Merge pull request #1902 from BishopLiu/master

FIX: update version information

Author: BishopLiu

README.md

@@ -59,6 +59,8 @@ for testing and comparing recommendation algorithms.
 
 
 ## RecBole News
+![new](/asset/new.gif) **11/01/2023**: We release RecBole [v1.2.0](https://github.com/RUCAIBox/RecBole/releases/tag/v1.2.0).
+
 ![new](/asset/new.gif) **11/06/2022**: We release [the optimal hyperparameters of the model and their tuning ranges](https://recbole.io/hyperparameters/index.html).
 
 ![new](/asset/new.gif) **10/05/2022**: We release RecBole [v1.1.1](https://github.com/RUCAIBox/RecBole/releases/tag/v1.1.1).
@@ -247,6 +249,7 @@ We will keep improving our implementations, and update these test results.
 ## RecBole Major Releases
 | Releases | Date       |
 |----------|------------|
+| v1.2.0   | 11/01/2023 |
 | v1.1.1   | 10/05/2022 |
 | v1.0.0   | 09/17/2021 |
 | v0.2.0   | 01/15/2021 |
@@ -290,7 +293,7 @@ We thank the nice contributions through PRs from [@rowedenny](https://github.com
 
 
 ## Cite
-If you find RecBole useful for your research or development, please cite the following papers: [RecBole[1.0]](https://arxiv.org/abs/2011.01731), [RecBole[2.0]](https://dl.acm.org/doi/abs/10.1145/3459637.3482016) and [RecBole[1.1.1]](https://arxiv.org/abs/2211.15148).
+If you find RecBole useful for your research or development, please cite the following papers: [RecBole[1.0]](https://arxiv.org/abs/2011.01731), [RecBole[2.0]](https://dl.acm.org/doi/abs/10.1145/3459637.3482016) and [RecBole[1.2.0]](https://dl.acm.org/doi/10.1145/3539618.3591889).
 
 ```bibtex
 @inproceedings{recbole[1.0],
@@ -308,11 +311,11 @@ If you find RecBole useful for your research or development, please cite the fol
   pages={4722--4726},
   year={2022}
 }
-@misc{recbole[1.1.1],
-  author = {Xu, Lanling and Tian, Zhen and Zhang, Gaowei and Wang, Lei and Zhang, Junjie and Zheng, Bowen and Li, Yifan and Hou, Yupeng and Pan, Xingyu and Chen, Yushuo and Zhao, Wayne Xin and Chen, Xu and Wen, Ji-Rong},
-  title = {Recent Advances in RecBole: Extensions with more Practical Considerations},
-  journal   = {arXiv preprint arXiv:2211.15148},
-  year = {2022}
+@inproceedings{recbole[1.2.0],
+author = {Xu, Lanling and Tian, Zhen and Zhang, Gaowei and Zhang, Junjie and Wang, Lei and Zheng, Bowen and Li, Yifan and Tang, Jiakai and Zhang, Zeyu and Hou, Yupeng and Pan, Xingyu and Zhao, Wayne Xin and Chen, Xu and Wen, Ji-Rong},
+title = {Towards a More User-Friendly and Easy-to-Use Benchmark Library for Recommender Systems},
+pages = {2837–2847},
+year = {2023}
 }
 ```
 
