datarec-lib 1.3.2__tar.gz

datarec_lib-1.3.2/LICENSE.txt

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2025 Alberto Carlo Maria Mancino
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

datarec_lib-1.3.2/PKG-INFO

@@ -0,0 +1,260 @@
+Metadata-Version: 2.4
+Name: datarec-lib
+Version: 1.3.2
+Summary: Standardized & reproducible data management for recommender systems.
+Author-email: Alberto Carlo Maria Mancino <alberto.mancino@poliba.it>, Salvatore Bufi <salvatore.bufi@poliba.it>, Angela Di Fazio <angela.difazio@poliba.it>, Daniele Malitesta <daniele.malitesta@centralesupelec.fr>, Antonio Ferrara <antonio.ferrara@poliba.it>, Claudio Pomo <claudio.pomo@poliba.it>, Tommaso Di Noia <tommaso.dinoia@poliba.it>
+License: MIT
+Project-URL: Homepage, https://sisinflab.github.io/DataRec/
+Project-URL: Repository, https://github.com/sisinflab/DataRec
+Project-URL: Issues, https://github.com/sisinflab/DataRec/issues
+Keywords: recommender-systems,data,ml,etl
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Operating System :: OS Independent
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: <3.15,>=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE.txt
+Requires-Dist: numpy<3,>=1.23
+Requires-Dist: pandas<3,>=2.3
+Requires-Dist: scikit-learn<2,>=1.6
+Requires-Dist: tqdm<5,>=4.64
+Requires-Dist: gdown<5,>=4.7
+Requires-Dist: requests<3,>=2.28
+Requires-Dist: py7zr<1,>=0.22
+Requires-Dist: PyYAML<7,>=6.0
+Requires-Dist: platformdirs<5,>=4.4.0
+Requires-Dist: appdirs<2,>=1.4.4
+Requires-Dist: typing_extensions
+Requires-Dist: networkx<4,>=3.2
+Requires-Dist: python-igraph<2,>=1.0
+Requires-Dist: PySocks<2,>=1.7
+Provides-Extra: torch
+Requires-Dist: torch>=2.0.0; extra == "torch"
+Provides-Extra: dev
+Requires-Dist: pytest<9,>=8.4; extra == "dev"
+Requires-Dist: build<2,>=1.3; extra == "dev"
+Requires-Dist: twine<7,>=6.2; extra == "dev"
+Requires-Dist: pip-chill<2,>=1.0; extra == "dev"
+Provides-Extra: docs
+Requires-Dist: babel; extra == "docs"
+Requires-Dist: backrefs; extra == "docs"
+Requires-Dist: certifi; extra == "docs"
+Requires-Dist: charset-normalizer; extra == "docs"
+Requires-Dist: click; extra == "docs"
+Requires-Dist: colorama; extra == "docs"
+Requires-Dist: ghp-import; extra == "docs"
+Requires-Dist: griffe; extra == "docs"
+Requires-Dist: idna; extra == "docs"
+Requires-Dist: Jinja2; extra == "docs"
+Requires-Dist: Markdown; extra == "docs"
+Requires-Dist: MarkupSafe; extra == "docs"
+Requires-Dist: mergedeep; extra == "docs"
+Requires-Dist: mkdocs; extra == "docs"
+Requires-Dist: mkdocs-autorefs; extra == "docs"
+Requires-Dist: mkdocs-get-deps; extra == "docs"
+Requires-Dist: mkdocs-material; extra == "docs"
+Requires-Dist: mkdocs-material-extensions; extra == "docs"
+Requires-Dist: mkdocs-section-index; extra == "docs"
+Requires-Dist: mkdocstrings; extra == "docs"
+Requires-Dist: mkdocstrings-python; extra == "docs"
+Requires-Dist: packaging; extra == "docs"
+Requires-Dist: paginate; extra == "docs"
+Requires-Dist: pathspec; extra == "docs"
+Requires-Dist: platformdirs; extra == "docs"
+Requires-Dist: Pygments; extra == "docs"
+Requires-Dist: pymdown-extensions; extra == "docs"
+Requires-Dist: python-dateutil; extra == "docs"
+Requires-Dist: PyYAML; extra == "docs"
+Requires-Dist: pyyaml_env_tag; extra == "docs"
+Requires-Dist: requests; extra == "docs"
+Requires-Dist: six; extra == "docs"
+Requires-Dist: urllib3; extra == "docs"
