Merge branch 'master' into GH987-fix-sample-query-options-annotation-in-average-fst

Author: rehanxt5

malariagen_data/anoph/genome_sequence.py

@@ -16,6 +16,8 @@
 
 
 class AnophelesGenomeSequenceData(AnophelesBase):
+    _cache_genome: Optional[zarr.hierarchy.Group]
+
     def __init__(
         self, virtual_contigs: Optional[Mapping[str, Sequence[str]]] = None, **kwargs
     ):
@@ -29,9 +31,6 @@ def __init__(
             virtual_contigs = dict()
         self._virtual_contigs = virtual_contigs
 
-        # Initialize cache attributes.
-        self._cache_genome = None
-
     @property
     def contigs(self) -> Tuple[str, ...]:
         """Contigs in the reference genome."""
@@ -62,13 +61,9 @@ def _genome_ref_id(self) -> str:
     def _genome_ref_name(self) -> str:
         return self.config["GENOME_REF_NAME"]
 
-    @_check_types
-    @doc(
-        summary="Open the reference genome zarr.",
-        returns="Zarr hierarchy containing the reference genome sequence.",
-    )
     def open_genome(self) -> zarr.hierarchy.Group:
-        if self._cache_genome is None:
+        """Open the reference genome zarr."""
+        if not hasattr(self, "_cache_genome") or self._cache_genome is None:
             path = f"{self._base_path}/{self._genome_zarr_path}"
             store = _init_zarr_store(fs=self._fs, path=path)
             self._cache_genome = zarr.open_consolidated(store=store)

malariagen_data/anoph/map_params.py

@@ -1,5 +1,6 @@
 """Parameters for functions plotting maps using ipyleaflet."""
 
+import warnings
 from typing import Dict, Tuple, Union
 
 import ipyleaflet  # type: ignore
@@ -17,22 +18,70 @@
 
 zoom_default: zoom = 3
 
-basemap_abbrevs = {
-    "mapnik": ipyleaflet.basemaps.OpenStreetMap.Mapnik,
-    "natgeoworldmap": ipyleaflet.basemaps.Esri.NatGeoWorldMap,
-    "opentopomap": ipyleaflet.basemaps.OpenTopoMap,
-    "positron": ipyleaflet.basemaps.CartoDB.Positron,
-    "satellite": ipyleaflet.basemaps.Gaode.Satellite,
-    "worldimagery": ipyleaflet.basemaps.Esri.WorldImagery,
-    "worldstreetmap": ipyleaflet.basemaps.Esri.WorldStreetMap,
-    "worldtopomap": ipyleaflet.basemaps.Esri.WorldTopoMap,
+# Candidate basemap abbreviations — loaded lazily to avoid import failures
+# if a provider has been decommissioned upstream.
+_basemap_abbrev_candidates = {
+    "mapnik": lambda: ipyleaflet.basemaps.OpenStreetMap.Mapnik,
+    "natgeoworldmap": lambda: ipyleaflet.basemaps.Esri.NatGeoWorldMap,
+    "opentopomap": lambda: ipyleaflet.basemaps.OpenTopoMap,
+    "positron": lambda: ipyleaflet.basemaps.CartoDB.Positron,
+    "satellite": lambda: ipyleaflet.basemaps.Gaode.Satellite,
+    "worldimagery": lambda: ipyleaflet.basemaps.Esri.WorldImagery,
+    "worldstreetmap": lambda: ipyleaflet.basemaps.Esri.WorldStreetMap,
+    "worldtopomap": lambda: ipyleaflet.basemaps.Esri.WorldTopoMap,
 }
 
