feat: add Random algorithm to GeneralRecommenders

docs/source/index.rst

@@ -11,7 +11,7 @@ Introduction
 RecBole is a unified, comprehensive and efficient framework developed based on PyTorch.
 It aims to help the researchers to reproduce and develop recommendation models.
 
-In the lastest release, our library includes 88 recommendation algorithms `[Model List]`_, covering four major categories:
+In the lastest release, our library includes 89 recommendation algorithms `[Model List]`_, covering four major categories:
 
 - General Recommendation
 - Sequential Recommendation

docs/source/user_guide/model/general/random.rst

@@ -0,0 +1,38 @@
+Random
+===========
+
+Introduction
+---------------------
+
+When discussing recommendation systems, accuracy is often regarded as the most crucial metric. 
+However, besides accuracy, several other key metrics can evaluate the effectiveness of a recommendation system, such as diversity, coverage, and efficiency. 
+In this context, the random recommendation algorithm is a valuable baseline. 
+In terms of implementation, for a given user and item, the random recommendation algorithm provides a random rating.
+
+Running with RecBole
+
+
+
+**A Running Example:**
+
+Write the following code to a python file, such as `run.py`
+
+.. code:: python
+
+   from recbole.quick_start import run_recbole
+
+   run_recbole(model='Random', dataset='ml-100k')
+
+And then:
+
+.. code:: bash
+
+   python run.py
+
+
+If you want to change parameters, dataset or evaluation settings, take a look at
+
+- :doc:`../../../user_guide/config_settings`
+- :doc:`../../../user_guide/data_intro`
+- :doc:`../../../user_guide/train_eval_intro`
+- :doc:`../../../user_guide/usage`

docs/source/user_guide/model_intro.rst

@@ -42,6 +42,7 @@ task of top-n recommendation. All the collaborative filter(CF) based models are
    model/general/nceplrec
    model/general/simplex
    model/general/ncl
+   model/general/random
    model/general/diffrec
    model/general/ldiffrec
 

recbole/model/general_recommender/__init__.py

@@ -21,6 +21,7 @@
 from recbole.model.general_recommender.nncf import NNCF
 from recbole.model.general_recommender.pop import Pop
 from recbole.model.general_recommender.ract import RaCT
+from recbole.model.general_recommender.random import Random
 from recbole.model.general_recommender.recvae import RecVAE
 from recbole.model.general_recommender.slimelastic import SLIMElastic
 from recbole.model.general_recommender.spectralcf import SpectralCF

recbole/model/general_recommender/random.py

@@ -0,0 +1,44 @@
+# -*- coding: utf-8 -*-
+# @Time   : 2023/03/01
+# @Author : João Felipe Guedes
+# @Email  : guedes.joaofelipe@poli.ufrj.br
+# UPDATE
+
+r"""
+Random
+################################################
+
+"""
+
+import torch
+import random
+
+from recbole.model.abstract_recommender import GeneralRecommender
+from recbole.utils import InputType, ModelType
+
+
+class Random(GeneralRecommender):
+    """Random is an fundamental model that recommends random items."""
+
+    input_type = InputType.POINTWISE
+    type = ModelType.TRADITIONAL
+
+    def __init__(self, config, dataset):
+        super(Random, self).__init__(config, dataset)
+        torch.manual_seed(config["seed"] + self.n_users + self.n_items)
+        self.fake_loss = torch.nn.Parameter(torch.zeros(1))
+
+    def forward(self):
+        pass
+
+    def calculate_loss(self, interaction):
+        return torch.nn.Parameter(torch.zeros(1))
+
+    def predict(self, interaction):
+        return torch.rand(len(interaction)).squeeze(-1)
+
+    def full_sort_predict(self, interaction):
+        batch_user_num = interaction[self.USER_ID].shape[0]
+        result = torch.rand(self.n_items, 1).to(torch.float64)
+        result = torch.repeat_interleave(result.unsqueeze(0), batch_user_num, dim=0)
+        return result.view(-1)

tests/model/test_model_auto.py

@@ -30,6 +30,12 @@ def test_pop(self):
         }
         quick_test(config_dict)
 
+    def test_random(self):
+        config_dict = {
+            "model": "Random",
+        }
+        quick_test(config_dict)
+
     def test_itemknn(self):
         config_dict = {
             "model": "ItemKNN",