+Requires-Dist: watchdog; extra == "docs"
+Dynamic: license-file
+
+# 🧩 DataRec: A Python Library for Standardized and Reproducible Data Management in Recommender Systems
+
+[![Documentation](https://img.shields.io/badge/docs-online-blue.svg)](https://sisinflab.github.io/DataRec/)
+[![License](https://img.shields.io/github/license/sisinflab/DataRec.svg)](LICENSE)
+[![Python 3.9+](https://img.shields.io/badge/Python-3.9%2B-3776AB?logo=python&logoColor=white)](https://www.python.org/downloads/)
+
+---
+
+<img src="docs/assets/images/datarec_logo.png" width="600" alt="DataRec Logo">
+
+**DataRec** focuses on the **data management phase** of recommender systems, promoting **standardization**, **interoperability**, and **best practices** for data filtering, splitting, analysis, and export.
+
+Official repository of the paper:  
+📄 *DataRec: A Python Library for Standardized and Reproducible Data Management in Recommender Systems* (SIGIR 2025) [doi](https://dl.acm.org/doi/10.1145/3726302.3730320)
+
+---
+
+## 📑 Table of Contents
+- [Features](#features-)
+- [Installation](#installation)
+- [Quickstart](#quickstart-)
+- [Datasets](#datasets-)
+- [Documentation](#documentation-)
+- [Contributing](#contributing-)
+- [Citation](#citation-)
+- [Authors and Contributors](#authors-and-contributors-)
+- [Related Projects](#related-projects-)
+- [License](#license-)
+
+---
+
+## Features ✨
+- **Dataset Management**: multi-format I/O with dynamic schema specification.  
+- **Reference Datasets**: curated, versioned, and traceable datasets.  
+- **Filtering Strategies**: widely used user/item interaction filters.  
+- **Splitting Strategies**: temporal and random splits for reproducible evaluation.  
+- **Data Characteristics**: compute dataset-level statistics (e.g., sparsity, popularity).  
+- **Interoperability**: export datasets to external recommendation frameworks.  
+
+<img src="docs/assets/images/datarec_architecture.png" width="400" alt="DataRec Architecture">
+
+---
+
+## Installation
+
+### From source (recommended for development)
+```bash
+git clone https://github.com/sisinflab/DataRec.git
+cd DataRec
+python3.9 -m venv venv
+source venv/bin/activate
+pip install --upgrade pip
+pip install -r requirements.txt
+# editable mode + optional dependency groups (defined in pyproject.toml)
+pip install -e '.[dev,docs]'
+```
+
+
+## Quickstart 🚀
+
+```python
+from datarec.datasets import AmazonOffice
+from datarec.processing import FilterOutDuplicatedInteractions, UserItemIterativeKCore
+from datarec.splitters import RandomHoldOut
+
+# 1️⃣ Load a reference dataset
+data = AmazonOffice(version='2014').prepare_and_load()
+
+# 2️⃣ Apply preprocessing filters
+data = FilterOutDuplicatedInteractions().run(data)
+data = UserItemIterativeKCore(cores=5).run(data)
+
+# 3️⃣ Split into train/validation/test
+splitter = RandomHoldOut(test_ratio=0.2, val_ratio=0.1, seed=42)
+splits = splitter.run(data)
+
+train, val, test = splits['train'], splits['val'], splits['test']
+```
+
+### Pipeline paths
+When using YAML pipelines, store only filenames in the steps and pass the base folders at runtime:
+
+```python
+from datarec.pipeline import Pipeline
+
+pipeline = Pipeline.from_yaml("create_pipeline.yml")
+pipeline.apply(input_folder="./data", output_folder="./outputs")
+```
+
+For file loaders use `filename` (instead of `path`) and for export steps use `filename`
