replay-rec 0.18.0__tar.gz → 0.18.1__tar.gz

{replay_rec-0.18.0 → replay_rec-0.18.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: replay-rec
-Version: 0.18.0
+Version: 0.18.1
 Summary: RecSys Library
 Home-page: https://sb-ai-lab.github.io/RePlay/
 License: Apache-2.0
@@ -21,10 +21,13 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Provides-Extra: all
 Provides-Extra: spark
 Provides-Extra: torch
+Provides-Extra: torch-openvino
 Requires-Dist: fixed-install-nmslib (==2.1.2)
 Requires-Dist: hnswlib (>=0.7.0,<0.8.0)
-Requires-Dist: lightning (>=2.0.2,<=2.4.0) ; extra == "torch" or extra == "all"
+Requires-Dist: lightning (>=2.0.2,<=2.4.0) ; extra == "torch" or extra == "torch-openvino" or extra == "all"
 Requires-Dist: numpy (>=1.20.0)
+Requires-Dist: onnx (>=1.16.2,<1.17.0) ; extra == "torch-openvino" or extra == "all"
+Requires-Dist: openvino (>=2024.3.0,<2024.4.0) ; extra == "torch-openvino" or extra == "all"
 Requires-Dist: optuna (>=3.2.0,<3.3.0)
 Requires-Dist: pandas (>=1.3.5,<=2.2.2)
 Requires-Dist: polars (>=1.0.0,<1.1.0)
@@ -32,10 +35,10 @@ Requires-Dist: psutil (>=6.0.0,<6.1.0)
 Requires-Dist: pyarrow (>=12.0.1)
 Requires-Dist: pyspark (>=3.0,<3.6) ; (python_full_version >= "3.8.1" and python_version < "3.11") and (extra == "spark" or extra == "all")
 Requires-Dist: pyspark (>=3.4,<3.6) ; (python_version >= "3.11" and python_version < "3.12") and (extra == "spark" or extra == "all")
-Requires-Dist: pytorch-ranger (>=0.1.1,<0.2.0) ; extra == "torch" or extra == "all"
+Requires-Dist: pytorch-ranger (>=0.1.1,<0.2.0) ; extra == "torch" or extra == "torch-openvino" or extra == "all"
 Requires-Dist: scikit-learn (>=1.0.2,<2.0.0)
 Requires-Dist: scipy (>=1.8.1,<2.0.0)
-Requires-Dist: torch (>=1.8,<=2.4.0) ; extra == "torch" or extra == "all"
+Requires-Dist: torch (>=1.8,<=2.5.0) ; extra == "torch" or extra == "torch-openvino" or extra == "all"
 Project-URL: Repository, https://github.com/sb-ai-lab/RePlay
 Description-Content-Type: text/markdown
 
@@ -44,11 +47,15 @@ Description-Content-Type: text/markdown
 
 [![GitHub License](https://img.shields.io/github/license/sb-ai-lab/RePlay)](https://github.com/sb-ai-lab/RePlay/blob/main/LICENSE)
 [![PyPI - Version](https://img.shields.io/pypi/v/replay-rec)](https://pypi.org/project/replay-rec)
+[![Documentation](https://img.shields.io/badge/docs-latest-brightgreen.svg)](https://sb-ai-lab.github.io/RePlay/)
 [![PyPI - Downloads](https://img.shields.io/pypi/dm/replay-rec)](https://pypistats.org/packages/replay-rec)
 <br>
 [![GitHub Workflow Status (with event)](https://img.shields.io/github/actions/workflow/status/sb-ai-lab/replay/main.yml)](https://github.com/sb-ai-lab/RePlay/actions/workflows/main.yml?query=branch%3Amain)
+[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/charliermarsh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
+[![Python Versions](https://img.shields.io/pypi/pyversions/replay-rec.svg?logo=python&logoColor=white)](https://pypi.org/project/replay-rec)
 [![Join the community on GitHub Discussions](https://badgen.net/badge/join%20the%20discussion/on%20github/black?icon=github)](https://github.com/sb-ai-lab/RePlay/discussions)
 
+
 RePlay is an advanced framework designed to facilitate the development and evaluation of recommendation systems. It provides a robust set of tools covering the entire lifecycle of a recommendation system pipeline:
 
 ## 🚀 Features:
@@ -63,61 +70,25 @@ RePlay is an advanced framework designed to facilitate the development and evalu
 1. **Diverse Hardware Support:** Compatible with various hardware configurations including CPU, GPU, Multi-GPU.
 2. **Cluster Computing Integration:** Integrating with PySpark for distributed computing, enabling scalability for large-scale recommendation systems.
 
