numpy-cache 0.1.0__tar.gz

numpy_cache-0.1.0/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [2026] [Alexander Nazimov (@macht1212)]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

numpy_cache-0.1.0/PKG-INFO

@@ -0,0 +1,265 @@
+Metadata-Version: 2.4
+Name: numpy-cache
+Version: 0.1.0
+Summary: High-performance LZ4 cache for NumPy arrays
+Author-email: "@macht1212" <nasimov.alexander@gmail.com>
+License-Expression: Apache-2.0
+Project-URL: Repository, https://github.com/macht1212/numpy-cache
+Project-URL: Homepage, https://github.com/macht1212/numpy-cache
+Keywords: numpy,cache,compression,lz4
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Topic :: Software Development :: Libraries
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Requires-Python: <4.0.0,>=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy<3.0.0,>=2.5.2
+Dynamic: license-file
+
+# NumPy Cache – Fast LZ4-Based Caching for NumPy Arrays
+### High‑performance, lightweight disk cache for NumPy arrays with LZ4 compression – now with configurable compression speed.
+
+[![CI](https://github.com/macht1212/numpy-cache/actions/workflows/ci.yml/badge.svg)](https://github.com/macht1212/numpy-cache/actions/workflows/ci.yml)  
+[![Python](https://img.shields.io/badge/Python-3.12%20|%203.13%20|%203.14%20|%203.15-blue)](https://www.python.org/) ![](/icons/NumPy-2.5.2-blue.svg) ![](/icons/License-Apache%202.0-blue.svg)
+
+## 📌 The Problem
+When dealing with large NumPy arrays, developers face a classic trade‑off:
+
+| Method |	Speed (100 MB) |	File Size |	Issue |
+|--------|-----------------|--------------|-------|
+| `np.save()` / `np.savez()` |	~45 ms |	100 MB |	Huge storage, slow network transfer |
+| `np.savez_compressed()` |	~3.6 s |	~90 MB |	Single‑threaded DEFLATE (zlib) is too slow |
+| **numpy_cache** |	**~100 ms** |	**~40‑50 MB** |	**Best of both worlds** ✅ |
+
+There is a clear gap: no lightweight, specialised solution combines `np.save()` speed with good compression – until now.
+
+## 🚀 Features
+- ✅ Blazing fast – 20 × faster than np.savez_compressed()
+- ✅ Good compression – 2 × smaller than np.save()
+- ✅ Pure C extension – minimal overhead, maximum performance
+- ✅ Configurable speed – acceleration parameter (1–16) lets you trade compression ratio for speed
+- ✅ NumPy integration – works with all numeric dtypes (int, uint, float, bool)
+- ✅ Multi‑dimensional – supports up to 8 dimensions
+- ✅ Contiguous arrays – automatically handles non‑contiguous slices
+- ✅ Empty arrays – properly saves and loads zero‑size arrays
+- ✅ Lightweight – no external dependencies beyond NumPy and LZ4
+- ✅ Apache 2.0 License – free for commercial and personal use
+  
+## 📦 Installation
+#### System Dependencies
+First, install the LZ4 library:
+```bash
+# Ubuntu / Debian
+sudo apt-get install liblz4-dev
+
+# macOS (Homebrew)
+brew install lz4
+
+# Fedora / RHEL
+sudo dnf install lz4-devel
+
+# Arch Linux
+sudo pacman -S lz4
+```
+
+**Supported Python versions**: 3.12, 3.13, 3.14, 3.15
+
+#### Install from PyPI
+```bash
+pip install numpy-cache
+```
+
+#### Install from source
+```bash
+git clone https://github.com/macht1212/numpy-cache.git
+cd numpy-cache
+poetry install
+```
+
+## 🧪 Usage
+```python
+import numpy as np
+from numpy_cache import save, load
+
+# Create a large array
+arr = np.random.randn(5000, 5000).astype(np.float32)
+
+# Save with LZ4 (default acceleration = 4)
+save(arr, 'my_array.npc')
+
+# Control compression speed vs. ratio
+# acceleration=1 → best compression, slower
+# acceleration=16 → fastest, slightly worse compression
+save(arr, 'my_array_fast.npc', acceleration=16)
+
+# Load back
+loaded = load('my_array.npc')
+
+# Verify
+np.testing.assert_array_equal(arr, loaded)
+```
+
+### Acceleration Parameter
+- **1–4**: Better compression ratio, slower.
+- **5–10**: Balanced default (4 is recommended).
+- **11–16**: Maximum speed, slightly larger files.
+
+### Supported Dtypes
+All NumPy numeric types are supported:
+
+- `float32`, `float64`
+- `int8`, `int16`, `int32`, `int64`
+- `uint8`, `uint16`, `uint32`, `uint64`
+- `bool_`
+
+### Multi‑dimensional Arrays
+```python
+arr_3d = np.random.randn(100, 100, 100)
+save(arr_3d, '3d_array.npc')
+```
+
+### Non‑contiguous Slices
+```python
+arr = np.random.randn(1000, 1000)
+slice_arr = arr[::2, ::2]  # Not contiguous
+save(slice_arr, 'slice.npc')  # Handles automatically
+```
