scparadise.scnoah.report_classif_sens_spec

scparadise.scnoah.report_classif_sens_spec#

scparadise.scnoah.report_classif_sens_spec(adata, celltype=None, pred_celltype=None, save_report=False, report_name='report_sens_spec.csv', save_path='', ndigits=3)[source]#

Returns specificity and recall (also called sensitivity) metrics of predicted cell types. You should use it after prediction on annotated test dataset (shows results of validation). Helps in understanding model quality.

Parameters:

  • adata (AnnData) – Annotated data matrix. Previously annotated test dataset not used for model tuning or training.

  • celltype (str, , (default: None)) – Level of cell annotation to show metrics. Key in adata.obs dataframe.

  • pred_celltype (str, , (default: None)) – Predicted level of cell annotation. Key in adata.obs dataframe.

  • save_report (bool, (default: False)) – Save report as csv file or not.

  • report_name (str, (default: 'report_sens_spec.csv')) – Name of a file to save report.

  • save_path (path object) – Path to a folder to save report.

  • ndigits (int (default: 3)) – Round a number to a given precision in decimal digits.

Contents