-## 📖 Documentation is available [here](https://sb-ai-lab.github.io/RePlay/).
-
 <a name="toc"></a>
 # Table of Contents
 
-* [Installation](#installation)
 * [Quickstart](#quickstart)
+* [Installation](#installation)
 * [Resources](#examples)
 * [Contributing to RePlay](#contributing)
 
 
-<a name="installation"></a>
-## 🔧 Installation
-
-Installation via `pip` package manager is recommended by default:
-
-```bash
-pip install replay-rec
-```
-
-In this case it will be installed the `core` package without `PySpark` and `PyTorch` dependencies.
-Also `experimental` submodule will not be installed.
-
-To install `experimental` submodule please specify the version with `rc0` suffix.
-For example:
-
-```bash
-pip install replay-rec==XX.YY.ZZrc0
-```
-
-### Extras
-
-In addition to the core package, several extras are also provided, including:
-- `[spark]`: Install PySpark functionality
-- `[torch]`: Install PyTorch and Lightning functionality
-- `[all]`: `[spark]` `[torch]`
+<a name="quickstart"></a>
+## 📈 Quickstart
 
-Example:
 ```bash
-# Install core package with PySpark dependency
-pip install replay-rec[spark]
-
-# Install package with experimental submodule and PySpark dependency
-pip install replay-rec[spark]==XX.YY.ZZrc0
+pip install replay-rec[all]
 ```
 
-To build RePlay from sources please use the [instruction](CONTRIBUTING.md#installing-from-the-source).
-
-If you encounter an error during RePlay installation, check the [troubleshooting](https://sb-ai-lab.github.io/RePlay/pages/installation.html#troubleshooting) guide.
-
-
-<a name="quickstart"></a>
-## 📈 Quickstart (PySpark-based)
-
+Pyspark-based model and [fast](https://github.com/sb-ai-lab/RePlay/blob/main/examples/11_sasrec_dataframes_comparison.ipynb) polars-based data preprocessing:
 ```python
+from polars import from_pandas
 from rs_datasets import MovieLens
 
 from replay.data import Dataset, FeatureHint, FeatureInfo, FeatureSchema, FeatureType
@@ -131,10 +102,10 @@ from replay.splitters import RatioSplitter
 spark = State().session
 
 ml_1m = MovieLens("1m")
-K=10
+K = 10
 
-# data preprocessing
-interactions = convert2spark(ml_1m.ratings)
+# convert data to polars
+interactions = from_pandas(ml_1m.ratings)
 
 # data splitting
 splitter = RatioSplitter(
@@ -148,7 +119,7 @@ splitter = RatioSplitter(
 )
 train, test = splitter.split(interactions)
 
-# dataset creating
+# datasets creation
 feature_schema = FeatureSchema(
     [
         FeatureInfo(
@@ -174,20 +145,18 @@ feature_schema = FeatureSchema(
     ]
 )
 
-train_dataset = Dataset(
-    feature_schema=feature_schema,
-    interactions=train,
-)
-test_dataset = Dataset(
-    feature_schema=feature_schema,
-    interactions=test,
-)
+train_dataset = Dataset(feature_schema=feature_schema, interactions=train)
+test_dataset = Dataset(feature_schema=feature_schema, interactions=test)
 
 # data encoding
 encoder = DatasetLabelEncoder()
 train_dataset = encoder.fit_transform(train_dataset)
 test_dataset = encoder.transform(test_dataset)
 
+# convert datasets to spark
+train_dataset.to_spark()
+test_dataset.to_spark()
+
 # model training
 model = ItemKNN()
 model.fit(train_dataset)
@@ -214,6 +183,44 @@ metrics.add_result("ItemKNN", recs)
 print(metrics.results)
 ```
 