+(instead of `output_path`) in the YAML.
+
+---
+
+## Datasets 📊
+The complete and up-to-date list of datasets (with metadata and statistics) is available in the documentation:
+
+👉 **[Datasets Section](https://sisinflab.github.io/DataRec/datasets_nav/)**
+
+---
+
+## Documentation 📚
+Full documentation available at: **https://sisinflab.github.io/DataRec/**  
+Includes API reference, guides, tutorials, and dataset overview.
+
+---
+
+## Contributing 🤝
+
+Contributions are welcome!  
+To contribute:
+1. Create a feature/fix branch.  
+2. Add tests and documentation updates as needed.  
+3. Run tests before pushing.  
+4. Open a pull request describing your changes clearly.
+
+> The project also receives updates from a **private development repository** maintained by SisInfLab.
+
+---
+
+## Citation 📖
+
+If you use DataRec in your research, please cite our SIGIR 2025 paper:
+
+```bibtex
+@inproceedings{DBLP:conf/sigir/MancinoBF0MPN25,
+  author       = {Alberto Carlo Maria Mancino and
+                  Salvatore Bufi and
+                  Angela Di Fazio and
+                  Antonio Ferrara and
+                  Daniele Malitesta and
+                  Claudio Pomo and
+                  Tommaso Di Noia},
+  title        = {DataRec: {A} Python Library for Standardized and Reproducible Data
+                  Management in Recommender Systems},
+  booktitle    = {{SIGIR}},
+  pages        = {3478--3487},
+  publisher    = {{ACM}},
+  year         = {2025}
+}
+```
+
+---
+
+## Authors and Contributors 👥
+
+**Authors**  
+- Alberto Carlo Maria Mancino (Politecnico di Bari)  
+- Salvatore Bufi  
+- Angela Di Fazio  
+- Daniele Malitesta  
+- Antonio Ferrara  
+- Claudio Pomo  
+- Tommaso Di Noia  
+
+### Contributors
+
+| | | | |
+|:--:|:--:|:--:|:--:|
+| [<img src="https://avatars.githubusercontent.com/AlbertoMancino" width="70px"><br>**Alberto C. M. Mancino**](https://github.com/AlbertoMancino) | [<img src="https://avatars.githubusercontent.com/a-difazio" width="70px"><br>**Angela Di Fazio**](https://github.com/a-difazio) | [<img src="https://avatars.githubusercontent.com/salvatore-bufi" width="70px"><br>**Salvatore Bufi**](https://github.com/salvatore-bufi) | [<img src="https://avatars.githubusercontent.com/GiuseppeFasano" width="70px"><br>**Giuseppe Fasano**](https://github.com/GiuseppeFasano) |
+| [<img src="https://avatars.githubusercontent.com/GianLu210" width="70px"><br>**Gianluca Colonna**](https://github.com/GianLu210) | [<img src="https://avatars.githubusercontent.com/MariaLuigiaN" width="70px"><br>**Maria L. N. De Bonis**](https://github.com/MariaLuigiaN) | [<img src="https://avatars.githubusercontent.com/Marco-Valentini" width="70px"><br>**Marco Valentini**](https://github.com/Marco-Valentini) |  |
+---
+
+## Related Projects 🧩
+
+- **Ducho** — library for multimodal representation learning: https://github.com/sisinflab/Ducho  
+- **D&D4Rec Tutorial (RecSys 2025)** — *Standard Practices for Data Processing and Multimodal Feature Extraction in Recommendation with DataRec and Ducho*:  
+  https://sites.google.com/view/dd4rec-tutorial/home
+
+---
+
+## License 📜
+Distributed under the **MIT License**.  
+See [LICENSE](LICENSE).
+
+---
+
+<p align="center">
+  <em>Maintained with ❤️ by <a href="https://github.com/sisinflab">SisInfLab</a></em> 
+</p>
+<p align="center">
+<img src=docs/assets/images/sisinflab_logo.png width="100" alt="DataRec Logo">
+</p>

