How this file is connected to other assets
Careful evaluation of the classifier model is important so that we can truly understand the capabilities and performance of a Tc predicting model. Particularly important to us is the ability for the m
Discover other files like this one
Seeing how the Orb latent space classifier model predicts materials with Tc greater than 90 K, when the model was only trained on materials with Tc less than 90 K.
Visualizing the counts of materials in the training and evaluation dataset by their Tc. First bin is non-superconductors, the rest are ranges of 20 K increments.
Not a very robust report yet. We're not through all the data points and these results come from a few different models (trained with more data as it came available)
Evaluating the validation set (1155 samples) on the trained CatBoost model to predict Tc.