推薦システムの実行

パッケージのインストール

(recsys_full) offline$ pip install torch==2.5.1 torchvision==0.20.1 torchaudio==2.5.1 --index-url https://download.pytorch.org/whl/cu124
# PyTorch2.6以上の場合、RecBoleのコードの修正が必要になる。
# ...（3分程度）...
(recsys_full) offline$ pip install ray
(recsys_full) offline$ pip install pyarrow
(recsys_full) offline$ pip install kmeans_pytorch
(recsys_full) offline$ pip install recbole
(recsys_full) offline$ pip freeze
...（略）...
absl-py==2.2.1
aiosignal==1.3.2
attrs==25.3.0
click==8.1.8
colorama==0.4.4
colorlog==4.7.2
filelock==3.13.1
frozenlist==1.5.0
fsspec==2024.6.1
grpcio==1.71.0
Jinja2==3.1.4
jsonschema==4.23.0
jsonschema-specifications==2024.10.1
kmeans-pytorch==0.3
Markdown==3.7
MarkupSafe==2.1.5
mpmath==1.3.0
msgpack==1.1.0
narwhals==1.33.0
networkx==3.3
nvidia-cublas-cu12==12.4.5.8
nvidia-cuda-cupti-cu12==12.4.127
nvidia-cuda-nvrtc-cu12==12.4.127
nvidia-cuda-runtime-cu12==12.4.127
nvidia-cudnn-cu12==9.1.0.70
nvidia-cufft-cu12==11.2.1.3
nvidia-curand-cu12==10.3.5.147
nvidia-cusolver-cu12==11.6.1.9
nvidia-cusparse-cu12==12.3.1.170
nvidia-nccl-cu12==2.21.5
nvidia-nvjitlink-cu12==12.4.127
nvidia-nvtx-cu12==12.4.127
plotly==6.0.1
protobuf==6.30.2
pyarrow==19.0.1
PyYAML==6.0.2
ray==2.44.1
recbole==1.2.0
referencing==0.36.2
rpds-py==0.24.0
setuptools==70.2.0
sympy==1.13.1
tabulate==0.9.0
tensorboard==2.19.0
tensorboard-data-server==0.7.2
texttable==1.7.0
thop==0.1.1.post2209072238
torch==2.5.1+cu124
torchaudio==2.5.1+cu124
torchvision==0.20.1+cu124
triton==3.1.0
typing_extensions==4.12.2
Werkzeug==3.1.3
...（略）...

VSCodeの起動

(recsys_full) offline$ code .

推薦処理プログラムの準備

下記ファイルをダウンロードし、offline/src/ディレクトリに移動する。
- recsyslab / recsys-full / src / offline / src /
  - recommenders/__init__.py
  - recommenders/base_recommender.py
  - recommenders/bpr_recommender.py
  - recommenders/movies_movies_recommender.py
  - recommenders/pupularity_recommender.py
  - utils/__init__.py
  - utils/dataset.py
  - utils/recommend_result.py
  - config.yaml
  - offline.ini
  - update.py

(recsys_full) offline$ tree src/
src/
├── config.yaml                       # <-
├── keygen.py
├── ml2rdb.py
├── offline.ini                       # <-
├── recommenders                      # <-
│   ├── __init__.py                   # <-
│   ├── base_recommender.py           # <-
│   ├── bpr_recommender.py            # <-
│   ├── movies_movies_recommender.py  # <-
│   └── popularity_recommender.py     # <-
├── update.py                         # <-
├── user2encrypt.py
└── utils                             # <-
    ├── __init__.py                   # <-
    ├── dataset.py                    # <-
    └── recommend_result.py           # <-

3 directories, 14 files

結果の確認

(recsys_full) offline/src$ cd ../
(recsys_full) offline$ tree data/
data/
├── genres.csv
├── ml-latest-small
│   ├── README.txt
│   ├── links.csv
│   ├── movies.csv
│   ├── ratings.csv
│   └── tags.csv
├── ml-ls.inter                          # <-
├── ml-ls.item                           # <-
├── ml-ls.user                           # <-
├── ml-rdb
│   ├── genres.csv
│   ├── links.csv
│   ├── movies.csv
│   ├── movies_genres.csv
│   ├── ratings.csv
│   ├── tags.csv
│   └── users.csv
├── movies.csv
├── movies_genres.csv
├── movies_movies_similarity_matrix.csv  # <-
├── rating_matrix.csv                    # <-
├── ratings.csv
├── reclist_bpr.csv                      # <-
├── reclist_movies_movies.csv            # <-
├── reclist_popularity.csv               # <-
├── tags.csv
├── users.csv
└── users_.csv

3 directories, 27 files
(recsys_full) offline$ cd data/
(recsys_full) offline/data$
 less rating_matrix.csv
 less movies_movies_similarity_matrix.csv
 less ml-ls.inter
 less ml-ls.item
 less ml-ls.user
 less reclist_popularity.csv
 less reclist_movies_movies.csv
 less reclist_bpr.csv

参考

風間正弘，飯塚洸二郎，松村優也，『著推薦システム実践入門 ―仕事で使える導入ガイド』，オライリー・ジャパン，2022．
与謝秀作，『特集3 最新レコメンドエンジン総実装協調フィルタリングから深層学習まで』，WEB+DB PRESS Vol.129，pp.69-100，技術評論社，2022．
[🐛BUG] Wrong number of users and items in datasets information · Issue #1516 · RUCAIBox/RecBole
RecBole v1.2.0 — RecBole 1.2.0 documentation