https://github.com/mobiletelesystems/rectools
RecTools - library to build Recommendation Systems easier and faster than ever before
https://github.com/mobiletelesystems/rectools
deep-learning machine-learning personalization recomendations recommendation-algorithms recommendation-engine recommendation-system recommender-system recsys
Last synced: 6 months ago
JSON representation
RecTools - library to build Recommendation Systems easier and faster than ever before
- Host: GitHub
- URL: https://github.com/mobiletelesystems/rectools
- Owner: MobileTeleSystems
- License: apache-2.0
- Created: 2022-07-13T09:24:15.000Z (about 3 years ago)
- Default Branch: main
- Last Pushed: 2025-04-10T14:41:17.000Z (6 months ago)
- Last Synced: 2025-04-10T15:03:30.966Z (6 months ago)
- Topics: deep-learning, machine-learning, personalization, recomendations, recommendation-algorithms, recommendation-engine, recommendation-system, recommender-system, recsys
- Language: Python
- Homepage:
- Size: 6.68 MB
- Stars: 348
- Watchers: 8
- Forks: 45
- Open Issues: 45
-
Metadata Files:
- Readme: README.md
- Changelog: CHANGELOG.md
- Contributing: CONTRIBUTING.rst
- License: LICENSE
- Code of conduct: CODE_OF_CONDUCT.md
- Security: SECURITY.md
Awesome Lists containing this project
README
# RecTools
[](https://pypi.org/project/rectools)
[](https://pypi.org/project/rectools)
[](https://rectools.readthedocs.io)
[](https://github.com/MobileTeleSystems/RecTools/blob/main/LICENSE)
[](https://app.codecov.io/gh/MobileTeleSystems/RecTools)
[](https://github.com/MobileTeleSystems/RecTools/actions/workflows/test.yml?query=branch%3Amain++)
[](https://github.com/MobileTeleSystems/RecTools/graphs/contributors)
[](https://pepy.tech/project/rectools)
[](https://t.me/RecTools_Support)
Documentation |
Examples |
Tutorials |
Contributing |
Releases |
Developers Board
RecTools is an easy-to-use Python library which makes the process of building recommender systems easier and
faster than ever before.
## ✨ Highlights: Transformer models released! ✨
**BERT4Rec and SASRec are now available in RecTools:**
- Fully compatible with our `fit` / `recommend` paradigm and require NO special data processing
- Explicitly described in our [Transformers Theory & Practice Tutorial](examples/tutorials/transformers_tutorial.ipynb): loss options, item embedding options, category features utilization and more!
- Configurable, customizable, callback-friendly, checkpoints-included, logs-out-of-the-box, custom-validation-ready, multi-gpu-compatible! See [Transformers Advanced Training User Guide](examples/tutorials/transformers_advanced_training_guide.ipynb) and [Transformers Customization Guide](examples/tutorials/transformers_customization_guide.ipynb)
- Public benchmarks which compare RecTools models to other open-source implementations following BERT4Rec replicability paper show that RecTools implementations achieve highest scores on multiple datasets: [Performance on public transformers benchmarks](https://github.com/blondered/bert4rec_repro?tab=readme-ov-file#rectools-transformers-benchmark-results)
## Get started
Prepare data with
```shell
wget https://files.grouplens.org/datasets/movielens/ml-1m.zip
unzip ml-1m.zip
```
```python
import pandas as pd
from implicit.nearest_neighbours import TFIDFRecommender
from rectools import Columns
from rectools.dataset import Dataset
from rectools.models import ImplicitItemKNNWrapperModel
# Read the data
ratings = pd.read_csv(
"ml-1m/ratings.dat",
sep="::",
engine="python", # Because of 2-chars separators
header=None,
names=[Columns.User, Columns.Item, Columns.Weight, Columns.Datetime],
)
# Create dataset
dataset = Dataset.construct(ratings)
# Fit model
model = ImplicitItemKNNWrapperModel(TFIDFRecommender(K=10))
model.fit(dataset)
# Make recommendations
recos = model.recommend(
users=ratings[Columns.User].unique(),
dataset=dataset,
k=10,
filter_viewed=True,
)
```
## Installation
RecTools is on PyPI, so you can use `pip` to install it.
```
pip install rectools
```
The default version doesn't contain all the dependencies, because some of them are needed only for specific functionality. Available user extensions are the following:
- `lightfm`: adds wrapper for LightFM model,
- `torch`: adds models based on neural nets,
- `visuals`: adds visualization tools,
- `nmslib`: adds fast ANN recommenders.
