├── .gitignore
├── KMeans_Topic_Select.py
├── LDA_Topic_Select.py
├── LICENSE
├── Project_Main.py
├── README.md
├── commit_processing.py
├── data
├── geo_data.csv
├── label_comment.csv
├── sentence_cut.txt
├── text_resource.txt
└── xiecheng_ugc.csv
├── model_saved
└── init.py
├── pic
├── gaopin1.png
├── ip.png
├── lda_topic_select.png
├── lda_topic_select1.png
├── poi可视化.png
├── poi打分.png
├── 不一致.png
├── 主题.png
├── 各主题分数.png
├── 地址.png
├── 情感分析图.png
├── 数据库.png
├── 文本分类.png
├── 模型对比.png
├── 模型对比2.png
├── 流程.png
├── 结构1.png
└── 高频2.png
├── requirement.txt
├── sa_analysis.py
├── sa_model_predict.py
├── sa_model_train.py
└── setting.py
/.gitignore:
--------------------------------------------------------------------------------
1 | # Created by .ignore support plugin (hsz.mobi)
2 | ### Example user template template
3 |
4 | # IntelliJ project files
5 | .idea
6 | *.iml
7 | out
8 | gen
9 | __pycache__/
10 | model/__pycache__
11 | ### Python template
12 | # Byte-compiled / optimized / DLL files
13 | __pycache__/
14 | *.py[cod]
15 | *$py.class
16 | # C extensions
17 | *.so
18 |
19 | # Distribution / packaging
20 | .Python
21 | build/
22 | develop-eggs/
23 | dist/
24 | downloads/
25 | eggs/
26 | .eggs/
27 | lib/
28 | lib64/
29 | parts/
30 | sdist/
31 | var/
32 | wheels/
33 | pip-wheel-metadata/
34 | share/python-wheels/
35 | *.egg-info/
36 | .installed.cfg
37 | *.egg
38 | MANIFEST
39 |
40 | # PyInstaller
41 | # Usually these files are written by a python script from a template
42 | # before PyInstaller builds the exe, so as to inject date/other infos into it.
43 | *.manifest
44 | *.spec
45 |
46 | # Installer logs
47 | pip-log.txt
48 | pip-delete-this-directory.txt
49 |
50 | # Unit test / coverage reports
51 | htmlcov/
52 | .tox/
53 | .nox/
54 | .coverage
55 | .coverage.*
56 | .cache
57 | nosetests.xml
58 | coverage.xml
59 | *.cover
60 | .hypothesis/
61 | .pytest_cache/
62 |
63 | # Translations
64 | *.mo
65 | *.pot
66 |
67 | # Django stuff:
68 | *.log
69 | local_settings.py
70 | db.sqlite3
71 |
72 | # Flask stuff:
73 | instance/
74 | .webassets-cache
75 |
76 | # Scrapy stuff:
77 | .scrapy
78 |
79 | # Sphinx documentation
80 | docs/_build/
81 |
82 | # PyBuilder
83 | target/
84 |
85 | # Jupyter Notebook
86 | .ipynb_checkpoints
87 |
88 | # IPython
89 | profile_default/
90 | ipython_config.py
91 |
92 | # pyenv
93 | .python-version
94 |
95 | # pipenv
96 | # According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
97 | # However, in case of collaboration, if having platform-specific dependencies or dependencies
98 | # having no cross-platform support, pipenv may install dependencies that don't work, or not
99 | # install all needed dependencies.
100 | #Pipfile.lock
101 |
102 | # celery beat schedule file
103 | celerybeat-schedule
104 |
105 | # SageMath parsed files
106 | *.sage.py
107 |
108 | # Environments
109 | .env
110 | .venv
111 | env/
112 | venv/
113 | ENV/
114 | env.bak/
115 | venv.bak/
116 |
117 | # Spyder project settings
118 | .spyderproject
119 | .spyproject
120 |
121 | # Rope project settings
122 | .ropeproject
123 |
124 | # mkdocs documentation
125 | /site
126 |
127 | # mypy
128 | .mypy_cache/
129 | .dmypy.json
130 | dmypy.json
131 |
132 | # Pyre type checker
133 | .pyre/
134 |
135 | ### Example user template template
136 | ### Example user template
137 |
138 | # IntelliJ project files
139 | .idea
140 | *.iml
141 | out
142 | gen
143 |
--------------------------------------------------------------------------------
/KMeans_Topic_Select.py:
--------------------------------------------------------------------------------
1 | # -*- coding: utf-8 -*-
2 | # @USER: CarryChang
--------------------------------------------------------------------------------
/LDA_Topic_Select.py:
--------------------------------------------------------------------------------
1 | # -*- coding: utf-8 -*-
2 | # @USER: CarryChang
3 | from sklearn.feature_extraction.text import CountVectorizer
4 | from gensim.corpora.dictionary import Dictionary
5 | # 加载 LDA 模型库
6 | from gensim.models.ldamodel import LdaModel
7 | # 加载计算 LDA 模型的评估库
8 | from gensim.models.coherencemodel import CoherenceModel
9 | # 加载 LDA 主题模型
10 | from sklearn.decomposition import LatentDirichletAllocation
11 | import matplotlib.pyplot as plt
12 | import jieba.posseg as pseg
13 | from tqdm import tqdm
14 | import numpy as np
15 | from setting import *
16 | # 分词器预热
17 | list(pseg.cut('垃圾饭店'))
18 |
19 | # 定义处理函数
20 | def get_n_filter(sentence_list):
21 | # 提取语料提取后的名词
22 | n_filter_list = list()
23 | for sentence_ in tqdm(sentence_list):
24 | n_filter = list()
25 | words = pseg.cut(sentence_)
26 | for word, flag in words:
27 | # 过滤长度大于 1 的名词
28 | if 'n' in flag and len(word) > 1:
29 | n_filter.append(word)
30 | n_filter_list.append(n_filter)
31 | return n_filter_list
32 | def topic_number_search():
33 | # 设初始的主题数 start_topic_number
34 | start_topic_number = 1
35 | # 设置最大的主题数 topic_numbers_max
36 | topic_numbers_max = 10
37 | # 收集模型分数
38 | error_list = list()
39 | # 定义主题数搜索列表，每次计算差距 2 个 topic
40 | topics_list = list(range(start_topic_number, topic_numbers_max + 1, 2))
41 | for topic_numbers in tqdm(topics_list):
42 | lda_model = LdaModel(corpus=corpus,
43 | id2word=dictionary,
44 | num_topics=topic_numbers)
45 | # 计算主题模型的分数
46 | CM = CoherenceModel(
47 | model=lda_model,
48 | texts=data_comment_n,
49 | dictionary=dictionary, )
50 | # 收集不同主题数下的一致性分数
51 | error_list.append(CM.get_coherence())
52 | return error_list, topics_list
53 | def best_lda_trian():
54 | # 使用 best_topic_numbers 作为主题数，其余参数均使用默认即可
