def parse_ifttt_dataset():
WORD_FREQ_CUT_OFF = 2
annot_file = '/Users/yinpengcheng/Research/SemanticParsing/ifttt/Data/lang.all.txt'
code_file = '/Users/yinpengcheng/Research/SemanticParsing/ifttt/Data/code.all.txt'
data = preprocess_ifttt_dataset(annot_file, code_file)
# build the grammar
grammar = get_grammar([e['parse_tree'] for e in data])
annot_tokens = list(chain(*[e['query_tokens'] for e in data]))
annot_vocab = gen_vocab(annot_tokens, vocab_size=30000, freq_cutoff=WORD_FREQ_CUT_OFF)
logging.info('annot vocab. size: %d', annot_vocab.size)
# we have no terminal tokens in ifttt
all_terminal_tokens = []
terminal_vocab = gen_vocab(all_terminal_tokens, vocab_size=4000, freq_cutoff=WORD_FREQ_CUT_OFF)
# now generate the dataset!
train_data = DataSet(annot_vocab, terminal_vocab, grammar, 'ifttt.train_data')
dev_data = DataSet(annot_vocab, terminal_vocab, grammar, 'ifttt.dev_data')
test_data = DataSet(annot_vocab, terminal_vocab, grammar, 'ifttt.test_data')
all_examples = []
can_fully_reconstructed_examples_num = 0
examples_with_empty_actions_num = 0
for entry in data:
idx = entry['id']
query_tokens = entry['query_tokens']
code = entry['code']
parse_tree = entry['parse_tree']
# check if query tokens are valid
query_token_ids = [annot_vocab[token] for token in query_tokens if token not in string.punctuation]
valid_query_tokens_ids = [tid for tid in query_token_ids if tid != annot_vocab.unk]
# remove examples with rare words from train and dev, avoid overfitting
if len(valid_query_tokens_ids) == 0 and 0 <= idx < 77495 + 5171:
continue
rule_list, rule_parents = parse_tree.get_productions(include_value_node=True)
actions = []
can_fully_reconstructed = True
rule_pos_map = dict()
for rule_count, rule in enumerate(rule_list):
if not grammar.is_value_node(rule.parent):
assert rule.value is None
parent_rule = rule_parents[(rule_count, rule)][0]
if parent_rule:
parent_t = rule_pos_map[parent_rule]
else:
parent_t = 0
rule_pos_map[rule] = len(actions)
d = {'rule': rule, 'parent_t': parent_t, 'parent_rule': parent_rule}
action = Action(APPLY_RULE, d)
actions.append(action)
else:
raise RuntimeError('no terminals should be in ifttt dataset!')
if len(actions) == 0:
examples_with_empty_actions_num += 1
continue
example = DataEntry(idx, query_tokens, parse_tree, code, actions,
{'str_map': None, 'raw_code': entry['raw_code']})
if can_fully_reconstructed:
can_fully_reconstructed_examples_num += 1
# train, valid, test splits
if 0 <= idx < 77495:
train_data.add(example)
elif idx < 77495 + 5171:
dev_data.add(example)
else:
test_data.add(example)
all_examples.append(example)
# print statistics
max_query_len = max(len(e.query) for e in all_examples)
max_actions_len = max(len(e.actions) for e in all_examples)
# serialize_to_file([len(e.query) for e in all_examples], 'query.len')
# serialize_to_file([len(e.actions) for e in all_examples], 'actions.len')
logging.info('train_data examples: %d', train_data.count)
logging.info('dev_data examples: %d', dev_data.count)
logging.info('test_data examples: %d', test_data.count)
logging.info('examples that can be fully reconstructed: %d/%d=%f',
can_fully_reconstructed_examples_num, len(all_examples),
can_fully_reconstructed_examples_num / len(all_examples))
logging.info('empty_actions_count: %d', examples_with_empty_actions_num)
logging.info('max_query_len: %d', max_query_len)
logging.info('max_actions_len: %d', max_actions_len)
train_data.init_data_matrices(max_query_length=40, max_example_action_num=6)
dev_data.init_data_matrices()
test_data.init_data_matrices()
serialize_to_file((train_data, dev_data, test_data),
'data/ifttt.freq{WORD_FREQ_CUT_OFF}.bin'.format(WORD_FREQ_CUT_OFF=WORD_FREQ_CUT_OFF))
return train_data, dev_data, test_data
def parse_ifttt_dataset():
WORD_FREQ_CUT_OFF = 2
annot_file = '/Users/yinpengcheng/Research/SemanticParsing/ifttt/Data/lang.all.txt'
code_file = '/Users/yinpengcheng/Research/SemanticParsing/ifttt/Data/code.all.txt'
data = preprocess_ifttt_dataset(annot_file, code_file)
# build the grammar
grammar = get_grammar([e['parse_tree'] for e in data])
annot_tokens = list(chain(*[e['query_tokens'] for e in data]))
annot_vocab = gen_vocab(annot_tokens,
vocab_size=30000,
freq_cutoff=WORD_FREQ_CUT_OFF)
logging.info('annot vocab. size: %d', annot_vocab.size)
# we have no terminal tokens in ifttt
all_terminal_tokens = []
terminal_vocab = gen_vocab(all_terminal_tokens,
vocab_size=4000,
freq_cutoff=WORD_FREQ_CUT_OFF)
