Make github workflow work (#1)

Fix github workflow for tests and dependencies --------- Co-authored-by: Philipp A. <[email protected]> Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
theislab · Nov 9, 2024 · 6d2c1ca · 6d2c1ca
1 parent 8c20963
commit 6d2c1ca
Show file tree

Hide file tree

Showing 8 changed files with 85 additions and 67 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -1,8 +1,9 @@
 # Changelog
 
 ## [Unreleased]
+
 -
 
 ## [0.1.0] - 2024-08-21
 
-- Moved all files from repo to scverse cookiecutter project template
+-   Moved all files from repo to scverse cookiecutter project template
diff --git a/docs/make.bat b/docs/make.bat
@@ -1,35 +1,35 @@
-@ECHO OFF
-
-pushd %~dp0
-
-REM Command file for Sphinx documentation
-
-if "%SPHINXBUILD%" == "" (
-	set SPHINXBUILD=sphinx-build
-)
-set SOURCEDIR=source
-set BUILDDIR=build
-
-%SPHINXBUILD% >NUL 2>NUL
-if errorlevel 9009 (
-	echo.
-	echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
-	echo.installed, then set the SPHINXBUILD environment variable to point
-	echo.to the full path of the 'sphinx-build' executable. Alternatively you
-	echo.may add the Sphinx directory to PATH.
-	echo.
-	echo.If you don't have Sphinx installed, grab it from
-	echo.https://www.sphinx-doc.org/
-	exit /b 1
-)
-
-if "%1" == "" goto help
-
-%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
-goto end
-
-:help
-%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
-
-:end
-popd
+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=sphinx-build
+)
+set SOURCEDIR=source
+set BUILDDIR=build
+
+%SPHINXBUILD% >NUL 2>NUL
+if errorlevel 9009 (
+	echo.
+	echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
+	echo.installed, then set the SPHINXBUILD environment variable to point
+	echo.to the full path of the 'sphinx-build' executable. Alternatively you
+	echo.may add the Sphinx directory to PATH.
+	echo.
+	echo.If you don't have Sphinx installed, grab it from
+	echo.https://www.sphinx-doc.org/
+	exit /b 1
+)
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+
+:end
+popd
diff --git a/docs/requirements.txt b/docs/requirements.txt
@@ -1,4 +1,3 @@
 sphinx
 sphinx-autodoc-typehints
 sphinx_rtd_theme
-
diff --git a/pyproject.toml b/pyproject.toml
@@ -7,8 +7,8 @@ name = "drvi"
 version = "0.1.0"
 description = "Disentangled Generative Representation of Single Cell Omics"
 readme = "README.md"
-requires-python = ">=3.10,<3.12"
-license = {file = "LICENSE"}
+requires-python = ">=3.10,<3.13"
+license = "BSD-3-Clause"
 authors = [
     {name = "Amir Ali Moinfar"},
 ]
@@ -21,11 +21,11 @@ urls.Home-page = "https://github.com/theislab/drvi"
 
 # Please make an issue if you need wider range of versions
 dependencies = [
-    "torch==2.1.0",
+    "torch>=2.1.0,<2.4",
     "lightning>=2.0,<2.1",
     "scanpy==1.9.5",
     "scikit-learn>=1.5.1",
-    "scipy>=1.11.3",
+    "scipy>=1.11.3,<1.13",
     "scvi-tools==1.0.4",
     ## TODO: Remove when scvi-tools and jax become ok again
     "jax<=0.4.20",
@@ -34,7 +34,6 @@ dependencies = [
     "anndata>=0.10.2",
     "numpy>=1.16.1",  # for np.linspace
     "pandas>=1.2.0",
-    "merlin-dataloader==23.8.0",
     ## TODO: update this when this is resolved: https://github.com/boto/botocore/issues/2926
     # lightning-cloud depends on boto3 that is currently not compatible with urllib3 so resolution takes forever
     "urllib3<2",
@@ -71,6 +70,9 @@ tutorials = [
     "leidenalg",
     "gprofiler",
 ]
+merlin = [
+    "merlin-dataloader==23.8.0",
+]
 
 [tool.coverage.run]
 source = ["drvi"]

diff --git a/src/drvi/scvi_tools_based/__init__.py b/src/drvi/scvi_tools_based/__init__.py
@@ -14,7 +14,7 @@
 if console.is_jupyter is True:
     console.is_jupyter = False
 ch = RichHandler(show_path=False, console=console, show_time=False)
-formatter = logging.Formatter("drvi: %(message)s")
+formatter = logging.Formatter("DRVI: %(message)s")
 ch.setFormatter(formatter)
 logger.addHandler(ch)
 

diff --git a/src/drvi/scvi_tools_based/merlin_data/__init__.py b/src/drvi/scvi_tools_based/merlin_data/__init__.py
@@ -1,9 +1,21 @@
-from drvi.scvi_tools_based.merlin_data import fields
+import importlib
+import logging
 
-from ._data import MerlinData
-from ._data_loader import MerlinTransformedDataLoader
-from ._data_manager import MerlinDataManager
-from ._data_splitter import MerlinDataSplitter
+logger = logging.getLogger(__name__)
+
+if importlib.util.find_spec("merlin"):
+    from . import fields
+    from ._data import MerlinData
+    from ._data_loader import MerlinTransformedDataLoader
+    from ._data_manager import MerlinDataManager
+    from ._data_splitter import MerlinDataSplitter
+else:
+    fields = None
+    MerlinData = None
+    MerlinTransformedDataLoader = None
+    MerlinDataManager = None
+    MerlinDataSplitter = None
+    logger.warning("Merlin is not installed. To use merline dataloader please install it.")
 
