Skip to content

Commit

Permalink
Merge branch 'feature/hierarchical_recommender' into 'main'
Browse files Browse the repository at this point in the history 
Add HierarchicalRecommender

See pull request #60
  • Loading branch information
@shashist
shashist committed Nov 11, 2024
2 parents 1d3d813 + 93ec302 commit 4e95eea
Show file tree
Hide file tree
Showing 11 changed files with 2,196 additions and 73 deletions.
3 changes: 2 additions & 1 deletion README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -193,7 +193,8 @@ To build RePlay from sources please use the [instruction](CONTRIBUTING.md#instal
10. [10_bert4rec_example.ipynb](https://github.com/sb-ai-lab/RePlay/blob/main/examples/10_bert4rec_example.ipynb) - An example of using transformer-based BERT4Rec model to generate recommendations.
11. [11_sasrec_dataframes_comparison.ipynb](https://github.com/sb-ai-lab/RePlay/blob/main/examples/11_sasrec_dataframes_comparison.ipynb) - speed comparison of using different frameworks (pandas, polars, pyspark) for data processing during SASRec training.
12. [12_neural_ts_exp.ipynb](https://github.com/sb-ai-lab/RePlay/blob/main/examples/12_neural_ts_exp.ipynb) - An example of using Neural Thompson Sampling bandit model (based on Wide&Deep architecture).

13. [13_personalized_bandit_comparison.ipynb](https://github.com/sb-ai-lab/RePlay/blob/main/examples/13_personalized_bandit_comparison.ipynb) - A comparison of context-free and contextual bandit models.
14. [14_hierarchical_recommender.ipynb](https://github.com/sb-ai-lab/RePlay/blob/main/examples/14_hierarchical_recommender.ipynb) - An example of using HierarchicalRecommender with user-disjoint LinUCB.

### Videos and papers
* **Video guides**:
Expand Down
16 changes: 16 additions & 0 deletions docs/pages/modules/models.rst
View file
Original file line number Diff line number Diff line change
Expand Up @@ -33,6 +33,8 @@ ___________________
"Wrapper for implicit (Experimental)", "Python CPU"
"Wrapper for LightFM (Experimental)", "Python CPU"
"RL-based CQL Recommender (Experimental)", "PySpark"
"ULinUCB (Experimental)", "Python CPU"
"Hierarchical Recommender (Experimental)", "PySpark"

To get more info on how to choose base model, please see this :doc:`page </pages/useful_data/algorithm_selection>`.

Expand Down Expand Up @@ -294,6 +296,11 @@ NeuralTS (Experimental)
.. autoclass:: replay.experimental.models.NeuralTS
:special-members: __init__

ULinUCB Recommender (Experimental)
``````````````````````````````````
.. autoclass:: replay.experimental.models.ULinUCB
:special-members: __init__

CQL Recommender (Experimental)
```````````````````````````````````
Conservative Q-Learning (CQL) algorithm is a SAC-based data-driven deep reinforcement learning algorithm,
Expand All @@ -305,6 +312,15 @@ which achieves state-of-the-art performance in offline RL problems.
:special-members: __init__