Install extension:
```
pip install rectools[extension-name]
```
Install all extensions:
```
pip install rectools[all]
```
## Recommender Models
The table below lists recommender models that are available in RecTools.
See [recommender baselines extended tutorial](https://github.com/MobileTeleSystems/RecTools/blob/main/examples/tutorials/baselines_extended_tutorial.ipynb) for deep dive into theory & practice of our supported models.
| Model | Type | Description (🎏 for user/item features, 🔆 for warm inference, ❄️ for cold inference support) | Tutorials & Benchmarks |
|----|----|---------|--------|
| SASRec | Neural Network | `rectools.models.SASRecModel` - Transformer-based sequential model with unidirectional attention mechanism and "Shifted Sequence" training objective
🎏| 📕 [Transformers Theory & Practice](examples/tutorials/transformers_tutorial.ipynb)
📗 [Advanced training guide](examples/tutorials/transformers_advanced_training_guide.ipynb)
📘 [Customization guide](examples/tutorials/transformers_customization_guide.ipynb)
🚀 [Top performance on public benchmarks](https://github.com/blondered/bert4rec_repro?tab=readme-ov-file#rectools-transformers-benchmark-results) |
| BERT4Rec | Neural Network | `rectools.models.BERT4RecModel` - Transformer-based sequential model with bidirectional attention mechanism and "MLM" (masked item) training objective
🎏| 📕 [Transformers Theory & Practice](examples/tutorials/transformers_tutorial.ipynb)
📗 [Advanced training guide](examples/tutorials/transformers_advanced_training_guide.ipynb)
📘 [Customization guide](examples/tutorials/transformers_customization_guide.ipynb)
🚀 [Top performance on public benchmarks](https://github.com/blondered/bert4rec_repro?tab=readme-ov-file#rectools-transformers-benchmark-results) |
| [implicit](https://github.com/benfred/implicit) ALS Wrapper | Matrix Factorization | `rectools.models.ImplicitALSWrapperModel` - Alternating Least Squares Matrix Factorizattion algorithm for implicit feedback.
🎏| 📙 [Theory & Practice](https://rectools.readthedocs.io/en/latest/examples/tutorials/baselines_extended_tutorial.html#Implicit-ALS)
🚀 [50% boost to metrics with user & item features](examples/5_benchmark_iALS_with_features.ipynb) |
| [implicit](https://github.com/benfred/implicit) BPR-MF Wrapper | Matrix Factorization | `rectools.models.ImplicitBPRWrapperModel` - Bayesian Personalized Ranking Matrix Factorization algorithm. | 📙 [Theory & Practice](https://rectools.readthedocs.io/en/latest/examples/tutorials/baselines_extended_tutorial.html#Bayesian-Personalized-Ranking-Matrix-Factorization-(BPR-MF)) |
| [implicit](https://github.com/benfred/implicit) ItemKNN Wrapper | Nearest Neighbours | `rectools.models.ImplicitItemKNNWrapperModel` - Algorithm that calculates item-item similarity matrix using distances between item vectors in user-item interactions matrix | 📙 [Theory & Practice](https://rectools.readthedocs.io/en/latest/examples/tutorials/baselines_extended_tutorial.html#ItemKNN) |
| [LightFM](https://github.com/lyst/lightfm) Wrapper | Matrix Factorization | `rectools.models.LightFMWrapperModel` - Hybrid matrix factorization algorithm which utilises user and item features and supports a variety of losses.
🎏 🔆 ❄️| 📙 [Theory & Practice](https://rectools.readthedocs.io/en/latest/examples/tutorials/baselines_extended_tutorial.html#LightFM)
🚀 [10-25 times faster inference with RecTools](examples/6_benchmark_lightfm_inference.ipynb)|
| EASE | Linear Autoencoder | `rectools.models.EASEModel` - Embarassingly Shallow Autoencoders implementation that explicitly calculates dense item-item similarity matrix | 📙 [Theory & Practice](https://rectools.readthedocs.io/en/latest/examples/tutorials/baselines_extended_tutorial.html#EASE) |
| PureSVD | Matrix Factorization | `rectools.models.PureSVDModel` - Truncated Singular Value Decomposition of user-item interactions matrix | 📙 [Theory & Practice](https://rectools.readthedocs.io/en/latest/examples/tutorials/baselines_extended_tutorial.html#PureSVD) |
| DSSM | Neural Network | `rectools.models.DSSMModel` - Two-tower Neural model that learns user and item embeddings utilising their explicit features and learning on triplet loss.