55 | best_lda_model = LatentDirichletAllocation(n_components=best_topic_numbers)
56 | # 开始训练 LDA 模型
57 | best_lda_model.fit(n_comment_count_vec)
58 | # 设置每个主题下关联的主题词数量
59 | topic_words_numbers = 30
60 | # 获取所有的词典中的词语
61 | feature_names = n_count_vectorizer.get_feature_names()
62 | # 打印每个主题和附属的主题词
63 | for topic_idx, topic in enumerate(best_lda_model.components_):
64 | print("Topic # {}: ".format(int(topic_idx)))
65 | print(" ".join([feature_names[i] for i in topic.argsort()[:-topic_words_numbers - 1:-1]]))
66 |
67 | def topic_vis():
68 | # 横坐标表示聚类点
69 | plt.xlabel('topic_number')
70 | # 纵坐标表示一致性分数
71 | plt.ylabel('coherence_score')
72 | # 对主题数进行标注
73 | plt.plot(topics_list, error_list, '*-')
74 | plt.show()
75 |
76 | if __name__ == '__main__':
77 | import pandas as pd
78 | data = pd.read_csv('data/xiecheng_ugc.csv')
79 | # 对用户评论进行名词标注
80 | data['comment_n'] = get_n_filter(data['content'].tolist())
81 | data_comment_n = data['comment_n'].tolist()
82 | n_count_vectorizer = CountVectorizer(max_features=n_features)
83 | # 对用户评价中的名词进行字典转换
84 | n_comment_count_vec = n_count_vectorizer.fit_transform([str(i) for i in data_comment_n])
85 | # 生成统计词典
86 | dictionary = Dictionary(data_comment_n)
87 | # 利用词典对生成每个词进行字典向量化
88 | corpus = [dictionary.doc2bow(text) for text in data_comment_n]
89 | # 开始搜素最佳主题数
90 | error_list, topics_list = topic_number_search()
91 | # 开始对主题数量进行可视化
92 | topic_vis()
93 | # 求得最大一致性分数所在的索引
94 | max_score_index = np.argmax(error_list)
95 | # 根据最大的值的索引找到最佳的主题数
96 | best_topic_numbers = topics_list[max_score_index]
97 | print('找到最佳的主题数为：{}'.format(best_topic_numbers))
98 | # 使用找到的最佳主题数进行主题模型训练
99 | best_lda_trian()
--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
1 | Apache License
2 | Version 2.0, January 2004
3 | http://www.apache.org/licenses/
4 |
5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
6 |
7 | 1. Definitions.
8 |
9 | "License" shall mean the terms and conditions for use, reproduction,
10 | and distribution as defined by Sections 1 through 9 of this document.
11 |
12 | "Licensor" shall mean the copyright owner or entity authorized by
13 | the copyright owner that is granting the License.
14 |
15 | "Legal Entity" shall mean the union of the acting entity and all
16 | other entities that control, are controlled by, or are under common
17 | control with that entity. For the purposes of this definition,
18 | "control" means (i) the power, direct or indirect, to cause the
19 | direction or management of such entity, whether by contract or
20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the
21 | outstanding shares, or (iii) beneficial ownership of such entity.
22 |
23 | "You" (or "Your") shall mean an individual or Legal Entity
24 | exercising permissions granted by this License.
25 |
26 | "Source" form shall mean the preferred form for making modifications,
27 | including but not limited to software source code, documentation
28 | source, and configuration files.
29 |
30 | "Object" form shall mean any form resulting from mechanical
31 | transformation or translation of a Source form, including but
32 | not limited to compiled object code, generated documentation,
33 | and conversions to other media types.
34 |
35 | "Work" shall mean the work of authorship, whether in Source or
36 | Object form, made available under the License, as indicated by a
37 | copyright notice that is included in or attached to the work
38 | (an example is provided in the Appendix below).
39 |
40 | "Derivative Works" shall mean any work, whether in Source or Object
41 | form, that is based on (or derived from) the Work and for which the
42 | editorial revisions, annotations, elaborations, or other modifications
43 | represent, as a whole, an original work of authorship. For the purposes
44 | of this License, Derivative Works shall not include works that remain
45 | separable from, or merely link (or bind by name) to the interfaces of,
46 | the Work and Derivative Works thereof.
47 |
48 | "Contribution" shall mean any work of authorship, including
49 | the original version of the Work and any modifications or additions
50 | to that Work or Derivative Works thereof, that is intentionally
51 | submitted to Licensor for inclusion in the Work by the copyright owner
52 | or by an individual or Legal Entity authorized to submit on behalf of
53 | the copyright owner. For the purposes of this definition, "submitted"
54 | means any form of electronic, verbal, or written communication sent
55 | to the Licensor or its representatives, including but not limited to
56 | communication on electronic mailing lists, source code control systems,
57 | and issue tracking systems that are managed by, or on behalf of, the
58 | Licensor for the purpose of discussing and improving the Work, but
59 | excluding communication that is conspicuously marked or otherwise
60 | designated in writing by the copyright owner as "Not a Contribution."
61 |
62 | "Contributor" shall mean Licensor and any individual or Legal Entity
63 | on behalf of whom a Contribution has been received by Licensor and
64 | subsequently incorporated within the Work.
65 |
66 | 2. Grant of Copyright License. Subject to the terms and conditions of
67 | this License, each Contributor hereby grants to You a perpetual,
68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
69 | copyright license to reproduce, prepare Derivative Works of,
70 | publicly display, publicly perform, sublicense, and distribute the
71 | Work and such Derivative Works in Source or Object form.
