ncem.estimators.EstimatorCVAEncem

class ncem.estimators.EstimatorCVAEncem(cond_type: str = 'gcn', use_type_cond: bool = True, log_transform: bool = False)

Estimator class for conditional variational autoencoder NCEM models. Subclass of EstimatorGraph.

Attributes

img_keys_all	Return all image keys.
nodes_idx_all	Return all node indices.
nodes_idx_eval	alias of Dict[str, list]
nodes_idx_test	alias of Dict[str, list]
nodes_idx_train	alias of Dict[str, list]
patient_ids_bytarget	Return patient identifiers by target.
patient_ids_unique	Return unique patient identifiers.

Methods

evaluate_any(img_keys, node_idx[, batch_size])	Evaluate model on any given data set.
evaluate_any_posterior_sampling(img_keys, …)	Evaluate model based on resampled dataset for posterior resampling.
evaluate_per_node_type([batch_size])	Evaluate model for each node type seperately.
get_data(data_origin, data_path, radius[, …])	Get data used in estimator classes.
init_model([optimizer, learning_rate, …])	Initialize a ModelCVAEncem object.
predict([batch_size])	Return observed labels and full predictions (including scale model) grouped exactly as in nodes_idx_test.
pretrain_decoder([decoder_epochs, patience, …])	Pre-train decoder model.
split_data_given(img_keys_test, …)	Split data by given partition.
split_data_node(test_split, validation_split)	Split nodes randomly into partitions.
split_data_target_cell(target_cell, …[, seed])	Split nodes randomly into partitions.
train([epochs, epochs_warmup, …])	Train model.
train_aggressive([aggressive_enc_patience, …])	Train model aggressive.
train_normal([epochs, patience, …])	Train model normal.