+<a name="installation"></a>
+## 🔧 Installation
+
+Installation via `pip` package manager is recommended by default:
+
+```bash
+pip install replay-rec
+```
+
+In this case it will be installed the `core` package without `PySpark` and `PyTorch` dependencies.
+Also `experimental` submodule will not be installed.
+
+To install `experimental` submodule please specify the version with `rc0` suffix.
+For example:
+
+```bash
+pip install replay-rec==XX.YY.ZZrc0
+```
+
+### Extras
+
+In addition to the core package, several extras are also provided, including:
+- `[spark]`: Install PySpark functionality
+- `[torch]`: Install PyTorch and Lightning functionality
+- `[all]`: `[spark]` `[torch]`
+
+Example:
+```bash
+# Install core package with PySpark dependency
+pip install replay-rec[spark]
+
+# Install package with experimental submodule and PySpark dependency
+pip install replay-rec[spark]==XX.YY.ZZrc0
+```
+
+To build RePlay from sources please use the [instruction](CONTRIBUTING.md#installing-from-the-source).
+
+
 <a name="examples"></a>
 ## 📑  Resources
 
@@ -226,14 +233,19 @@ print(metrics.results)
 6. [06_item2item_recommendations.ipynb](https://github.com/sb-ai-lab/RePlay/blob/main/examples/06_item2item_recommendations.ipynb) - Item to Item recommendations example.
 7. [07_filters.ipynb](https://github.com/sb-ai-lab/RePlay/blob/main/examples/07_filters.ipynb) - An example of using filters.
 8. [08_recommending_for_categories.ipynb](https://github.com/sb-ai-lab/RePlay/blob/main/examples/08_recommending_for_categories.ipynb) - An example of recommendation for product categories.
-9. [09_sasrec_example.ipynb](https://github.com/sb-ai-lab/RePlay/blob/main/examples/09_sasrec_example.ipynb) - An example of using transformers to generate recommendations.
-
+9. [09_sasrec_example.ipynb](https://github.com/sb-ai-lab/RePlay/blob/main/examples/09_sasrec_example.ipynb) - An example of using transformer-based SASRec model to generate recommendations.
+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**:
 	- [Replay for offline recommendations, AI Journey 2021](https://www.youtube.com/watch?v=ejQZKGAG0xs)
 
 * **Research papers**:
+    - [RePlay: a Recommendation Framework for Experimentation and Production Use](https://arxiv.org/abs/2409.07272) Alexey Vasilev, Anna Volodkevich, Denis Kulandin, Tatiana Bysheva, Anton Klenitskiy. In The 18th ACM Conference on Recommender Systems (RecSys '24)
 	- [Turning Dross Into Gold Loss: is BERT4Rec really better than SASRec?](https://doi.org/10.1145/3604915.3610644) Anton Klenitskiy, Alexey Vasilev. In The 17th ACM Conference on Recommender Systems (RecSys '23)
     - [The Long Tail of Context: Does it Exist and Matter?](https://arxiv.org/abs/2210.01023). Konstantin Bauman, Alexey Vasilev, Alexander Tuzhilin. In Workshop on Context-Aware Recommender Systems (CARS) (RecSys '22)
     - [Multiobjective Evaluation of Reinforcement Learning Based Recommender Systems](https://doi.org/10.1145/3523227.3551485). Alexey Grishanov, Anastasia Ianina, Konstantin Vorontsov. In The 16th ACM Conference on Recommender Systems (RecSys '22)
@@ -244,3 +256,4 @@ print(metrics.results)
 
 We welcome community contributions. For details please check our [contributing guidelines](CONTRIBUTING.md).
 
