replay-rec 0.19.0__tar.gz → 0.20.0__tar.gz

replay_rec-0.20.0/NOTICE

@@ -0,0 +1,41 @@
+Apache Spark
+Copyright 2014 and onwards The Apache Software Foundation.
+
+This product includes software developed at
+The Apache Software Foundation (http://www.apache.org/).
+
+
+Export Control Notice
+---------------------
+
+This distribution includes cryptographic software. The country in which you currently reside may have
+restrictions on the import, possession, use, and/or re-export to another country, of encryption software.
+BEFORE using any encryption software, please check your country's laws, regulations and policies concerning
+the import, possession, or use, and re-export of encryption software, to see if this is permitted. See
+<http://www.wassenaar.org/> for more information.
+
+The U.S. Government Department of Commerce, Bureau of Industry and Security (BIS), has classified this
+software as Export Commodity Control Number (ECCN) 5D002.C.1, which includes information security software
+using or performing cryptographic functions with asymmetric algorithms. The form and manner of this Apache
+Software Foundation distribution makes it eligible for export under the License Exception ENC Technology
+Software Unrestricted (TSU) exception (see the BIS Export Administration Regulations, Section 740.13) for
+both object code and source code.
+
+The following provides more details on the included cryptographic software:
+
+This software uses Apache Commons Crypto (https://commons.apache.org/proper/commons-crypto/) to
+support authentication, and encryption and decryption of data sent across the network between
+services.
+
+
+Metrics
+Copyright 2010-2013 Coda Hale and Yammer, Inc.
+
+This product includes software developed by Coda Hale and Yammer, Inc.
+
+This product includes code derived from the JSR-166 project (ThreadLocalRandom, Striped64,
+LongAdder), which was released with the following comments:
+
+    Written by Doug Lea with assistance from members of JCP JSR-166
+    Expert Group and released to the public domain, as explained at
+    http://creativecommons.org/publicdomain/zero/1.0/

{replay_rec-0.19.0 → replay_rec-0.20.0}/PKG-INFO

@@ -1,45 +1,44 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: replay-rec
-Version: 0.19.0
+Version: 0.20.0
 Summary: RecSys Library
-Home-page: https://sb-ai-lab.github.io/RePlay/
-License: Apache-2.0
+License-Expression: Apache-2.0
+License-File: LICENSE
+License-File: NOTICE
 Author: AI Lab
-Requires-Python: >=3.8.1,<3.12
+Requires-Python: >=3.9, <3.13
+Classifier: Operating System :: Unix
 Classifier: Development Status :: 4 - Beta
 Classifier: Environment :: Console
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
-Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Natural Language :: English
-Classifier: Operating System :: Unix
-Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.9
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
 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 == "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)
-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 == "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,<3.0.0) ; (python_version >= "3.9") and (extra == "torch" or extra == "torch-openvino" or extra == "all")
-Requires-Dist: torch (>=1.8,<=2.4.1) ; (python_version >= "3.8" and python_version < "3.9") and (extra == "torch" or extra == "torch-openvino" or extra == "all")
+Provides-Extra: torch-cpu
+Requires-Dist: lightning (<2.6.0) ; extra == "torch" or extra == "torch-cpu"
+Requires-Dist: lightning ; extra == "torch"
+Requires-Dist: lightning ; extra == "torch-cpu"
+Requires-Dist: numpy (>=1.20.0,<2)
+Requires-Dist: pandas (>=1.3.5,<2.4.0)
+Requires-Dist: polars (<2.0)
+Requires-Dist: psutil (<=7.0.0) ; extra == "spark"
+Requires-Dist: psutil ; extra == "spark"
+Requires-Dist: pyarrow (<22.0)
+Requires-Dist: pyspark (>=3.0,<3.5) ; extra == "spark"
+Requires-Dist: pyspark ; extra == "spark"
+Requires-Dist: pytorch-optimizer (>=3.8.0,<3.9.0) ; extra == "torch" or extra == "torch-cpu"
+Requires-Dist: pytorch-optimizer ; extra == "torch"
+Requires-Dist: pytorch-optimizer ; extra == "torch-cpu"
+Requires-Dist: scikit-learn (>=1.6.1,<1.7.0)
+Requires-Dist: scipy (>=1.13.1,<1.14)
+Requires-Dist: setuptools
+Requires-Dist: torch (>=1.8,<3.0.0) ; extra == "torch" or extra == "torch-cpu"
+Requires-Dist: torch ; extra == "torch"
+Requires-Dist: torch ; extra == "torch-cpu"
+Requires-Dist: tqdm (>=4.67,<5)
+Project-URL: Homepage, https://sb-ai-lab.github.io/RePlay/
 Project-URL: Repository, https://github.com/sb-ai-lab/RePlay
 Description-Content-Type: text/markdown
 