@@ -326,8 +329,9 @@ Here is the list of our lead developers in each development phase. They are the
 |         Time          |        Version         |                Lead Developers                 |                Paper            |
 | :-------------------: | :--------------------: | :--------------------------------------------: | ---------------------------------------------- |
 | June 2020<br> ~<br> Nov. 2020 |        v0.1.1         |  Shanlei Mu ([@ShanleiMu](https://github.com/ShanleiMu)), Yupeng Hou ([@hyp1231](https://github.com/hyp1231)),<br> Zihan Lin ([@linzihan-backforward](https://github.com/linzihan-backforward)), Kaiyuan Li ([@tsotfsk](https://github.com/tsotfsk))| [PDF](https://dl.acm.org/doi/abs/10.1145/3459637.3482016) |
-|    Nov. 2020<br> ~ <br> Oct. 2022    | v0.1.2 ~ v1.0.1 |      Yushuo Chen ([@chenyushuo](https://github.com/chenyushuo)), Xingyu Pan ([@2017pxy](https://github.com/2017pxy))    | [PDF](https://dl.acm.org/doi/abs/10.1145/3459637.3482016)  |
-| Oct. 2022<br/> ~ <br/> now | v1.1.0 ~ v1.1.1 | Lanling Xu ([@Sherry-XLL](https://github.com/Sherry-XLL)), Zhen Tian ([@chenyuwuxin](https://github.com/chenyuwuxin)), Gaowei Zhang ([@Wicknight](https://github.com/Wicknight)), Lei Wang ([@Paitesanshi](https://github.com/Paitesanshi)), Junjie Zhang ([@leoleojie](https://github.com/leoleojie)) | [PDF](https://arxiv.org/abs/2211.15148) |
+|    Nov. 2020<br> ~ <br> Jul. 2022    | v0.1.2 ~ v1.0.1 |      Yushuo Chen ([@chenyushuo](https://github.com/chenyushuo)), Xingyu Pan ([@2017pxy](https://github.com/2017pxy))    | [PDF](https://dl.acm.org/doi/abs/10.1145/3459637.3482016)  |
+| Jul. 2022<br/> ~ <br/> Nov. 2023 | v1.1.0 ~ v1.1.1 | Lanling Xu ([@Sherry-XLL](https://github.com/Sherry-XLL)), Zhen Tian ([@chenyuwuxin](https://github.com/chenyuwuxin)), Gaowei Zhang ([@Wicknight](https://github.com/Wicknight)), Lei Wang ([@Paitesanshi](https://github.com/Paitesanshi)), Junjie Zhang ([@leoleojie](https://github.com/leoleojie)) | [PDF](https://dl.acm.org/doi/10.1145/3539618.3591889) |
+| Nov. 2023<br/> ~ <br/> now | v1.2.0 | Bowen Zheng ([@zhengbw0324](https://github.com/zhengbw0324)), Chen Ma ([@Yilu114](https://github.com/Yilu114)) | [PDF](https://dl.acm.org/doi/10.1145/3539618.3591889) |
 
 
 ## License

README_CN.md

@@ -54,6 +54,8 @@ RecBole 是一个基于 PyTorch 实现的，面向研究者的，易于开发与
 
 
 ## RecBole 新闻
+![new](/asset/new.gif) **11/01/2023**: 我们发布了 [v1.2.0](https://github.com/RUCAIBox/RecBole/releases/tag/v1.2.0).
+
 ![new](/asset/new.gif) **11/06/2022**: 我们公开了[模型的最优超参数及其调参范围](https://recbole.io/hyperparameters/index.html).
 
 ![new](/asset/new.gif) **10/05/2022**: 我们发布了 [v1.1.1](https://github.com/RUCAIBox/RecBole/releases/tag/v1.1.1).
@@ -217,12 +219,13 @@ NOTE: 我们的测试结果只给出了RecBole库中实现模型的大致时间
 
 
 ## RecBole 重要发布
-| Releases  | Date   |
-|-----------|--------|
-| v1.1.1 | 10/05/2022 |
-| v1.0.0    | 09/17/2021 |
-| v0.2.0    | 01/15/2021 |
-| v0.1.1    | 11/03/2020 |
+| Releases | Date       |
+|----------|------------|
+| v1.2.0   | 11/01/2023 |
+| v1.1.1   | 10/05/2022 |
+| v1.0.0   | 09/17/2021 |
+| v0.2.0   | 01/15/2021 |
+| v0.1.1   | 11/03/2020 |
 