datarec_lib-1.3.2/README.md

@@ -0,0 +1,183 @@
+# 🧩 DataRec: A Python Library for Standardized and Reproducible Data Management in Recommender Systems
+
+[![Documentation](https://img.shields.io/badge/docs-online-blue.svg)](https://sisinflab.github.io/DataRec/)
+[![License](https://img.shields.io/github/license/sisinflab/DataRec.svg)](LICENSE)
+[![Python 3.9+](https://img.shields.io/badge/Python-3.9%2B-3776AB?logo=python&logoColor=white)](https://www.python.org/downloads/)
+
+---
+
+<img src="docs/assets/images/datarec_logo.png" width="600" alt="DataRec Logo">
+
+**DataRec** focuses on the **data management phase** of recommender systems, promoting **standardization**, **interoperability**, and **best practices** for data filtering, splitting, analysis, and export.
+
+Official repository of the paper:  
+📄 *DataRec: A Python Library for Standardized and Reproducible Data Management in Recommender Systems* (SIGIR 2025) [doi](https://dl.acm.org/doi/10.1145/3726302.3730320)
+
+---
+
+## 📑 Table of Contents
+- [Features](#features-)
+- [Installation](#installation)
+- [Quickstart](#quickstart-)
+- [Datasets](#datasets-)
+- [Documentation](#documentation-)
+- [Contributing](#contributing-)
+- [Citation](#citation-)
+- [Authors and Contributors](#authors-and-contributors-)
+- [Related Projects](#related-projects-)
+- [License](#license-)
+
+---
+
+## Features ✨
+- **Dataset Management**: multi-format I/O with dynamic schema specification.  
+- **Reference Datasets**: curated, versioned, and traceable datasets.  
+- **Filtering Strategies**: widely used user/item interaction filters.  
+- **Splitting Strategies**: temporal and random splits for reproducible evaluation.  
+- **Data Characteristics**: compute dataset-level statistics (e.g., sparsity, popularity).  
+- **Interoperability**: export datasets to external recommendation frameworks.  
+
+<img src="docs/assets/images/datarec_architecture.png" width="400" alt="DataRec Architecture">
+
+---
+
+## Installation
+
+### From source (recommended for development)
+```bash
+git clone https://github.com/sisinflab/DataRec.git
+cd DataRec
+python3.9 -m venv venv
+source venv/bin/activate
+pip install --upgrade pip
+pip install -r requirements.txt
+# editable mode + optional dependency groups (defined in pyproject.toml)
+pip install -e '.[dev,docs]'
+```
+
+
+## Quickstart 🚀
+
+```python
+from datarec.datasets import AmazonOffice
+from datarec.processing import FilterOutDuplicatedInteractions, UserItemIterativeKCore
+from datarec.splitters import RandomHoldOut
+
+# 1️⃣ Load a reference dataset
+data = AmazonOffice(version='2014').prepare_and_load()
+
+# 2️⃣ Apply preprocessing filters
+data = FilterOutDuplicatedInteractions().run(data)
+data = UserItemIterativeKCore(cores=5).run(data)
+
+# 3️⃣ Split into train/validation/test
+splitter = RandomHoldOut(test_ratio=0.2, val_ratio=0.1, seed=42)
+splits = splitter.run(data)
+
+train, val, test = splits['train'], splits['val'], splits['test']
+```
+
+### Pipeline paths
+When using YAML pipelines, store only filenames in the steps and pass the base folders at runtime:
+
+```python
+from datarec.pipeline import Pipeline
+
+pipeline = Pipeline.from_yaml("create_pipeline.yml")
+pipeline.apply(input_folder="./data", output_folder="./outputs")
+```
+
+For file loaders use `filename` (instead of `path`) and for export steps use `filename`
+(instead of `output_path`) in the YAML.
