def DemoConsole(graph, utility, sess, model_dir, dat):
i = 0
print("Listening to incoming questions...")
while (True):
question_id = 'iac-' + str(i)
table_key = raw_input("> What table do you want? \n")
table_key = "csv/custom-csv/" + table_key + ".csv"
while (True):
tokens = raw_input("> ")
print("\n")
if tokens == 'new':
break
print("Question:", tokens, "Table:", table_key)
example = dat.load_example(question_id, tokens, table_key)
data = [example]
data_utils.construct_vocab(data, utility, True)
final_data = data_utils.complete_wiki_processing(data, utility, 'demo')
answer = get_prediction(sess, final_data, graph, utility)
final_answer = ''
certainty = answer[2]
if answer[1] == 'scalar':
final_answer = str(answer[0][0])
debugging = str(answer[0][1])
else:
print(answer)
a = answer[0][0][0]
row = a[1][0]
col = a[2]
if col < 15:
list_answer = dat.custom_tables[table_key].number_columns[col][row]
else:
list_answer = dat.custom_tables[table_key].word_columns[col-15][row]
if type(list_answer) == float:
final_answer = str(list_answer)
else:
for l in list_answer:
final_answer += " " + str(l)
print("\n")
if (certainty < FLAGS.certainty_threshold):
print("> I do not know the answer to your question, although I would say..." + "\n")
print "> " + final_answer + "\n"
i += 1
def main(args):
utility = Utility()
train_name = "random-split-1-train.examples"
dev_name = "random-split-1-dev.examples"
test_name = "pristine-unseen-tables.examples"
#load data
dat = wiki_data.WikiQuestionGenerator(train_name, dev_name, test_name, FLAGS.data_dir)
train_data, dev_data, test_data = dat.load()
utility.words = []
utility.word_ids = {}
utility.reverse_word_ids = {}
#construct vocabulary
data_utils.construct_vocab(train_data, utility)
data_utils.construct_vocab(dev_data, utility, True)
data_utils.construct_vocab(test_data, utility, True)
data_utils.add_special_words(utility)
data_utils.perform_word_cutoff(utility)
#convert data to int format and pad the inputs
train_data = data_utils.complete_wiki_processing(train_data, utility, True)
dev_data = data_utils.complete_wiki_processing(dev_data, utility, False)
test_data = data_utils.complete_wiki_processing(test_data, utility, False)
print "# train examples ", len(train_data)
print "# dev examples ", len(dev_data)
print "# test examples ", len(test_data)
print "running open source"
#construct TF graph and train or evaluate
master(train_data, dev_data, utility)
def main(args):
utility = Utility()
train_name = "random-split-1-train.examples"
dev_name = "random-split-1-dev.examples"
test_name = "pristine-unseen-tables.examples"
#load data
dat = wiki_data.WikiQuestionGenerator(train_name, dev_name, test_name,
FLAGS.data_dir)
train_data, dev_data, test_data = dat.load()
utility.words = []
utility.word_ids = {}
utility.reverse_word_ids = {}
#construct vocabulary
data_utils.construct_vocab(train_data, utility)
data_utils.construct_vocab(dev_data, utility, True)
data_utils.construct_vocab(test_data, utility, True)
data_utils.add_special_words(utility)
data_utils.perform_word_cutoff(utility)
#convert data to int format and pad the inputs
train_data = data_utils.complete_wiki_processing(train_data, utility, True)
dev_data = data_utils.complete_wiki_processing(dev_data, utility, False)
test_data = data_utils.complete_wiki_processing(test_data, utility, False)
print "# train examples ", len(train_data)
print "# dev examples ", len(dev_data)
print "# test examples ", len(test_data)
print "running open source"
#construct TF graph and train or evaluate
master(train_data, dev_data, utility)
def Test(graph, utility, batch_size, sess, model_dir, dat, file_name):
ids, questions, table_keys, answers = wiki_data.load_custom_questions(file_name)
data = []
for i in range(len(questions)):
example = dat.load_example(ids[i], questions[i], table_keys[i])
data.append(example)
data_utils.construct_vocab(data, utility, True)
final_data = data_utils.complete_wiki_processing(data, utility, 'demo')
predictions = evaluate_custom(sess, final_data, answers, batch_size, graph, table_keys[0], dat)
total = len(predictions)
correct = 0.0
for i in range(total):
if predictions[i] == answers[i]:
correct += 1
else:
print(questions[i], predictions[i], answers[i])
accuracy = (correct / total) * 100
print("Total test cases:", total)
print("Correct answers:", correct)
print("Accuracy:", accuracy)
def init_data(
data_dir,
preserve_vocab=False,
split_filenames={
'train': 'random-split-1-train.examples',
'dev': 'random-split-1-dev.examples',
'test': 'pristine-unseen-tables.examples'
},
annotated_filenames={
'train': 'training.annotated',
'test': 'pristine-unseen-tables.annotated'
}):
""" Load WikiTableQuestions data.