Hierarchical models
___________________

Hierarchical Recommender (Experimental)
```````````````````````````````````````
.. autoclass:: replay.experimental.models.HierarchicalRecommender
:special-members: __init__


Wrappers and other models with distributed inference
____________________________________________________
Wrappers for popular recommendation libraries and algorithms
Expand Down
1 change: 1 addition & 0 deletions docs/pages/useful_data/algorithm_selection.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -32,6 +32,7 @@ The same goes for new items.
|Wilson Recommender |Collaborative | binary ratings | + | - |
|UCB |Collaborative | binary ratings | + | + |
|KL-UCB |Collaborative | binary ratings | + | + |
|LinUCB |Collaborative | binary ratings | + | - |
|Random Recommender |Collaborative | converted to unary ratings | + | + |
|K-Nearest Neighbours |Collaborative | converted to unary ratings | + | - |
|Alternating Least Squares |Collaborative | implicit feedback | - | - |
Expand Down
2 changes: 2 additions & 0 deletions docs/pages/useful_data/res_1m.csv
View file
Original file line number Diff line number Diff line change
Expand Up @@ -8,8 +8,10 @@ PopRec,0.645,0.157,0.39,0.244,0.034,0.118,12.3
MultVAE,0.64,0.151,0.396,0.238,0.031,0.123,26.977
NeuroMF,0.627,0.111,0.318,0.193,0.257,0.235,350.737
ADMM SLIM,0.591,0.084,0.304,0.159,0.367,0.237,77.647
Hierarchical Recommender (as HCB), 0.566, 0.081, 0.243, 0.154, 0.030, 0.195, 278.18
Word2Vec,0.515,0.072,0.244,0.138,0.145,0.24,25.133
Wilson,0.414,0.045,0.181,0.092,0.017,0.262,10.034
RandomRec (popular),0.382,0.028,0.142,0.069,0.654,0.318,6.827
uLinUCB, 0.211, 0.014, 0.076, 0.036, 0.008, 0.385, 35.986
RandomRec (uniform),0.183,0.009,0.068,0.026,0.961,0.537,7.898
ALS (Explicit),0.093,0.005,0.033,0.013,0.266,0.684,13.876
79 changes: 7 additions & 72 deletions examples/13_personalized_bandit_comparison.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -162,57 +162,10 @@
},
{
"cell_type": "code",
"execution_count": 6,
"id": "69aa3572",
"execution_count": null,
"id": "f6917809",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"24/10/03 17:31:28 WARN Utils: Your hostname, sudakovcom-MS-7D48 resolves to a loopback address: 127.0.1.1; using 10.255.173.26 instead (on interface enp3s0)\n",
"24/10/03 17:31:28 WARN Utils: Set SPARK_LOCAL_IP if you need to bind to another address\n",
"Using Spark's default log4j profile: org/apache/spark/log4j-defaults.properties\n",
"Setting default log level to \"WARN\".\n",
"To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel).\n",
"24/10/03 17:31:28 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable\n",
"24/10/03 17:31:28 WARN SparkConf: Note that spark.local.dir will be overridden by the value set by the cluster manager (via SPARK_LOCAL_DIRS in mesos/standalone/kubernetes and LOCAL_DIRS in YARN).\n"
]
},
{
"data": {
"text/html": [
"\n",
" <div>\n",
" <p><b>SparkSession - hive</b></p>\n",
" \n",
" <div>\n",
" <p><b>SparkContext</b></p>\n",
"\n",
" <p><a href=\"http://localhost:4040\">Spark UI</a></p>\n",
"\n",
" <dl>\n",
" <dt>Version</dt>\n",
" <dd><code>v3.2.4</code></dd>\n",
" <dt>Master</dt>\n",
" <dd><code>local[*]</code></dd>\n",
" <dt>AppName</dt>\n",
" <dd><code>pyspark-shell</code></dd>\n",
" </dl>\n",
" </div>\n",
" \n",
" </div>\n",
" "
],
"text/plain": [
"<pyspark.sql.session.SparkSession at 0x78a215982bb0>"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"outputs": [],
"source": [
"spark = State().session\n",
"spark"
Expand Down Expand Up @@ -674,13 +627,7 @@
"name": "stderr",
"output_type": "stream",
"text": [
"03-Oct-24 17:32:03, replay, INFO: Columns with ids of users or items are present in mapping. The dataframe will be treated as an interactions log.\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"03-Oct-24 17:32:03, replay, INFO: Columns with ids of users or items are present in mapping. The dataframe will be treated as an interactions log.\n",
"/home/sudakovcom/Desktop/RePlayHDILab2024/.conda/lib/python3.8/site-packages/pyspark/sql/pandas/conversion.py:471: FutureWarning: iteritems is deprecated and will be removed in a future version. Use .items instead.\n",
" arrow_data = [[(c, t) for (_, c), t in zip(pdf_slice.iteritems(), arrow_types)]\n"
]
Expand Down Expand Up @@ -1082,13 +1029,7 @@
"name": "stderr",
"output_type": "stream",
"text": [
"03-Oct-24 17:32:47, replay, INFO: Column with ids of users or items is absent in mapping. The dataframe will be treated as a users'/items' features dataframe.\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"03-Oct-24 17:32:47, replay, INFO: Column with ids of users or items is absent in mapping. The dataframe will be treated as a users'/items' features dataframe.\n",
"/home/sudakovcom/Desktop/RePlayHDILab2024/.conda/lib/python3.8/site-packages/pyspark/sql/pandas/conversion.py:471: FutureWarning: iteritems is deprecated and will be removed in a future version. Use .items instead.\n",
" arrow_data = [[(c, t) for (_, c), t in zip(pdf_slice.iteritems(), arrow_types)]\n"
]
Expand Down Expand Up @@ -1445,13 +1386,7 @@
"name": "stderr",
"output_type": "stream",
"text": [
"03-Oct-24 17:33:02, replay, INFO: Column with ids of users or items is absent in mapping. The dataframe will be treated as a users'/items' features dataframe.\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"03-Oct-24 17:33:02, replay, INFO: Column with ids of users or items is absent in mapping. The dataframe will be treated as a users'/items' features dataframe.\n",
"/home/sudakovcom/Desktop/RePlayHDILab2024/.conda/lib/python3.8/site-packages/pyspark/sql/pandas/conversion.py:471: FutureWarning: iteritems is deprecated and will be removed in a future version. Use .items instead.\n",
" arrow_data = [[(c, t) for (_, c), t in zip(pdf_slice.iteritems(), arrow_types)]\n"
]
Expand Down Expand Up @@ -4198,7 +4133,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.20"
"version": "3.9.16"
}
},
"nbformat": 4,
Expand Down
Loading

0 comments on commit 4e95eea

Please sign in to comment.