Esempio n. 1
0
def query_doc_sim():
    category = request.form['category']
    in_type = request.form['type']
    if in_type == 'doc':
        f1 = request.files['text1']
        f2 = request.files['text2']
        if save_file(f1) and save_file(f2):
            f_text1 = read_file(f1)
            f_text2 = read_file(f2)
    else:
        f_text1 = request.form['text1'].encode('utf-8').strip()
        f_text2 = request.form['text2'].encode('utf-8').strip()

    inference_engine_wrapper = InferenceEngineWrapper(get_model_dir(category),
                                                      get_lda_conf(),
                                                      get_emb_file(category))
    doc1_seg = inference_engine_wrapper.tokenize(f_text1)
    doc2_seg = inference_engine_wrapper.tokenize(f_text2)
    distances = inference_engine_wrapper.cal_query_doc_similarity(
        doc1_seg, doc2_seg)

    return json.dumps(
        {
            "LDA Similarity": distances[0],
            "TWE Similarity": distances[1]
        },
        ensure_ascii=False)
Esempio n. 2
0
import sys
from familia_wrapper import InferenceEngineWrapper

if sys.version_info < (3, 0):
    input = raw_input

if __name__ == '__main__':
    if len(sys.argv) < 4:
        sys.stderr.write("Usage:python {} {} {} {}.\n".format(
            sys.argv[0], "model_dir", "conf_file", "emb_file"))
        exit(-1)

    # 获取参数
    model_dir = sys.argv[1]
    conf_file = sys.argv[2]
    emb_file = sys.argv[3]
    # 创建InferenceEngineWrapper对象
    inference_engine_wrapper = InferenceEngineWrapper(model_dir, conf_file,
                                                      emb_file)
    while True:
        # 输入短文本和长文本
        query = input("Enter Query: ").strip()
        doc = input("Enter Document: ").strip()
        query_seg = inference_engine_wrapper.tokenize(query)
        doc_seg = inference_engine_wrapper.tokenize(doc)
        distances = inference_engine_wrapper.cal_query_doc_similarity(
            query_seg, doc_seg)
        # 打印结果
        print("LDA Similarity = {}".format(distances[0]))
        print("TWE similarity = {}".format(distances[1]))
Esempio n. 3
0
# 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) < 4:
        sys.stderr.write("Usage:python {} {} {} {}.\n".format(
            sys.argv[0], "model_dir", "conf_file", "emb_file"))
        exit(-1)

    # 获取参数
    model_dir = sys.argv[1]
    conf_file = sys.argv[2]
    emb_file = sys.argv[3]
    # 创建InferenceEngineWrapper对象
    inference_engine_wrapper = InferenceEngineWrapper(model_dir, conf_file, emb_file)
    while True:
        # 输入短文本和长文本
        query = input("Enter Query: ").strip()
        doc = input("Enter Document: ").strip()
        distances = inference_engine_wrapper.cal_query_doc_similarity(query, doc)
        # 打印结果
        print("LDA Similarity = {}".format(distances[0]))
        print("TWE similarity = {}".format(distances[1]))