preserve_vocab is used when perturbed data is loaded,
in which case special words are given hard-coded ids
to match that of the unperturbed data case
"""
utility = Utility()
train_name = split_filenames['train']
dev_name = split_filenames['dev']
test_name = split_filenames['test']
# load data
dat = wiki_data.WikiQuestionGenerator(train_name, dev_name, test_name,
data_dir)
train_data, dev_data, test_data = dat.load(annotated_filenames)
utility.words = []
utility.word_ids = {}
utility.reverse_word_ids = {}
# construct vocabulary
data_utils.construct_vocab(train_data, utility)
data_utils.construct_vocab(dev_data, utility, True)
data_utils.construct_vocab(test_data, utility, True)
data_utils.add_special_words(utility)
# set absolute word_ids for special words
if preserve_vocab:
print("hardcoded ids for special words")
word_to_swap = utility.reverse_word_ids[9133]
word_id_to_swap = utility.word_ids[utility.entry_match_token]
utility.word_ids[word_to_swap] = utility.word_ids[
utility.entry_match_token]
utility.word_ids[utility.entry_match_token] = 9133
utility.entry_match_token_id = utility.word_ids[
utility.entry_match_token]
utility.reverse_word_ids[word_id_to_swap] = word_to_swap
utility.reverse_word_ids[9133] = utility.entry_match_token
word_to_swap = utility.reverse_word_ids[9134]
word_id_to_swap = utility.word_ids[utility.column_match_token]
utility.word_ids[word_to_swap] = utility.word_ids[
utility.column_match_token]
utility.word_ids[utility.column_match_token] = 9134
utility.column_match_token_id = utility.word_ids[
utility.column_match_token]
utility.reverse_word_ids[word_id_to_swap] = word_to_swap
utility.reverse_word_ids[9134] = utility.column_match_token
word_to_swap = utility.reverse_word_ids[9135]
word_id_to_swap = utility.word_ids[utility.dummy_token]
utility.word_ids[word_to_swap] = utility.word_ids[utility.dummy_token]
utility.word_ids[utility.dummy_token] = 9135
utility.dummy_token_id = utility.word_ids[utility.dummy_token]
utility.reverse_word_ids[word_id_to_swap] = word_to_swap
utility.reverse_word_ids[9135] = utility.dummy_token
word_to_swap = utility.reverse_word_ids[9136]
word_id_to_swap = utility.word_ids[utility.unk_token]
utility.word_ids[word_to_swap] = utility.word_ids[utility.unk_token]
utility.word_ids[utility.unk_token] = 9136
utility.unk_token_id = utility.word_ids[utility.unk_token]
utility.reverse_word_ids[word_id_to_swap] = word_to_swap
utility.reverse_word_ids[9136] = utility.unk_token
print(utility.entry_match_token_id, utility.column_match_token_id,
utility.dummy_token_id, utility.unk_token_id)
data_utils.perform_word_cutoff(utility)
unprocessed_dev_data = copy.deepcopy(dev_data)
# convert data to int format and pad the inputs
train_data = data_utils.complete_wiki_processing(train_data, utility, True)
dev_data = data_utils.complete_wiki_processing(dev_data, utility, False)
test_data = data_utils.complete_wiki_processing(test_data, utility, False)
print(("# train examples ", len(train_data)))
print(("# dev examples ", len(dev_data)))
print(("# test examples ", len(test_data)))
return train_data, dev_data, test_data, utility, unprocessed_dev_data
def Demo(graph, utility, sess, model_dir, dat):
i = 0
s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
s.bind((config.socket_address, config.socket_port))
s.listen(1)
print("Listening to incoming questions...")
while (True):
conn, addr = s.accept()
data = conn.recv(1024).decode("utf-8").split("****----****")
table_key = data[0]
tokens = data[1]
question_id = 'iac-' + str(i)
print("Question:", tokens, "Table:", table_key)
example = dat.load_example(question_id, tokens, table_key)
data = [example]
data_utils.construct_vocab(data, utility, True)
final_data = data_utils.complete_wiki_processing(data, utility, 'demo')
answer = get_prediction(sess, final_data, graph, utility)
final_answer = ''
certainty = answer[2]
if answer[1] == 'scalar':
final_answer = str(answer[0][0])
debugging = answer[0][1]
debugging['answer_neural'].append(int(answer[0][0]))
else:
print("Debugging in MODEL:")
a = answer[0][0][0]
debugging = answer[0][1]
print(debugging)
rows = a[1]
col = a[2]
rows_answer = []
for row in rows:
row_answer = ''
if col < 15:
list_answer = dat.custom_tables[table_key].number_columns[col][row]
else:
list_answer = dat.custom_tables[table_key].word_columns[col-15][row]
if type(list_answer) == float:
debugging['answer_neural'].append(list_answer)
row_answer = str(list_answer)
else:
for l in list_answer:
row_answer += " " + str(l)
debugging['answer_neural'].append(row_answer[1:])
rows_answer.append(row_answer)
final_answer = ','.join(rows_answer)
print("Answer:", final_answer + "\n")
if (certainty < FLAGS.certainty_threshold):
print("I do not know the answer to your question, although that would be my guess.")
debugging['below_threshold'] = True
final_answer = "I cannot answer that question with the information in the table."
result = {"answer": final_answer, "debugging": debugging}
result = str(result)
i += 1
conn.send(result.encode())
conn.close()
