Skip to main content

A Python library to train machine learning models for defect prediction of infrastructure code.

Project description

Build Documentation LGTM Grade pypi-version pypi-status release-date python-version

radon-defect-prediction

The RADON command-line client for Infrastructure-as-Code Defect Prediction.

How to Install

From PyPI:

pip install radon-defect-predictor

From source code:

git clone https://github.com/radon-h2020/radon-defect-prediction.git
cd radon-defect-predictor
pip install -r requirements.txt
pip install .

Quick Start

usage: radon-defect-predictor [-h] [-v] {train,predict,model} ...

A Python library to train machine learning models for defect prediction of infrastructure code

positional arguments:
  {train,predict,model}
    train               train a brand new model from scratch
    model               get a pre-trained model to test unseen instances
    predict             predict unseen instances

optional arguments:
  -h, --help            show this help message and exit
  -v, --version         show program's version number and exit

How to build Docker container

docker build --tag radon-dp:latest .

How to run Docker container

First, create a host volume to share data and results between the host machine and the Docker container:

mkdir /tmp/radon-dp-volume/

Train

Create a training dataset metrics.csv and copy/move it to /tmp/radon-dp-volume/. See how to generate the training data for defect prediction here.

Run:

docker run -v /tmp/radon-dp-volume:/app radon-dp:latest radon-defect-predictor train metrics.csv ...

See the docs for more details about this command.

The built model can be accessed at /tmp/radon-dp-volume/radondp_model.joblib.

Model

Run:

docker run -v /tmp/radon-dp-volume:/app radon-dp:latest radon-defect-predictor download-model ...

See the docs for more details about this command.

The downloaded model can be accessed at /tmp/radon-dp-volume/radondp_model.joblib.

Predict

Move the model and the files to predict in the shared volume. For example, if you want to run the prediction on a .csar, then

cp patah/to/file.csar /tmp/radon-dp-volume.

Alternatively, you can create a volume from the folder containing the .csar (in that case, make sure to move the model within it).

Run:

docker run -v /tmp/radon-dp-volume:/app radon-dp:latest radon-defect-predictor predict ...

See the docs for more details about this command.

The predictions can be accessed at /tmp/radon-dp-volume/radondp_predictions.json.

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

radon-defect-predictor-0.2.7.tar.gz (13.5 kB view hashes)

Uploaded source

Built Distribution

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Huawei Huawei PSF Sponsor Microsoft Microsoft PSF Sponsor NVIDIA NVIDIA PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page