+_basemap_abbrevs: dict | None = None
+
+
+def get_basemap_abbrevs() -> dict:
+    """Return available basemap abbreviations, skipping any unavailable providers."""
+    global _basemap_abbrevs
+    if _basemap_abbrevs is None:
+        _basemap_abbrevs = {}
+        for key, provider_fn in _basemap_abbrev_candidates.items():
+            try:
+                _basemap_abbrevs[key] = provider_fn()
+            except Exception:
+                warnings.warn(
+                    f"Basemap provider {key!r} is not available and will be skipped.",
+                    stacklevel=2,
+                )
+    return _basemap_abbrevs
+
+
+# Keep basemap_abbrevs as a property-like alias for backwards compatibility.
+# Code that does `map_params.basemap_abbrevs` will call get_basemap_abbrevs().
+class _BasemapAbbrevProxy:
+    def __getattr__(self, item):
+        return getattr(get_basemap_abbrevs(), item)
+
+    def __iter__(self):
+        return iter(get_basemap_abbrevs())
+
+    def __getitem__(self, item):
+        return get_basemap_abbrevs()[item]
+
+    def __contains__(self, item):
+        return item in get_basemap_abbrevs()
+
+    def keys(self):
+        return get_basemap_abbrevs().keys()
+
+    def values(self):
+        return get_basemap_abbrevs().values()
+
+    def items(self):
+        return get_basemap_abbrevs().items()
+
+
+basemap_abbrevs = _BasemapAbbrevProxy()
+
 basemap: TypeAlias = Annotated[
     Union[str, Dict, ipyleaflet.TileLayer, xyzservices.lib.TileProvider],
     f"""
     Basemap from ipyleaflet or other TileLayer provider. Strings are abbreviations mapped to corresponding
-    basemaps, available values are {list(basemap_abbrevs.keys())}.
+    basemaps, available values are {list(_basemap_abbrev_candidates.keys())}.
     """,
 ]
 

malariagen_data/anoph/snp_frq.py

@@ -1,3 +1,4 @@
+from functools import cached_property
 from typing import Optional, Dict, Union, Callable, List
 import warnings
 
@@ -40,9 +41,6 @@ def __init__(
         # to the superclass constructor.
         super().__init__(**kwargs)
 
-        # Set up cache variables.
-        self._cache_annotator = None
-
     def _snp_df_melt(self, *, ds_snp: xr.Dataset) -> pd.DataFrame:
         """Set up a dataframe with SNP site and filter data,
         melting each alternate allele into a separate row."""
@@ -81,13 +79,12 @@ def _snp_df_melt(self, *, ds_snp: xr.Dataset) -> pd.DataFrame:
 
         return df_snps
 
+    @cached_property
     def _snp_effect_annotator(self):
         """Set up variant effect annotator."""
-        if self._cache_annotator is None:
-            self._cache_annotator = veff.Annotator(
-                genome=self.open_genome(), genome_features=self.genome_features()
-            )
-        return self._cache_annotator
+        return veff.Annotator(
+            genome=self.open_genome(), genome_features=self.genome_features()
+        )
 
     @_check_types
     @doc(
@@ -112,7 +109,7 @@ def snp_effects(
         df_snps = self._snp_df_melt(ds_snp=ds_snp)
 
         # Setup variant effect annotator.
-        ann = self._snp_effect_annotator()
+        ann = self._snp_effect_annotator
 
         # Add effects to the dataframe.
         ann.get_effects(transcript=transcript, variants=df_snps)
@@ -249,7 +246,7 @@ def snp_allele_frequencies(
 
         if effects:
             # Add effect annotations.
-            ann = self._snp_effect_annotator()
+            ann = self._snp_effect_annotator
             ann.get_effects(
                 transcript=transcript, variants=df_snps, progress=self._progress
             )
@@ -586,7 +583,7 @@ def snp_allele_frequencies_advanced(
             frequency = np.compress(loc_variant, frequency, axis=0)
 
         # Set up variant effect annotator.
-        ann = self._snp_effect_annotator()
+        ann = self._snp_effect_annotator
 
         # Add effects to the dataframe.
         ann.get_effects(
@@ -832,7 +829,7 @@ def snp_genotype_allele_counts(
         df_snps = pd.concat([df_snps, df_counts], axis=1)
 
         # Add effect annotations.
-        ann = self._snp_effect_annotator()
+        ann = self._snp_effect_annotator
         ann.get_effects(
             transcript=transcript, variants=df_snps, progress=self._progress
         )