Metadata-Version: 2.4
Name: sawmil
Version: 0.1.6
Summary: Sparse Multiple-Instance Learning: SVM, NSK, sMIL and sAwMIL.
Project-URL: Homepage, https://github.com/carlomarxdk/sawmil
Project-URL: Issues, https://github.com/carlomarxdk/sawmil/issues
Project-URL: Paper, https://arxiv.org/abs/2506.23921
Project-URL: DOI, https://doi.org/10.5281/zenodo.16990499
Project-URL: Citation, https://github.com/carlomarxdk/sawmil/blob/main/citation.cff
Author: Germans Savcisens, Tina Eliassi-Rad
License: MIT License
        
        Copyright (c) 2025 Germans Savcisens and Tina Eliassi-Rad
        
        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.
License-File: LICENSE
Keywords: MIL,bag,kernels,multiple-instance-learning,sawmil,sparse,svm
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3 :: Only
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Scientific/Engineering :: Information Analysis
Classifier: Topic :: Scientific/Engineering :: Mathematics
Classifier: Typing :: Typed
Requires-Python: >=3.11
Requires-Dist: numpy>=1.22
Requires-Dist: scikit-learn>=1.2
Provides-Extra: dev
Requires-Dist: build; extra == 'dev'
Requires-Dist: mypy; extra == 'dev'
Requires-Dist: pytest-cov; extra == 'dev'
Requires-Dist: pytest>=7; extra == 'dev'
Requires-Dist: ruff; extra == 'dev'
Requires-Dist: twine; extra == 'dev'
Provides-Extra: full
Requires-Dist: gurobipy>=12.0.3; extra == 'full'
Requires-Dist: osqp>=1.0.4; extra == 'full'
Requires-Dist: scipy>=1.16.1; extra == 'full'
Provides-Extra: gurobi
Requires-Dist: gurobipy>=12.0.3; extra == 'gurobi'
Provides-Extra: osqp
Requires-Dist: osqp>=1.0.4; extra == 'osqp'
Requires-Dist: scipy>=1.16.1; extra == 'osqp'
Description-Content-Type: text/markdown

[![PyPI version](https://img.shields.io/pypi/v/sawmil.svg)](https://pypi.org/project/sawmil/)
![Python versions](https://img.shields.io/pypi/pyversions/sawmil.svg)
![Wheel](https://img.shields.io/pypi/wheel/sawmil.svg)
![License](https://img.shields.io/pypi/l/sawmil.svg)
[![DOI](https://zenodo.org/badge/1046623935.svg)](https://doi.org/10.5281/zenodo.16990499)

# Sparse Multiple-Instance Learning in Python
> [!Warning]
>
> It is an **alpha** version of the package.

MIL models based on the Support Vector Machines (NSK, sMIL, sAwMIL).
Inspired by the outdated [misvm](https://github.com/garydoranjr/misvm) package.

**Note**: This is an alpha version.

## Implemented Models

### Normalized Set Kernels (`NSK`)

> Gärtner, Thomas, Peter A. Flach, Adam Kowalczyk, and Alex J. Smola. [Multi-instance kernels](https://dl.acm.org/doi/10.5555/645531.656014). Proceedings of the 19th International Conference on Machine Learning (2002).

### Sparse MIL (`sMIL`)

> Bunescu, Razvan C., and Raymond J. Mooney. [Multiple instance learning for sparse positive bags](https://dl.acm.org/doi/10.1145/1273496.1273510). Proceedings of the 24th International Conference on Machine Learning (2007).

### Sparse Aware MIL (`sAwMIL`)

Classifier used in [trilemma-of-truth](https://github.com/carlomarxdk/trilemma-of-truth):
> Savcisens, Germans, and Tina Eliassi-Rad. [The Trilemma of Truth in Large Language Models](https://arxiv.org/abs/2506.23921). arXiv preprint arXiv:2506.23921 (2025).

---

## Installation

`sawmil` supports two QP backends: [Gurobi](https://gurobi.com) and [OSQP](https://osqp.org/).
By default, the base package installs **without** any solver; pick one (or both) via extras.

