annbatch 0.1.0

A minibatch loader for AnnData stores

annbatch

[!IMPORTANT] This package will now only make breaking changes on the minor version release until its major release.

A data loader and io utilities for mini-batched data loading of on-disk AnnData files, co-developed by Lamin Labs and scverse

Getting started

Please refer to the documentation, in particular, the API documentation.

Installation

You need to have Python 3.12 or newer installed on your system. If you don't have Python installed, we recommend installing uv.

To install the latest release of annbatch from PyPI:

pip install "annbatch[zarrs]"

We provide extras for torch, cupy-cuda12, cupy-cuda13, and zarrs-python. cupy provides accelerated handling of the data via preload_to_gpu once it has been read off disk and does not need to be used in conjunction with torch.

[!IMPORTANT] zarrs-python gives the necessary performance boost for the sharded data produced by our preprocessing functions to be useful when loading data off a local filesystem.

To install all optional dependencies::

pip install "annbatch[zarrs,torch,cupy-cuda13]"

(Note: Replace cupy-cuda13 with the extra matching your local CUDA version)

Detailed tutorial

For a detailed tutorial, please see the in-depth section of our docs

Basic usage example

Basic preprocessing:

from annbatch import DatasetCollection

import zarr
from pathlib import Path

# Using zarrs is necessary for local filesystem performance.
# Ensure you installed it using our `[zarrs]` extra i.e., `pip install "annbatch[zarrs]"` to get the right version.
zarr.config.set(
    {"codec_pipeline.path": "zarrs.ZarrsCodecPipeline"}
)

# Create a collection at the given path. The subgroups will all be anndata stores.
collection = DatasetCollection("path/to/output/collection.zarr")
collection.add_adata(
    adata_paths=[
        "path/to/your/file1.h5ad",
        "path/to/your/file2.h5ad"
    ],
    shuffle=True,  # shuffling is needed if you want to use chunked access, but is the default
)

Data loading:

[!IMPORTANT] Without custom loading via {meth}annbatch.Loader.use_collection or load_adata{s} or load_dataset{s}, all columns of the (obs) {class}pandas.DataFrame will be loaded and yielded potentially degrading performance.

from pathlib import Path

from annbatch import Loader
import anndata as ad
import zarr

# Using zarrs is necessary for local filesystem performance.
# Ensure you installed it using our `[zarrs]` extra i.e., `pip install "annbatch[zarrs]"` to get the right version.
zarr.config.set(
    {"codec_pipeline.path": "zarrs.ZarrsCodecPipeline"}
)

# WARNING: Without custom loading *all* obs columns will be loaded and yielded potentially degrading performance.
def custom_load_func(g: zarr.Group) -> ad.AnnData:
    return ad.AnnData(
        X=ad.io.sparse_dataset(g["layers"]["counts"]),
        obs=ad.io.read_elem(g["obs"])[some_subset_of_columns_useful_for_training]
    )

# A non empty collection
collection = DatasetCollection("path/to/output/collection.zarr")
# This settings override ensures that you don't lose/alter your categorical codes when reading the data in!
with ad.settings.override(remove_unused_categories=False):
    ds = Loader(
        batch_size=4096,
        chunk_size=32,
        preload_nchunks=256,
        to_torch=True
    )
    # `use_collection` automatically uses the on-disk `X` and full `obs` in the `Loader`
    # but the `load_adata` arg can override this behavior
    # (see `custom_load_func` above for an example of customization).
    ds = ds.use_collection(collection, load_adata=custom_load_func)

# Iterate over dataloader (plugin replacement for torch.utils.DataLoader)
for batch in ds:
    x, obs = batch["X"], batch["obs"]
    # Important: For performance reasons convert to dense on GPU
    x = x.cuda().to_dense()

[!IMPORTANT] For usage of our loader inside of torch, please see this note for more info. At the minimum, be aware that deadlocking will occur on linux unless you pass multiprocessing_context="spawn" to the torch.utils.data.DataLoader class.

Release notes

See the changelog.

Contact

For questions and help requests, you can reach out in the scverse discourse. If you found a bug, please use the issue tracker.