+

{replay_rec-0.18.0 → replay_rec-0.18.1}/README.md

@@ -3,11 +3,15 @@
 
 [![GitHub License](https://img.shields.io/github/license/sb-ai-lab/RePlay)](https://github.com/sb-ai-lab/RePlay/blob/main/LICENSE)
 [![PyPI - Version](https://img.shields.io/pypi/v/replay-rec)](https://pypi.org/project/replay-rec)
+[![Documentation](https://img.shields.io/badge/docs-latest-brightgreen.svg)](https://sb-ai-lab.github.io/RePlay/)
 [![PyPI - Downloads](https://img.shields.io/pypi/dm/replay-rec)](https://pypistats.org/packages/replay-rec)
 <br>
 [![GitHub Workflow Status (with event)](https://img.shields.io/github/actions/workflow/status/sb-ai-lab/replay/main.yml)](https://github.com/sb-ai-lab/RePlay/actions/workflows/main.yml?query=branch%3Amain)
+[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/charliermarsh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
+[![Python Versions](https://img.shields.io/pypi/pyversions/replay-rec.svg?logo=python&logoColor=white)](https://pypi.org/project/replay-rec)
 [![Join the community on GitHub Discussions](https://badgen.net/badge/join%20the%20discussion/on%20github/black?icon=github)](https://github.com/sb-ai-lab/RePlay/discussions)
 
+
 RePlay is an advanced framework designed to facilitate the development and evaluation of recommendation systems. It provides a robust set of tools covering the entire lifecycle of a recommendation system pipeline:
 
 ## 🚀 Features:
@@ -22,61 +26,25 @@ RePlay is an advanced framework designed to facilitate the development and evalu
 1. **Diverse Hardware Support:** Compatible with various hardware configurations including CPU, GPU, Multi-GPU.
 2. **Cluster Computing Integration:** Integrating with PySpark for distributed computing, enabling scalability for large-scale recommendation systems.
 
-## 📖 Documentation is available [here](https://sb-ai-lab.github.io/RePlay/).
-
 <a name="toc"></a>
 # Table of Contents
 
-* [Installation](#installation)
 * [Quickstart](#quickstart)
+* [Installation](#installation)
 * [Resources](#examples)
 * [Contributing to RePlay](#contributing)
 
 
-<a name="installation"></a>
-## 🔧 Installation
-
-Installation via `pip` package manager is recommended by default:
-
-```bash
-pip install replay-rec
-```
-
-In this case it will be installed the `core` package without `PySpark` and `PyTorch` dependencies.
-Also `experimental` submodule will not be installed.
-
-To install `experimental` submodule please specify the version with `rc0` suffix.
-For example:
-
-```bash
-pip install replay-rec==XX.YY.ZZrc0
-```
-
-### Extras
-
-In addition to the core package, several extras are also provided, including:
-- `[spark]`: Install PySpark functionality
-- `[torch]`: Install PyTorch and Lightning functionality
-- `[all]`: `[spark]` `[torch]`
+<a name="quickstart"></a>
+## 📈 Quickstart
 
-Example:
 ```bash
-# Install core package with PySpark dependency
-pip install replay-rec[spark]
-
-# Install package with experimental submodule and PySpark dependency
-pip install replay-rec[spark]==XX.YY.ZZrc0
+pip install replay-rec[all]
 ```
 