+
+## 📊 Benchmarks
+### Test system:
+
+- Ubuntu 24.04.4 LTS, 12th Gen Intel i5-1235U (12 cores), 16 GB RAM, NVMe SSD
+- Python 3.12, NumPy 2.5.2, LZ4 1.9.4
+
+All arrays are `float32`. Sizes:
+
+- `shape0`: 100×100 = 10 000 elements ≈ 0.04 MB
+- `shape1`: 500×500 = 250 000 elements ≈ 1 MB
+
+### Write Performance (time in μs)
+
+| Method| 	0.04 MB| 	1 MB| 
+|-------|----------|--------|
+| `np.save`| 	89.6| 	879.6| 
+| `np.savez`| 	117.4| 	1 083.0| 
+| `np.savez_compressed`| 	1 056.1| 	28 921.5| 
+| **numpy_cache (accel=1)**| 	**71.8**| 	**759.4**| 
+| **numpy_cache (accel=4)**| 	**70.1**| 	**755.6**| 
+| **numpy_cache (accel=16)**| 	**74.9**| 	**738.9**| 
+
+### Read Performance (time in μs)
+
+| Method| 	0.04 MB| 	1 MB| 
+|-------|----------|--------|
+| `np.save`| 	41.7| 	91.9| 
+| `np.savez`| 	83.0| 	401.1| 
+| `np.savez_compressed`| 	267.5| 	4 858.8| 
+| **numpy_cache (accel=1)**| 	**19.2**| 	**385.0**| 
+| **numpy_cache (accel=4)**| 	**17.5**| 	**421.0**| 
+| **numpy_cache (accel=16)**| 	**17.0**| 	**474.5**| 
+
+### File Size Comparison (1 MB array)
+- `np.save` / `np.savez`: ~1.0 MB
+- `np.savez_compressed`: ~0.5 MB (varies)
+- **numpy_cache**: ~0.4 MB (depends on acceleration)
+
+### Key Takeaways
+**numpy_cache** is **24–40× faster** than `np.savez_compressed` for writes.
+
+For reads, it is **5–12× faster** than `np.savez_compressed`.
+
+Compression ratio is **better than** `np.savez` and usually close to `np.savez_compressed`.
+
+The `acceleration` parameter lets you fine‑tune the speed/ratio trade‑off.
+
+## 🛠️ How It Works
+### Architecture
+1. Pure C Extension – compiled into a Python module for maximum performance.
+2. LZ4 Compression – uses LZ4_compress_fast() with configurable acceleration.
+3. Custom Binary Format – packed header (96 bytes) + compressed payload.
+4. Direct NumPy Integration – zero‑copy access to array data where possible.
+
+### File Format
+The header is packed (no padding) to ensure portability:
+
+```C
+#pragma pack(push, 1)
+typedef struct {
+    uint64_t uncompressed_size;
+    uint64_t compressed_size;
+    uint64_t shape[MAX_DIMS];   // up to 8 dimensions
+    uint32_t magic;             // 0x4C5A4E43 ("LZNC")
+    uint32_t version;           // 1
+    uint32_t ndim;
+    uint32_t dtype;             // NumPy type ID
+} CacheHeader;
+#pragma pack(pop)
+```
+
+- Magic identifies the file format.
+- Version allows future upgrades.
+- The header is followed immediately by the LZ4‑compressed data.
+
+## Project Structure
+```text
+numpy_cache/
+├── csrc/
+│   └── cache_module.c      # C extension
+├── src/
+│   └── numpy_cache/
+│       ├── __init__.py     # Python wrapper
+│       └── _cache.so       # Compiled extension
+├── tests/
+│   ├── test_cache.py       # Unit tests
+│   └── test_benchmarks.py  # Performance benchmarks
+├── setup.py                # Setuptools configuration
+├── pyproject.toml          # Poetry configuration
+├── CHANGELOG.md
+└── README.md
+```
+
+## Build from Source
+```bash
+# Install development dependencies
+poetry install
+
+# Build the C extension
+poetry run python setup.py build_ext --inplace
+
+# Run tests
+poetry run pytest
+
+# Run benchmarks
+poetry run pytest tests/test_benchmarks.py --benchmark-only
+```
+
+## Run Benchmarks Separately
+```bash
+# Write benchmarks
+poetry run pytest tests/test_benchmarks.py -k "write" --benchmark-only
+
+# Read benchmarks
+poetry run pytest tests/test_benchmarks.py -k "read" --benchmark-only
+```
+
+## 🗺️ Roadmap (Future Improvements)
+- Multi‑threaded compression – parallelise LZ4 for even faster saving of huge arrays.
+- Asynchronous I/O – background saving without blocking the main thread.
+- Progress bar – visual feedback for very large arrays (via tqdm integration).
+- Windows support – ensure compatibility with MSVC and the Windows API.
+- Zstd backend – optional support for Zstandard compression (better ratio).
+- Memory mapping – load arrays directly from disk without full decompression (for streaming).
+
+## 📄 License
+This project is licensed under the Apache License, Version 2.0 – see the [LICENSE](/LICENSE) file for details.
+
+## 🙏 Acknowledgments
+- [LZ4](https://github.com/lz4/lz4) – extremely fast compression library.
+- [NumPy](https://numpy.org/) – fundamental array computing.
+- [Python](https://www.python.org/) – the language that makes it all possible.
+
+### Happy caching! 🚀