tensorflow-recommenders

TensorFlow Recommenders is a library for building recommender system models using TensorFlow.

https://github.com/tensorflow/recommenders

Science Score: 54.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
○
DOI references
○
Academic publication links
✓
Committers with academic emails
1 of 43 committers (2.3%) from academic institutions
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (10.1%) to scientific vocabulary

Keywords

recommender recommender-system tensorflow tensorflow-recommenders

Keywords from Contributors

jax

Last synced: 6 months ago · JSON representation ·

Repository

TensorFlow Recommenders is a library for building recommender system models using TensorFlow.

Basic Info

Host: GitHub
Owner: tensorflow
License: apache-2.0
Language: Python
Default Branch: main
Homepage:
Size: 1.87 MB

Statistics

Stars: 1,973
Watchers: 49
Forks: 293
Open Issues: 279
Releases: 16

Topics

recommender recommender-system tensorflow tensorflow-recommenders

Created over 5 years ago · Last pushed 7 months ago

Metadata Files

Readme Changelog Contributing License Citation

README.md

TensorFlow Recommenders

TensorFlow Recommenders logo

TensorFlow Recommenders is a library for building recommender system models using TensorFlow.

It helps with the full workflow of building a recommender system: data preparation, model formulation, training, evaluation, and deployment.

It's built on Keras and aims to have a gentle learning curve while still giving you the flexibility to build complex models.

Installation

Make sure you have TensorFlow 2.x installed, and install from pip:

shell pip install tensorflow-recommenders

Documentation

Have a look at our tutorials and API reference.