+
+---
+
+## Datasets 📊
+The complete and up-to-date list of datasets (with metadata and statistics) is available in the documentation:
+
+👉 **[Datasets Section](https://sisinflab.github.io/DataRec/datasets_nav/)**
+
+---
+
+## Documentation 📚
+Full documentation available at: **https://sisinflab.github.io/DataRec/**  
+Includes API reference, guides, tutorials, and dataset overview.
+
+---
+
+## Contributing 🤝
+
+Contributions are welcome!  
+To contribute:
+1. Create a feature/fix branch.  
+2. Add tests and documentation updates as needed.  
+3. Run tests before pushing.  
+4. Open a pull request describing your changes clearly.
+
+> The project also receives updates from a **private development repository** maintained by SisInfLab.
+
+---
+
+## Citation 📖
+
+If you use DataRec in your research, please cite our SIGIR 2025 paper:
+
+```bibtex
+@inproceedings{DBLP:conf/sigir/MancinoBF0MPN25,
+  author       = {Alberto Carlo Maria Mancino and
+                  Salvatore Bufi and
+                  Angela Di Fazio and
+                  Antonio Ferrara and
+                  Daniele Malitesta and
+                  Claudio Pomo and
+                  Tommaso Di Noia},
+  title        = {DataRec: {A} Python Library for Standardized and Reproducible Data
+                  Management in Recommender Systems},
+  booktitle    = {{SIGIR}},
+  pages        = {3478--3487},
+  publisher    = {{ACM}},
+  year         = {2025}
+}
+```
+
+---
+
+## Authors and Contributors 👥
+
+**Authors**  
+- Alberto Carlo Maria Mancino (Politecnico di Bari)  
+- Salvatore Bufi  
+- Angela Di Fazio  
+- Daniele Malitesta  
+- Antonio Ferrara  
+- Claudio Pomo  
+- Tommaso Di Noia  
+
+### Contributors
+
+| | | | |
+|:--:|:--:|:--:|:--:|
+| [<img src="https://avatars.githubusercontent.com/AlbertoMancino" width="70px"><br>**Alberto C. M. Mancino**](https://github.com/AlbertoMancino) | [<img src="https://avatars.githubusercontent.com/a-difazio" width="70px"><br>**Angela Di Fazio**](https://github.com/a-difazio) | [<img src="https://avatars.githubusercontent.com/salvatore-bufi" width="70px"><br>**Salvatore Bufi**](https://github.com/salvatore-bufi) | [<img src="https://avatars.githubusercontent.com/GiuseppeFasano" width="70px"><br>**Giuseppe Fasano**](https://github.com/GiuseppeFasano) |
+| [<img src="https://avatars.githubusercontent.com/GianLu210" width="70px"><br>**Gianluca Colonna**](https://github.com/GianLu210) | [<img src="https://avatars.githubusercontent.com/MariaLuigiaN" width="70px"><br>**Maria L. N. De Bonis**](https://github.com/MariaLuigiaN) | [<img src="https://avatars.githubusercontent.com/Marco-Valentini" width="70px"><br>**Marco Valentini**](https://github.com/Marco-Valentini) |  |
+---
+
+## Related Projects 🧩
+
+- **Ducho** — library for multimodal representation learning: https://github.com/sisinflab/Ducho  
+- **D&D4Rec Tutorial (RecSys 2025)** — *Standard Practices for Data Processing and Multimodal Feature Extraction in Recommendation with DataRec and Ducho*:  
+  https://sites.google.com/view/dd4rec-tutorial/home
+
+---
+
+## License 📜
+Distributed under the **MIT License**.  
+See [LICENSE](LICENSE).
+
+---
+
+<p align="center">
+  <em>Maintained with ❤️ by <a href="https://github.com/sisinflab">SisInfLab</a></em> 
+</p>
+<p align="center">
+<img src=docs/assets/images/sisinflab_logo.png width="100" alt="DataRec Logo">
+</p>