72 |
73 | 3. Grant of Patent License. Subject to the terms and conditions of
74 | this License, each Contributor hereby grants to You a perpetual,
75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable
76 | (except as stated in this section) patent license to make, have made,
77 | use, offer to sell, sell, import, and otherwise transfer the Work,
78 | where such license applies only to those patent claims licensable
79 | by such Contributor that are necessarily infringed by their
80 | Contribution(s) alone or by combination of their Contribution(s)
81 | with the Work to which such Contribution(s) was submitted. If You
82 | institute patent litigation against any entity (including a
83 | cross-claim or counterclaim in a lawsuit) alleging that the Work
84 | or a Contribution incorporated within the Work constitutes direct
85 | or contributory patent infringement, then any patent licenses
86 | granted to You under this License for that Work shall terminate
87 | as of the date such litigation is filed.
88 |
89 | 4. Redistribution. You may reproduce and distribute copies of the
90 | Work or Derivative Works thereof in any medium, with or without
91 | modifications, and in Source or Object form, provided that You
92 | meet the following conditions:
93 |
94 | (a) You must give any other recipients of the Work or
95 | Derivative Works a copy of this License; and
96 |
97 | (b) You must cause any modified files to carry prominent notices
98 | stating that You changed the files; and
99 |
100 | (c) You must retain, in the Source form of any Derivative Works
101 | that You distribute, all copyright, patent, trademark, and
102 | attribution notices from the Source form of the Work,
103 | excluding those notices that do not pertain to any part of
104 | the Derivative Works; and
105 |
106 | (d) If the Work includes a "NOTICE" text file as part of its
107 | distribution, then any Derivative Works that You distribute must
108 | include a readable copy of the attribution notices contained
109 | within such NOTICE file, excluding those notices that do not
110 | pertain to any part of the Derivative Works, in at least one
111 | of the following places: within a NOTICE text file distributed
112 | as part of the Derivative Works; within the Source form or
113 | documentation, if provided along with the Derivative Works; or,
114 | within a display generated by the Derivative Works, if and
115 | wherever such third-party notices normally appear. The contents
116 | of the NOTICE file are for informational purposes only and
117 | do not modify the License. You may add Your own attribution
118 | notices within Derivative Works that You distribute, alongside
119 | or as an addendum to the NOTICE text from the Work, provided
120 | that such additional attribution notices cannot be construed
121 | as modifying the License.
122 |
123 | You may add Your own copyright statement to Your modifications and
124 | may provide additional or different license terms and conditions
125 | for use, reproduction, or distribution of Your modifications, or
126 | for any such Derivative Works as a whole, provided Your use,
127 | reproduction, and distribution of the Work otherwise complies with
128 | the conditions stated in this License.
129 |
130 | 5. Submission of Contributions. Unless You explicitly state otherwise,
131 | any Contribution intentionally submitted for inclusion in the Work
132 | by You to the Licensor shall be under the terms and conditions of
133 | this License, without any additional terms or conditions.
134 | Notwithstanding the above, nothing herein shall supersede or modify
135 | the terms of any separate license agreement you may have executed
136 | with Licensor regarding such Contributions.
137 |
138 | 6. Trademarks. This License does not grant permission to use the trade
139 | names, trademarks, service marks, or product names of the Licensor,
140 | except as required for reasonable and customary use in describing the
141 | origin of the Work and reproducing the content of the NOTICE file.
142 |
143 | 7. Disclaimer of Warranty. Unless required by applicable law or
144 | agreed to in writing, Licensor provides the Work (and each
145 | Contributor provides its Contributions) on an "AS IS" BASIS,
146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
147 | implied, including, without limitation, any warranties or conditions
148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
149 | PARTICULAR PURPOSE. You are solely responsible for determining the
150 | appropriateness of using or redistributing the Work and assume any
151 | risks associated with Your exercise of permissions under this License.
152 |
153 | 8. Limitation of Liability. In no event and under no legal theory,
154 | whether in tort (including negligence), contract, or otherwise,
155 | unless required by applicable law (such as deliberate and grossly
156 | negligent acts) or agreed to in writing, shall any Contributor be
157 | liable to You for damages, including any direct, indirect, special,
158 | incidental, or consequential damages of any character arising as a
159 | result of this License or out of the use or inability to use the
160 | Work (including but not limited to damages for loss of goodwill,
161 | work stoppage, computer failure or malfunction, or any and all
162 | other commercial damages or losses), even if such Contributor
163 | has been advised of the possibility of such damages.
164 |
165 | 9. Accepting Warranty or Additional Liability. While redistributing
166 | the Work or Derivative Works thereof, You may choose to offer,
167 | and charge a fee for, acceptance of support, warranty, indemnity,
168 | or other liability obligations and/or rights consistent with this
169 | License. However, in accepting such obligations, You may act only
170 | on Your own behalf and on Your sole responsibility, not on behalf
171 | of any other Contributor, and only if You agree to indemnify,
172 | defend, and hold each Contributor harmless for any liability
173 | incurred by, or claims asserted against, such Contributor by reason
174 | of your accepting any such warranty or additional liability.
175 |
176 | END OF TERMS AND CONDITIONS
177 |
178 | APPENDIX: How to apply the Apache License to your work.
179 |
180 | To apply the Apache License to your work, attach the following
181 | boilerplate notice, with the fields enclosed by brackets "[]"
182 | replaced with your own identifying information. (Don't include
183 | the brackets!) The text should be enclosed in the appropriate
184 | comment syntax for the file format. We also recommend that a
185 | file or class name and description of purpose be included on the
186 | same "printed page" as the copyright notice for easier
187 | identification within third-party archives.
188 |
189 | Copyright [yyyy] [name of copyright owner]
190 |
191 | Licensed under the Apache License, Version 2.0 (the "License");
192 | you may not use this file except in compliance with the License.
193 | You may obtain a copy of the License at
194 |
195 | http://www.apache.org/licenses/LICENSE-2.0
196 |
197 | Unless required by applicable law or agreed to in writing, software
198 | distributed under the License is distributed on an "AS IS" BASIS,
199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
200 | See the License for the specific language governing permissions and
201 | limitations under the License.
