Exploratory data analysis and stellar classification with pandas, seaborn and sklearn.
Hipparcos Stellar Catalog, collected by the Hipparcos satellite, from Kaggle.
This repository includes two jupyter notebooks:
-
HipparcosEDA.ipynb: exploratory data analysis of the Hipparcos dataset via different visualization routines using pandas and seaborn. -
HipparcosML.ipynb: classification of the Hipparcos stars based on their variability and spectral type (see here for more details on the different categories), using random forests, k-NN and PCA in sklearn.