# now generate the dataset!
train_data = DataSet(annot_vocab, terminal_vocab, grammar,
'ifttt.train_data')
dev_data = DataSet(annot_vocab, terminal_vocab, grammar, 'ifttt.dev_data')
test_data = DataSet(annot_vocab, terminal_vocab, grammar,
'ifttt.test_data')
all_examples = []
can_fully_reconstructed_examples_num = 0
examples_with_empty_actions_num = 0
for entry in data:
idx = entry['id']
query_tokens = entry['query_tokens']
code = entry['code']
parse_tree = entry['parse_tree']
# check if query tokens are valid
query_token_ids = [
annot_vocab[token] for token in query_tokens
if token not in string.punctuation
]
valid_query_tokens_ids = [
tid for tid in query_token_ids if tid != annot_vocab.unk
]
# remove examples with rare words from train and dev, avoid overfitting
if len(valid_query_tokens_ids) == 0 and 0 <= idx < 77495 + 5171:
continue
rule_list, rule_parents = parse_tree.get_productions(
include_value_node=True)
actions = []
can_fully_reconstructed = True
rule_pos_map = dict()
for rule_count, rule in enumerate(rule_list):
if not grammar.is_value_node(rule.parent):
assert rule.value is None
parent_rule = rule_parents[(rule_count, rule)][0]
if parent_rule:
parent_t = rule_pos_map[parent_rule]
else:
parent_t = 0
rule_pos_map[rule] = len(actions)
d = {
'rule': rule,
'parent_t': parent_t,
'parent_rule': parent_rule
}
action = Action(APPLY_RULE, d)
actions.append(action)
else:
raise RuntimeError('no terminals should be in ifttt dataset!')
if len(actions) == 0:
examples_with_empty_actions_num += 1
continue
example = DataEntry(idx, query_tokens, parse_tree, code, actions, {
'str_map': None,
'raw_code': entry['raw_code']
})
if can_fully_reconstructed:
can_fully_reconstructed_examples_num += 1
# train, valid, test splits
if 0 <= idx < 77495:
train_data.add(example)
elif idx < 77495 + 5171:
dev_data.add(example)
else:
test_data.add(example)
all_examples.append(example)
# print statistics
max_query_len = max(len(e.query) for e in all_examples)
max_actions_len = max(len(e.actions) for e in all_examples)
# serialize_to_file([len(e.query) for e in all_examples], 'query.len')
# serialize_to_file([len(e.actions) for e in all_examples], 'actions.len')
logging.info('train_data examples: %d', train_data.count)
logging.info('dev_data examples: %d', dev_data.count)
logging.info('test_data examples: %d', test_data.count)
logging.info('examples that can be fully reconstructed: %d/%d=%f',
can_fully_reconstructed_examples_num, len(all_examples),
can_fully_reconstructed_examples_num / len(all_examples))
logging.info('empty_actions_count: %d', examples_with_empty_actions_num)
logging.info('max_query_len: %d', max_query_len)
logging.info('max_actions_len: %d', max_actions_len)
train_data.init_data_matrices(max_query_length=40,
max_example_action_num=6)
dev_data.init_data_matrices()
test_data.init_data_matrices()
serialize_to_file((train_data, dev_data, test_data),
'data/ifttt.freq{WORD_FREQ_CUT_OFF}.bin'.format(
WORD_FREQ_CUT_OFF=WORD_FREQ_CUT_OFF))
return train_data, dev_data, test_data
def parse_train_dataset(args):
MAX_QUERY_LENGTH = 70 # FIXME: figure out the best config!