-To build RePlay from sources please use the [instruction](CONTRIBUTING.md#installing-from-the-source).
-
-If you encounter an error during RePlay installation, check the [troubleshooting](https://sb-ai-lab.github.io/RePlay/pages/installation.html#troubleshooting) guide.
-
-
-<a name="quickstart"></a>
-## 📈 Quickstart (PySpark-based)
-
+Pyspark-based model and [fast](https://github.com/sb-ai-lab/RePlay/blob/main/examples/11_sasrec_dataframes_comparison.ipynb) polars-based data preprocessing:
 ```python
+from polars import from_pandas
 from rs_datasets import MovieLens
 
 from replay.data import Dataset, FeatureHint, FeatureInfo, FeatureSchema, FeatureType
@@ -90,10 +58,10 @@ from replay.splitters import RatioSplitter
 spark = State().session
 
 ml_1m = MovieLens("1m")
-K=10
+K = 10
 
-# data preprocessing
-interactions = convert2spark(ml_1m.ratings)
+# convert data to polars
+interactions = from_pandas(ml_1m.ratings)
 
 # data splitting
 splitter = RatioSplitter(
@@ -107,7 +75,7 @@ splitter = RatioSplitter(
 )
 train, test = splitter.split(interactions)
 
-# dataset creating
+# datasets creation
 feature_schema = FeatureSchema(
     [
         FeatureInfo(
@@ -133,20 +101,18 @@ feature_schema = FeatureSchema(
     ]
 )
 
-train_dataset = Dataset(
-    feature_schema=feature_schema,
-    interactions=train,
-)
-test_dataset = Dataset(
-    feature_schema=feature_schema,
-    interactions=test,
-)
+train_dataset = Dataset(feature_schema=feature_schema, interactions=train)
+test_dataset = Dataset(feature_schema=feature_schema, interactions=test)
 
 # data encoding
 encoder = DatasetLabelEncoder()
 train_dataset = encoder.fit_transform(train_dataset)
 test_dataset = encoder.transform(test_dataset)
 
+# convert datasets to spark
+train_dataset.to_spark()
+test_dataset.to_spark()
+
 # model training
 model = ItemKNN()
 model.fit(train_dataset)
@@ -173,6 +139,44 @@ metrics.add_result("ItemKNN", recs)
 print(metrics.results)
 ```
 
+<a name="installation"></a>
+## 🔧 Installation
+
+Installation via `pip` package manager is recommended by default:
+
+```bash
+pip install replay-rec
+```
+
+In this case it will be installed the `core` package without `PySpark` and `PyTorch` dependencies.
+Also `experimental` submodule will not be installed.
+
+To install `experimental` submodule please specify the version with `rc0` suffix.
+For example:
+
+```bash
+pip install replay-rec==XX.YY.ZZrc0
+```
+
+### Extras
+
+In addition to the core package, several extras are also provided, including:
+- `[spark]`: Install PySpark functionality
+- `[torch]`: Install PyTorch and Lightning functionality
+- `[all]`: `[spark]` `[torch]`
+
+Example:
+```bash
+# Install core package with PySpark dependency
+pip install replay-rec[spark]
+
+# Install package with experimental submodule and PySpark dependency
+pip install replay-rec[spark]==XX.YY.ZZrc0
+```
+
+To build RePlay from sources please use the [instruction](CONTRIBUTING.md#installing-from-the-source).
+
+
 <a name="examples"></a>
 ## 📑  Resources
 
@@ -185,14 +189,19 @@ print(metrics.results)
 6. [06_item2item_recommendations.ipynb](https://github.com/sb-ai-lab/RePlay/blob/main/examples/06_item2item_recommendations.ipynb) - Item to Item recommendations example.
 7. [07_filters.ipynb](https://github.com/sb-ai-lab/RePlay/blob/main/examples/07_filters.ipynb) - An example of using filters.
 8. [08_recommending_for_categories.ipynb](https://github.com/sb-ai-lab/RePlay/blob/main/examples/08_recommending_for_categories.ipynb) - An example of recommendation for product categories.
-9. [09_sasrec_example.ipynb](https://github.com/sb-ai-lab/RePlay/blob/main/examples/09_sasrec_example.ipynb) - An example of using transformers to generate recommendations.
-
+9. [09_sasrec_example.ipynb](https://github.com/sb-ai-lab/RePlay/blob/main/examples/09_sasrec_example.ipynb) - An example of using transformer-based SASRec model to generate recommendations.
+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**:
 	- [Replay for offline recommendations, AI Journey 2021](https://www.youtube.com/watch?v=ejQZKGAG0xs)
 