202 |
--------------------------------------------------------------------------------
/Project_Main.py:
--------------------------------------------------------------------------------
1 | # -*- coding: utf-8 -*-
2 |
3 | from sa_analysis import topic_sa_analysis
4 | import jieba.posseg as pseg
5 | from sa_model_train import model_train
6 | import multiprocessing
7 | from setting import *
8 | from tqdm import tqdm
9 | import os
10 |
11 | # 识别标点符号进行句子切分
12 | def doc2sentence(resource_text):
13 | # jieba 预热
14 | print(pseg.cut('预热'))
15 | with open(sentence_cut_path, 'w', encoding='utf-8') as sentence_cut:
16 | for sentence in tqdm(resource_text):
17 | if len(sentence.strip()) > 1:
18 | for word, flag in pseg.cut(sentence):
19 | if flag != 'x':
20 | sentence_cut.write(word)
21 | else:
22 | sentence_cut.write('\n')
23 |
24 | # 多线程主题句查询
25 | def find_topic_sentence():
26 | if not os.path.exists(topic_path):
27 | os.mkdir(topic_path)
28 | task_split = []
29 | for topic_n, key_words_list in topic_words_list.items():
30 | task_split.append([topic_path, topic_n, key_words_list])
31 | # task multiprocessing
32 | thread_number = len(topic_words_list.keys())
33 | pool = multiprocessing.Pool(processes=thread_number)
34 | pool.map(find_key_txt, task_split)
35 | def find_key_txt(data_list):
36 | sentence_cut = open(sentence_cut_path, 'r', encoding='utf-8')
37 | with open('{}/{}.txt'.format(data_list[0], data_list[1]), 'w', encoding='utf-8') as key_txt:
38 | for sentence in sentence_cut.readlines():
39 | for i in data_list[2]:
40 | if i in sentence:
41 | key_txt.write(sentence)
42 | # 关闭文件
43 | sentence_cut.close()
44 | print('{} 已经查找完成'.format(data_list[1]))
45 |
46 | if __name__ == '__main__':
47 | # 情感分析模型训练
48 | model_train()
49 | with open('data/text_resource.txt', 'r', encoding='utf-8') as resource_text:
50 | resource_text = resource_text.readlines()
51 | # 整句切分
52 | doc2sentence(resource_text)
53 | # 主题句查询
54 | find_topic_sentence()
55 | # 主题情感极性可视化
56 | topic_sa_analysis()
57 |
--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
1 | [](https://996.icu)
2 | #### Customer_satisfaction_Analysis
3 |
4 | [](https://starchart.cc/CarryChang/Customer_Satisfaction_Analysis)
5 |
6 | ##### 结果整合
7 |
8 |
9 | ##### Demo 演示
10 | - [视频演示demo](https://github.com/CarryChang/C-CNN-for-Chinese-Sentiment-Analysis/blob/master/video/demo.mp4)
11 | - [详细步骤](https://www.lanqiao.cn/courses/2628)
12 |
13 | ##### 基于用户 UGC 的在线民宿满意度挖掘，负责数据采集、主题抽取、情感分析等任务。开发的目的是克服用户打分和评论不一致，实现了在线评论采集和用户满意度分析。
14 |
15 |
16 |
17 | ##### 主要功能包括在线原始评论采集、主题聚类、评论情感分析与结果可视化展示等四个模块，如下所示。
18 |
19 |
20 |
21 |
22 | >1. 提取后的民宿地址和在线评论等信息如下。
23 |
24 |
25 |
26 | >2. 搭建了百度地图 POI 查询入口，可以进行自动化的批量查询地理信息。
27 |
28 |
29 |
30 | > 3. 通过高频词可视化展示，归纳出评论主题。
31 |
32 |
33 |
34 |
35 | > 4. 构建了基于在线民宿语料的 LDA 自动化主题聚类模型，利用主题中心词能找出对应的主题属性字典，并使用用户打分作为标注，然后通过多种分类模型，选用最优模型对提出的评价主体 进行情感分析，针对主题属性表进行主题提取后的文本进行情感分析，分别得出当前主题对应的情感趋势，横坐标为所有关于主题为“环境”的情感得分，纵坐标为对应的情感的条数，可以起到纵观当前“环境”主题下的情感趋势，趋势往右代表当前主题评价较好，总共有{“交通”，“价格”，“体验”，“服务”，“特色”，“环境”，“设施”，“餐饮”}的主题，选取“环境”主题进行可视化之后的结果如下图所示。
36 |
37 |
38 |
39 |
40 |
41 | > 5. 通过POI热力图的方式对在线民宿满意度进行展示。
42 |
43 |
44 |
45 |
46 | > 6. 代码结构如下。
47 |
48 |
49 |
50 | ##### 专利信息
51 |
52 |
53 |
54 | ##### 新版本特性
55 | > 1. 使用 litNLP 深度情感推理
56 | > 2. 增加多进程提高多个 topic 下的文本匹配速度
57 | > 3. Project_Main.py 直接完成细粒度情感极性可视化操作
58 |
--------------------------------------------------------------------------------
/commit_processing.py:
--------------------------------------------------------------------------------
1 | # -*- coding: utf-8 -*-
2 | import jieba.posseg as pseg
3 | import multiprocessing
4 | from setting import *
5 | import os
6 |
7 | # 识别标点符号进行句子切分
8 | def doc2sentence(resource_text):
9 | with open(sentence_cut_path, 'w', encoding='utf-8') as sentence_cut:
10 | for sentence in resource_text:
11 | if len(sentence.strip()) > 1:
12 | for word, flag in pseg.cut(sentence):
13 | if flag != 'x':
14 | sentence_cut.write(word)
15 | else:
16 | sentence_cut.write('\n')
17 |
18 | # 多线程主题句查询
19 | def find_topic_sentence():
20 | if not os.path.exists(topic_path):
21 | os.mkdir(topic_path)
22 | task_split = []
23 | for topic_n, key_words_list in topic_words_list.items():
24 | task_split.append([topic_path, topic_n, key_words_list])
25 | # task multiprocessing
26 | thread_number = len(topic_words_list.keys())
27 | pool = multiprocessing.Pool(processes=thread_number)
28 | pool.map(find_key_txt, task_split)
29 |
30 | def find_key_txt(data_list):
31 | sentence_cut = open(sentence_cut_path, 'r', encoding='utf-8')
32 | with open('{}/{}.txt'.format(data_list[0], data_list[1]), 'w', encoding='utf-8') as key_txt:
33 | for sentence in sentence_cut.readlines():
34 | for i in data_list[2]:
35 | if i in sentence:
36 | key_txt.write(sentence)
37 | # 关闭文件
38 | sentence_cut.close()
39 | print('{} 已经查找完成'.format(data_list[1]))
--------------------------------------------------------------------------------
/data/geo_data.csv:
--------------------------------------------------------------------------------
1 | name,address,score,comment_number,price,location
2 | 林木森驿站(重庆北碚步行街中心店),北碚区胜利街1号附13号，近北碚地铁终点站2号出口。 ,4.4,188,224,北碚区
3 | 重庆如家客栈,璧山区镇政府保利电影院楼上4楼，近广场大厦。 ,3.9,40,78,北碚区
4 | 重庆颂棠别院,大足区佛都大道216号昌州古城14号楼C05，近676县道。 ,4.6,419,129,大足区
5 | 奉节依斗门客栈,奉节诗城东路131号，近诗城博物馆。 ,4.6,91,142,奉节县
6 | 重庆武陵山枳人客栈,涪陵区武陵山大裂谷景区，近武陵山森林公园。 ,4.8,153,376,涪陵区
7 | 重庆般若静舍客栈,江北区江北农场宏帆路星辰苑，近北滨路。 ,4.6,562,190,江北区
8 | 重庆镜域旅游俱乐部酒店,江北区观音桥朗晴广场A塔29楼，近观音桥步行街。 ,4.7,402,166,江北区
9 | 重庆明然玥客栈,江北区观音桥北城天街35号同创国际商业街4楼，九街高屋对面，近洋河路。 ,4.6,875,242,江北区
10 | 重庆瓦舍美宿客栈,江北区观音桥红鼎国际B座2单元17楼1711，近建新北路。 ,4.8,115,248,江北区
11 | 重庆四面山龙腾客栈,江津区重庆市 江津区 四面山镇龙潭路(家园超市斜对面)。 ,3.8,65,145,江津区
12 | 重庆四面山天然居山庄,江津区四面山洪洞村一社（江津区，近四面山派出所） ,4.3,46,125,江津区
13 | 重庆香山农庄,江津区四面山风景区大洪湖景点停车场旁，大洪湖码头旁。 ,4.8,93,190,江津区
14 | 重庆倦鸟驿站,开州区滨湖中段7号商务楼，无。 ,4.6,80,292,开州区
15 | 梁平平野园林大酒店,梁平区梁山街道八角村，近梁平机场、机场环线。 ,4.7,141,188,梁平区
16 | 重庆和悦庄客栈,南岸区南坪西路68号，近花园路。 ,4.8,389,439,南岸区
17 | 重庆江涛客栈,南岸区南坪东路31号二楼，女子医院斜对面。 ,3.2,135,30,南岸区
18 | 重庆尚玉客栈,南岸区学府大道323号，近工商大学。 ,3.9,61,57,南岸区
19 | 重庆隐约南山客栈,南岸区重庆南岸区南山抗战遗址博物馆旁南山公园路1号。 ,4.0,43,372,南岸区
20 | 重庆阿川雅阁风情客栈,南川区金佛山西坡三汇场，近卫生院二分院。 ,4.1,71,134,南川区
21 | 重庆金佛山9号客栈,南川区金佛山西坡天星小镇9号楼，近天星小镇游客服务中心。 ,3.9,59,138,南川区
22 | 重庆金佛山小桥流水人家客栈,南川区金佛山西坡三汇场，近石林村。 ,4.4,158,209,南川区
23 | 重庆金佛山印象天星风情客栈,南川区天星小镇，近金佛山西大门。 ,4.1,51,181,南川区
24 | 重庆美都驿栈,南川区金佛山西坡三汇场，近金佛山西大门。 ,4.2,107,188,南川区
25 | 重庆乡土风情客栈,南川区金佛山西坡三汇场，近金佛山西大门。 ,4.1,55,89,南川区
26 | 重庆鑫源居客栈,南川区金佛山西坡三汇场三汇路89号，近金佛山西大门。 ,4.6,113,143,南川区
27 | 彭水阿依河山庄,彭水阿依河景区大门旁，近阿依河社区。 ,3.4,94,143,彭水苗族土家族自治县
28 | 重庆黑山千缘客栈,綦江区万盛经开区黑山旅游景区北门接待中心紫薇5路5栋，近414省道。 ,4.7,67,113,綦江区
29 | 重庆黑山小筑客栈,綦江区万盛经开区黑山谷南大门售票厅旁，黑山谷南门。 ,4.0,63,238,綦江区
30 | 重庆山谷人家农家乐,綦江区黑山谷商业购物街B栋，近黑山谷售票处。 ,4.0,46,168,綦江区
31 | 重庆万盛黑山谷南门秀容宾馆,綦江区万盛江流西路31号，近414省道。 ,3.1,34,76,綦江区
32 | 重庆诚悦庄客栈,黔江区濯水镇濯水居委五组4幢龚家大院内，近镇政府。 ,4.6,108,196,黔江区
33 | 重庆蹲趴背包客栈,沙坪坝区天陈路二号世源大厦，近三峡广场步行街。 ,4.5,338,36,沙坪坝区
34 | 嘉古院客栈(重庆磁器口古镇店),沙坪坝区磁器口古镇横街16号，近动感影院。 ,3.3,458,171,沙坪坝区
35 | 重庆U城客栈,沙坪坝区大学城北路94号U城天街。 ,4.6,106,80,沙坪坝区
36 | 重庆七号花园客栈,九龙坡区香榭丽街半山七号（九龙坡区，近烟灯山公园） ,4.8,49,133,沙坪坝区
37 | 重庆融汇泉·别院,沙坪坝区梨树湾融汇温泉城汇泉路6号，近融汇温泉。 ,4.8,406,1614,沙坪坝区
38 | 重庆世茂客栈,沙坪坝区磁器口正街88号，近磁童路。 ,4.3,164,133,沙坪坝区
39 | 石柱黄水水云间客栈,石柱黄水莼乡路285号27幢1-1（石柱，近黄水景区） ,4.7,37,780,石柱土家族自治县
40 | 石柱小鸟金山客栈,石柱南宾镇人民街（石柱，近玉带北街） ,2.0,51,107,石柱土家族自治县
41 | 重庆安居古城南大门客栈,铜梁区安居古城南大门（铜梁区，近古城游客接待中心） ,4.3,46,116,铜梁区
42 | 重庆锦鸿客栈,铜梁区安居镇兴隆街164号1-1（铜梁区，安居古城接待中心对面） ,3.7,32,97,铜梁区
43 | 重庆青居别苑,铜梁区安居古城西街1号（铜梁区，近城隍庙） ,4.6,230,257,铜梁区
44 | 重庆青风客栈,九龙坡区石新路178号沛鑫汽配城综合楼4楼，近四季香山小区大门、东风起亚。 ,4.3,96,74,万州区
45 | 重庆三峡行客栈,万州区沙龙路二段230号，近科兴苑、宏远批发市场。 ,4.8,34,39,万州区
46 | 途涂客栈(武隆仙女山店),武隆仙女山镇翠云路62号，近武隆县游客接待中心。 ,4.7,285,266,武隆区
47 | 武隆丛林精品客栈,武隆仙女山镇黄鹏河大峡谷，近038乡道。 ,4.3,57,587,武隆区
48 | 武隆多来福客栈,武隆巷口镇芙蓉中路86号2幢3楼，近白杨路。 ,4.7,327,68,武隆区
49 | 武隆观景客栈,武隆仙女山镇游客中心背后，近天秀仙居。 ,4.4,378,119,武隆区
50 | 武隆郡临仙山农家乐,武隆仙女山新区翠云路8号，距离游客接待中心旁500米。 ,4.1,98,53,武隆区
51 | 武隆强兴客栈,武隆巷口镇芙蓉中路71号2幢12楼汽车站对面，武隆汽车站对面。 ,4.5,107,80,武隆区
52 | 武隆仙乐客栈,武隆仙女山镇逸云路39号，近市民公园。 ,3.1,62,62,武隆区