WORD_FREQ_CUT_OFF = 0
# nl_file = './data/mix.nl'
# sql_file = './data/mix-1.sql'
# data_file = './data/train.json'
# ast_file = './data/mix.json'
train_data = preprocess_sql_dataset(args.train_data, args.train_data_ast)
dev_data = preprocess_sql_dataset(args.dev_data, args.dev_data_ast)
test_data = preprocess_sql_dataset(args.test_data, args.test_data_ast)
data = train_data + dev_data + test_data
print("data size: {}".format(len(data)))
parse_trees = [e['parse_tree'] for e in data]
# apply unary closures
# unary_closures = get_top_unary_closures(parse_trees, k=20)
# for parse_tree in parse_trees:
# apply_unary_closures(parse_tree, unary_closures)
# build the grammar
grammar = get_grammar(parse_trees)
with open('sql.grammar.unary_closure.txt', 'w') as f:
for rule in grammar:
f.write(rule.__repr__() + '\n')
nl_tokens = list(chain(*[e['query_tokens'] for e in data]))
nl_vocab = gen_vocab(nl_tokens,
vocab_size=5000,
freq_cutoff=WORD_FREQ_CUT_OFF)
# enumerate all terminal tokens to build up the terminal tokens vocabulary
all_terminal_tokens = []
for entry in data:
parse_tree = entry['parse_tree']
for node in parse_tree.get_leaves():
if grammar.is_value_node(node):
terminal_val = node.value
terminal_str = str(terminal_val)
terminal_tokens = get_terminal_tokens(terminal_str)
for terminal_token in terminal_tokens:
assert len(terminal_token) > 0
all_terminal_tokens.append(terminal_token)
# print all_terminal_tokens
table_schema = args.table_schema
terminal_vocab = gen_vocab(all_terminal_tokens,
vocab_size=5000,
freq_cutoff=WORD_FREQ_CUT_OFF)
non_schema_vocab_size = terminal_vocab.size
db_dict, schema_vocab = load_table_schema_data(table_schema)
terminal_vocab = gen_schema_vocab(schema_vocab, terminal_vocab)
db_mask = gen_db_mask(terminal_vocab, non_schema_vocab_size, table_schema)
# print terminal_vocab
# now generate the dataset!
# print(terminal_vocab)
# print(terminal_vocab.token_id_map.keys())
train_data = DataSet(nl_vocab, terminal_vocab, grammar, db_mask,
'sql.train_data')
dev_data = DataSet(nl_vocab, terminal_vocab, grammar, db_mask,
'sql.dev_data')
test_data = DataSet(nl_vocab, terminal_vocab, grammar, db_mask,
'sql.test_data')
all_examples = []
can_fully_reconstructed_examples_num = 0
examples_with_empty_actions_num = 0
# print(list(terminal_vocab.iteritems()))
for index, entry in enumerate(data):
idx = entry['id']
query_tokens = entry['query_tokens']
code = entry['code']
parse_tree = entry['parse_tree']
rule_list, rule_parents = parse_tree.get_productions(
include_value_node=True)
actions = []
can_fully_reconstructed = True
rule_pos_map = dict()
for rule_count, rule in enumerate(rule_list):
# if rule_count == 116:
# continue
if not grammar.is_value_node(rule.parent):
assert rule.value is None, rule.value
parent_rule = rule_parents[(rule_count, rule)][0]
if parent_rule:
parent_t = rule_pos_map[parent_rule]
else:
parent_t = 0
rule_pos_map[rule] = len(actions)
d = {
'rule': rule,
'parent_t': parent_t,
'parent_rule': parent_rule
}
action = Action(APPLY_RULE, d)
actions.append(action)
else:
assert rule.is_leaf, (rule.type, rule.value, rule.label)
parent_rule = rule_parents[(rule_count, rule)][0]
parent_t = rule_pos_map[parent_rule]
terminal_val = rule.value
terminal_str = str(terminal_val)
terminal_tokens = get_terminal_tokens(terminal_str)
# assert len(terminal_tokens) > 0
for terminal_token in terminal_tokens:
term_tok_id = terminal_vocab[terminal_token]
tok_src_idx = -1
try:
tok_src_idx = query_tokens.index(terminal_token)
except ValueError:
pass
d = {
'literal': terminal_token,
'rule': rule,
'parent_rule': parent_rule,
'parent_t': parent_t
}
# cannot copy, only generation
# could be unk!
if tok_src_idx < 0 or tok_src_idx >= MAX_QUERY_LENGTH:
action = Action(GEN_TOKEN, d)
if terminal_token not in terminal_vocab:
if terminal_token not in query_tokens:
# print terminal_token
can_fully_reconstructed = False
else: # copy
if term_tok_id != terminal_vocab.unk:
d['source_idx'] = tok_src_idx
action = Action(GEN_COPY_TOKEN, d)
else:
d['source_idx'] = tok_src_idx
action = Action(COPY_TOKEN, d)
actions.append(action)
d = {
'literal': '<eos>',
'rule': rule,
'parent_rule': parent_rule,
'parent_t': parent_t
}
actions.append(Action(GEN_TOKEN, d))
if len(actions) == 0:
examples_with_empty_actions_num += 1
continue
mask = db_mask[entry['db_id']]
example = DataEntry(idx, query_tokens, parse_tree, code, actions, mask,
{
'str_map': None,
'raw_code': entry['raw_code']
})
if can_fully_reconstructed:
can_fully_reconstructed_examples_num += 1
# train, valid, test splits
if 0 <= index < args.train_data_size:
train_data.add(example)
elif index < args.train_data_size + args.dev_data_size:
dev_data.add(example)
else:
test_data.add(example)
all_examples.append(example)
# print("test data size {}".format(len(test_data)))
# print statistics
max_query_len = max(len(e.query) for e in all_examples)
max_actions_len = max(len(e.actions) for e in all_examples)
# serialize_to_file([len(e.query) for e in all_examples], 'query.len')
# serialize_to_file([len(e.actions) for e in all_examples], 'actions.len')
logging.info('examples that can be fully reconstructed: %d/%d=%f',
can_fully_reconstructed_examples_num, len(all_examples),
can_fully_reconstructed_examples_num / len(all_examples))
logging.info('empty_actions_count: %d', examples_with_empty_actions_num)
logging.info('max_query_len: %d', max_query_len)
logging.info('max_actions_len: %d', max_actions_len)
train_data.init_data_matrices(max_query_length=70,
max_example_action_num=350)
dev_data.init_data_matrices(max_query_length=70,
max_example_action_num=350)
test_data.init_data_matrices(max_query_length=70,
max_example_action_num=350)
# serialize_to_file((train_data, dev_data, test_data),
# './data/sql.freq{WORD_FREQ_CUT_OFF}.max_action350.pre_suf.unary_closure.bin'.format(WORD_FREQ_CUT_OFF=WORD_FREQ_CUT_OFF))
print("train data size:{}".format(train_data.count))
print("dev data size:{}".format(dev_data.count))
print("test data size:{}".format(test_data.count))
serialize_to_file((train_data, dev_data, test_data), args.output_path)
return train_data, dev_data, test_data
def parse_hs_dataset():
MAX_QUERY_LENGTH = 70 # FIXME: figure out the best config!