@@ -208,7 +207,6 @@ pip install replay-rec==XX.YY.ZZrc0
 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
@@ -219,9 +217,35 @@ pip install replay-rec[spark]
 pip install replay-rec[spark]==XX.YY.ZZrc0
 ```
 
+Additionally, `replay-rec[torch]` may be installed with CPU-only version of `torch` by providing its respective index URL during installation:
+```bash
+# Install package with the CPU version of torch
+pip install replay-rec[torch] --extra-index-url https://download.pytorch.org/whl/cpu
+```
+
+
 To build RePlay from sources please use the [instruction](CONTRIBUTING.md#installing-from-the-source).
 
 
+### Optional features
+RePlay includes a set of optional features which require users to install optional dependencies manually. These features include:
+
+1) Hyperpearameter search via Optuna:
+```bash
+pip install optuna
+```
+
+2) Model compilation via OpenVINO:
+```bash
+pip install openvino onnx
+```
+
+3) Vector database and hierarchical search support:
+```bash
+pip install hnswlib fixed-install-nmslib
+```
+
+
 <a name="examples"></a>
 ## 📑  Resources
 

{replay_rec-0.19.0 → replay_rec-0.20.0}/README.md

@@ -163,7 +163,6 @@ pip install replay-rec==XX.YY.ZZrc0
 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
@@ -174,9 +173,35 @@ pip install replay-rec[spark]
 pip install replay-rec[spark]==XX.YY.ZZrc0
 ```
 
+Additionally, `replay-rec[torch]` may be installed with CPU-only version of `torch` by providing its respective index URL during installation:
+```bash
+# Install package with the CPU version of torch
+pip install replay-rec[torch] --extra-index-url https://download.pytorch.org/whl/cpu
+```
+
+
 To build RePlay from sources please use the [instruction](CONTRIBUTING.md#installing-from-the-source).
 
 
+### Optional features
+RePlay includes a set of optional features which require users to install optional dependencies manually. These features include:
+
+1) Hyperpearameter search via Optuna:
+```bash
+pip install optuna
+```
+
+2) Model compilation via OpenVINO:
+```bash
+pip install openvino onnx
+```
+
+3) Vector database and hierarchical search support:
+```bash
+pip install hnswlib fixed-install-nmslib
+```
+
+
 <a name="examples"></a>
 ## 📑  Resources
 

{replay_rec-0.19.0 → replay_rec-0.20.0}/pyproject.toml

@@ -1,35 +1,28 @@
 [build-system]
 requires = [
-    "poetry-core>=1.0.0",
+    "poetry-core>=2.0.0",
     "poetry-dynamic-versioning>=1.0.0,<2.0.0",
+    "setuptools",
 ]
 build-backend = "poetry_dynamic_versioning.backend"
 
