Fix bug with multiple regions in PCA and snp_allele_counts (#338)

* fix bug with multiple regions

* fix exception handling

* upgrade pre-commit and relint

.flake8

@@ -1,7 +1,12 @@
 [flake8]
 ignore =
-    E203 # whitespace before ':' - doesn't work well with black
-    E402 # module level import not at top of file
-    E501 # line too long - let black worry about that
-    E731 # do not assign a lambda expression, use a def
-    W503 # line break before binary operator
+    # whitespace before ':' - doesn't work well with black
+    E203
+    # module level import not at top of file
+    E402
+    # line too long - let black worry about that
+    E501
+    # do not assign a lambda expression, use a def
+    E731
+    # line break before binary operator
+    W503

.pre-commit-config.yaml

@@ -1,26 +1,26 @@
 # https://pre-commit.com/
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.3.0
+    rev: v4.4.0
     hooks:
       - id: trailing-whitespace
       - id: end-of-file-fixer
       - id: check-yaml
   # isort should run before black as black sometimes tweaks the isort output
   - repo: https://github.com/pycqa/isort
-    rev: 5.10.1
+    rev: 5.12.0
     hooks:
       - id: isort
   # https://github.com/python/black#version-control-integration
   - repo: https://github.com/psf/black
-    rev: 22.10.0
+    rev: 23.1.0
     hooks:
       - id: black
   - repo: https://github.com/keewis/blackdoc
     rev: v0.3.8
     hooks:
       - id: blackdoc
   - repo: https://github.com/pycqa/flake8
-    rev: 5.0.4
+    rev: 6.0.0
     hooks:
       - id: flake8

malariagen_data/af1.py

@@ -130,7 +130,6 @@ def __init__(
         pre=False,
         **kwargs,  # used by simplecache, init_filesystem(url, **kwargs)
     ):
-
         super().__init__(
             url=url,
             config_path=CONFIG_PATH,
@@ -303,7 +302,6 @@ def genome_features(
         return super().genome_features(region=region, attributes=attributes)
 
     def _plot_genes_setup_data(self, *, region):
-
         # Here we override the superclass implementation because the
         # gene annotations don't include a "Name" attribute.
         #

malariagen_data/ag3.py

@@ -164,7 +164,6 @@ def __init__(
         pre=False,
         **kwargs,  # used by simplecache, init_filesystem(url, **kwargs)
     ):
-
         super().__init__(
             url=url,
             config_path=CONFIG_PATH,
@@ -513,7 +512,6 @@ def cross_metadata(self):
         debug = self._log.debug
 
         if self._cache_cross_metadata is None:
-
             path = f"{self._base_path}/v3/metadata/crosses/crosses.fam"
             fam_names = [
                 "cross",
@@ -692,7 +690,6 @@ def cnv_hmm(
         debug("access CNV HMM data and concatenate as needed")
         lx = []
         for r in region:
-
             ly = []
             for s in sample_sets:
                 y = self._cnv_hmm_dataset(
@@ -723,7 +720,6 @@ def cnv_hmm(
 
         debug("handle sample query")
         if sample_query is not None:
-
             debug("load sample metadata")
             df_samples = self.sample_metadata(sample_sets=sample_sets)
 
@@ -914,7 +910,6 @@ def cnv_coverage_calls(
         debug("access data and concatenate as needed")
         lx = []
         for r in region:
-
             debug("obtain coverage calls for the contig")
             x = self._cnv_coverage_calls_dataset(
                 contig=r.contig,
@@ -1083,7 +1078,6 @@ def cnv_discordant_read_calls(
         debug("access data and concatenate as needed")
         lx = []
         for c in contig:
-
             ly = []
             for s in sample_sets:
                 y = self._cnv_discordant_read_calls_dataset(
@@ -1189,7 +1183,6 @@ def _gene_cnv(self, *, region, sample_sets, sample_query, max_coverage_variance)
             total=len(df_genes),
         )
         for gene in genes_iterator:
-
             # locate windows overlapping the gene
             loc_gene_start = bisect_left(end, gene.start)
             loc_gene_stop = bisect_right(pos, gene.end)
@@ -1403,12 +1396,10 @@ def _gene_cnv_frequencies(
         debug("compute cohort frequencies")
         freq_cols = dict()
         for coh, loc_coh in coh_dict.items():
-
             n_samples = np.count_nonzero(loc_coh)
             debug(f"{coh}, {n_samples} samples")
 
             if n_samples >= min_cohort_size:
-
                 # subset data to cohort
                 is_amp_coh = np.compress(loc_coh, is_amp, axis=1)
                 is_del_coh = np.compress(loc_coh, is_del, axis=1)
@@ -1626,7 +1617,6 @@ def _gene_cnv_frequencies_advanced(
 
         debug("build event count and nobs for each cohort")
         for cohort_index, cohort in enumerate(df_cohorts.itertuples()):
-
             # construct grouping key
             cohort_key = cohort.taxon, cohort.area, cohort.period
 
@@ -2528,7 +2518,6 @@ def plot_aim_heatmap(
 
 @numba.njit("Tuple((int8, int64))(int8[:], int8)")
 def _cn_mode_1d(a, vmax):
-
     # setup intermediates
     m = a.shape[0]
     counts = np.zeros(vmax + 1, dtype=numba.int64)
@@ -2556,7 +2545,6 @@ def _cn_mode_1d(a, vmax):
 
 @numba.njit("Tuple((int8[:], int64[:]))(int8[:, :], int8)")
 def _cn_mode(a, vmax):
-
     # setup intermediates
     n = a.shape[1]
 

malariagen_data/amin1.py

@@ -31,7 +31,6 @@
 
 class Amin1:
     def __init__(self, url=DEFAULT_URL, **kwargs):
-
         # setup filesystem
         self._fs, self._path = init_filesystem(url, **kwargs)
 
@@ -159,7 +158,6 @@ def open_snp_calls(self):
         return self._cache_snp_genotypes
 
     def _snp_calls_dataset(self, *, region, inline_array, chunks):
-
         assert isinstance(region, Region)
         contig = region.contig