TOK = ['<UNK>', '<END>', 'WHERE', 'AND',
'EQL', 'GT', 'LT', '<BEG>']
self.COND_OPS = ['EQL', 'GT', 'LT']
#the model actually doesn't use type embedding when db_content == 1
if db_content == 0:
is_train = True
else:
is_train = False
self.agg_type_embed_layer = WordEmbedding(word_emb, N_word, gpu,
self.SQL_TOK, trainable=is_train)
self.sel_type_embed_layer = WordEmbedding(word_emb, N_word, gpu,
self.SQL_TOK, trainable=is_train)
self.cond_type_embed_layer = WordEmbedding(word_emb, N_word, gpu,
self.SQL_TOK, trainable=is_train)
self.embed_layer = WordEmbedding(word_emb, N_word, gpu,
self.SQL_TOK, trainable=trainable_emb)
#Predict aggregator
self.agg_pred = AggPredictor(N_word, N_h, N_depth)
#Predict select column + condition number and columns
self.selcond_pred = SelCondPredictor(N_word, N_h, N_depth, gpu, db_content)
#Predict condition operators and string values
self.op_str_pred = CondOpStrPredictor(N_word, N_h, N_depth,
self.max_col_num, self.max_tok_num, gpu, db_content)
self.CE = nn.CrossEntropyLoss()
self.softmax = nn.Softmax()
self.log_softmax = nn.LogSoftmax()
self.bce_logit = nn.BCEWithLogitsLoss()
if gpu:
self.cuda()
def __init__(self, word_emb, N_word, N_h=100, N_depth=2,
gpu=False, use_ca=True, trainable_emb=False):
super(SQLNet, self).__init__()
self.use_ca = use_ca
self.trainable_emb = trainable_emb
self.gpu = gpu
self.N_h = N_h
self.N_depth = N_depth
self.max_col_num = 45
self.max_tok_num = 200
self.SQL_TOK = ['<UNK>', '<END>', 'WHERE', 'AND', 'OR', '==', '>', '<', '!=', '<BEG>']
self.COND_OPS = ['>', '<', '==', '!=']
# Word embedding
self.embed_layer = WordEmbedding(word_emb, N_word, gpu, self.SQL_TOK, our_model=True, trainable=trainable_emb)
# Predict the number of selected columns
self.sel_num = SelNumPredictor(N_word, N_h, N_depth, use_ca=use_ca)
#Predict which columns are selected
self.sel_pred = SelPredictor(N_word, N_h, N_depth, self.max_tok_num, use_ca=use_ca)
#Predict aggregation functions of corresponding selected columns
self.agg_pred = AggPredictor(N_word, N_h, N_depth, use_ca=use_ca)
#Predict number of conditions, condition columns, condition operations and condition values
self.cond_pred = SQLNetCondPredictor(N_word, N_h, N_depth, self.max_col_num, self.max_tok_num, use_ca, gpu)
# Predict condition relationship, like 'and', 'or'
self.where_rela_pred = WhereRelationPredictor(N_word, N_h, N_depth, use_ca=use_ca)
self.CE = nn.CrossEntropyLoss()
self.softmax = nn.Softmax(dim=-1)
self.log_softmax = nn.LogSoftmax()
self.bce_logit = nn.BCEWithLogitsLoss()
if gpu:
self.cuda()
def __init__(self,
word_emb,
N_word,
N_h=120,
N_depth=2,
use_ca=True,
gpu=True,
trainable_emb=False,
db_content=0):
super(SQLNet, self).__init__()
self.trainable_emb = trainable_emb
self.db_content = db_content
self.use_ca = use_ca
self.gpu = gpu
self.N_h = N_h
self.N_depth = N_depth
self.max_col_num = 45
self.max_tok_num = 200
self.SQL_TOK = [
'<UNK>', '<END>', 'WHERE', 'AND', 'OR', '==', '>', '<', '!=',
'<BEG>'
]
self.COND_OPS = ['>', '<', '==', '!=']
#the model actually doesn't use type embedding when db_content == 1
if db_content == 0:
is_train = True
else:
is_train = False
# self.sel_num_type_embed_layer = WordEmbedding(word_emb, N_word, gpu,
# self.SQL_TOK, trainable=is_train)
self.agg_type_embed_layer = WordEmbedding(word_emb,
N_word,
gpu,
self.SQL_TOK,
trainable=is_train)
self.sel_type_embed_layer = WordEmbedding(word_emb,
N_word,
gpu,
self.SQL_TOK,
trainable=is_train)
self.cond_type_embed_layer = WordEmbedding(word_emb,
N_word,
gpu,
self.SQL_TOK,
trainable=is_train)
self.where_rela_type_embed_layer = WordEmbedding(word_emb,
N_word,
gpu,
self.SQL_TOK,
trainable=is_train)
self.embed_layer = WordEmbedding(word_emb,
N_word,
gpu,
self.SQL_TOK,
trainable=trainable_emb)
# # Predict selected column number
# self.sel_num = SelNumPredictor(N_word, N_h, N_depth)
#
# # Predict which columns are selected
# self.sel_pred = SelPredictor(N_word, N_h, N_depth, self.max_tok_num, use_ca=use_ca)
#Predict aggregator
self.agg_pred = AggPredictor(N_word, N_h, N_depth)
# # Predict number of conditions, condition columns, condition operations and condition values
# self.cond_pred = SQLNetCondPredictor(N_word, N_h, N_depth, self.max_col_num, self.max_tok_num,use_ca, gpu, db_content)
#Predict selected column number + select column + condition number and columns
self.selcond_pred = SelCondPredictor(N_word, N_h, N_depth, gpu,
db_content)
#Predict condition operators and string values
self.op_str_pred = CondOpStrPredictor(N_word, N_h, N_depth,
self.max_col_num,
self.max_tok_num, gpu,
db_content)
# Predict conditions' relation
self.where_rela_pred = WhereRelationPredictor(N_word,
N_h,
N_depth,
use_ca=use_ca)
self.CE = nn.CrossEntropyLoss()
self.softmax = nn.Softmax()
self.log_softmax = nn.LogSoftmax()
self.bce_logit = nn.BCEWithLogitsLoss()
if gpu:
self.cuda()