WORD_FREQ_CUT_OFF = 3
annot_file = '/Users/yinpengcheng/Research/SemanticParsing/CodeGeneration/card_datasets/hearthstone/all_hs.mod.in'
code_file = '/Users/yinpengcheng/Research/SemanticParsing/CodeGeneration/card_datasets/hearthstone/all_hs.out'
data = preprocess_hs_dataset(annot_file, code_file)
parse_trees = [e['parse_tree'] for e in data]
# apply unary closures
unary_closures = get_top_unary_closures(parse_trees, k=20)
for parse_tree in parse_trees:
apply_unary_closures(parse_tree, unary_closures)
# build the grammar
grammar = get_grammar(parse_trees)
with open('hs.grammar.unary_closure.txt', 'w') as f:
for rule in grammar:
f.write(rule.__repr__() + '\n')
annot_tokens = list(chain(*[e['query_tokens'] for e in data]))
annot_vocab = gen_vocab(annot_tokens,
vocab_size=5000,
freq_cutoff=WORD_FREQ_CUT_OFF)
def get_terminal_tokens(_terminal_str):
"""
get terminal tokens
break words like MinionCards into [Minion, Cards]
"""
tmp_terminal_tokens = [
t for t in _terminal_str.split(' ') if len(t) > 0
]
_terminal_tokens = []
for token in tmp_terminal_tokens:
sub_tokens = re.sub(r'([a-z])([A-Z])', r'\1 \2', token).split(' ')
_terminal_tokens.extend(sub_tokens)
_terminal_tokens.append(' ')
return _terminal_tokens[:-1]
# enumerate all terminal tokens to build up the terminal tokens vocabulary
all_terminal_tokens = []
for entry in data:
parse_tree = entry['parse_tree']
for node in parse_tree.get_leaves():
if grammar.is_value_node(node):
terminal_val = node.value
terminal_str = str(terminal_val)
terminal_tokens = get_terminal_tokens(terminal_str)
for terminal_token in terminal_tokens:
assert len(terminal_token) > 0
all_terminal_tokens.append(terminal_token)
terminal_vocab = gen_vocab(all_terminal_tokens,
vocab_size=5000,
freq_cutoff=WORD_FREQ_CUT_OFF)
# now generate the dataset!
train_data = DataSet(annot_vocab, terminal_vocab, grammar, 'hs.train_data')
dev_data = DataSet(annot_vocab, terminal_vocab, grammar, 'hs.dev_data')
test_data = DataSet(annot_vocab, terminal_vocab, grammar, 'hs.test_data')
all_examples = []
can_fully_reconstructed_examples_num = 0
examples_with_empty_actions_num = 0
for entry in data:
idx = entry['id']
query_tokens = entry['query_tokens']
code = entry['code']
parse_tree = entry['parse_tree']
rule_list, rule_parents = parse_tree.get_productions(
include_value_node=True)
actions = []
can_fully_reconstructed = True
rule_pos_map = dict()
for rule_count, rule in enumerate(rule_list):
if not grammar.is_value_node(rule.parent):
assert rule.value is None
parent_rule = rule_parents[(rule_count, rule)][0]
if parent_rule:
parent_t = rule_pos_map[parent_rule]
else:
parent_t = 0
rule_pos_map[rule] = len(actions)
d = {
'rule': rule,
'parent_t': parent_t,
'parent_rule': parent_rule
}
action = Action(APPLY_RULE, d)
actions.append(action)
else:
assert rule.is_leaf
parent_rule = rule_parents[(rule_count, rule)][0]
parent_t = rule_pos_map[parent_rule]
terminal_val = rule.value
terminal_str = str(terminal_val)
terminal_tokens = get_terminal_tokens(terminal_str)
# assert len(terminal_tokens) > 0
for terminal_token in terminal_tokens:
term_tok_id = terminal_vocab[terminal_token]
tok_src_idx = -1
try:
tok_src_idx = query_tokens.index(terminal_token)
except ValueError:
pass
d = {
'literal': terminal_token,
'rule': rule,
'parent_rule': parent_rule,
'parent_t': parent_t
}
# cannot copy, only generation
# could be unk!
if tok_src_idx < 0 or tok_src_idx >= MAX_QUERY_LENGTH:
action = Action(GEN_TOKEN, d)
if terminal_token not in terminal_vocab:
if terminal_token not in query_tokens:
# print terminal_token
can_fully_reconstructed = False
else: # copy
if term_tok_id != terminal_vocab.unk:
d['source_idx'] = tok_src_idx
action = Action(GEN_COPY_TOKEN, d)
else:
d['source_idx'] = tok_src_idx
action = Action(COPY_TOKEN, d)
actions.append(action)
d = {
'literal': '<eos>',
'rule': rule,
'parent_rule': parent_rule,
'parent_t': parent_t
}
actions.append(Action(GEN_TOKEN, d))
if len(actions) == 0:
examples_with_empty_actions_num += 1
continue
example = DataEntry(idx, query_tokens, parse_tree, code, actions, {
'str_map': None,
'raw_code': entry['raw_code']
})
if can_fully_reconstructed:
can_fully_reconstructed_examples_num += 1
# train, valid, test splits
if 0 <= idx < 533:
train_data.add(example)
elif idx < 599:
dev_data.add(example)
else:
test_data.add(example)
all_examples.append(example)
# print statistics
max_query_len = max(len(e.query) for e in all_examples)
max_actions_len = max(len(e.actions) for e in all_examples)
# serialize_to_file([len(e.query) for e in all_examples], 'query.len')
# serialize_to_file([len(e.actions) for e in all_examples], 'actions.len')
logging.info('examples that can be fully reconstructed: %d/%d=%f',
can_fully_reconstructed_examples_num, len(all_examples),
can_fully_reconstructed_examples_num / len(all_examples))
logging.info('empty_actions_count: %d', examples_with_empty_actions_num)
logging.info('max_query_len: %d', max_query_len)
logging.info('max_actions_len: %d', max_actions_len)
train_data.init_data_matrices(max_query_length=70,
max_example_action_num=350)
dev_data.init_data_matrices(max_query_length=70,
max_example_action_num=350)
test_data.init_data_matrices(max_query_length=70,
max_example_action_num=350)
serialize_to_file((
train_data, dev_data, test_data
), 'data/hs.freq{WORD_FREQ_CUT_OFF}.max_action350.pre_suf.unary_closure.bin'
.format(WORD_FREQ_CUT_OFF=WORD_FREQ_CUT_OFF))
return train_data, dev_data, test_data
def parse_hs_dataset():
MAX_QUERY_LENGTH = 70 # FIXME: figure out the best config!
WORD_FREQ_CUT_OFF = 3
annot_file = '/Users/yinpengcheng/Research/SemanticParsing/CodeGeneration/card_datasets/hearthstone/all_hs.mod.in'
code_file = '/Users/yinpengcheng/Research/SemanticParsing/CodeGeneration/card_datasets/hearthstone/all_hs.out'
data = preprocess_hs_dataset(annot_file, code_file)
parse_trees = [e['parse_tree'] for e in data]
# apply unary closures
unary_closures = get_top_unary_closures(parse_trees, k=20)
for parse_tree in parse_trees:
apply_unary_closures(parse_tree, unary_closures)
# build the grammar
grammar = get_grammar(parse_trees)
with open('hs.grammar.unary_closure.txt', 'w') as f:
for rule in grammar:
f.write(rule.__repr__() + '\n')
annot_tokens = list(chain(*[e['query_tokens'] for e in data]))
annot_vocab = gen_vocab(annot_tokens, vocab_size=5000, freq_cutoff=WORD_FREQ_CUT_OFF)
def get_terminal_tokens(_terminal_str):
"""
get terminal tokens
break words like MinionCards into [Minion, Cards]
"""
tmp_terminal_tokens = [t for t in _terminal_str.split(' ') if len(t) > 0]
_terminal_tokens = []
for token in tmp_terminal_tokens:
sub_tokens = re.sub(r'([a-z])([A-Z])', r'\1 \2', token).split(' ')
_terminal_tokens.extend(sub_tokens)
_terminal_tokens.append(' ')
return _terminal_tokens[:-1]
# enumerate all terminal tokens to build up the terminal tokens vocabulary
all_terminal_tokens = []
for entry in data:
parse_tree = entry['parse_tree']
for node in parse_tree.get_leaves():
if grammar.is_value_node(node):
terminal_val = node.value
terminal_str = str(terminal_val)
terminal_tokens = get_terminal_tokens(terminal_str)
for terminal_token in terminal_tokens:
assert len(terminal_token) > 0
all_terminal_tokens.append(terminal_token)
terminal_vocab = gen_vocab(all_terminal_tokens, vocab_size=5000, freq_cutoff=WORD_FREQ_CUT_OFF)
