def slda_infer():
category = request.form['category']
in_type = request.form['type']
f_text = input_doc_str(in_type)
inference_engine_wrapper = InferenceEngineWrapper(get_model_dir(category),
get_slda_conf())
seg_list = inference_engine_wrapper.tokenize(f_text)
sentences = []
length = len(seg_list)
for index in range(0, length, 5):
sentences.append(seg_list[index:index + 5])
topic_dist = inference_engine_wrapper.slda_infer(sentences)
return json_format(topic_dist)
def doc_topic_word_slda():
category = request.form['category']
in_type = request.form['type']
f_text = input_doc_str(in_type)
inference_engine_wrapper = InferenceEngineWrapper(get_model_dir(category),
get_slda_conf())
seg_list = inference_engine_wrapper.tokenize(f_text)
sentences = []
length = len(seg_list)
for index in range(0, length, 5):
sentences.append(seg_list[index:index + 5])
topic_dist = inference_engine_wrapper.slda_infer(sentences)
result = {}
for key, value in dict(topic_dist).items():
twe_wrapper = TopicalWordEmbeddingsWrapper(get_model_dir(category),
get_emb_file(category))
result_dict = dict(
twe_wrapper.nearest_words_around_topic(int(key), get_count()))
result[value] = result_dict
return json.dumps(result)
import sys
from familia_wrapper import InferenceEngineWrapper
if sys.version_info < (3, 0):
input = raw_input
if __name__ == '__main__':
if len(sys.argv) < 3:
sys.stderr.write("Usage:python {} {} {}\n".format(
sys.argv[0], "model_dir", "conf_file"))
exit(-1)
# 获取参数
model_dir = sys.argv[1]
conf_file = sys.argv[2]
# 创建InferenceEngineWrapper对象
inference_engine_wrapper = InferenceEngineWrapper(model_dir, conf_file)
while True:
input_text = input("Enter Document: ")
# 分词
seg_list = inference_engine_wrapper.tokenize(input_text.strip())
# 构建句子结构,5个词为一个句子
sentences = []
length = len(seg_list)
for index in range(0, length, 5):
sentences.append(seg_list[index:index + 5])
# 进行推断
topic_dist = inference_engine_wrapper.slda_infer(sentences)
# 打印结果
print("Document Topic Distribution:")
print(topic_dist)
import sys
from familia_wrapper import InferenceEngineWrapper
if sys.version_info < (3,0):
input = raw_input
if __name__ == '__main__':
if len(sys.argv) < 3:
sys.stderr.write("Usage:python {} {} {}\n".format(
sys.argv[0], "model_dir", "conf_file"))
exit(-1)
# 获取参数
model_dir = sys.argv[1]
conf_file = sys.argv[2]
# 创建InferenceEngineWrapper对象
inference_engine_wrapper = InferenceEngineWrapper(model_dir, conf_file)
while True:
input_text = input("Enter Document: ")
# 分词
seg_list = inference_engine_wrapper.tokenize(input_text.strip())
# 构建句子结构,5个词为一个句子
sentences = []
length = len(seg_list)
for index in range(0, length, 5):
sentences.append(seg_list[index: index + 5])
# 进行推断
topic_dist = inference_engine_wrapper.slda_infer(sentences)
# 打印结果
print("Document Topic Distribution:")
print(topic_dist)