-[tool.black]
-line-length = 120
-target-versions = ["py38", "py39", "py310", "py311"]
-
-[tool.poetry]
+[project]
 name = "replay-rec"
-packages = [{include = "replay"}]
 license = "Apache-2.0"
 description = "RecSys Library"
 authors = [
-    "AI Lab",
-    "Alexey Vasilev",
-    "Anna Volodkevich",
-    "Alexey Grishanov",
-    "Yan-Martin Tamm",
-    "Boris Shminke",
-    "Alexander Sidorenko",
-    "Roza Aysina",
+    {name = "AI Lab"},
+    {name = "Alexey Vasilev"},
+    {name = "Anna Volodkevich"},
+    {name = "Alexey Grishanov"},
+    {name = "Yan-Martin Tamm"},
+    {name = "Boris Shminke"},
+    {name = "Alexander Sidorenko"},
+    {name = "Roza Aysina"},
 ]
 readme = "README.md"
-homepage = "https://sb-ai-lab.github.io/RePlay/"
-repository = "https://github.com/sb-ai-lab/RePlay"
 classifiers = [
     "Operating System :: Unix",
-    "Intended Audience :: Science/Research",
     "Development Status :: 4 - Beta",
     "Environment :: Console",
     "Intended Audience :: Developers",
@@ -37,44 +30,53 @@ classifiers = [
     "Natural Language :: English",
     "Topic :: Scientific/Engineering :: Artificial Intelligence",
 ]
+requires-python = ">=3.9, <3.13"
+dependencies = [
+    "setuptools",
+    "numpy (>=1.20.0,<2)",
+    "pandas (>=1.3.5,<2.4.0)",
+    "polars (<2.0)",
+    "scipy (>=1.13.1,<1.14)",
+    "scikit-learn (>=1.6.1,<1.7.0)",
+    "pyarrow (<22.0)",
+    "tqdm (>=4.67,<5)",
+    "pyspark (>=3.0,<3.5); extra == 'spark'",
+    "psutil (<=7.0.0); extra == 'spark'",
+    "torch (>=1.8, <3.0.0); extra == 'torch' or extra == 'torch-cpu'",
+    "pytorch-optimizer (>=3.8.0,<3.9.0); extra == 'torch' or extra == 'torch-cpu'",
+    "lightning (<2.6.0); extra == 'torch' or extra == 'torch-cpu'",
+]
+dynamic = ["dependencies"]
+version = "0.20.0"
+
+[project.optional-dependencies]
+spark = ["pyspark", "psutil"]
+torch = ["torch", "pytorch-optimizer", "lightning"]
+torch-cpu = ["torch", "pytorch-optimizer", "lightning"]
+
+[project.urls]
+homepage = "https://sb-ai-lab.github.io/RePlay/"
+repository = "https://github.com/sb-ai-lab/RePlay"
+
+[tool.black]
+line-length = 120
+target-version = ["py39", "py310", "py311", "py312"]
+
+[tool.poetry]
+packages = [{include = "replay"}]
 exclude = [
     "replay/conftest.py",
     "replay/experimental",
 ]
-version = "0.19.0"
 
 [tool.poetry.dependencies]
-python = ">=3.8.1, <3.12"
-numpy = ">=1.20.0"
-pandas = ">=1.3.5, <=2.2.2"
-polars = "~1.0.0"
-optuna = "~3.2.0"
-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, <3.0.0", python = ">=3.9", optional = true},
-    {version = ">=1.8, <=2.4.1", python = ">=3.8,<3.9", optional = true},
+    {markers = "extra == 'torch-cpu' and extra !='torch'", source = "torch-cpu-mirror"},
+    {markers = "extra == 'torch' and extra !='torch-cpu'", source = "PyPI"},
 ]
-lightning = {version = ">=2.0.2, <=2.4.0", optional = true}
-pytorch-ranger = {version = "^0.1.1", optional = true}
-fixed-install-nmslib = "2.1.2"
-hnswlib = "^0.7.0"
-
-[tool.poetry.extras]
-spark = ["pyspark"]
-torch = ["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]
+coverage-conditional-plugin = "^0.9.0"
 jupyter = "~1.0.0"
 jupyterlab = "^3.6.0"
 pytest = ">=7.1.0"
@@ -93,33 +95,36 @@ docutils = "0.16"
 data-science-types = "0.2.23"
 filelock = "~3.14.0"
 
+[[tool.poetry.source]]
+name = "torch-cpu-mirror"
+url = "https://download.pytorch.org/whl/cpu"
+priority = "explicit"
+
 [tool.poetry-dynamic-versioning]
 enable = false
-format-jinja = """0.19.0{{ env['PACKAGE_SUFFIX'] }}"""
+format-jinja = """0.20.0{{ env['PACKAGE_SUFFIX'] }}"""
 vcs = "git"
 
 [tool.ruff]
 exclude = [".git", ".venv", "__pycache__", "env", "venv", "docs", "projects", "examples"]
-extend-select = ["C90", "T10", "T20", "UP004"]
 line-length = 120
+
+[tool.ruff.lint]
 select = ["ARG", "C4", "E", "EM", "ERA", "F", "FLY", "I", "INP", "ISC", "N", "PERF", "PGH", "PIE", "PYI", "Q", "RUF", "SIM", "TID", "W"]
+extend-select = ["C90", "T10", "T20", "UP004"]
+ignore = ["SIM115"]
+mccabe = {max-complexity = 13}
+isort = {combine-as-imports = true, force-wrap-aliases = true}
 
-[tool.ruff.flake8-quotes]
+[tool.ruff.lint.flake8-quotes]
 docstring-quotes = "double"
 inline-quotes = "double"
 multiline-quotes = "double"
 
-[tool.ruff.flake8-unused-arguments]
+[tool.ruff.lint.flake8-unused-arguments]
 ignore-variadic-names = false
 
-[tool.ruff.isort]
-combine-as-imports = true
-force-wrap-aliases = true
-
-[tool.ruff.mccabe]
-max-complexity = 13
-
-[tool.ruff.per-file-ignores]
+[tool.ruff.lint.per-file-ignores]
 "*/" = ["PERF203", "RUF001", "RUF002", "RUF012", "E402"]
 "__init__.py" = ["F401"]
 "replay/utils/model_handler.py" = ["F403", "F405"]

replay_rec-0.20.0/replay/__init__.py

@@ -0,0 +1,7 @@
+"""RecSys library"""
+
+# NOTE: This ensures distutils monkey-patching is performed before any
+# functionality removed in Python 3.12 is used in downstream packages (like lightfm)
+import setuptools as _
+
+__version__ = "0.20.0"

{replay_rec-0.19.0 → replay_rec-0.20.0}/replay/data/dataset.py

@@ -610,9 +610,9 @@ class Dataset:
             if self.is_pandas:
                 try:
                     data[column] = data[column].astype(int)
-                except Exception:
+                except Exception as exc:
                     msg = f"IDs in {source.name}.{column} are not encoded. They are not int."
-                    raise ValueError(msg)
+                    raise ValueError(msg) from exc
 
         if self.is_pandas:
             is_int = np.issubdtype(dict(data.dtypes)[column], int)
@@ -775,10 +775,10 @@ def check_dataframes_types_equal(dataframe: DataFrameLike, other: DataFrameLike)
 
     :returns: True if dataframes have same type.
     """
-    if isinstance(dataframe, PandasDataFrame) and isinstance(other, PandasDataFrame):
-        return True
-    if isinstance(dataframe, SparkDataFrame) and isinstance(other, SparkDataFrame):
-        return True
-    if isinstance(dataframe, PolarsDataFrame) and isinstance(other, PolarsDataFrame):
-        return True
-    return False
+    return any(
+        [
+            isinstance(dataframe, PandasDataFrame) and isinstance(other, PandasDataFrame),
+            isinstance(dataframe, SparkDataFrame) and isinstance(other, SparkDataFrame),
+            isinstance(dataframe, PolarsDataFrame) and isinstance(other, PolarsDataFrame),
+        ]
+    )