
最近Google開源了基于Tensorflow的推薦器, 一個新的開源Tensorflow包。它的特點可以總結為下面四個:
- 它有助于開發和評估靈活的候選nomination模型;
- 它可以很容易地将商品、使用者和上下文資訊合并到推薦模型中;
- 它可以訓練多任務模型,幫助優化多個推薦目标;
- 它使用TensorFlow Serving為最終模型提供服務。
這些特性非常容易使用,因為TFRS包含了不同的子產品,可以幫助使用者輕松地定制各個層和名額。TFRS還形成了一個内聚的整體,使得各個元件能夠非常好地協調。重點在于能使預設設定合理化,使常見任務更加直覺且易于實作,并提供更複雜和自定義的推薦,使其更靈活。
TensorFlow Recommenders是使用TensorFlow建構推薦系統模型的庫。它有助于建構推薦系統的完整工作流程,包括:
資料準備、模型制定、模型訓練、模型評估和部署等。
該模型是建立在Keras之上的,更加便于建構複雜模型。
安裝&案例
1. 安裝先安裝Tensorflow 2.x,然後使用pip進行安裝即可。
# !pip install tensorflow_datasets
# !pip install tensorflow-recommenders
2. 簡單案例
我們用Movielens 100K資料為例建構矩陣分解模型
from typing import Dict, Text
import tensorflow as tf
import tensorflow_datasets as tfds
import tensorflow_recommenders as tfrs
# Ratings資料.
ratings = tfds.load('movie_lens/100k-ratings', split="train")
# movies的所有Features .
movies = tfds.load('movie_lens/100k-movies', split="train")
選擇基礎特征
ratings = ratings.map(lambda x: {
"movie_id": tf.strings.to_number(x["movie_id"]),
"user_id": tf.strings.to_number(x["user_id"])
})
movies = movies.map(lambda x: tf.strings.to_number(x["movie_id"]))
構模組化型
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))
随機shuffle對訓練集和測試集進行分割,Randomly shuffle data and split between train and test.
tf.random.set_seed(42)
shuffled = ratings.shuffle(100_000, seed=42, reshuffle_each_iteration=False)
train = shuffled.take(80_000)
test = shuffled.skip(80_000).take(20_000)
# 模型訓練.
model.fit(train.batch(4096), epochs=5)
# 模型評估.
model.evaluate(test.batch(4096), return_dict=True)
使用教程
因為該項目剛剛開始,是以教程不是很多,我們僅舉一個簡單的例子,有興趣的可以去參考文獻學習,内容很少,非常适合初學者。
我們先使用帶有TFRS的MovieLens 100K資料集建構一個簡單的矩陣分解模型。我們可以使用此模型為給定使用者推薦電影。
入門代碼
1. 安裝TFRS & 資料集pip install -q tensorflow-recommenders
pip install -q --upgrade tensorflow-datasets
2. 導入功能子產品 from typing import Dict, Text
import numpy as np
import tensorflow as tf
import tensorflow_datasets as tfds
import tensorflow_recommenders as tfrs
3. 讀取資料 # 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"])
4. 建構詞彙表并且将使用者id和電影的title轉為整數,用于後續embedding 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)
5. 模型定義
我們繼承tfrs.Model來定義TFRS模型,并且實作compute_loss.
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)
定義兩個模型&檢索任務。
# 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)
)
)
6. 模型訓練&評估 # 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.ann.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]}")
小結
這是TensorFlow Recommenders Team使用TensorFlow建構推薦系統模型的庫。目前是工程的前期,有志之士可以速速加入學習,今後大師指日可待!加油加油加油。
參考文獻
- Github:https://github.com/tensorflow/recommenders
- Tutorial:https://www.tensorflow.org/recommenders/examples/quickstart
- API:https://www.tensorflow.org/recommenders/api_docs/python/tfrs/
- Google Open-Sources TensorFlow Recommenders (TFRS): Helping Users Find What They Love
我是一品煉丹師時晴,歡迎大家關注我們的公衆号:
煉丹筆記!