Skip to main content

No project description provided

Project description

Incx

IncX (Incremental Explanations) is an innovative approach designed to incrementally generate saliency maps and explanations in real-time.

Penguin Gif

Getting Started

To run this project, you will need to use pyenv for Python version management and poetry for dependency management. Below are the steps to set up your environment and run the project.

Prerequisites

  1. Pyenv Installation
    Pyenv is a tool for managing multiple versions of Python on your system. Follow the instructions below to install it:

  2. Installing Python Version
    Once pyenv is installed, use it to install the Python version specified in the .python-version file located in the root directory of this project. Run the following command:

    pyenv install
    
  3. Install poetry

  4. Configure poetry to create virtual environments in the current project directory. This will ensure that you can easily handle different environments for different projects.

    poetry config virtualenvs.in-project true
    
  5. Use poetry to install the project dependencies and create a virtual environment:

    poetry install
    

Experiments

To replicate the experiments comparing D-RISE and IncX, follow these steps:

poetry run pytest --cov=incrementalexplainer --cov-report=term-missing

python experiments/d_rise/get_blob_names.py

python experiments/d_rise/get_metrics.py

poetry run python experiments/incx/get_job_names.py

python experiments/incx/get_saliency_maps.py

Unit Tests

To ensure the code is working correctly and is well-covered by tests, run the following command using poetry and pytest:

poetry run pytest

This command will execute all the tests defined in the tests/ directory, providing feedback on code correctness and coverage.

Linting and Formatting

To maintain code quality and style consistency, use the following commands:

  1. Linting Use ruff to check for code issues and automatically fix them:

    poetry run ruff check . --fix
    
  2. Formatting Use ruff to format the code according to style guidelines:

    poetry run ruff format .
    

How to install the package

pip install incx

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

incx-0.0.1.tar.gz (29.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

incx-0.0.1-py3-none-any.whl (43.6 kB view details)

Uploaded Python 3

File details

Details for the file incx-0.0.1.tar.gz.

File metadata

  • Download URL: incx-0.0.1.tar.gz
  • Upload date:
  • Size: 29.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.10.13 Windows/10

File hashes

Hashes for incx-0.0.1.tar.gz
Algorithm Hash digest
SHA256 2ed55ff79c4275745d0c4217f387eaad9446ba2c8377f27367a7a45e37d9e079
MD5 e67be692b9b14e85dc05ab03a21e3cd7
BLAKE2b-256 8f6add26bfb45e7e7b4dc782567d248cc563272689c9ee40177d97c25cd4bd36

See more details on using hashes here.

File details

Details for the file incx-0.0.1-py3-none-any.whl.

File metadata

  • Download URL: incx-0.0.1-py3-none-any.whl
  • Upload date:
  • Size: 43.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.10.13 Windows/10

File hashes

Hashes for incx-0.0.1-py3-none-any.whl
Algorithm Hash digest
SHA256 5f37ec63943c1bfc387fe058db3a8ece8132059e8ef1d44bfb3429ffa33bb726
MD5 c1f24e3be330a0edf421dcb4dfafcaed
BLAKE2b-256 438d6a7ab71cf53c1838249b874674a12df07e3d7669763e7e15b47757ab3a25

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page