Update black to fix bug: https://www.mail-archive.com/[email protected]/msg1829077.html

Author: tomwhite

.pre-commit-config.yaml

@@ -12,7 +12,7 @@ repos:
     hooks:
       - id: isort
   - repo: https://github.com/python/black
-    rev: 20.8b1
+    rev: 21.10b0
     hooks:
       - id: black
         language_version: python3

sgkit/io/bgen/bgen_reader.py

@@ -175,7 +175,7 @@ def _read_metafile_partition(path: Path, partition: int) -> pd.DataFrame:
 
 
 def read_metafile(path: PathType) -> dd.DataFrame:
-    """ Read cbgen metafile containing partitioned variant info """
+    """Read cbgen metafile containing partitioned variant info"""
     with bgen_metafile(path) as mf:
         divisions = [mf.partition_size * i for i in range(mf.npartitions)] + [
             mf.nvariants - 1
@@ -189,7 +189,7 @@ def read_metafile(path: PathType) -> dd.DataFrame:
 
 
 def read_samples(path: PathType) -> pd.DataFrame:
-    """ Read BGEN .sample file """
+    """Read BGEN .sample file"""
     df = pd.read_csv(path, sep=" ", skiprows=[1], usecols=[0])
     df.columns = ["sample_id"]
     return df

sgkit/io/utils.py

@@ -23,7 +23,7 @@
 def dataframe_to_dict(
     df: dd.DataFrame, dtype: Optional[Mapping[str, DType]] = None
 ) -> Mapping[str, ArrayLike]:
-    """ Convert dask dataframe to dictionary of arrays """
+    """Convert dask dataframe to dictionary of arrays"""
     arrs = {}
     for c in df:
         a = df[c].to_dask_array(lengths=True)

sgkit/stats/pca.py

@@ -28,7 +28,7 @@ def pca_est(
     random_state: RandomStateType = 0,
     variable: str = "call_alternate_allele_count",
 ) -> BaseEstimator:
-    """ Create PCA estimator """
+    """Create PCA estimator"""
     if ploidy is None:
         if "ploidy" not in ds.dims:
             raise ValueError(
@@ -79,7 +79,7 @@ def pca_fit(
     variable: str = "call_alternate_allele_count",
     check_missing: bool = True,
 ) -> BaseEstimator:
-    """ Fit PCA estimator """
+    """Fit PCA estimator"""
     AC = _allele_counts(ds, variable, check_missing=check_missing)
     return est.fit(da.asarray(AC).T)
 
@@ -92,7 +92,7 @@ def pca_transform(
     check_missing: bool = True,
     merge: bool = True,
 ) -> Dataset:
-    """ Apply PCA estimator to new data """
+    """Apply PCA estimator to new data"""
     AC = _allele_counts(ds, variable, check_missing=check_missing)
     projection = est.transform(da.asarray(AC).T)
     new_ds = Dataset(
@@ -111,7 +111,7 @@ def _get(est: BaseEstimator, attr: str, fn: Any = lambda v: v) -> Optional[Array
 
 
 def pca_stats(ds: Dataset, est: BaseEstimator, *, merge: bool = True) -> Dataset:
-    """ Extract attributes from PCA estimator """
+    """Extract attributes from PCA estimator"""
     new_ds = {
         variables.sample_pca_component: (
             ("variants", "components"),

sgkit/tests/test_pca.py

@@ -16,7 +16,7 @@
 def simulate_cohort_genotypes(
     n_variant: int, n_sample: int, n_cohort: int, seed: int = 0
 ) -> NDArray:
-    """ Sample genotypes from distinct ancestral populations """
+    """Sample genotypes from distinct ancestral populations"""
     rs = np.random.RandomState(seed)
     # Determine size of each cohort (which will be roughly equal)
     cohort_sizes = list(map(len, np.array_split(np.arange(n_sample), n_cohort)))
@@ -38,7 +38,7 @@ def simulate_dataset(
     n_cohort: Optional[int] = None,
     chunks: Any = (None, None),
 ) -> Dataset:
-    """ Simulate dataset with optional population structure """
+    """Simulate dataset with optional population structure"""
     ds = simulate_genotype_call_dataset(n_variant, n_sample, seed=0)
     if n_cohort:
         ac = simulate_cohort_genotypes(
@@ -284,7 +284,7 @@ def validate_allel_comparison(ds_sg: Dataset, ds_sk: Dataset) -> None:
 
 
 def _align_vectors(x: ArrayLike, axis: int) -> ArrayLike:
-    """ Align vectors to common, arbitrary half-space """
+    """Align vectors to common, arbitrary half-space"""
     assert x.ndim == 2
     v = np.random.RandomState(1).rand(x.shape[axis])
     signs = np.dot(x, v)[:, np.newaxis] if axis == 1 else np.dot(v[np.newaxis], x)