codes.benchmark.bench_plots#
Functions
|
Returns a list of colors sampled from a custom color palette. |
|
Plot the mean inference time with standard deviation for different surrogate models. |
|
Plot the MAE for different surrogate models. |
|
Function to make one comparative plot of the interpolation, extrapolation, sparse, and batch size errors. |
|
Plot Δdex errors over time for different evaluation modes. |
|
Plot average predictive uncertainty and errors over time in log-space (dex). |
|
Plot catastrophic error recall (Δdex) vs fraction flagged by uncertainty, across multiple catastrophic percentiles, plus performance improvement curves. |
Comparative heatmaps of log-space uncertainty vs Δdex. |
|
|
Plot comparative heatmaps of correlation between gradient and prediction errors for multiple surrogate models. |
|
Plot the correlation between the gradients of the data and the prediction errors. |
|
Plot comparative error distributions for each surrogate model. |
|
Plot the distribution of errors for each quantity as a smoothed histogram plot. |
|
Plot mean, median, and percentile error envelopes over time. |
|
Plot errors over time for different surrogate models (relative, Δdex, or iterative Δdex). |
|
Plot one sample's full iterative trajectory: ground truth vs. |
|
Plot example predictions in log-space (Δdex) alongside ground truth targets for either interpolation or extrapolation mode. |
Plot example predictions with uncertainty in log10 space (dex). |
|
|
Plot the generalization errors of different surrogate models. |
|
Plot the generalization errors of a model for various metrics. |
|
Plot correlation between gradients (normalized) and Δdex errors using a heatmap. |
|
Plot the training and test losses for different surrogate models. |
|
Plot the test loss trajectories for different surrogate models on a single plot, after log-transforming and normalizing each trajectory. |
|
Plot the test loss trajectories for different surrogate models over training duration. |
|
Plot the loss trajectories for the training of multiple models. |
|
Plot the training and test loss trajectories with dual y-axes. |
Plot mean Δdex over time for each surrogate: main vs ensemble. |
|
|
Plot the relative errors over time for different surrogate models. |
|
Plot the training and test losses for the surrogate model. |
|
Plot a comparative grouped bar chart of catastrophic confidence measures and return a metric quantifying the net skew of over- versus underconfidence. |
|
Plot correlation between predictive log-space uncertainty and log-space errors (delta dex). |
|
Plot log-space uncertainty and Δdex over time for multiple surrogates. |
|
Plot the correlation between predictive uncertainty and prediction errors. |
|
Create a figure with two subplots: relative errors over time and uncertainty over time for different surrogate models. |
|
Save the plot to a file, creating necessary directories if they don't exist. |
|
Save a plot with an incremented filename if a file with the same name already exists. |