Quick start

Building a factorization model for the Movielens 100K dataset is very simple (Colab):

```python from typing import Dict, Text

import tensorflow as tf import tensorflowdatasets as tfds import tensorflowrecommenders as tfrs

Ratings data.

ratings = tfds.load('movielens/100k-ratings', split="train")

Features of all the available movies.

movies = tfds.load('movielens/100k-movies', split="train")

Select the basic features.

ratings = ratings.map(lambda x: { "movieid": tf.strings.tonumber(x["movieid"]), "userid": tf.strings.tonumber(x["userid"]) }) movies = movies.map(lambda x: tf.strings.tonumber(x["movieid"]))

Build a model.

class Model(tfrs.Model):

def init(self): super().init()

# Set up user representation.
self.user_model = tf.keras.layers.Embedding(
    input_dim=2000, output_dim=64)
# Set up movie representation.
self.item_model = tf.keras.layers.Embedding(
    input_dim=2000, output_dim=64)
# Set up a retrieval task and evaluation metrics over the
# entire dataset of candidates.
self.task = tfrs.tasks.Retrieval(
    metrics=tfrs.metrics.FactorizedTopK(
        candidates=movies.batch(128).map(self.item_model)
    )
)

def compute_loss(self, features: Dict[Text, tf.Tensor], training=False) -> tf.Tensor:

user_embeddings = self.user_model(features["user_id"])
movie_embeddings = self.item_model(features["movie_id"])

return self.task(user_embeddings, movie_embeddings)

model = Model() model.compile(optimizer=tf.keras.optimizers.Adagrad(0.5))

Randomly shuffle data and split between train and test.

tf.random.setseed(42) shuffled = ratings.shuffle(100000, seed=42, reshuffleeachiteration=False)

train = shuffled.take(80000) test = shuffled.skip(80000).take(20_000)

Train.

model.fit(train.batch(4096), epochs=5)

Evaluate.

model.evaluate(test.batch(4096), return_dict=True) ```

Owner

Name: tensorflow
Login: tensorflow
Kind: organization
Email: github-admin@tensorflow.org

Website: http://www.tensorflow.org
Repositories: 107
Profile: https://github.com/tensorflow

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "Kula"
  given-names: "Maciej"
- family-names: "Chen"
  given-names: "James"
- family-names: "Yi"
  given-names: "Xinyang"
- family-names: "Yao"
  given-names: "Tiansheng"
- family-names: "Sathiamoorthy"
  given-names: "Maheswaran"
- family-names: "Hong"
  given-names: "Lichan"
- family-names: "Chi"
  given-names: "Ed"
title: "TensorFlow Recommenders"
date-released: 2020-09-16
url: "https://github.com/tensorflow/recommenders"

GitHub Events

Total

Issues event: 11
Watch event: 137
Delete event: 6
Issue comment event: 35
Push event: 13
Pull request event: 13
Fork event: 19
Create event: 6

Last Year

Issues event: 11
Watch event: 137
Delete event: 6
Issue comment event: 35
Push event: 13
Pull request event: 13
Fork event: 19
Create event: 6

Committers

Last synced: about 1 year ago

All Time

Total Commits: 329
Total Committers: 43
Avg Commits per committer: 7.651
Development Distribution Score (DDS): 0.608

Past Year

Commits: 8
Committers: 2
Avg Commits per committer: 4.0
Development Distribution Score (DDS): 0.25

Top Committers

Name	Email	Commits
Maciej Kula	m**a@g**m	129
TonyWZ	z**n@g**m	44
TensorFlow Recommenders Authors	t**s@g**m	40
Albert Villanova del Moral	8****a	12
Wei Wei	w**e@g**m	12
TensorFlow Recommenders Team	t**m@g**m	11
Ziyin Huang	z**h@g**m	9
pshiko	p**w@g**m	6
Lichan Hong	l**n@g**m	6
Chen Qian	c**y@g**m	5
Tiansheng Yao	t**o@g**m	4
Mark Daoust	m**t@g**m	4
Jiaxi Tang	j**t@g**m	3
Tayo Oguntebi	t**o@g**m	3
Tim Schmeier	t**s@s**m	3
TimSchmeier	T****r	2
Maciej Kula	m****a	2
Bruce Fontaine	b**n@g**m	2
Hongyi Wen	h**7@c**u	2
Kanchi Shimono	d**o@g**m	2
Mahesh Sathiamoorthy	n**n@g**m	2
Xinyang Yi	x**g@g**m	2
Yash Katariya	y**a@g**m	2
Zhaoyue Cheng	z**c@g**m	2
hojinYang	h**7@g**m	2
Anima Singh	a**h@g**m	1
Danila Sinopalnikov	s**v@g**m	1
Jan Cervenka	j**a@y**m	1
hyphmongo	3****o	1
Samuel Marks	8****s	1
and 13 more...

Committer Domains (Top 20 + Academic)

google.com: 28 zacstewart.com: 1 cornell.edu: 1 spotify.com: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time

Total issues: 151
Total pull requests: 57
Average time to close issues: 25 days
Average time to close pull requests: 25 days
Total issue authors: 103
Total pull request authors: 16
Average comments per issue: 3.64
Average comments per pull request: 1.05
Merged pull requests: 17
Bot issues: 0
Bot pull requests: 38

Past Year

Issues: 12
Pull requests: 10
Average time to close issues: N/A
Average time to close pull requests: about 4 hours
Issue authors: 12
Pull request authors: 4
Average comments per issue: 0.5
Average comments per pull request: 0.9
Merged pull requests: 4
Bot issues: 0
Bot pull requests: 6

View more stats

Top Authors

Issue Authors

ericy51 (6)
OmarMAmin (5)
abdollahpouri (5)
flynhigher (4)
zhifeng-huang (4)
ydennisy (4)
datasciyj (3)
riyaj8888 (3)
BrianMiner (3)
EdwardALockhart (3)
nialloh23 (3)
hkristof03 (3)
mustfkeskin (2)
houghtonweihu (2)
malinphy (2)

Pull Request Authors

copybara-service[bot] (44)
flynhigher (6)
keivanipchihagh (2)
getumen (2)
ZhaoyueCheng (2)
aniruthraj (2)
marygiotandoi (1)
vidhant (1)
shanemhansen (1)
rageSpin (1)
Nik-code (1)
gaikwadrahul8 (1)
AmgadHasan (1)
tiruk007 (1)
patrickorlando (1)

Top Labels

Issue Labels

question (15) bug (1)

Pull Request Labels

Packages

Total packages: 2
Total downloads:
- pypi 286,540 last-month
Total docker downloads: 10

Total dependent packages: 1
(may contain duplicates)
Total dependent repositories: 32
(may contain duplicates)
Total versions: 32
Total maintainers: 2

pypi.org: tensorflow-recommenders

Tensorflow Recommenders, a TensorFlow library for recommender systems.

Homepage: https://github.com/tensorflow/recommenders
Documentation: https://tensorflow-recommenders.readthedocs.io/
License: Apache 2.0
Latest release: 0.7.3
published about 3 years ago

Versions: 15
Dependent Packages: 1
Dependent Repositories: 32
Downloads: 286,540 Last month
Docker Downloads: 10

Rankings

Downloads: 0.6%

Stargazers count: 1.7%

Dependent repos count: 2.6%

Average: 2.8%

Forks count: 3.3%

Docker downloads count: 3.8%

Dependent packages count: 4.8%

Maintainers (2)

google_opensource tensorflow-recommenders-team

Last synced: 6 months ago

proxy.golang.org: github.com/tensorflow/recommenders

Documentation: https://pkg.go.dev/github.com/tensorflow/recommenders#section-documentation
License: apache-2.0
Latest release: v0.7.3
published about 3 years ago

Versions: 17
Dependent Packages: 0
Dependent Repositories: 0

Rankings

Dependent packages count: 6.5%

Average: 6.7%

Dependent repos count: 7.0%

Last synced: 6 months ago

Dependencies

.github/workflows/pylint-presubmit.yml actions

actions/checkout v2 composite
actions/setup-python v2 composite
trilom/file-changes-action v1.2.4 composite

.github/workflows/test.yaml actions

actions/checkout v2 composite
actions/setup-python v2 composite

requirements.txt pypi

absl-py >=0.1.6
tensorflow >=2.9.0
tensorflow-macos >=2.9.0

tensorflow_recommenders/dev_requirements.txt pypi

fire * development