# Preprocessing

```{eval-rst}
.. currentmodule:: campmc
```

Convenience pipeline that prepares count data for partitioning: cell/gene
filters, total-count normalization, log1p, HVG selection, scaling, and PCA.
After a successful run, ``adata.obsm['X_pca']`` is ready for
{func}`campmc.partition`.

Skip preprocessing when PCA is already present (e.g. Scanpy’s reduced demo
datasets). See {func}`campmc.preprocess` for a runnable example.

```{eval-rst}
.. autosummary::
   :nosignatures:
   :toctree: ../generated/

   preprocess
```