53 | 武隆仙女山陌陌客栈,武隆仙女山镇银杏大道35号附1号，近203省道。 ,4.7,284,188,武隆区
54 | 武隆闲暇农家乐,武隆仙女镇银杏大道，近游客接待中心。 ,3.9,97,100,武隆区
55 | 武隆再回首农家乐,武隆天生三桥景区。 ,4.6,63,107,武隆区
56 | 仙女山菩镜丘客栈,武隆仙女镇夜宴仙女山7-3-1，近翠云路。 ,4.9,33,559,武隆区
57 | 闲暇空间连锁客栈(武隆分店),武隆仙女山镇翠云路68号，近七星环路。 ,4.8,1314,256,武隆区
58 | 重庆武隆仙女山之间堂客栈,武隆仙女山镇步云路6号，近大槽。 ,4.7,88,930,武隆区
59 | 重庆市秀山茶峒摄影民宿,秀山洪安镇老街3号，近万年台对面。 ,4.8,137,138,秀山土家族苗族自治县
60 | 酉阳东篱苑客栈,酉阳桃花源镇酉州古城第29栋（酉阳，近桃花源景区） ,4.3,86,152,酉阳土家族苗族自治县
61 | 酉阳龚滩古镇巴适客栈,酉阳龚滩镇新华社区（酉阳） ,4.1,36,96,酉阳土家族苗族自治县
62 | 酉阳龚滩古镇老院子客栈,酉阳龚滩古镇内知珍里街（酉阳） ,4.5,109,98,酉阳土家族苗族自治县
63 | 酉阳龚滩古镇唐街客栈,酉阳龚滩古镇内（酉阳） ,4.3,245,100,酉阳土家族苗族自治县
64 | 酉阳龚滩秀景精品客栈,酉阳龚滩古镇景区内（酉阳，近古镇中心小广场） ,4.8,69,90,酉阳土家族苗族自治县
65 | 酉阳上林风情客栈,酉阳酉州古城32号（酉阳，近桃花源景区） ,4.3,147,146,酉阳土家族苗族自治县
66 | 酉阳水泊人家客栈,酉阳龚滩古镇南门停车场入口第一家店作坊路5号（酉阳，近龚滩镇小学） ,4.4,158,128,酉阳土家族苗族自治县
67 | 酉阳酉州古城爱晚庭客栈,酉阳酉州古城31号（酉阳，近桃花源景区） ,4.3,294,134,酉阳土家族苗族自治县
68 | 重庆酉阳龚滩古镇小滩子客栈,酉阳龚滩古镇B区入口南门停车场旁（酉阳） ,3.5,79,90,酉阳土家族苗族自治县
69 | 重庆酉阳归园田居客栈,酉阳酉州古城北门1—B号（酉阳，近210省道） ,3.8,82,116,酉阳土家族苗族自治县
70 | 加州客栈(重庆红琦店),渝北区红石路241号，近江北大浪淘沙。 ,4.3,296,199,渝北区
71 | 重庆2008金桥龙兴古镇客栈,渝北区龙兴镇天龙路59号，近华夏宗祠。 ,3.9,77,107,渝北区
72 | 重庆巴渝客栈,渝北区两江新区金兴大道龙景路1号（园博园正门），近园博园游船售票厅，悦来会展中心。 ,4.6,151,419,渝北区
73 | 重庆倦鸟驿栈,渝北区北部新区黄山大道金科中华坊三号商务楼，近高科体育中心。 ,4.6,325,368,渝北区
74 | 重庆六号花园客栈,渝北区颐泰园D栋2单元1-2，近凯歌路与双湖路交叉口。 ,4.5,81,51,渝北区
75 | 重庆隆门驿客栈,渝北区双凤桥街道长空路144号，近桃园公园。 ,4.7,468,89,渝北区
76 | 重庆慢时光客栈,渝北区玫瑰城绣色锦衣星辰37栋，近南方翻译学院。 ,4.7,136,72,渝北区
77 | 重庆青风客栈悦来会展中心店,渝北区滨江路84号附1-4号，近悦来会展中心。 ,4.2,213,201,渝北区
78 | 重庆渝州情客栈,渝北区红锦大道21号加来金大厦9-11层，近近轨道3号线红旗河沟站、金龙路。 ,4.3,92,114,渝北区
79 | 重庆·重玖玖客栈,渝中区八一路好吃街218号19楼，近轨道交通1号线、2号线。 ,4.3,353,238,渝中区
80 | 重庆临江客栈,渝中区西来寺36号（一号桥与魁星楼之间），近临江门1号桥华仁医院。 ,4.2,602,118,渝中区
81 | 重庆龙猫客栈,渝中区解放碑五一路9号帝都广场B栋35-14（王府井百货对面），近八一路右侧。 ,4.6,308,30,渝中区
82 | 重庆南旅艺术客栈,渝中区重庆渝中区长滨路19号海客瀛洲B栋4-8（朝天门码头）。 ,4.8,61,175,渝中区
83 | 重庆能仁客栈,渝中区重庆渝中区解放碑好吃街对面布丁酒店旁1楼。 ,4.0,39,143,渝中区
84 | 重庆弱水咖啡客栈,渝中区大溪沟河街66号，近嘉陵江滨江路。 ,4.7,82,50,渝中区
85 | 重庆缘宿江景客栈,渝中区海客瀛州C栋1007接待处，近长江滨江路。 ,4.7,49,288,渝中区
86 | 重庆源财客栈,渝中区较场口四贤巷30号青鸟大厦3楼，近民生路。 ,3.3,50,136,渝中区
87 | 云阳龙缸湘圆农家乐,云阳龙缸景区（云阳，近民俗天街） ,4.2,43,90,云阳县
88 | 重庆建宏客栈,长寿区长寿古镇万寿南路A区37栋，近米寿东街。 ,4.0,113,85,长寿区
89 | 重庆御临客栈,长寿区长寿古镇C区2-1-2，近竹园。 ,4.0,45,161,长寿区
90 | 重庆长寿古镇秦彩格客栈,长寿区长寿古镇桃园西四路1号105幢1-1，近万寿广场。 ,4.4,110,179,长寿区
91 |
--------------------------------------------------------------------------------
/model_saved/init.py:
--------------------------------------------------------------------------------
1 | # -*- coding: utf-8 -*-
2 | # @USER: CarryChang
--------------------------------------------------------------------------------
/pic/gaopin1.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CarryChang/Customer_Satisfaction_Analysis/c1ebfc056dbad05ced1ea9e1754b38aa2e627c59/pic/gaopin1.png
--------------------------------------------------------------------------------
/pic/ip.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CarryChang/Customer_Satisfaction_Analysis/c1ebfc056dbad05ced1ea9e1754b38aa2e627c59/pic/ip.png
--------------------------------------------------------------------------------
/pic/lda_topic_select.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CarryChang/Customer_Satisfaction_Analysis/c1ebfc056dbad05ced1ea9e1754b38aa2e627c59/pic/lda_topic_select.png
--------------------------------------------------------------------------------
/pic/lda_topic_select1.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CarryChang/Customer_Satisfaction_Analysis/c1ebfc056dbad05ced1ea9e1754b38aa2e627c59/pic/lda_topic_select1.png
--------------------------------------------------------------------------------
/pic/poi可视化.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CarryChang/Customer_Satisfaction_Analysis/c1ebfc056dbad05ced1ea9e1754b38aa2e627c59/pic/poi可视化.png
--------------------------------------------------------------------------------
/pic/poi打分.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CarryChang/Customer_Satisfaction_Analysis/c1ebfc056dbad05ced1ea9e1754b38aa2e627c59/pic/poi打分.png
