deepof.post_hoc

Data structures and functions for analyzing supervised and unsupervised model results.

Functions

align_deepof_kinematics_with_unsupervised_labels(...)	Align kinematics with unsupervised labels.
annotate_time_chunks(deepof_project, ...[, ...])	Annotate time chunks produced after change-point detection using the unsupervised pipeline.
chunk_cv_splitter(chunk_stats, breaks[, n_folds])	Split a dataset into training and testing sets, grouped by video.
chunk_summary_statistics(chunked_dataset, ...)	Extract summary statistics from a chunked dataset using seglearn.
compute_UMAP(embeddings, cluster_assignments)	Compute UMAP embeddings for visualization purposes.
compute_steady_state(transition_matrices[, ...])	Compute the steady state of each transition matrix provided in a dictionary.
compute_transition_matrix_per_condition(...)	Compute the transition matrices specific to each condition.
condition_distance_binning(embedding, ...[, ...])	Compute the distance between the embeddings of two conditions, using the specified aggregation method.
enrichment_across_conditions([embedding, ...])	Compute the population of each cluster across conditions.
explain_clusters(chunk_stats, hard_counts, ...)	Compute SHAP feature importance for models mapping chunk_stats to cluster assignments.
fit_normative_global_model(...)	Fit a global model to the normal embeddings.
get_aggregated_embedding(embedding[, ...])	Aggregate the embeddings of a set of videos, using the specified aggregation method.
get_time_on_cluster(soft_counts, breaks[, ...])	Compute how much each animal spends on each cluster.
get_transitions(state_sequence, n_states)	Compute the transitions between states in a state sequence.
recluster(coordinates, embeddings[, ...])	Recluster the data using a HMM-based approach.
select_time_bin([embedding, soft_counts, ...])	Select a time bin and filters all relevant objects (embeddings, soft_counts, breaks, and supervised annotations).
separation_between_conditions(cur_embedding, ...)	Compute the distance between the embeddings of two conditions, using the specified aggregation method.
train_supervised_cluster_detectors(...[, ...])	Train supervised models to detect clusters from kinematic features.