 __all__ = [
     "MerlinData",

diff --git a/src/drvi/scvi_tools_based/merlin_data/_data.py b/src/drvi/scvi_tools_based/merlin_data/_data.py
@@ -3,8 +3,7 @@
 from typing import Literal
 from uuid import uuid4
 
-import merlin.dtypes
-import merlin.schema
+import merlin.io
 import pandas as pd
 import pyarrow.parquet as pq
 from scvi.data import _constants

diff --git a/src/drvi/scvi_tools_based/model/_drvi.py b/src/drvi/scvi_tools_based/model/_drvi.py
@@ -19,11 +19,8 @@
     MerlinDataSplitter,
     MerlinTransformedDataLoader,
 )
-from drvi.scvi_tools_based.merlin_data.fields import (
-    MerlinCategoricalJointObsField,
-    MerlinCategoricalObsField,
-    MerlinLayerField,
-    MerlinNumericalJointObsField,
+from drvi.scvi_tools_based.merlin_data import (
+    fields as melin_fields,
 )
 from drvi.scvi_tools_based.model.base import DRVIArchesMixin, GenerativeMixin
 from drvi.scvi_tools_based.module import DRVIModule
@@ -38,7 +35,7 @@ class DRVI(VAEMixin, DRVIArchesMixin, UnsupervisedTrainingMixin, BaseModelClass,
     Parameters
     ----------
     adata
-        AnnData object that has been registered via :meth:`~mypackage.MyModel.setup_anndata`.
+        AnnData object that has been registered via :meth:`~drvi.model.DRVI.setup_anndata`.
     n_latent
         Dimensionality of the latent space.
     encoder_dims
@@ -52,7 +49,7 @@ class DRVI(VAEMixin, DRVIArchesMixin, UnsupervisedTrainingMixin, BaseModelClass,
     categorical_covariates
         Categorical Covariates as a list of texts. You can specify emb dimension by appending @dim to each cpvariate.
     **model_kwargs
-        Keyword args for :class:`~mypackage.MyModule`
+        Keyword args for :class:`~drvi.model.DRVI`
 
     Examples
     --------
@@ -77,12 +74,16 @@ def __init__(
         super().__init__(adata)
 
         # TODO: Remove later. Currently used to detect autoreload problems sooner.
-        if isinstance(adata, MerlinData):
-            self._data_splitter_cls = MerlinDataSplitter
-        elif isinstance(adata, AnnData):
+        if isinstance(adata, AnnData):
             pass
+        elif MerlinData is not None and isinstance(adata, MerlinData):
+            self._data_splitter_cls = MerlinDataSplitter
         else:
-            raise ValueError("Only AnnData and MerlinData is supported")
+            raise ValueError(
+                "Only AnnData and MerlinData are supported. "
+                "If you have passes an instalce of MerlinData and still get this error, "
+                "make sure merlin is installed as a dependency."
+            )
 
         categorical_covariates_info = FeatureInfoList(categorical_covariates, axis="obs", default_dim=10)
         if REGISTRY_KEYS.CAT_COVS_KEY in self.adata_manager.data_registry:
@@ -185,10 +186,10 @@ def setup_merlin_data(
         setup_method_args["drvi_version"] = drvi.__version__
 
         fields = [
-            MerlinLayerField(REGISTRY_KEYS.X_KEY, layer, is_count_data=is_count_data),
-            MerlinCategoricalObsField(REGISTRY_KEYS.LABELS_KEY, labels_key),
-            MerlinCategoricalJointObsField(REGISTRY_KEYS.CAT_COVS_KEY, categorical_covariate_keys),
-            MerlinNumericalJointObsField(REGISTRY_KEYS.CONT_COVS_KEY, continuous_covariate_keys),
+            melin_fields.MerlinLayerField(REGISTRY_KEYS.X_KEY, layer, is_count_data=is_count_data),
+            melin_fields.MerlinCategoricalObsField(REGISTRY_KEYS.LABELS_KEY, labels_key),
+            melin_fields.MerlinCategoricalJointObsField(REGISTRY_KEYS.CAT_COVS_KEY, categorical_covariate_keys),
+            melin_fields.MerlinNumericalJointObsField(REGISTRY_KEYS.CONT_COVS_KEY, continuous_covariate_keys),
         ]
         merlin_manager = MerlinDataManager(fields, setup_method_args=setup_method_args)
         merlin_manager.register_fields(merlin_data, **kwargs)
@@ -224,7 +225,7 @@ def _make_data_loader(
             return super()._make_data_loader(
                 adata, indices, batch_size, shuffle, data_loader_class, **data_loader_kwargs
             )
-        elif isinstance(adata, MerlinData):
+        elif MerlinData is not None and isinstance(adata, MerlinData):
             adata_manager = self.get_anndata_manager(adata)
             if adata_manager is None:
                 raise AssertionError(
@@ -241,4 +242,8 @@ def _make_data_loader(
                 **data_loader_kwargs,
             )
         else:
-            raise ValueError("Only AnnData and MerlinData is supported")
+            raise ValueError(
+                "Only AnnData and MerlinData are supported. "
+                "If you have passes an instalce of MerlinData and still get this error, "
+                "make sure merlin is installed as a dependency."
+            )