In this tutorial, we build a simple matrix factorization model using the MovieLens 100K dataset with TFRS. We can use this model to recommend movies for a given user.
Import TFRS
from typing import Dict, Textimport numpy as npimport tensorflow as tfimport tensorflow_datasets as tfdsimport tensorflow_recommenders as tfrs
复制代码
Read the data
# 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: { "movie_title": x["movie_title"], "user_id": x["user_id"]})movies = movies.map(lambda x: x["movie_title"])
复制代码
Build vocabularies to convert user ids and movie titles into integer indices for embedding layers:
user_ids_vocabulary = tf.keras.layers.experimental.preprocessing.StringLookup(mask_token=None)user_ids_vocabulary.adapt(ratings.map(lambda x: x["user_id"]))movie_titles_vocabulary = tf.keras.layers.experimental.preprocessing.StringLookup(mask_token=None)movie_titles_vocabulary.adapt(movies)
复制代码
Define a model
We can define a TFRS model by inheriting from tfrs.Model and implementing the compute_loss method:
class MovieLensModel(tfrs.Model): # We derive from a custom base class to help reduce boilerplate. Under the hood, # these are still plain Keras Models. def __init__( self, user_model: tf.keras.Model, movie_model: tf.keras.Model, task: tfrs.tasks.Retrieval): super().__init__() # Set up user and movie representations. self.user_model = user_model self.movie_model = movie_model # Set up a retrieval task. self.task = task def compute_loss(self, features: Dict[Text, tf.Tensor], training=False) -> tf.Tensor: # Define how the loss is computed. user_embeddings = self.user_model(features["user_id"]) movie_embeddings = self.movie_model(features["movie_title"]) return self.task(user_embeddings, movie_embeddings)
复制代码
Define the two models and the retrieval task.
# Define user and movie models.user_model = tf.keras.Sequential([ user_ids_vocabulary, tf.keras.layers.Embedding(user_ids_vocabulary.vocab_size(), 64)])movie_model = tf.keras.Sequential([ movie_titles_vocabulary, tf.keras.layers.Embedding(movie_titles_vocabulary.vocab_size(), 64)])# Define your objectives.task = tfrs.tasks.Retrieval(metrics=tfrs.metrics.FactorizedTopK( movies.batch(128).map(movie_model) ))
复制代码
Fit and evaluate it.
Create the model, train it, and generate predictions:
# Create a retrieval model.model = MovieLensModel(user_model, movie_model, task)model.compile(optimizer=tf.keras.optimizers.Adagrad(0.5))# Train for 3 epochs.model.fit(ratings.batch(4096), epochs=3)# Use brute-force search to set up retrieval using the trained representations.index = tfrs.layers.factorized_top_k.BruteForce(model.user_model)index.index(movies.batch(100).map(model.movie_model), movies)# Get some recommendations._, titles = index(np.array(["42"]))print(f"Top 3 recommendations for user 42: {titles[0, :3]}")
复制代码
代码地址: https://codechina.csdn.net/csdn_codechina/enterprise_technology/-/blob/master/NLP_recommend/TensorFlow%20Recommenders:%20Quickstart.ipynb
评论