 
 ## 开源贡献
@@ -262,7 +265,7 @@ NOTE: 我们的测试结果只给出了RecBole库中实现模型的大致时间
 
 
 ## 引用
-如果你觉得 RecBole 对你的科研工作有帮助，请引用我们的论文：[RecBole[1.0]](https://arxiv.org/abs/2011.01731)，[RecBole[2.0]](https://dl.acm.org/doi/abs/10.1145/3459637.3482016) 和 [RecBole[1.1.1]](https://arxiv.org/abs/2211.15148)。
+如果你觉得 RecBole 对你的科研工作有帮助，请引用我们的论文：[RecBole[1.0]](https://arxiv.org/abs/2011.01731)，[RecBole[2.0]](https://dl.acm.org/doi/abs/10.1145/3459637.3482016) 和 [RecBole[1.2.0]](https://dl.acm.org/doi/10.1145/3539618.3591889)。
 
 ```bibtex
 @inproceedings{recbole[1.0],
@@ -280,11 +283,11 @@ NOTE: 我们的测试结果只给出了RecBole库中实现模型的大致时间
   pages={4722--4726},
   year={2022}
 }
-@misc{recbole[1.1.1],
-  author = {Xu, Lanling and Tian, Zhen and Zhang, Gaowei and Wang, Lei and Zhang, Junjie and Zheng, Bowen and Li, Yifan and Hou, Yupeng and Pan, Xingyu and Chen, Yushuo and Zhao, Wayne Xin and Chen, Xu and Wen, Ji-Rong},
-  title = {Recent Advances in RecBole: Extensions with more Practical Considerations},
-  journal   = {arXiv preprint arXiv:2211.15148},
-  year = {2022}
+@inproceedings{recbole[1.2.0],
+author = {Xu, Lanling and Tian, Zhen and Zhang, Gaowei and Zhang, Junjie and Wang, Lei and Zheng, Bowen and Li, Yifan and Tang, Jiakai and Zhang, Zeyu and Hou, Yupeng and Pan, Xingyu and Zhao, Wayne Xin and Chen, Xu and Wen, Ji-Rong},
+title = {Towards a More User-Friendly and Easy-to-Use Benchmark Library for Recommender Systems},
+pages = {2837–2847},
+year = {2023}
 }
 ```
 
@@ -297,9 +300,9 @@ RecBole由 [中国人民大学, 北京邮电大学, 华东师范大学](https://
 |         时间段          |        版本         |               首席开发者                 |               论文               |
 | :-------------------: | :--------------------: | :--------------------------------------------: | ---------------------------------------------- |
 | 2020年6月<br> ~<br> 2020年11月 |        v0.1.1         |  牟善磊 ([@ShanleiMu](https://github.com/ShanleiMu)), 侯宇蓬 ([@hyp1231](https://github.com/@hyp1231)),<br> 林子涵 ([@linzihan-backforward](https://github.com/linzihan-backforward)), 李凯元 ([@tsotfsk](https://github.com/tsotfsk))| [PDF](https://dl.acm.org/doi/abs/10.1145/3459637.3482016) |
-|   2020年11月<br> ~ <br> 2022年10月   | v0.1.2 ~ v1.0.1 |      陈昱硕 ([@chenyushuo](https://github.com/https://github.com/chenyushuo)), 潘星宇 ([@2017pxy](https://github.com/2017pxy))    | [PDF](https://dl.acm.org/doi/abs/10.1145/3459637.3482016)    |
-| 2022年10月<br/> ~ <br/> 现在 | v1.1.0 ~ v1.1.1 | 徐澜玲 ([@Sherry-XLL](https://github.com/Sherry-XLL)), 田震 ([@chenyuwuxin](https://github.com/chenyuwuxin)), 张高玮 ([@Wicknight](https://github.com/Wicknight)), 王磊 ([@Paitesanshi](https://github.com/Paitesanshi)), 张君杰 ([@leoleojie](https://github.com/leoleojie)) | [PDF](https://arxiv.org/abs/2211.15148) |
-
+|   2020年11月<br> ~ <br> 2022年7月   | v0.1.2 ~ v1.0.1 |      陈昱硕 ([@chenyushuo](https://github.com/https://github.com/chenyushuo)), 潘星宇 ([@2017pxy](https://github.com/2017pxy))    | [PDF](https://dl.acm.org/doi/abs/10.1145/3459637.3482016)    |
+| 2022年7月<br/> ~ <br/> 2023年11月 | v1.1.0 ~ v1.1.1 | 徐澜玲 ([@Sherry-XLL](https://github.com/Sherry-XLL)), 田震 ([@chenyuwuxin](https://github.com/chenyuwuxin)), 张高玮 ([@Wicknight](https://github.com/Wicknight)), 王磊 ([@Paitesanshi](https://github.com/Paitesanshi)), 张君杰 ([@leoleojie](https://github.com/leoleojie)) | [PDF](https://dl.acm.org/doi/10.1145/3539618.3591889) |
+| 2023年11月<br/> ~ <br/> 现在 | v1.2.0 | 郑博文 ([@zhengbw0324](https://github.com/zhengbw0324)), 马辰 ([@Yilu114](https://github.com/Yilu114)) | [PDF](https://dl.acm.org/doi/10.1145/3539618.3591889) |
 
