def lda_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_lda_conf())
seg_list = inference_engine_wrapper.tokenize(f_text)
topic_dist = inference_engine_wrapper.lda_infer(seg_list)
return json_format(topic_dist)
def doc_topic_word_lda():
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_lda_conf())
seg_list = inference_engine_wrapper.tokenize(f_text)
topic_dist = inference_engine_wrapper.lda_infer(seg_list)
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)
result.append(ent)
return result
if __name__ == '__main__':
path = '/media/iiip/数据/duanduan/data/validation.csv'
documents = read_whole_file(path)
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)
topic_result = {}
for key in documents:
print key
seg_list = inference_engine_wrapper.tokenize(documents[key])
# 进行推断
topic_dist = inference_engine_wrapper.lda_infer(seg_list)
topic_result[key] = cal_topic(topic_dist)
file = open(path.replace(".csv", "_topic.csv"), 'w')
writer = csv.writer(file)
for each in topic_result:
writer.writerow([each, topic_result[each][0], topic_result[each][1]])
file.close()
# return topic_result
# Use of this source code is governed by a BSD-style license that can be # found in the LICENSE file. # # Author: [email protected] 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) # 进行推断 topic_dist = inference_engine_wrapper.lda_infer(seg_list) # 打印结果 print("Document Topic Distribution:") print(topic_dist)