ToR[e]cSys
News
It is happy to know the new package of Tensorflow Recommenders.
ToR[e]cSys is a PyTorch Framework to implement recommendation system algorithms, including but not limited to click-through-rate (CTR) prediction, learning-to-ranking (LTR), and Matrix/Tensor Embedding. The project objective is to develop a ecosystem to experiment, share, reproduce, and deploy in real world in a smooth and easy way (Hope it can be done).
Installation
TBU
Documentation
The complete documentation for ToR[e]cSys is available via ReadTheDocs website.
Thank you for ReadTheDocs! You are the best!
Implemented Models
1. Subsampling
| Model Name | Research Paper | Year |
|---|---|---|
| Word2Vec | Omer Levy et al, 2015. Improving Distributional Similarity with Lessons Learned from Word Embeddings | 2015 |
2. Negative Sampling
| Model Name | Research Paper | Year |
|---|---|---|
| TBU |
3. Click through Rate (CTR) Model
4. Embedding Model
| Model Name | Research Paper | Year |
|---|---|---|
| Matrix Factorization | / | / |
| Starspace | Ledell Wu et al, 2017 StarSpace: Embed All The Things! | 2017 |
5. Learning-to-Rank (LTR) Model
| Model Name | Research Paper | Year |
|---|---|---|
| Personalized Re-ranking Model | Changhua Pei et al, 2019. Personalized Re-ranking for Recommendation | 2019 |
Getting Started
There are several ways using ToR[e]cSys to develop a Recommendation System. Before talking about them, we first need to discuss about components of ToR[e]cSys.
A model in ToR[e]cSys is constructed by two parts mainly: inputs and model, and they will be wrapped into a sequential module (torecsys.models.sequential) to be trained by Trainer (torecsys.trainer.Trainer). \
For inputs module (torecsys.inputs), it will handle most kinds of inputs in recommendation system, like categorical features, images, etc, with several kinds of methods, including token embedding, pre-trained image models, etc.
For models module (torecsys.models), it will implement some famous models in recommendation system, like Factorization Machine family. I hope I can make the library rich. To construct a model in the module, in addition to the modules implemented in PyTorch, I will also implement some layers in torecsys.layers which are called by models usually.
After the explanation of ToR[e]cSys, let's move on to the Getting Started. We can use ToR[e]cSys in the following ways:
-
Run by command-line (In development)
torecsys build --inputs_config='{}'
--model_config='{"method":"FM", "embed_size": 8, "num_fields": 2}'
--regularizer_config='{"weight_decay": 0.1}'
--criterion_config='{"method": "MSELoss"}'
--optimizer_config='{"method": "SGD", "lr": "0.01"}'
... ```
-
Run by class method
import torecsys as trs
build trainer by class method
trainer = trs.trainer.Trainer()
.bind_objective("CTR")
.set_inputs()
.set_model(method="FM", embed_size=8, num_fields=2)
.set_sequential()
.set_regularizer(weight_decay=0.1)
.build_criterion(method="MSELoss")
.build_optimizer(method="SGD", lr="0.01")
.build_loader(name="train", ...)
.build_loader(name="eval", ...)
.set_target_fields("labels")
.set_max_num_epochs(10)
.use_cuda()
start to fit the model
trainer.fit() ```
-
Run like PyTorch Module
import torch import torch.nn as nn import torecsys as trs
some codes here
inputs = trs.inputs.InputsWrapper(schema=schema) model = trs.models.FactorizationMachineModel(embed_size=8, num_fields=2)
for i in range(epochs): optimizer.zero_grad() outputs = model(**inputs(batches)) loss = criterion(outputs, labels) loss.backward() optimizer.step() ```
(In development) You can anyone you like to train a Recommender System and serve it in the following ways:
-
Run by command-line
> torecsys serve --load_from='{}'
-
Run by class method
import torecsys as trs
serving = trs.serving.Model()
.load_from(filepath=filepath) .run() ```
-
Serve it yourself
from flask import Flask, request import torecsys as trs
model = trs.serving.Model()
.load_from(filepath=filepath)
@app.route("/predict") def predict(): args = request.json inference = model.predict(args) return inference, 200
if name == "main": app.run() ```
For further details, please refer to the example in repository or read the documentation. Hope you enjoy~
Examples
TBU
Sample Codes
TBU
Sample of Experiments
TBU
Authors
- Jasper Li - Developer
License
ToR[e]cSys is MIT-style licensed, as found in the LICENSE file.
1 Dec 14, 2021
1 Jul 14, 2022
2 May 19, 2022
3 May 24, 2022
1.4k Dec 27, 2022
2.8k Dec 29, 2022
2 Nov 15, 2021
2 Jun 1, 2022
2 Feb 15, 2022
1 Jan 1, 2022
215 Nov 29, 2022
67 Jan 4, 2023
880 Jan 3, 2023
33 Dec 2, 2022
5.4k Jan 2, 2023
80 Dec 21, 2022
135 Dec 31, 2022
3 Jan 23, 2022
0 Jan 23, 2022
880 Jan 3, 2023
1 Nov 15, 2021
5 Oct 2, 2022
1.2k Jan 4, 2023
4.2k Jan 2, 2023
87 Nov 29, 2022
8 May 28, 2022
7 Mar 12, 2022
2 Feb 4, 2022
704 Jan 6, 2023