 * **Research papers**:
+    - [RePlay: a Recommendation Framework for Experimentation and Production Use](https://arxiv.org/abs/2409.07272) Alexey Vasilev, Anna Volodkevich, Denis Kulandin, Tatiana Bysheva, Anton Klenitskiy. In The 18th ACM Conference on Recommender Systems (RecSys '24)
 	- [Turning Dross Into Gold Loss: is BERT4Rec really better than SASRec?](https://doi.org/10.1145/3604915.3610644) Anton Klenitskiy, Alexey Vasilev. In The 17th ACM Conference on Recommender Systems (RecSys '23)
     - [The Long Tail of Context: Does it Exist and Matter?](https://arxiv.org/abs/2210.01023). Konstantin Bauman, Alexey Vasilev, Alexander Tuzhilin. In Workshop on Context-Aware Recommender Systems (CARS) (RecSys '22)
     - [Multiobjective Evaluation of Reinforcement Learning Based Recommender Systems](https://doi.org/10.1145/3523227.3551485). Alexey Grishanov, Anastasia Ianina, Konstantin Vorontsov. In The 16th ACM Conference on Recommender Systems (RecSys '22)
@@ -202,3 +211,4 @@ print(metrics.results)
 ## 💡 Contributing to RePlay
 
 We welcome community contributions. For details please check our [contributing guidelines](CONTRIBUTING.md).
+

{replay_rec-0.18.0 → replay_rec-0.18.1}/pyproject.toml

@@ -41,7 +41,7 @@ exclude = [
     "replay/conftest.py",
     "replay/experimental",
 ]
-version = "0.18.0"
+version = "0.18.1"
 
 [tool.poetry.dependencies]
 python = ">=3.8.1, <3.12"
@@ -53,11 +53,13 @@ scipy = "^1.8.1"
 psutil = "~6.0.0"
 scikit-learn = "^1.0.2"
 pyarrow = ">=12.0.1"
+openvino = {version = "~2024.3.0", optional = true}
+onnx = {version = "~1.16.2", optional = true}
 pyspark = [
     {version = ">=3.4,<3.6", python = ">=3.11,<3.12", optional = true},
     {version = ">=3.0,<3.6", python = ">=3.8.1,<3.11", optional = true},
 ]
-torch = {version = ">=1.8, <=2.4.0", optional = true}
+torch = {version = ">=1.8, <=2.5.0", optional = true}
 lightning = {version = ">=2.0.2, <=2.4.0", optional = true}
 pytorch-ranger = {version = "^0.1.1", optional = true}
 fixed-install-nmslib = "2.1.2"
@@ -66,7 +68,8 @@ hnswlib = "^0.7.0"
 [tool.poetry.extras]
 spark = ["pyspark"]
 torch = ["torch", "pytorch-ranger", "lightning"]
-all = ["pyspark", "torch", "pytorch-ranger", "lightning"]
+torch-openvino = ["torch", "pytorch-ranger", "lightning", "openvino", "onnx"]
+all = ["pyspark", "torch", "pytorch-ranger", "lightning", "openvino", "onnx"]
 
 [tool.poetry.group.dev.dependencies]
 jupyter = "~1.0.0"
@@ -85,10 +88,11 @@ myst-parser = "1.0.0"
 ghp-import = "2.1.0"
 docutils = "0.16"
 data-science-types = "0.2.23"
+filelock = "~3.14.0"
 
 [tool.poetry-dynamic-versioning]
 enable = false
-format-jinja = """0.18.0{{ env['PACKAGE_SUFFIX'] }}"""
+format-jinja = """0.18.1{{ env['PACKAGE_SUFFIX'] }}"""
 vcs = "git"
 
 [tool.ruff]

{replay_rec-0.18.0 → replay_rec-0.18.1}/replay/__init__.py

@@ -1,3 +1,3 @@
 """ RecSys library """
 
-__version__ = "0.18.0"
+__version__ = "0.18.1"

{replay_rec-0.18.0 → replay_rec-0.18.1}/replay/data/dataset.py

@@ -458,13 +458,23 @@ class Dataset:
             if feature.feature_hint in [FeatureHint.ITEM_ID, FeatureHint.QUERY_ID]:
                 return nunique(self._ids_feature_map[feature.feature_hint], column)
             assert feature.feature_source
+            if feature.feature_type == FeatureType.CATEGORICAL_LIST:
+                if self.is_spark:
+                    data = (
+                        self._feature_source_map[feature.feature_source]
+                        .select(column)
+                        .withColumn(column, sf.explode(column))
+                    )
+                else:
+                    data = self._feature_source_map[feature.feature_source][[column]].explode(column)
+                return nunique(data, column)
             return nunique(self._feature_source_map[feature.feature_source], column)
 
