refactor: use cached_property for _snp_effect_annotator in snp_frq.py

Author: Tanisha127

malariagen_data/anoph/genome_sequence.py

@@ -29,8 +29,6 @@ def __init__(
             virtual_contigs = dict()
         self._virtual_contigs = virtual_contigs
 
-        # Initialize cache attributes.
-        self._cache_genome = None
 
     @property
     def contigs(self) -> Tuple[str, ...]:
@@ -62,13 +60,9 @@ 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/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
         )

malariagen_data/plasmodium.py

@@ -51,29 +51,13 @@ def _load_config(self, data_config):
         return config_content
 
     def sample_metadata(self):
-        """Access sample metadata and return as pandas dataframe.
-        Returns
-        -------
-        df : pandas.DataFrame
-            A dataframe of sample metadata on the samples that were sequenced as part of this resource.
-            Includes the time and place of collection, quality metrics, and accesion numbers.
-            One row per sample.
-        """
         if self._cache_sample_metadata is None:
             path = os.path.join(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
 
     def _open_variant_calls_zarr(self):
-        """Open variant calls zarr.
-
-        Returns
-        -------
-        root : zarr.hierarchy.Group
-            Root of zarr containing information on variant calls.
-
-        """
         if self._cache_variant_calls_zarr is None:
             path = os.path.join(self._path, self.CONF["variant_calls_zarr_path"])
             store = _init_zarr_store(fs=self._fs, path=path)
@@ -196,14 +180,6 @@ def variant_calls(self, extended=False, inline_array=True, chunks="native"):
         return ds
 
     def open_genome(self):
-        """Open the reference genome zarr.
-
-        Returns
-        -------
-        root : zarr.hierarchy.Group
-            Zarr hierarchy containing the reference genome sequence.
-
-        """
         if self._cache_genome is None:
             path = os.path.join(self._path, self.CONF["reference_path"])
             store = _init_zarr_store(fs=self._fs, path=path)