This project is about recommendation system including rank&match models and metrics which are all implemented by tensorflow 2.x.
You can use these models with model.fit() ，and model.predict() through tf.keras.Model.
The implement for tensorflow 1.x is in this github.
To install, simply use pip to pull down from PyPI.
pip install deep-rec-kitIf you want to use latest features, or develop new features, you can also build it from source.
git clone https://github.com/QunBB/RecSys
cd RecSys
pip install -e ....... means that it will be continuously updated.
| model | paper | blog | implemented |
|---|---|---|---|
| ...... | |||
| Dual Augmented Two-tower Model | [DLP-KDD 2021] A Dual Augmented Two-tower Model for Online Large-scale Recommendation | zhihu | |
| ComiRec | [KDD 2020] Controllable Multi-Interest Framework for Recommendation | zhihu | |
| MIND | [CIKM 2019] Multi-Interest Network with Dynamic Routing for Recommendation at Tmall | zhihu | |
| Youtube DNN | [RecSys 2016] Deep Neural Networks for YouTube Recommendations | zhihu |
Metrics for recommendation system.
It will be coming soon.
importnumpyasnpimporttensorflowastffromrecsys.featureimportField, Taskfromrecsys.multidomain.pepnetimportpepnettask_list= [
Task(name='click'),
Task(name='like'),
Task(name='fav')
]
num_domain=3defcreate_model():
fields= [
Field('uid', vocabulary_size=100),
Field('item_id', vocabulary_size=20, belong='item'),
Field('his_item_id', vocabulary_size=20, emb='item_id', length=20, belong='history'),
Field('context_id', vocabulary_size=20, belong='context'),
# domain's fieldsField(f'domain_id', vocabulary_size=num_domain, belong='domain'),
Field(f'domain_impression', vocabulary_size=1, belong='domain', dtype="float32")
]
model=pepnet(fields, task_list, [64, 32],
history_agg='attention', agg_kwargs={}
# history_agg='transformer', agg_kwargs={'num_layers': 1, 'd_model': 4, 'num_heads': 2, 'dff': 64}
)
print(model.summary())
returnmodeldefcreate_dataset():
n_samples=2000np.random.seed(2024)
data= {
'uid': np.random.randint(0, 100, [n_samples]),
'item_id': np.random.randint(0, 20, [n_samples]),
'his_item_id': np.random.randint(0, 20, [n_samples, 20]),
'context_id': np.random.randint(0, 20, [n_samples]),
'domain_id': np.random.randint(0, num_domain, [n_samples]),
'domain_impression': np.random.random([n_samples])
}
labels= {t.name: np.random.randint(0, 2, [n_samples]) fortintask_list}
returndata, labelsif__name__=='__main__':
model=create_model()
data, labels=create_dataset()
model.compile(optimizer='adam', loss=tf.keras.losses.BinaryCrossentropy(), metrics=['accuracy'])
model.fit(data, labels, batch_size=32, epochs=10)Those layers with prefix "dnn" will use the adam optimizer, and adagrad for prefix "embedding". Also, you must have the default optimizer for legacy layers.
importtensorflowastffromrecsys.featureimportField, Taskfromrecsys.multidomain.pepnetimportpepnettask_list= [
Task(name='click'),
Task(name='like'),
Task(name='fav')
]
num_domain=3defcreate_model():
# absolutely same as the above ......defcreate_dataset():
# absolutely same as the above ......deftrain(data, labels):
model=create_model()
model.compile(optimizer={'dnn': 'adam', 'embedding': 'Adagrad', 'default': 'adam'},
loss=tf.keras.losses.BinaryCrossentropy(),
metrics=['accuracy'])
model.fit(data, labels, batch_size=32, epochs=10)
checkpoint=tf.train.Checkpoint(model=model)
checkpoint.save('./pepnet-saved/model.ckpt')
print(model({k: v[:10] fork, vindata.items()}))
print(model.optimizer['embedding'].variables())
defrestore(data):
model=create_model()
model.compile(optimizer={'dnn': 'adam', 'embedding': 'Adagrad', 'default': 'adam'},
loss=tf.keras.losses.BinaryCrossentropy(),
metrics=['accuracy'])
checkpoint=tf.train.Checkpoint(model=model)
checkpoint.restore('./pepnet-saved/model.ckpt-1')
print(model({k: v[:10] fork, vindata.items()}))
forlayerinmodel.optimizer:
model.optimizer[layer].build(model.special_layer_variables[layer])
print(model.optimizer['embedding'].variables())
if__name__=='__main__':
data, labels=create_dataset()
train(data, labels)
restore(data)