# now generate the dataset!
train_data = DataSet(annot_vocab, terminal_vocab, grammar, 'hs.train_data')
dev_data = DataSet(annot_vocab, terminal_vocab, grammar, 'hs.dev_data')
test_data = DataSet(annot_vocab, terminal_vocab, grammar, 'hs.test_data')
all_examples = []
can_fully_reconstructed_examples_num = 0
examples_with_empty_actions_num = 0
for entry in data:
idx = entry['id']
query_tokens = entry['query_tokens']
code = entry['code']
parse_tree = entry['parse_tree']
rule_list, rule_parents = parse_tree.get_productions(include_value_node=True)
actions = []
can_fully_reconstructed = True
rule_pos_map = dict()
for rule_count, rule in enumerate(rule_list):
if not grammar.is_value_node(rule.parent):
assert rule.value is None
parent_rule = rule_parents[(rule_count, rule)][0]
if parent_rule:
parent_t = rule_pos_map[parent_rule]
else:
parent_t = 0
rule_pos_map[rule] = len(actions)
d = {'rule': rule, 'parent_t': parent_t, 'parent_rule': parent_rule}
action = Action(APPLY_RULE, d)
actions.append(action)
else:
assert rule.is_leaf
parent_rule = rule_parents[(rule_count, rule)][0]
parent_t = rule_pos_map[parent_rule]
terminal_val = rule.value
terminal_str = str(terminal_val)
terminal_tokens = get_terminal_tokens(terminal_str)
# assert len(terminal_tokens) > 0
for terminal_token in terminal_tokens:
term_tok_id = terminal_vocab[terminal_token]
tok_src_idx = -1
try:
tok_src_idx = query_tokens.index(terminal_token)
except ValueError:
pass
d = {'literal': terminal_token, 'rule': rule, 'parent_rule': parent_rule, 'parent_t': parent_t}
# cannot copy, only generation
# could be unk!
if tok_src_idx < 0 or tok_src_idx >= MAX_QUERY_LENGTH:
action = Action(GEN_TOKEN, d)
if terminal_token not in terminal_vocab:
if terminal_token not in query_tokens:
# print terminal_token
can_fully_reconstructed = False
else: # copy
if term_tok_id != terminal_vocab.unk:
d['source_idx'] = tok_src_idx
action = Action(GEN_COPY_TOKEN, d)
else:
d['source_idx'] = tok_src_idx
action = Action(COPY_TOKEN, d)
actions.append(action)
d = {'literal': '<eos>', 'rule': rule, 'parent_rule': parent_rule, 'parent_t': parent_t}
actions.append(Action(GEN_TOKEN, d))
if len(actions) == 0:
examples_with_empty_actions_num += 1
continue
example = DataEntry(idx, query_tokens, parse_tree, code, actions, {'str_map': None, 'raw_code': entry['raw_code']})
if can_fully_reconstructed:
can_fully_reconstructed_examples_num += 1
# train, valid, test splits
if 0 <= idx < 533:
train_data.add(example)
elif idx < 599:
dev_data.add(example)
else:
test_data.add(example)
all_examples.append(example)
# print statistics
max_query_len = max(len(e.query) for e in all_examples)
max_actions_len = max(len(e.actions) for e in all_examples)
# serialize_to_file([len(e.query) for e in all_examples], 'query.len')
# serialize_to_file([len(e.actions) for e in all_examples], 'actions.len')
logging.info('examples that can be fully reconstructed: %d/%d=%f',
can_fully_reconstructed_examples_num, len(all_examples),
can_fully_reconstructed_examples_num / len(all_examples))
logging.info('empty_actions_count: %d', examples_with_empty_actions_num)
logging.info('max_query_len: %d', max_query_len)
logging.info('max_actions_len: %d', max_actions_len)
train_data.init_data_matrices(max_query_length=70, max_example_action_num=350)
dev_data.init_data_matrices(max_query_length=70, max_example_action_num=350)
test_data.init_data_matrices(max_query_length=70, max_example_action_num=350)
serialize_to_file((train_data, dev_data, test_data),
'data/hs.freq{WORD_FREQ_CUT_OFF}.max_action350.pre_suf.unary_closure.bin'.format(WORD_FREQ_CUT_OFF=WORD_FREQ_CUT_OFF))
return train_data, dev_data, test_data
