Merge pull request #1684 from ivirshup/precommit

Pre-commit

.azure-pipelines.yml

@@ -55,12 +55,6 @@ jobs:
       pip list
     displayName: 'Display installed versions'
 
-  - script: |
-      pip install black
-      black . --check --diff
-      python -m scanpy.tests.blackdiff 10
-    displayName: 'Black'
-
   - script: |
       pytest --color=yes --ignore=scanpy/tests/_images --nunit-xml="nunit/test-results.xml"
     displayName: 'PyTest'

.github/workflows/pre-commit.yml

@@ -0,0 +1,14 @@
+name: pre-commit
+
+on:
+  pull_request:
+  push:
+    branches: [master]
+
+jobs:
+  pre-commit:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v2
+    - uses: actions/setup-python@v2
+    - uses: pre-commit/action@v2.0.0

.pre-commit-config.yaml

@@ -0,0 +1,5 @@
+repos:
+-   repo: https://github.com/python/black
+    rev: 20.8b1
+    hooks:
+    -   id: black

docs/dev/getting-set-up.rst

@@ -38,6 +38,28 @@ To do this manually, first make a fork of the repository by clicking the "fork"
     git remote add upstream https://github.com/theislab/scanpy.git
     # git branch --set-upstream-to "upstream/master"
 
+`pre-commit`
+~~~~~~~~~~~~
+
+We use `precommit <https://pre-commit.com>`__ to run some styling checks in an automated way.
+We also test against these checks, so make sure you follow them!
+
+You can install pre-commit with:
+
+.. code:: shell
+
+    pip install pre-commit
+
+You can then install it to run while developing here with:
+
+.. code:: shell
+
+    pre-commit install
+
+From the root of the repo.
+
+If you choose not to run the hooks on each commit, you can run them manually with `pre-commit run --files={your files}`.
+
 .. _creating-a-branch:
 
 Creating a branch for your feature

pyproject.toml

@@ -31,48 +31,4 @@ target-version = ['py36']
 skip-string-normalization = true
 exclude = '''
 /build/.*
-|/scanpy/(
-    get
-    |__init__
-    |logging
-    |_utils
-    |neighbors/__init__
-    |external/(exporting|tl/_palantir)
-    |preprocessing/(
-        _qc
-        |_simple
-        |_normalization
-        |_highly_variable_genes
-        |_deprecated/highly_variable_genes
-    )
-    |tools/(
-        _dpt
-        |_sim
-        |_paga
-        |_umap
-        |_utils
-        |_louvain
-        |_tsne_fix
-        |_top_genes
-        |_score_genes
-        |_utils_clustering
-        |_rank_genes_groups
-    )
-    |plotting/(
-        __init__
-        |palettes
-        |_tools/(__init__|paga)
-    )
-    |tests/(
-        test_get
-        |test_neighbors
-        |test_readwrite
-        |test_clustering
-        |test_preprocessing
-        |test_rank_genes_groups
-        |test_marker_gene_overlap
-        |test_highly_variable_genes
-        |test_rank_genes_groups_logreg
-        |notebooks/(test_paga_paul15_subsampled|test_pbmc3k)
-    )
-).py'''
+'''

scanpy/__init__.py

@@ -3,26 +3,41 @@
 from ._metadata import __version__, __author__, __email__
 
 from ._utils import check_versions
+
 check_versions()
 del check_versions
 
 # the actual API
-from ._settings import settings, Verbosity  # start with settings as several tools are using it
+from ._settings import (
+    settings,
+    Verbosity,
+)  # start with settings as several tools are using it
 from . import tools as tl
 from . import preprocessing as pp
 from . import plotting as pl
 from . import datasets, logging, queries, external, get
 
 from anndata import AnnData, concat
-from anndata import read_h5ad, read_csv, read_excel, read_hdf, read_loom, read_mtx, read_text, read_umi_tools
+from anndata import (
+    read_h5ad,
+    read_csv,
+    read_excel,
+    read_hdf,
+    read_loom,
+    read_mtx,
+    read_text,
+    read_umi_tools,
+)
 from .readwrite import read, read_10x_h5, read_10x_mtx, write, read_visium
 from .neighbors import Neighbors
 
 set_figure_params = settings.set_figure_params
 
 # has to be done at the end, after everything has been imported
 import sys
+
 sys.modules.update({f'{__name__}.{m}': globals()[m] for m in ['tl', 'pp', 'pl']})
 from ._utils import annotate_doc_types
+
 annotate_doc_types(sys.modules[__name__], 'scanpy')
 del sys, annotate_doc_types

scanpy/_utils.py

@@ -401,7 +401,8 @@ def sanitize_anndata(adata):
 def view_to_actual(adata):
     if adata.is_view:
         warnings.warn(
-            "Revieved a view of an AnnData. Making a copy.", stacklevel=2,
+            "Revieved a view of an AnnData. Making a copy.",
+            stacklevel=2,
         )
         adata._init_as_actual(adata.copy())
 
@@ -432,7 +433,9 @@ def moving_average(a: np.ndarray, n: int):
 
 
 def update_params(
-    old_params: Mapping[str, Any], new_params: Mapping[str, Any], check=False,
+    old_params: Mapping[str, Any],
+    new_params: Mapping[str, Any],
+    check=False,
 ) -> Dict[str, Any]:
     """\
     Update old_params with new_params.
@@ -474,8 +477,7 @@ def update_params(
 
 
 def check_nonnegative_integers(X: Union[np.ndarray, sparse.spmatrix]):
-    """Checks values of X to ensure it is count data
-    """
+    """Checks values of X to ensure it is count data"""
     from numbers import Integral
 
     data = X if isinstance(X, np.ndarray) else X.data
@@ -492,8 +494,7 @@ def check_nonnegative_integers(X: Union[np.ndarray, sparse.spmatrix]):
 
 
 def select_groups(adata, groups_order_subset='all', key='groups'):
-    """Get subset of groups in adata.obs[key].
-    """
+    """Get subset of groups in adata.obs[key]."""
     groups_order = adata.obs[key].cat.categories
     if key + '_masks' in adata.uns:
         groups_masks = adata.uns[key + '_masks']
@@ -555,7 +556,9 @@ def warn_with_traceback(message, category, filename, lineno, file=None, line=Non
 
 
 def subsample(
-    X: np.ndarray, subsample: int = 1, seed: int = 0,
+    X: np.ndarray,
+    subsample: int = 1,
+    seed: int = 0,
 ) -> Tuple[np.ndarray, np.ndarray]:
     """\
     Subsample a fraction of 1/subsample samples from the rows of X.