 ## 免责声明
 RecBole 基于 [MIT License](./LICENSE) 进行开发，本项目的所有数据和代码只能被用于学术目的。

conda/conda_release.sh

@@ -6,3 +6,5 @@ conda-build --python 3.8 .
 printf "python 3.8 version is released \n"
 conda-build --python 3.9 .
 printf "python 3.9 version is released \n"
+conda-build --python 3.10 .
+printf "python 3.10 version is released \n"

conda/meta.yaml

@@ -1,6 +1,6 @@
 package:
   name: recbole
-  version: 1.1.1
+  version: 1.2.0
 
 source:
   path: ../
@@ -12,30 +12,36 @@ requirements:
     - python
     - numpy >=1.17.2
     - scipy >=1.6.0
-    - pandas >=1.0.5
+    - pandas >=1.3.0
     - tqdm >=4.48.2
     - pyyaml >=5.1.0
     - scikit-learn >=0.23.2
     - pytorch >=1.10.0
-    - colorlog==4.7.2
-    - colorama==0.4.4
+    - colorlog >=4.7.2
+    - colorama >=0.4.4
     - tensorboard >=2.5.0
     - tabulate >=0.8.10
     - plotly >=4.0.0
+    - texttable >=0.9.0
+    - psutil >=5.9.0
+    - ray-tune >=1.6.0
   run:
     - python
     - numpy >=1.17.2
     - scipy >=1.6.0
-    - pandas >=1.0.5
+    - pandas >=1.3.0
     - tqdm >=4.48.2
     - pyyaml >=5.1.0
     - scikit-learn >=0.23.2
     - pytorch >=1.10.0
-    - colorlog==4.7.2
-    - colorama==0.4.4
+    - colorlog >=4.7.2
+    - colorama >=0.4.4
     - tensorboard >=2.5.0
     - tabulate >=0.8.10
     - plotly >=4.0.0
+    - texttable >=0.9.0
+    - psutil >=5.9.0
+    - ray-tune >=1.6.0
 test:
   imports:
     - recbole

recbole/__init__.py

@@ -2,4 +2,4 @@
 from __future__ import print_function
 from __future__ import division
 
-__version__ = "1.1.1"
+__version__ = "1.2.0"

recbole/model/general_recommender/ldiffrec.py

@@ -26,7 +26,6 @@
     ModelMeanType,
     mean_flat,
 )
-from kmeans_pytorch import kmeans
 
 
 class AutoEncoder(nn.Module):
@@ -68,6 +67,8 @@ def __init__(
             )
 
         else:
+            from kmeans_pytorch import kmeans
+
             self.cluster_ids, _ = kmeans(
                 X=item_emb, num_clusters=n_cate, distance="euclidean", device=device
             )

requirements.txt

@@ -2,15 +2,16 @@ torch>=1.10.0
 numpy>=1.17.2
 scipy>=1.6.0
 hyperopt==0.2.5
-pandas>=1.4.0
+pandas>=1.3.0
 tqdm>=4.48.2
 scikit_learn>=0.23.2
 pyyaml>=5.1.0
-colorlog==4.7.2
-colorama==0.4.4
+colorlog>=4.7.2
+colorama>=0.4.4
 tensorboard>=2.5.0
 thop>=0.1.1.post2207130030
 ray>=1.13.0, <=2.6.3
 tabulate>=0.8.10 
 plotly>=4.0.0
-texttable>=0.9.0
+texttable>=0.9.0
+psutil>=5.9.0

setup.py

@@ -10,7 +10,7 @@
     "torch>=1.10.0",
     "numpy>=1.17.2",
     "scipy>=1.6.0",
-    "pandas>=1.0.5",
+    "pandas>=1.3.0",
     "tqdm>=4.48.2",
     "colorlog==4.7.2",
     "colorama==0.4.4",
@@ -20,11 +20,14 @@
     "thop>=0.1.1.post2207130030",
     "tabulate>=0.8.10",
     "plotly>=4.0.0",
+    "texttable>=0.9.0",
+    "psutil>=5.9.0",
+    "ray>=1.13.0, <=2.6.3",
 ]
 
 setup_requires = []
 
-extras_require = {"hyperopt": ["hyperopt==0.2.5"], "ray": ["ray>=1.13.0"]}
+extras_require = {"hyperopt": ["hyperopt==0.2.5"]}
 
 classifiers = ["License :: OSI Approved :: MIT License"]
 
@@ -48,7 +51,7 @@
 
 setup(
     name="recbole",
-    version="1.1.1",  # please remember to edit recbole/__init__.py in response, once updating the version
+    version="1.2.0",  # please remember to edit recbole/__init__.py in response, once updating the version
     description="A unified, comprehensive and efficient recommendation library",
     long_description=long_description,
     long_description_content_type="text/markdown",