https://github.com/inoueakimitsu/milwrap

Wrapping single instance learning algorithms for fitting them to data for multiple instance learning
https://github.com/inoueakimitsu/milwrap

large-data machine-learning multi-class-classification multiple-instance-learning python sklearn

Last synced: 11 days ago
JSON representation

Wrapping single instance learning algorithms for fitting them to data for multiple instance learning

• Host: GitHub
• URL: https://github.com/inoueakimitsu/milwrap
• Owner: inoueakimitsu
• License: mit
• Created: 2021-09-29T11:06:11.000Z (about 3 years ago)
• Default Branch: main
• Last Pushed: 2023-02-06T22:41:39.000Z (almost 2 years ago)
• Last Synced: 2024-12-09T14:11:09.050Z (19 days ago)
• Topics: large-data, machine-learning, multi-class-classification, multiple-instance-learning, python, sklearn
• Language: Jupyter Notebook
• Homepage:
• Size: 580 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 5
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# milwrap

[![Build Status](https://app.travis-ci.com/inoueakimitsu/milwrap.svg?branch=main)](https://app.travis-ci.com/inoueakimitsu/milwrap)

 

[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/inoueakimitsu/milwrap/blob/master/introduction.ipynb)

Python package for multiple instance learning (MIL).

This wraps single instance learning algorithms so that they can be fitted to data for MIL.

## Features

- support count-based multiple instance assumptions (see [wikipedia](https://en.wikipedia.org/wiki/Multiple_instance_learning#:~:text=Presence-%2C%20threshold-%2C%20and%20count-based%20assumptions%5Bedit%5D))

- support multi-class setting

- support scikit-learn algorithms (such as `RandomForestClassifier`, `SVC`, `LogisticRegression`)

## Installation

```bash

pip install milwrap

```

## Usage

For more information, see [Use scikit-learn models in multiple instance learning based on the count-based assumption](https://github.com/inoueakimitsu/milwrap/blob/main/intro-en.md).

```python

# Prepare single-instance supervised-learning algorithm

# Note: only supports models with predict_proba() method.

from sklearn.linear_model import LogisticRegression

clf = LogisticRegression()

# Wrap it with MilCountBasedMultiClassLearner

from milwrap import MilCountBasedMultiClassLearner 

mil_learner = MilCountBasedMultiClassLearner(clf)

# Prepare follwing dataset

#

# - bags ... list of np.ndarray

#            (num_instance_in_the_bag * num_features)

# - lower_threshold ... np.ndarray (num_bags * num_classes)

# - upper_threshold ... np.ndarray (num_bags * num_classes)

#

# bags[i_bag] contains not less than lower_thrshold[i_bag, i_class]

# i_class instances.

# run multiple instance learning

clf_mil, y_mil = learner.fit(

    bags,

    lower_threshold,

    upper_threshold,

    n_classes,

    max_iter=10)

# after multiple instance learning,

# you can predict instance class

clf_mil.predict([instance_feature])

```

See `tests/test_countbased.py` for an example of a fully working test data generation process.

## License

milwrap is available under the MIT License.