Discussion topics for individual codes
Post Reply
Ada Coda
ASCL Robot
Posts: 1839
Joined: Thu May 08, 2014 5:37 am


Post by Ada Coda » Mon Aug 29, 2016 9:16 pm


Abstract: ExoPlanet provides a graphical interface for the construction, evaluation and application of a machine learning model in predictive analysis. With the back-end built using the numpy and scikit-learn libraries, ExoPlanet couples fast and well tested algorithms, a UI designed over the PyQt framework, and graphs rendered using Matplotlib. This serves to provide the user with a rich interface, rapid analytics and interactive visuals.

ExoPlanet is designed to have a minimal learning curve to allow researchers to focus more on the applicative aspect of machine learning algorithms rather than their implementation details and supports both methods of learning, providing algorithms for unsupervised and supervised training, which may be done with continuous or discrete labels. The parameters of each algorithms can be adjusted to ensure the best fit for the data. Training data is read from a CSV file, and after training is complete, ExoPlanet automates the building of the visual representations for the trained model. Once training and evaluation yield satisfactory results, the model may be used to make data based predictions on a new data set.

Credit: Theophilus, Abhijit; Reddy, Mohinish; Basak, Suryoday

Site: https://gitlab.com/jerrytheo16/exoplanet
Last edited by Ada Coda on Sun Oct 07, 2018 7:23 pm, edited 1 time in total.
Reason: Updated code entry.

Post Reply