--------------------------------------------------------------------------------
/pic/不一致.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CarryChang/Customer_Satisfaction_Analysis/c1ebfc056dbad05ced1ea9e1754b38aa2e627c59/pic/不一致.png
--------------------------------------------------------------------------------
/pic/主题.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CarryChang/Customer_Satisfaction_Analysis/c1ebfc056dbad05ced1ea9e1754b38aa2e627c59/pic/主题.png
--------------------------------------------------------------------------------
/pic/各主题分数.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CarryChang/Customer_Satisfaction_Analysis/c1ebfc056dbad05ced1ea9e1754b38aa2e627c59/pic/各主题分数.png
--------------------------------------------------------------------------------
/pic/地址.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CarryChang/Customer_Satisfaction_Analysis/c1ebfc056dbad05ced1ea9e1754b38aa2e627c59/pic/地址.png
--------------------------------------------------------------------------------
/pic/情感分析图.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CarryChang/Customer_Satisfaction_Analysis/c1ebfc056dbad05ced1ea9e1754b38aa2e627c59/pic/情感分析图.png
--------------------------------------------------------------------------------
/pic/数据库.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CarryChang/Customer_Satisfaction_Analysis/c1ebfc056dbad05ced1ea9e1754b38aa2e627c59/pic/数据库.png
--------------------------------------------------------------------------------
/pic/文本分类.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CarryChang/Customer_Satisfaction_Analysis/c1ebfc056dbad05ced1ea9e1754b38aa2e627c59/pic/文本分类.png
--------------------------------------------------------------------------------
/pic/模型对比.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CarryChang/Customer_Satisfaction_Analysis/c1ebfc056dbad05ced1ea9e1754b38aa2e627c59/pic/模型对比.png
--------------------------------------------------------------------------------
/pic/模型对比2.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CarryChang/Customer_Satisfaction_Analysis/c1ebfc056dbad05ced1ea9e1754b38aa2e627c59/pic/模型对比2.png
--------------------------------------------------------------------------------
/pic/流程.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CarryChang/Customer_Satisfaction_Analysis/c1ebfc056dbad05ced1ea9e1754b38aa2e627c59/pic/流程.png
--------------------------------------------------------------------------------
/pic/结构1.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CarryChang/Customer_Satisfaction_Analysis/c1ebfc056dbad05ced1ea9e1754b38aa2e627c59/pic/结构1.png
--------------------------------------------------------------------------------
/pic/高频2.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/CarryChang/Customer_Satisfaction_Analysis/c1ebfc056dbad05ced1ea9e1754b38aa2e627c59/pic/高频2.png
--------------------------------------------------------------------------------
/requirement.txt:
--------------------------------------------------------------------------------
1 | tensorflow==2.0.1
2 | litNlp==0.8.4
3 | pyLDAvis==2.1.2
4 | scikit-learn==0.22.1
5 | numpy
6 | pandas
7 | jieba
8 | tqdm
--------------------------------------------------------------------------------
/sa_analysis.py:
--------------------------------------------------------------------------------
1 | # -*- coding: utf-8 -*-
2 | from litNlp.predict import SA_Model_Predict
3 | import matplotlib.pyplot as plt
4 | from setting import *
5 | import numpy as np
6 | import os
7 | plt.rcParams['font.sans-serif'] = ['SimHei']
8 | plt.rcParams['axes.unicode_minus'] = False
9 |
10 | def topic_sa_analysis():
11 | sa_model = SA_Model_Predict(tokenize_path, sa_model_path_m, max_len=100)
12 | if not os.path.exists(topic_emotion_pic):
13 | os.mkdir(topic_emotion_pic)
14 | print(topic_emotion_pic+'文件夹已经建立，请查看当前文件路径')
15 | for key_word in topic_words_list.keys():
16 | sa_analysis_(key_word, sa_model)