### Base package (no solver)

```bash
pip install sawmil
```

### Option 1 — Gurobi backend

> Gurobi is commercial software. You’ll need a valid license (academic or commercial), refer to the [official website](https://gurobi.com).

```bash
pip install "sawmil[gurobi]"
# it installs numpy>=1.22 and scikit-learn>=1.7.0
```

### Option 2 — OSQP backend

```bash
pip install "sawmil[osqp]"
# in additionl to the base packages, it installs osqp>=1.0.4 and scipy
```

### Option 3 — All supported solvers

```bash
pip install "sawmil[full]"
```

### Picking the solver in code

```python
from sawmil import SVM

# solver= "osqp" (default is "gurobi")
clf = SVM(C=1.0, kernel="rbf", gamma=0.5, solver="osqp").fit(X, y)
```

## Requirements

```bash
numpy>=1.22
scikit-learn>=1.7.0
```

## Quick start

### 1. Generate dummy data

``` python
from dataset import make_complex_bags
import numpy as np
rng = np.random.default_rng(0)

ds = make_complex_bags(
    n_pos=300, n_neg=100, inst_per_bag=(5, 15), d=2,
    pos_centers=((+2,+1), (+4,+3)),
    neg_centers=((-1.5,-1.0), (-3.0,+0.5)),
    pos_scales=((2.0, 0.6), (1.2, 0.8)),
    neg_scales=((1.5, 0.5), (2.5, 0.9)),
    pos_intra_rate=(0.25, 0.85),
    ensure_pos_in_every_pos_bag=True,
    neg_pos_noise_rate=(0.00, 0.05),
    pos_neg_noise_rate=(0.00, 0.20),
    outlier_rate=0.1,
    outlier_scale=8.0,
    random_state=42,
)
```

### 2. NSK with RBF Kernel

**Load a kernel:**

```python
from sawmil.kernels import get_kernel
from sawmil.bag_kernels import make_bag_kernel
k = get_kernel("rbf", gamma=0.5) # base (single-instance kernel)
bag_k  = make_bag_kernel(k, use_intra_labels=False) # convert single-instance kernel to bagged kernel
```

**Fit NSK Model:**

```python
from sawmil.nsk import NSK

clf = NSK(C=0.1, bag_kernel=bag_k, scale_C=True, tol=1e-8, verbose=False).fit(ds, None)
print("Train acc:", clf.score(ds, np.array([b.y for b in ds.bags])))
```

### 3. Fit sMIL Model with Linear Kernel

```python
from src.sawmil.smil import sMIL

k = get_kernel("linear", normalizer="none") # base (single-instance kernel)
bag_k  = make_bag_kernel(Linear(), normalizer="none", use_intra_labels=False)
clf = sMIL(C=0.1, bag_kernel=bag_k, scale_C=True, tol=1e-6, verbose=False).fit(ds, None)

print("Train acc:", clf.score(ds, np.array([1 if b.y > 0 else -1 for b in ds.bags])))
```

See more examples in the [`example.ipynb`](https://github.com/carlomarxdk/sawmil/blob/main/example.ipynb) notebook.

### 4. Fit sAwMIL with Combined Kernels

```python
from src.sawmil.kernels import Product, Polynomial, Linear, RBF, Sum, Scale
from src.sawmil.sawmil import sAwMIL

k = Sum(Linear(), 
        Scale(0.5, 
              Product(Polynomial(degree=2), RBF(gamma=1.0))))

clf = sAwMIL(C=0.1, base_kernel=k,
             solver="gurobi", eta=0.95) # here eta is high, since all items in the bag are relevant
clf.fit(ds)
print("Train acc:", clf.score(ds, np.array([b.y for b in ds.bags])))
```

## Citation

If you use `sawmil` package in academic work, please cite:

Savcisens, G. & Eliassi-Rad, T. *sAwMIL: Python package for Sparse Multiple-Instance Learning* (2025).

```bibtex
@software{savcisens2025sawmil,
  author = {Savcisens, Germans and Eliassi-Rad, Tina},
  title = {sAwMIL: Python package for Sparse Multiple-Instance Learning},
  year = {2025},
  doi = {10.5281/zenodo.16990499},
  url = {https://github.com/carlomarxdk/sawmil}
}
```

If you want to reference a specific version of the package, find the [correct DOI here](https://doi.org/10.5281/zenodo.16990499).