🎏 🔆 | - |
| Popular | Heuristic | `rectools.models.PopularModel` - Classic baseline which computes popularity of items and also accepts params like time window and type of popularity computation.
❄️| - |
| Popular in Category | Heuristic | `rectools.models.PopularInCategoryModel` - Model that computes poularity within category and applies mixing strategy to increase Diversity.
❄️| - |
| Random | Heuristic | `rectools.models.RandomModel` - Simple random algorithm useful to benchmark Novelty, Coverage, etc.
❄️| - |
- All of the models follow the same interface. **No exceptions**
- No need for manual creation of sparse matrixes, torch dataloaders or mapping ids. Preparing data for models is as simple as `dataset = Dataset.construct(interactions_df)`
- Fitting any model is as simple as `model.fit(dataset)`
- For getting recommendations `filter_viewed` and `items_to_recommend` options are available
- For item-to-item recommendations use `recommend_to_items` method
- For feeding user/item features to model just specify dataframes when constructing `Dataset`. [Check our example](examples/4_dataset_with_features.ipynb)
- For warm / cold inference just provide all required ids in `users` or `target_items` parameters of `recommend` or `recommend_to_items` methods and make sure you have features in the dataset for warm users/items. **Nothing else is needed, everything works out of the box.**
- Our models can be initialized from configs and have useful methods like `get_config`, `get_params`, `save`, `load`. Common functions `model_from_config`, `model_from_params` and `load_model` are available. [Check our example](examples/9_model_configs_and_saving.ipynb)
## Extended validation tools
### `calc_metrics` for classification, ranking, "beyond-accuracy", DQ, popularity bias and between-model metrics
[User guide](https://github.com/MobileTeleSystems/RecTools/blob/main/examples/3_metrics.ipynb) | [Documentation](https://rectools.readthedocs.io/en/stable/features.html#metrics)
### `DebiasConfig` for debiased metrics calculation
[User guide](https://github.com/MobileTeleSystems/RecTools/blob/main/examples/8_debiased_metrics.ipynb) | [Documentation](https://rectools.readthedocs.io/en/stable/api/rectools.metrics.debias.DebiasConfig.html)
### `cross_validate` for model metrics comparison
[User guide](https://github.com/MobileTeleSystems/RecTools/blob/main/examples/2_cross_validation.ipynb)
### `VisualApp` for model recommendations comparison
[Example](https://github.com/MobileTeleSystems/RecTools/blob/main/examples/7_visualization.ipynb) | [Demo](https://recsysart.ru/voila/) | [Documentation](https://rectools.readthedocs.io/en/stable/api/rectools.visuals.visual_app.VisualApp.html)
### `MetricsApp` for metrics trade-off analysis
[Example](https://github.com/MobileTeleSystems/RecTools/blob/main/examples/2_cross_validation.ipynb) |
[Documentation](https://rectools.readthedocs.io/en/stable/api/rectools.visuals.metrics_app.MetricsApp.html)
## Contribution
[Contributing guide](CONTRIBUTING.rst)
To install all requirements
- you must have `python3` and `poetry` installed
- make sure you have no active virtual environments (deactivate conda `base` if applicable)
- run
```
make install
```
For autoformatting run
```
make format
```
For linters check run
```
make lint
```
For tests run
```
make test
```
For coverage run
```
make coverage
```
To remove virtual environment run
```
make clean
```
## RecTools Team
- [Emiliy Feldman](https://github.com/feldlime) [Maintainer]
- [Daria Tikhonovich](https://github.com/blondered) [Maintainer]
- [Andrey Semenov](https://github.com/In48semenov)
- [Mike Sokolov](https://github.com/mikesokolovv)
- [Maya Spirina](https://github.com/spirinamayya)
- [Grigoriy Gusarov](https://github.com/Gooogr)
- [Aki Ariga](https://github.com/chezou)
- [Nikolay Undalov](https://github.com/nsundalov)
Previous contributors: [Ildar Safilo](https://github.com/irsafilo) [ex-Maintainer], [Daniil Potapov](https://github.com/sharthZ23) [ex-Maintainer], [Alexander Butenko](https://github.com/iomallach), [Igor Belkov](https://github.com/OzmundSedler), [Artem Senin](https://github.com/artemseninhse), [Mikhail Khasykov](https://github.com/mkhasykov), [Julia Karamnova](https://github.com/JuliaKup), [Maxim Lukin](https://github.com/groundmax), [Yuri Ulianov](https://github.com/yukeeul), [Egor Kratkov](https://github.com/jegorus), [Azat Sibagatulin](https://github.com/azatnv), [Vadim Vetrov](https://github.com/Waujito)