crested.pl.hist.distribution

crested.pl.hist.distribution(adata, target='groundtruth', class_names=None, split=None, log_transform=True, share_y=False, **kwargs)

Histogram of region distribution for specified classes.

Parameters:

• adata (AnnData) – AnnData object containing the predictions in layers.

• target (str (default: 'groundtruth')) – The target to plot the distribution for, either “groundtruth” or the name of a prediction layer in adata.layers.

• class_names (Optional[list[str]] (default: None)) – List of classes in adata.obs. If None, will create a plot per class in adata.obs.

• split (Optional[str] (default: None)) – ‘train’, ‘val’, ‘test’ subset or None. If None, will use all targets. If not None, expects a “split” column in adata.var.

• log_transform (bool (default: True)) – Whether to log-transform the data before plotting.

• share_y (bool (default: False)) – Whether to share the y-axis across all plots.

• kwargs – Additional arguments passed to render_plot() to control the final plot output.

Return type:

Figure

See also

crested.pl.render_plot

Example

>>> crested.pl.hist.distribution(
...     adata, split="test", share_y=False, class_names=["Astro", "Vip"]
... )