Skip to main content

Tensorflow Recommenders, a TensorFlow library for recommender systems.

Project description

TensorFlow Recommenders

TensorFlow Recommenders logo

TensorFlow Recommenders build badge PyPI badge

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.


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

pip install tensorflow-recommenders


Have a look at our tutorials and API reference.

Quick start

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

from typing import Dict, Text

import tensorflow as tf
import tensorflow_datasets as tfds
import tensorflow_recommenders 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 = x: {
    "movie_id": tf.strings.to_number(x["movie_id"]),
    "user_id": tf.strings.to_number(x["user_id"])
movies = x: tf.strings.to_number(x["movie_id"]))

# Build a model.
class Model(tfrs.Model):

  def __init__(self):

    # 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(

  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()

# Randomly shuffle data and split between train and test.
shuffled = ratings.shuffle(100_000, seed=42, reshuffle_each_iteration=False)

train = shuffled.take(80_000)
test = shuffled.skip(80_000).take(20_000)

# Train., epochs=5)

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

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

tensorflow-recommenders-0.7.3.tar.gz (61.9 kB view hashes)

Uploaded Source

Built Distribution

tensorflow_recommenders-0.7.3-py3-none-any.whl (96.2 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page