         return callback
 
     def _set_cardinality(self, features_list: Sequence[FeatureInfo]) -> None:
         for feature in features_list:
-            if feature.feature_type == FeatureType.CATEGORICAL:
+            if feature.feature_type in [FeatureType.CATEGORICAL, FeatureType.CATEGORICAL_LIST]:
                 feature._set_cardinality_callback(self._get_cardinality(feature))
 
     def _fill_feature_schema(self, feature_schema: FeatureSchema) -> FeatureSchema:
@@ -581,6 +591,7 @@ class Dataset:
         data: DataFrameLike,
         column: str,
         source: FeatureSource,
+        feature_type: FeatureType,
         cardinality: Optional[int],
     ) -> None:
         """
@@ -593,6 +604,16 @@ class Dataset:
         Option: Keep this criterion, but suggest the user to disable the check if he understands
         that the criterion will not pass.
         """
+        if feature_type == FeatureType.CATEGORICAL_LIST:  # explode column if list
+            data = data.withColumn(column, sf.explode(column)) if self.is_spark else data[[column]].explode(column)
+
+            if self.is_pandas:
+                try:
+                    data[column] = data[column].astype(int)
+                except Exception:
+                    msg = f"IDs in {source.name}.{column} are not encoded. They are not int."
+                    raise ValueError(msg)
+
         if self.is_pandas:
             is_int = np.issubdtype(dict(data.dtypes)[column], int)
         elif self.is_spark:
@@ -632,6 +653,7 @@ class Dataset:
                     self.interactions,
                     feature.column,
                     FeatureSource.INTERACTIONS,
+                    feature.feature_type,
                     feature.cardinality,
                 )
                 if self.item_features is not None:
@@ -639,6 +661,7 @@ class Dataset:
                         self.item_features,
                         feature.column,
                         FeatureSource.ITEM_FEATURES,
+                        feature.feature_type,
                         feature.cardinality,
                     )
             elif feature.feature_hint == FeatureHint.QUERY_ID:
@@ -646,6 +669,7 @@ class Dataset:
                     self.interactions,
                     feature.column,
                     FeatureSource.INTERACTIONS,
+                    feature.feature_type,
                     feature.cardinality,
                 )
                 if self.query_features is not None:
@@ -653,6 +677,7 @@ class Dataset:
                         self.query_features,
                         feature.column,
                         FeatureSource.QUERY_FEATURES,
+                        feature.feature_type,
                         feature.cardinality,
                     )
             else:
@@ -661,6 +686,7 @@ class Dataset:
                     data,
                     feature.column,
                     feature.feature_source,
+                    feature.feature_type,
                     feature.cardinality,
                 )
 

{replay_rec-0.18.0 → replay_rec-0.18.1}/replay/data/dataset_utils/dataset_label_encoder.py

@@ -8,8 +8,8 @@ Contains classes for encoding categorical data
 import warnings
 from typing import Dict, Iterable, Iterator, Optional, Sequence, Set, Union
 
-from replay.data import Dataset, FeatureHint, FeatureSchema, FeatureSource
-from replay.preprocessing import LabelEncoder, LabelEncodingRule
+from replay.data import Dataset, FeatureHint, FeatureSchema, FeatureSource, FeatureType
+from replay.preprocessing import LabelEncoder, LabelEncodingRule, SequenceEncodingRule
 from replay.preprocessing.label_encoder import HandleUnknownStrategies
 
 
@@ -62,7 +62,10 @@ class DatasetLabelEncoder:
 
         self._fill_features_columns(dataset.feature_schema)
         for column, feature_info in dataset.feature_schema.categorical_features.items():
-            encoding_rule = LabelEncodingRule(
+            encoding_rule_class = (
+                SequenceEncodingRule if feature_info.feature_type == FeatureType.CATEGORICAL_LIST else LabelEncodingRule
+            )
+            encoding_rule = encoding_rule_class(
                 column, handle_unknown=self._handle_unknown_rule, default_value=self._default_value_rule
             )
             if feature_info.feature_hint == FeatureHint.QUERY_ID: