Evaluate residuals¶
Simple evaluation of residuals (coming from MLR model output).
Description¶
This diagnostic evaluates residuals created by MLR models.
Author¶
Manuel Schlund (DLR, Germany)
Project¶
CRESCENDO
Configuration options in recipe¶
- ignore: list of dict, optional
Ignore specific datasets by specifying multiple
dict
s of metadata.- mse_plot: dict, optional
Additional options for plotting the mean square errors (MSE). Specify additional keyword arguments for
seaborn.boxplot()
byplot_kwargs
and plot appearance options bypyplot_kwargs
(processed as functions ofmatplotlib.pyplot
).- pattern: str, optional
Pattern matched against ancestor file names.
- rmse_plot: dict, optional
Additional options for plotting the root mean square errors (RMSE). Specify additional keyword arguments for
seaborn.boxplot()
byplot_kwargs
and plot appearance options bypyplot_kwargs
(processed as functions ofmatplotlib.pyplot
).- savefig_kwargs: dict, optional
Keyword arguments for
matplotlib.pyplot.savefig()
.- seaborn_settings: dict, optional
Options for
seaborn.set()
(affects all plots).- weighted_samples: dict
If specified, use weighted root mean square error. The given keyword arguments are directly passed to
esmvaltool.diag_scripts.mlr.get_all_weights()
to calculate the sample weights. By default, area weights and time weights are used.