ym-pure-ml 0.7__tar.gz

ym_pure_ml-0.7/CITATION.cff

@@ -0,0 +1,20 @@
+cff-version: 1.2.0
+title: "PureML: a lightweight, NumPy-based deep learning framework"
+message: "If you use PureML in your work, please cite this software."
+type: software
+authors:
+  - family-names: Mishchyriak
+    given-names: Yehor
+repository-code: https://github.com/Yehor-Mishchyriak/PureML
+url: https://github.com/Yehor-Mishchyriak/PureML
+license: Apache-2.0
+version: 1.0.0
+release-date: 2025-10-12
+keywords: ["deep learning", "numpy", "autodiff", "education"]
+preferred-citation:
+  type: software
+  title: "PureML"
+  authors:
+    - family-names: Mishchyriak
+      given-names: Yehor
+  url: https://github.com/Yehor-Mishchyriak/PureML

ym_pure_ml-0.7/LICENSE

@@ -0,0 +1,201 @@
+                                 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 2025 Yehor Mishchyriak
+
+   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.

ym_pure_ml-0.7/MANIFEST.in

@@ -0,0 +1,6 @@
+include README.md
+include README.MD
+include LICENSE*
+include NOTICE*
+include CITATION.cff
+recursive-include pureml/datasets/MNIST/files *.zarr.zip

ym_pure_ml-0.7/NOTICE

@@ -0,0 +1,4 @@
+PureML
+Copyright (c) 2025 Yehor Mishchyriak
+
+This product includes software developed by Yehor Mishchyriak.

ym_pure_ml-0.7/PKG-INFO

@@ -0,0 +1,191 @@
+Metadata-Version: 2.4
+Name: ym-pure-ml
+Version: 0.7
+Summary: Transparent, NumPy-only deep learning framework for teaching, small-scale projects, prototyping, and reproducible experiments.
+Author: Yehor Mishchyriak
+License: Apache-2.0
+Project-URL: Source, https://github.com/Yehor-Mishchyriak/PureML
+Project-URL: Tracker, https://github.com/Yehor-Mishchyriak/PureML/issues
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Requires-Dist: numpy>=2.0
+Requires-Dist: zarr>=3.1
+Dynamic: author
+Dynamic: classifier
+Dynamic: description
+Dynamic: description-content-type
+Dynamic: license
+Dynamic: license-file
+Dynamic: project-url
+Dynamic: requires-dist
+Dynamic: requires-python
+Dynamic: summary
+
+# PureML — a tiny, transparent deep-learning framework in NumPy
+
+PureML is a learning-friendly deep-learning framework built entirely on top of **NumPy**. It aims to be **small, readable, and hackable** while still being practical for real experiments and teaching.
+
+- **No hidden magic** — a minimal autodiff Tensor + clear VJPs
+- **Batteries included** — core layers (Affine, Dropout, BatchNorm1d), common losses, an SGD optimizer, and a simple `DataLoader`
+- **Self-contained dataset demo** — a ready-to-use MNIST reader and an end-to-end “MNIST Beater” model
+- **Portable persistence** — zarr-backed `ArrayStorage` with zip compression for saving/loading model state
+
+> If you like **scikit-learn’s** simplicity and wish **deep learning** felt the same way for small/medium projects, PureML is for you.
+
+---
+
+## Install
+
+PureML targets Python **3.11+** and NumPy **2.x**.
+
+```bash
+# (Option A) From PyPI (when available)
+pip install pureml
+
+# (Option B) From source
+git clone https://github.com/<you>/pureml.git
+cd pureml
+pip install -e .
+```
+
+The only runtime deps are: `numpy`, `zarr` (plus lightweight helpers listed in `requirements.txt`).
+
+---
+
+## Quickstart: Train MNIST in a few lines
+
+```python
+from pureml.models.neural_networks import MNIST_BEATER
+from pureml.datasets import MnistDataset
+
+# 1) Load data (train uses one-hot labels; test gives class indices)
+with MnistDataset("train") as train, MnistDataset("test") as test:
+    # 2) Build the tiny network: Affine(784→256) → ReLU → Affine(256→10)
