Merge branch 'master' into GH716_add_constructor_params

Author: leehart

malariagen_data/anoph/snp_frq.py

@@ -3,6 +3,7 @@
 
 import allel  # type: ignore
 import numpy as np
+import numpy.typing as npt
 import pandas as pd
 from numpydoc_decorator import doc  # type: ignore
 import xarray as xr
@@ -518,8 +519,8 @@ def snp_allele_frequencies_advanced(
 
         # Set up main event variables.
         n_variants, n_cohorts = len(variant_position), len(df_cohorts)
-        count = np.zeros((n_variants, n_cohorts), dtype=int)
-        nobs = np.zeros((n_variants, n_cohorts), dtype=int)
+        count: npt.NDArray[np.float64] = np.zeros((n_variants, n_cohorts), dtype=int)
+        nobs: npt.NDArray[np.float64] = np.zeros((n_variants, n_cohorts), dtype=int)
 
         # Build event count and nobs for each cohort.
         cohorts_iterator = self._progress(

malariagen_data/plasmodium.py

@@ -1,5 +1,4 @@
 import json
-import os
 
 import dask.array as da
 import pandas as pd
@@ -60,7 +59,7 @@ def sample_metadata(self):
             One row per sample.
         """
         if self._cache_sample_metadata is None:
-            path = os.path.join(self._path, self.CONF["metadata_path"])
+            path = f"{self._path}/{self.CONF['metadata_path']}"
             with self._fs.open(path) as f:
                 self._cache_sample_metadata = pd.read_csv(f, sep="\t", na_values="")
         return self._cache_sample_metadata
@@ -75,7 +74,7 @@ def _open_variant_calls_zarr(self):
 
         """
         if self._cache_variant_calls_zarr is None:
-            path = os.path.join(self._path, self.CONF["variant_calls_zarr_path"])
+            path = f"{self._path}/{self.CONF['variant_calls_zarr_path']}"
             store = init_zarr_store(fs=self._fs, path=path)
             self._cache_variant_calls_zarr = zarr.open_consolidated(store=store)
         return self._cache_variant_calls_zarr
@@ -205,7 +204,7 @@ def open_genome(self):
 
         """
         if self._cache_genome is None:
-            path = os.path.join(self._path, self.CONF["reference_path"])
+            path = f"{self._path}/{self.CONF['reference_path']}"
             store = init_zarr_store(fs=self._fs, path=path)
             self._cache_genome = zarr.open_consolidated(store=store)
         return self._cache_genome
@@ -317,7 +316,7 @@ def genome_features(self, attributes=("ID", "Parent", "Name")):
         try:
             df = self._cache_genome_features[attributes]
         except KeyError:
-            path = os.path.join(self._path, self.CONF["annotations_path"])
+            path = f"{self._path}/{self.CONF['annotations_path']}"
             with self._fs.open(path, mode="rb") as f:
                 df = read_gff3(f, compression="gzip")
             if attributes is not None:

tests/anoph/test_hap_data.py

@@ -605,7 +605,7 @@ def test_haplotypes_virtual_contigs(
 
         # Test with region.
         seq = api.genome_sequence(region=chrom)
-        start, stop = sorted(np.random.randint(low=1, high=len(seq), size=2))
+        start, stop = sorted(map(int, np.random.randint(low=1, high=len(seq), size=2)))
         region = f"{chrom}:{start:,}-{stop:,}"
 
         # Standard checks.

tests/anoph/test_snp_frq.py

@@ -153,7 +153,7 @@ def test_snp_effects(fixture, api: AnophelesSnpFrequencyAnalysis):
 
     # Check some values.
     assert np.all(df["contig"] == transcript["contig"])
-    position = df["position"].values
+    position = df["position"].to_numpy()
     assert np.all(position >= transcript["start"])
     assert np.all(position <= transcript["end"])
     assert np.all(position[1:] >= position[:-1])  # type: ignore