Skip to content

JustinSmethers/KAGGLE-Predicting-a-pulsar-star

Repository files navigation

KAGGLE-Predicting-a-pulsar-star

This program aims to predict whether a star is a pulsar star given the pulsar_stars.csv data. The prediction is done using a Multi-Layer Perceptron classifier (MLPClassifer) algorithm and a LogisticRegression algorithm. The data required no cleaning, and the features were correlated nicely, resulting in both algorithms giving a ~0.98 precision. Further refining would require reading the paper explaining how the data was collected, and weighting features according towhich features are the most physically relevant. As opposed to weighing features based on the correlation heat map.

The data comes from kaggle https://www.kaggle.com/pavanraj159/predicting-a-pulsar-star

What you'll need

SKLearn

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published