get_best_models

behavenet.plotting.decoder_utils.get_best_models(metrics_df)

Find best decoder over l2 regularization and learning rate.

Returns a dataframe with test R^2s for each batch, for the best decoder in each category (defined by dataset, region, n_lags, and n_hid_layers).

Parameters:

metrics_df (pd.DataFrame) – output of get_r2s_by_trial()

Returns:

test R^2s for each batch

Return type:

pd.DataFrame