17 |
18 | def sa_analysis_(key_word, sa_model):
19 | print('{} 正在执行...'.format(key_word))
20 | key_txt = open('{}/{}.txt'.format(topic_path, key_word), 'r', encoding='utf-8').readlines()
21 | sentiments_score_predict = sa_model.predict(key_txt)
22 | # 情感极性输出
23 | sentiments_score_list = [i[1] for i in sentiments_score_predict]
24 | plt.hist(sentiments_score_list, bins=np.arange(0, 1, 0.01))
25 | plt.xlabel("情感值")
26 | plt.ylabel("评论数目")
27 | plt.title(key_word+'-情感极性分布图')
28 | plt.savefig('{}/{}.png'.format(topic_emotion_pic, key_word))
29 | plt.show()
30 | plt.close()
31 | print('{} 情感极性图完成'.format(key_word))
32 |
33 | # if __name__ == '__main__':
34 | # # 添加多线程提升预测速度
35 | # topic_sa_analysis()
36 |
--------------------------------------------------------------------------------
/sa_model_predict.py:
--------------------------------------------------------------------------------
1 | # -*- coding: utf-8 -*-
2 | from litNlp.predict import SA_Model_Predict
3 |
4 | def model_predict():
5 | model = SA_Model_Predict(tokenize_path, sa_model_path_m, max_len=100)
6 | sa_score = model.predict(predict_text)
7 | # 情感极性输出
8 | print([i[1] for i in sa_score])
9 |
10 | if __name__ == '__main__':
11 | # load conf
12 | from setting import *
13 | # example
14 | predict_text = ['这个我不喜欢', '这个我喜欢不']
15 | model_predict()
16 |
--------------------------------------------------------------------------------
/sa_model_train.py:
--------------------------------------------------------------------------------
1 | # -*- coding: utf-8 -*-
2 | import pandas as pd
3 | from litNlp.train import SA_Model_Train
4 | # load conf
5 | from setting import *
6 |
7 | def model_train():
8 | # data load
9 | train_data = pd.read_csv('data/label_comment.csv')
10 | # data process
11 | train_data['text_cut'] = train_data['text'].apply(lambda x: " ".join(list(x)))
12 | # train: evaluate 默认在训练完毕之后开启计算
13 | label = train_data['label']
14 | train_data = train_data['text_cut']
15 | # model load
16 | model = SA_Model_Train(max_words, embedding_dim, maxlen, tokenize_path, sa_model_path_m, train_method)
17 | # 模型训练
18 | model.train(train_data, label, num_classes=2, batch_size=256, epochs=2, verbose=1, evaluate=True)
19 | print('深度情感分析模型训练完毕')
20 |
21 | # if __name__ == '__main__':
22 | # # run model trian
23 | # model_train()
--------------------------------------------------------------------------------
/setting.py:
--------------------------------------------------------------------------------
1 | # -*- coding: utf-8 -*-
2 | # @USER: CarryChang
3 |
4 | # 设置词典大小为 n_features
5 | n_features = 3000
6 |
7 | # 存储断句的文件夹
8 | sentence_cut_path = 'data/sentence_cut.txt'
9 |
10 | # 主题句文件夹
11 | topic_path = 'topic_text'
12 |
13 | # 基于字典的查找
14 | topic_words_list = {
15 | '环境': {'环境', '周边', '风景', '空气', '江景', '小区', '景点', '夜景', '街', '周围', '景区', '声音', '景色'},
16 | '价格': {'价格', '房价', '性价比', '价位', '单价', '价钱'},
17 | '特色': {'特色', '装潢', '布置', '建筑', '结构', '格调', '装修', '设计', '风格', '隔音'},
18 | '设施': {'设施', '设备', '条件', '硬件', '房间', '热水', '马桶', '电梯', '阳台', '卫生间', '洗手间', '空调', '被子', '床', '大厅', '电话', '电', '摆设'},
19 | '餐饮': {'餐饮', '早餐', '咖啡', '味道', '饭', '菜', '水果', '特产', '餐', '美食', '烧烤', '宵夜', '食材', '饭馆', '小吃'},
20 | '交通': {'交通', '车程', '地段', '路程', '停车', '机场', '离', '车站', '地理', '位置', '地理', '中心', '海拔', '码头'},
21 | '服务': {'服务', '态度', '前台', '服务员', '老板', '掌柜', '店家', '工作人员'},
22 | '体验': {'体验', '整体', '感觉'},
23 | }
24 |
25 | # 存储情感极性的图
26 | topic_emotion_pic = 'topic_emotion_pic'
27 |
28 | # 最大句子长度
29 | maxlen = 100
30 |
31 | # 最大的tokenizer字典长度
32 | max_words = 1000
33 |
34 | # 设置embedding大小
35 | embedding_dim = 300
36 |
37 | # train_method : 模型训练方式，默认 textcnn，可选：bilstm , gru
38 | train_method = 'textcnn'
39 |
40 | # 模型的保存位置，后续用于推理
41 | sa_model_path_m = 'model_saved/model.h5'
42 |
43 | # 离线保存tokenizer
44 | tokenize_path = 'model_saved/tokenizer.pickle'
--------------------------------------------------------------------------------
