def predict_single(data):
response = []
predict_test_data = [
# "《中国风水十讲》是2007年华夏出版社出版的图书，作者是杨文衡",
# "你是最爱词:许常德李素珍/曲:刘天健你的故事写到你离去后为止",
# "《苏州商会档案丛编第二辑》是2012年华中师范大学出版社出版的图书，作者是马敏、祖苏、肖芃",
"广州珂妃化妆品有限公司创立于2005年，是一家集研发、生产、销售、服务为一体的多元化化妆品集团公司",
"吕雅堂（1907-）安徽寿县人，1926年10月南京中央军校第六期，后任国民革命军徐州剿总骑兵第一旅副旅长",
]
# num_actual_predict_examples = len(predict_test_data)
features = string_tokenizer(predict_test_data, label_list, max_seq_length,
tokenizer)
result = sess.run(fetches,
feed_dict={
'input_ids:0': features['input_ids'],
'input_mask:0': features['input_mask'],
'segment_ids:0': features['segment_ids']
})
for prediction in result:
prediction = prediction.tolist()
print("\n\n prediction:\n{}".format(prediction))
for idx, class_probability in enumerate(prediction):
predicate_predict = []
if class_probability > 0.5:
print(label_list[idx])
predicate_predict = []
predicate_predict.append(label_list[prediction.index(max(prediction))])
res = {"relations": predicate_predict}
response.append(res)
return json.dumps(response)
def predict_v1():
data = request.get_data()
json_data = json.loads(data.decode("utf-8"))
# 对不同数据进行切分，切分到小于max_raw_str_len
res = []
for doc in json_data["data"]:
segments = getSegments(doc)
# raw seg
# token
# token_unk
# predicate_ids
print("Total {} segments:\n{}".format(len(segments), segments))
features = string_tokenizer(segments, label_list, max_seq_length,
tokenizer)
result = sess.run(fetches,
feed_dict={
'input_ids:0': features['input_ids'],
'input_mask:0': features['input_mask'],
'segment_ids:0': features['segment_ids']
})
predicate_ids = []
for prediction in result:
prediction = prediction.tolist()
predicate_id = []
for idx, class_probability in enumerate(prediction):
predicate_predict = []
if class_probability > 0.5:
predicate_predict.append(label_list[idx])
predicate_id.append(idx)
predicate_ids.append(predicate_id)
# TODO: 其中某句话可能没有predicate，此时应该去除
seq_segments, seq_predicate_ids = [], []
for seg, pred in zip(segments, predicate_ids):
if len(pred) > 0:
seq_segments.append(seg)
seq_predicate_ids.append(pred)
triples = []
if len(seq_segments) > 0:
features_seq = sequence_tokenizer(seq_segments, seq_predicate_ids,
label_list, max_seq_length,
tokenizer)
# print("\nfeatures_seq:\n{}\n\n".format(features_seq))
seq_result = sess_seq.run(
# TODO: 是否可以只跑fetches_seq【3】
fetches_seq,
feed_dict={
'input_ids:0': features_seq['input_ids'],
'input_mask:0': features_seq['input_mask'],
'segment_ids:0': features_seq['segment_ids']
})
seq_label_result = seq_result[2]
# for token_label_prediction in seq_label_result:
# token_label_output_line = " ".join(token_label_id2label[id] for id in token_label_prediction)
# print("raw out:\n{}".format(token_label_prediction))
# print("label out:\n{}".format(token_label_output_line))
# print("\n")
res_index = 0
for (i, src) in enumerate(seq_segments):
for predicate_id in seq_predicate_ids[i]:
pred = label_list[predicate_id]
trps = getTriples_v1(seq_label_result[res_index], src,
pred)
triples.extend(trps)
res_index += 1
# print("triples: {}".format(triples))
res.append(triples)
return json.dumps(res, ensure_ascii=False)
def predict_pipline(data):
response = []
predict_test_data = [
# "《中国风水十讲》是2007年华夏出版社出版的图书，作者是杨文衡",
# "你是最爱词:许常德李素珍/曲:刘天健你的故事写到你离去后为止",
# "《苏州商会档案丛编第二辑》是2012年华中师范大学出版社出版的图书，作者是马敏、祖苏、肖芃",
"广州珂妃化妆品有限公司创立于2005年，是一家集研发、生产、销售、服务为一体的多元化化妆品集团公司",
"吕雅堂（1907-）安徽寿县人，1926年10月南京中央军校第六期，后任国民革命军徐州剿总骑兵第一旅副旅长",
]
# num_actual_predict_examples = len(predict_test_data)
features = string_tokenizer(predict_test_data, label_list, max_seq_length,
tokenizer)
result = sess.run(fetches,
feed_dict={
'input_ids:0': features['input_ids'],
'input_mask:0': features['input_mask'],
'segment_ids:0': features['segment_ids']
})
predicate_ids = []
for prediction in result:
prediction = prediction.tolist()
print("\n\n prediction:\n{}".format(prediction))
predicate_id = []
for idx, class_probability in enumerate(prediction):
predicate_predict = []
if class_probability > 0.5:
predicate_predict.append(label_list[idx])
predicate_id.append(idx)
predicate_ids.append(predicate_id)
res = {"relations": predicate_predict}
response.append(res)
features_seq = sequence_tokenizer(predict_test_data, predicate_ids,
label_list, max_seq_length, tokenizer)
seq_result = sess_seq.run(fetches_seq,
feed_dict={
'input_ids:0': features_seq['input_ids'],
'input_mask:0': features_seq['input_mask'],
'segment_ids:0': features_seq['segment_ids']
})
seq_label_result = seq_result[2]
for token_label_prediction in seq_label_result:
token_label_output_line = " ".join(token_label_id2label[id]
for id in token_label_prediction)
print("raw out:\n{}".format(token_label_prediction))
print("label out:\n{}".format(token_label_output_line))
print("\n")
res_index = 0
triples = []
for (i, src) in enumerate(predict_test_data):
for predicate_id in predicate_ids[i]:
pred = label_list[predicate_id]
# sub, obj = getS
# obj =
trps = getTriples_v1(seq_label_result[res_index], src, pred)
triples.extend(trps)
res_index += 1
# print("seq result: {}".format(seq_label_result))
print("triples: {}".format(triples))
return json.dumps(triples, ensure_ascii=False)