popv.algorithms.Random_Forest

popv.algorithms.Random_Forest#

class popv.algorithms.Random_Forest(batch_key='_batch_annotation', labels_key='_labels_annotation', layer_key=None, result_key='popv_rf_prediction', enable_cuml=False, classifier_dict={})[source]#

Class to compute Random forest classifier.

Parameters:

  • batch_key (str | None (default: '_batch_annotation')) – Key in obs field of adata for batch information. Default is “_batch_annotation”.

  • labels_key (str | None (default: '_labels_annotation')) – Key in obs field of adata for cell-type information. Default is “_labels_annotation”.

  • layer_key (str | None (default: None)) – Key in layers field of adata used for classification. By default uses ‘X’ (log1p10K).

  • result_key (str | None (default: 'popv_rf_prediction')) – Key in obs in which celltype annotation results are stored. Default is “popv_rf_prediction”.

  • enable_cuml (bool (default: False)) – Enable cuml, which currently doesn’t support weighting. Default to popv.settings.cuml.

  • classifier_dict (str | None (default: {})) – Dictionary to supply non-default values for RF classifier. Options at sklearn.ensemble.RandomForestClassifier.

Methods table#

compute_integration(adata)

Compute integration of adata inplace.

compute_umap(adata)

Compute UMAP embedding of adata inplace.

predict(adata)

Predict celltypes using Random Forest.

Methods#

abstractmethod Random_Forest.compute_integration(adata)[source]#

Compute integration of adata inplace.

abstractmethod Random_Forest.compute_umap(adata)[source]#

Compute UMAP embedding of adata inplace.

Random_Forest.predict(adata)[source]#

Predict celltypes using Random Forest.

Parameters:

adata – Anndata object. Results are stored in adata.obs[self.result_key].

Contents