datarec_lib-1.3.2/datarec/__init__.py

@@ -0,0 +1,28 @@
+from .io.rawdata import RawData
+from .data.dataset import DataRec, from_pickle
+from datarec.registry.utils import available_datasets, print_available_datasets
+
+
+from .io.cache import (
+    cache_summary,
+    cache_dir,
+    set_cache_dir,
+    reset_cache_dir,
+    clear_cache,
+)
+
+__all__ = [
+    # Core classes
+    "DataRec",
+    "from_pickle",
+    "RawData",
+    # Cache management
+    "cache_summary",
+    "cache_dir",
+    "set_cache_dir",
+    "reset_cache_dir",
+    "clear_cache",
+    # Dataset registry
+    "available_datasets",
+    "print_available_datasets",
+]

datarec_lib-1.3.2/datarec/data/__init__.py

@@ -0,0 +1,4 @@
+from .dataset import DataRec
+from .graph import GraphRec
+from .characteristics import CHARACTERISTICS
+from .topological_characteristics import TOPOLOGICAL_CHARACTERISTICS

datarec_lib-1.3.2/datarec/data/characteristics.py

@@ -0,0 +1,138 @@
+from __future__ import annotations
+
+import math
+import numpy as np
+from typing import TYPE_CHECKING, Callable, Dict
+
+if TYPE_CHECKING:  # avoids circular import at runtime
+    from datarec.data import DataRec
+
+CHARACTERISTICS: Dict[str, Callable[..., float]] = {}
+
+
+def characteristic(func=None, *, name=None):
+    if func is None:
+        return lambda f: characteristic(f, name=name)
+
+    key = name or func.__name__
+    if key in CHARACTERISTICS:
+        raise ValueError(f"{key} already registered")
+    CHARACTERISTICS[key] = func
+    return func
+
+@characteristic
+def n_users(dr: DataRec, scale_factor: int = 1000):
+    """
+    Calculates the scaled square root of the user-item interaction space.
+    """
+    return int(dr.data[dr.user_col].nunique())
+
+@characteristic
+def n_items(dr: DataRec, scale_factor: int = 1000):
+    """
+    Calculates the scaled square root of the user-item interaction space.
+    """
+    return int(dr.data[dr.item_col].nunique())
+
+@characteristic
+def n_interactions(dr: DataRec, scale_factor: int = 1000):
+    """
+    Calculates the scaled square root of the user-item interaction space.
+    """
+    return int(len(dr.data))
+
+
+@characteristic
+def space_size(dr: DataRec, scale_factor: int = 1000):
+    """
+    Calculates the scaled square root of the user-item interaction space.
+    """
+    return math.sqrt(dr.n_users * dr.n_items) / scale_factor
+
+
+@characteristic
+def space_size_log(dr: DataRec):
+    """
+    Calculates the log10 of the space_size metric.
+    """
+    return math.log10(space_size(dr))
+
+
+@characteristic
+def shape(dr: DataRec):
+    """
+    Calculates the shape of the interaction matrix (n_users / n_items).
+    """
+    return dr.n_users / dr.n_items
+
+
+@characteristic
+def shape_log(dr: DataRec):
+    """
+    Calculates the log10 of the shape metric.
+    """
+    return math.log10(shape(dr))
+
+
+@characteristic
+def density(dr: DataRec):
+    """
+    Calculates the density of the user-item interaction matrix.
+    """
+    return dr.transactions / (dr.n_users * dr.n_items)
+
+
+@characteristic
+def density_log(dr: DataRec):
+    """
+    Calculates the log10 of the density metric.
+    """
+    return math.log10(density(dr))
+
+
+def gini(x):
+    """
+    Calculates the Gini coefficient for a numpy array.
+
+    Args:
+        x (np.ndarray): An array of non-negative values.
+
+    Returns:
+        (float): The Gini coefficient, a measure of inequality.
+    """
+    x = np.sort(x)  # O(n log n)
+    n = len(x)
+    cum_index = np.arange(1, n + 1)
+    return (np.sum((2 * cum_index - n - 1) * x)) / (n * np.sum(x))
+
+
+@characteristic
+def gini_item(dr: DataRec):
+    """
+    Calculates the Gini coefficient for item popularity.
+    """
+    return gini(np.array(list(dr.sorted_items.values())))
+
+
+@characteristic
+def gini_user(dr: DataRec):
+    """
+    Calculates the Gini coefficient for user activity.
+    """
+    return gini(np.array(list(dr.sorted_users.values())))
+
+
+@characteristic
+def ratings_per_user(dr: DataRec):
+    """
+    Calculates the average number of ratings per user.
+    """
+    return dr.transactions / dr.n_users
+
+@characteristic
+def ratings_per_item(dr: DataRec):
+    """
+    Calculates the average number of ratings per item.
+    """
+    return dr.transactions / dr.n_items
+