+    model = MNIST_BEATER().train()
+
+    # 3) Fit on the training set
+    model.fit(train, batch_size=128, num_epochs=5)
+
+    # 4) Switch to eval: model.predict returns class indices
+    model.eval()
+    # Example: run on one batch from the test set
+    X_test, y_test = test[:128]
+    preds = model(X_test)
+    print(preds.data[:10])  # class ids
+```
+
+What you get out of the box:
+
+- A tiny network that learns MNIST
+- Clean logging of epoch loss
+- An inference mode (`.eval()`) that returns class indices directly
+
+---
+
+## Core concepts
+
+### 1) Tensors & Autodiff
+PureML wraps NumPy arrays in a small `Tensor` that records operations and exposes `.backward()` for gradients. The Tensor supports:
+- Elementwise + matmul ops (`+ - * / **`, `@`, `.T`)
+- Reshaping helpers like `.reshape(...)` and `.flatten(...)`
+- Non-grad ops like `.argmax(...)`
+- A `no_grad` context manager for inference/metrics
+
+> The goal is **clarity**: gradients are implemented as explicit vector-Jacobian products (VJPs) you can read in one file.
+
+### 2) Layers
+- **Affine (Linear)** — `Y = X @ W + b` (with sensible init)
+- **Dropout**
+- **BatchNorm1d** — with running mean/variance buffers and momentum
+
+Layers expose:
+- `.parameters` (trainables)
+- `.named_buffers()` (non-trainable state)
+- `.train()` / `.eval()` modes (with a per-layer `on_mode_change` hook)
+
+### 3) Losses
+- `MSE`
+- `BCE` (probabilities) and `Sigmoid+BCE` (logits)
+- `CCE` (categorical cross-entropy; supports `from_logits=True`)
+
+### 4) Optimizers & Schedulers
+- **SGD** (learning rate, optional momentum/weight decay depending on your version)
+- Drop-in schedulers are easy to add; see the `optimizers` module.
+
+### 5) Data utilities
+- Minimal `Dataset` protocol (`__len__`, `__getitem__`)
+- `DataLoader` with batching, shuffling, slice fast-paths, and an optional seeded RNG
+- Helpers like `one_hot(...)` and `multi_hot(...)`
+
+---
+
+## Saving & Loading
+
+PureML provides two levels of persistence:
+
+- **Parameters only** — compact save/load of learnable weights
+- **Full state** — parameters **+** buffers **+** top-level literals (versioned), using zarr with Blosc(zstd) compression inside a `.zip`
+
+```python
+# Save only trainable parameters
+model.save("mnist_params")
+
+# Save full state (params + buffers + literals) to .pureml.zip
+model.save_state("mnist_full_state")
+
+# Load later
+model = MNIST_BEATER().eval().load_state("mnist_full_state.pureml.zip")
+```
+
+---
+
+## MNIST dataset included
+
+The repo ships a compressed zarr archive of MNIST (uint8, 28×28). The `MnistDataset`:
+- Normalizes images to `[0,1]` float32
+- Uses one-hot labels for training mode
+- Supports slicing and context-manager cleanup
+
+---
+
+## Why PureML?
+
+- **Read the source, learn the math.** Every gradient is explicit and local.
+- **Great for teaching & research notes.** Small enough to copy into slides or notebooks.
+- **Fast enough for classic datasets.** Vectorized NumPy code + light I/O.
+
+If you need GPUs, distributed training, or huge model zoos, you should use PyTorch/JAX. PureML is intentionally small.
+
+---
+
+## Roadmap
+
+- More optimizers (Adam, RMSProp), LR schedulers
+- Convolutional layers and pooling
+- RNN/CNN examples and docs
+- Better metrics & visualization utilities
+- Typed public API + docstrings/docs site
+
+---
+
+## Contributing
+
+PRs, issues, and discussion are welcome! Please include:
+- A small, focused change
+- Clear rationale (what/why)
+- Tests where appropriate
+
+---
+
+## License
+
+MIT — see `LICENSE` in this repo.

