scparadise.scnoah.report_classif_full

scparadise.scnoah.report_classif_full(adata, celltype=None, pred_celltype=None, save_report=False, report_name='report.csv', save_path='', ndigits=4)

Returns metrics (precision, recall (also called sensitivity), specificity, f1-score, geometric mean, and index balanced accuracy of the geometric mean) of predicted cell types. You should use it after prediction on annotated test dataset (shows results of validation). Helps in understanding model quality.

adataAnnData

Annotated data matrix. Previously annotated test dataset not used for model tuning or training.

celltypestr, , (default: None)

Level of cell annotation to show metrics. Key in adata.obs dataframe.

pred_celltypestr, , (default: None)

Predicted level of cell annotation. Key in adata.obs dataframe.

save_reportbool, (default: False)

Save report as csv file or not.

report_namestr, (default: ‘report.csv’)

Name of a file to save report.

save_pathpath object

Path to a folder to save report.

ndigitsint (default: 4)

Round a number to a given precision in decimal digits.