API reference#
Import the package as:
import campmc as cp
Symbol |
Role |
|---|---|
Preprocessing (filter, normalize, HVG, PCA) |
|
Metacell partitioning (CAMP1–4) |
|
Quality, sizes, and rare-type recovery |
|
Plotting helpers |
Minimal example#
Runnable examples are on each API function page. A typical flow:
import campmc as cp
import scanpy as sc
adata = sc.datasets.pbmc68k_reduced()
cp.partition(adata, method="camp3", gamma=50, random_state=0)
cp.mt.quality(adata, partition_key="camp", label_key="louvain").head()
| metacell_id | size | compactness | separation | sc_ratio | INV | purity | label_entropy | |
|---|---|---|---|---|---|---|---|---|
| 0 | seed0-50-__all__ | 65 | -0.001010 | 0.140312 | 4.415655 | 30.340631 | 0.984615 | 0.114676 |
| 1 | seed1-50-__all__ | 34 | -0.000305 | 0.181345 | 10.381738 | 17.158705 | 0.911765 | 0.511578 |
| 2 | seed10-50-__all__ | 3 | -0.000724 | 0.063904 | 2.374693 | 5.376963 | 0.666667 | 0.918296 |
| 3 | seed11-50-__all__ | 158 | -0.000695 | 0.074471 | 2.823893 | 32.220764 | 0.708861 | 0.945308 |
| 4 | seed12-50-__all__ | 42 | -0.000890 | 0.048984 | 1.641697 | 26.113123 | 0.809524 | 0.884264 |
For raw counts, call campmc.preprocess() before partitioning.
See the User guide for method choice and AnnData keys.