ym_pure_ml-0.7/README.md

@@ -0,0 +1,159 @@
+# PureML — a tiny, transparent deep-learning framework in NumPy
+
+PureML is a learning-friendly deep-learning framework built entirely on top of **NumPy**. It aims to be **small, readable, and hackable** while still being practical for real experiments and teaching.
+
+- **No hidden magic** — a minimal autodiff Tensor + clear VJPs
+- **Batteries included** — core layers (Affine, Dropout, BatchNorm1d), common losses, an SGD optimizer, and a simple `DataLoader`
+- **Self-contained dataset demo** — a ready-to-use MNIST reader and an end-to-end “MNIST Beater” model
+- **Portable persistence** — zarr-backed `ArrayStorage` with zip compression for saving/loading model state
+
+> If you like **scikit-learn’s** simplicity and wish **deep learning** felt the same way for small/medium projects, PureML is for you.
+
+---
+
+## Install
+
+PureML targets Python **3.11+** and NumPy **2.x**.
+
+```bash
+# (Option A) From PyPI (when available)
+pip install pureml
+
+# (Option B) From source
+git clone https://github.com/<you>/pureml.git
+cd pureml
+pip install -e .
+```
+
+The only runtime deps are: `numpy`, `zarr` (plus lightweight helpers listed in `requirements.txt`).
+
+---
+
+## Quickstart: Train MNIST in a few lines
+
+```python
+from pureml.models.neural_networks import MNIST_BEATER
+from pureml.datasets import MnistDataset
+
+# 1) Load data (train uses one-hot labels; test gives class indices)
+with MnistDataset("train") as train, MnistDataset("test") as test:
+    # 2) Build the tiny network: Affine(784→256) → ReLU → Affine(256→10)
+    model = MNIST_BEATER().train()
+
+    # 3) Fit on the training set
+    model.fit(train, batch_size=128, num_epochs=5)
+
+    # 4) Switch to eval: model.predict returns class indices
+    model.eval()
+    # Example: run on one batch from the test set
+    X_test, y_test = test[:128]
+    preds = model(X_test)
+    print(preds.data[:10])  # class ids
+```
+
+What you get out of the box:
+
+- A tiny network that learns MNIST
+- Clean logging of epoch loss
+- An inference mode (`.eval()`) that returns class indices directly
+
+---
+
+## Core concepts
+
+### 1) Tensors & Autodiff
+PureML wraps NumPy arrays in a small `Tensor` that records operations and exposes `.backward()` for gradients. The Tensor supports:
+- Elementwise + matmul ops (`+ - * / **`, `@`, `.T`)
+- Reshaping helpers like `.reshape(...)` and `.flatten(...)`
+- Non-grad ops like `.argmax(...)`
+- A `no_grad` context manager for inference/metrics
+
+> The goal is **clarity**: gradients are implemented as explicit vector-Jacobian products (VJPs) you can read in one file.
+
+### 2) Layers
+- **Affine (Linear)** — `Y = X @ W + b` (with sensible init)
+- **Dropout**
+- **BatchNorm1d** — with running mean/variance buffers and momentum
+
+Layers expose:
+- `.parameters` (trainables)
+- `.named_buffers()` (non-trainable state)
+- `.train()` / `.eval()` modes (with a per-layer `on_mode_change` hook)
+
+### 3) Losses
+- `MSE`
+- `BCE` (probabilities) and `Sigmoid+BCE` (logits)
+- `CCE` (categorical cross-entropy; supports `from_logits=True`)
+
+### 4) Optimizers & Schedulers
+- **SGD** (learning rate, optional momentum/weight decay depending on your version)
+- Drop-in schedulers are easy to add; see the `optimizers` module.
+
+### 5) Data utilities
+- Minimal `Dataset` protocol (`__len__`, `__getitem__`)
+- `DataLoader` with batching, shuffling, slice fast-paths, and an optional seeded RNG
+- Helpers like `one_hot(...)` and `multi_hot(...)`
+
+---
+
+## Saving & Loading
+
+PureML provides two levels of persistence:
+
+- **Parameters only** — compact save/load of learnable weights
+- **Full state** — parameters **+** buffers **+** top-level literals (versioned), using zarr with Blosc(zstd) compression inside a `.zip`
+
+```python
+# Save only trainable parameters
+model.save("mnist_params")
+
+# Save full state (params + buffers + literals) to .pureml.zip
+model.save_state("mnist_full_state")
+
+# Load later
+model = MNIST_BEATER().eval().load_state("mnist_full_state.pureml.zip")
+```
+
+---
+
+## MNIST dataset included
+
+The repo ships a compressed zarr archive of MNIST (uint8, 28×28). The `MnistDataset`:
+- Normalizes images to `[0,1]` float32
+- Uses one-hot labels for training mode
+- Supports slicing and context-manager cleanup
+
+---
+
+## Why PureML?
+
+- **Read the source, learn the math.** Every gradient is explicit and local.
+- **Great for teaching & research notes.** Small enough to copy into slides or notebooks.
+- **Fast enough for classic datasets.** Vectorized NumPy code + light I/O.
+
+If you need GPUs, distributed training, or huge model zoos, you should use PyTorch/JAX. PureML is intentionally small.
+
+---
+
+## Roadmap
+
+- More optimizers (Adam, RMSProp), LR schedulers
+- Convolutional layers and pooling
+- RNN/CNN examples and docs
+- Better metrics & visualization utilities
+- Typed public API + docstrings/docs site
+
+---
+
+## Contributing
+
+PRs, issues, and discussion are welcome! Please include:
+- A small, focused change
+- Clear rationale (what/why)
+- Tests where appropriate
+
+---
+
+## License
+
+MIT — see `LICENSE` in this repo.

ym_pure_ml-0.7/pureml/__init__.py

@@ -0,0 +1,27 @@
+# pureml/__init__.py
+from .machinery import (
+    Tensor, TensorValuedFunction, GradientNotDefined,
+    is_grad_enabled, no_grad,
+)
+from .util import ArrayStorage, compose_steps, batches_of
+
+# expose subpackages on demand
+def __getattr__(name):
+    if name in {
+        "layers","activations","losses","optimizers",
+        "base","general_math","training_utils","datasets","models"
+    }:
+        import importlib
+        return importlib.import_module(f"{__name__}.{name}")
+    raise AttributeError(name)
+
+__all__ = [
+    # core
+    "Tensor","TensorValuedFunction","GradientNotDefined",
+    "is_grad_enabled","no_grad",
+    # utils
+    "ArrayStorage","compose_steps","batches_of",
+    # namespaces (lazy) (see above)
+    "layers","activations","losses","optimizers",
+    "base","general_math","training_utils","datasets","models",
+]