Skip to content

Latest commit

 

History

History
32 lines (19 loc) · 1.04 KB

v1_0.md

File metadata and controls

32 lines (19 loc) · 1.04 KB

Overview

We expect an kmeans_cluster HDF5 group at the root of the file, containing the k-means clustering parameters and results. The group itself should contain the parameters and results subgroups.

Definitions:

  • in_use: whether k-means is the chosen clustering method in choose_clustering.
  • num_cells: number of cells remaining after QC filtering.

Parameters

parameters should contain:

  • k: a scalar integer specifying the number of clusters to create.

Results

If in_use = true, results should contain:

  • clusters: an integer dataset of length equal to num_cells. This contains the cluster assignment for each cell, which should lie in [0, k).

    The total number of clusters may be less than k, e.g., when there are too few cells. For N clusters, there should be at least one occurrence of each integer in [0, N).

If in_use = false, clusters may be absent. Nonetheless, if it is present, it should follow the constraints listed above.

History

Added in version 1.0.