Merge pull request #546 from malariagen/site-mask-default-alimanfoo-2…

…024-06-04 Ensure a site mask is used by default for Anopheles popgen functions
malariagen · Jun 7, 2024 · f14f745 · f14f745
2 parents dc89c9c + 3e2ab61
commit f14f745
Show file tree

Hide file tree

Showing 11 changed files with 63 additions and 72 deletions.
diff --git a/malariagen_data/anoph/dipclust.py b/malariagen_data/anoph/dipclust.py
@@ -13,7 +13,6 @@
 )
 from ..plotly_dendrogram import plot_dendrogram
 from . import base_params, plotly_params, tree_params, dipclust_params
-from .base_params import DEFAULT
 from .snp_data import AnophelesSnpData
 
 
@@ -39,7 +38,7 @@ def __init__(
     def plot_diplotype_clustering(
         self,
         region: base_params.regions,
-        site_mask: base_params.site_mask = DEFAULT,
+        site_mask: Optional[base_params.site_mask] = base_params.DEFAULT,
         sample_sets: Optional[base_params.sample_sets] = None,
         sample_query: Optional[base_params.sample_query] = None,
         cohort_size: Optional[base_params.cohort_size] = None,
@@ -179,7 +178,7 @@ def plot_diplotype_clustering(
     def diplotype_pairwise_distances(
         self,
         region: base_params.regions,
-        site_mask: base_params.site_mask = DEFAULT,
+        site_mask: Optional[base_params.site_mask] = base_params.DEFAULT,
         sample_sets: Optional[base_params.sample_sets] = None,
         sample_query: Optional[base_params.sample_query] = None,
         site_class: Optional[base_params.site_class] = None,

diff --git a/malariagen_data/anoph/fst.py b/malariagen_data/anoph/fst.py
@@ -10,7 +10,6 @@
 import plotly.express as px
 
 from .snp_data import AnophelesSnpData
-from .base_params import DEFAULT
 from . import base_params, fst_params, gplt_params, plotly_params
 from ..util import CacheMiss, check_types
 
@@ -105,7 +104,7 @@ def fst_gwss(
         cohort1_query: base_params.sample_query,
         cohort2_query: base_params.sample_query,
         sample_sets: Optional[base_params.sample_sets] = None,
-        site_mask: base_params.site_mask = DEFAULT,
+        site_mask: Optional[base_params.site_mask] = base_params.DEFAULT,
         cohort_size: Optional[base_params.cohort_size] = fst_params.cohort_size_default,
         min_cohort_size: Optional[
             base_params.min_cohort_size
@@ -160,7 +159,7 @@ def plot_fst_gwss_track(
         cohort1_query: base_params.sample_query,
         cohort2_query: base_params.sample_query,
         sample_sets: Optional[base_params.sample_sets] = None,
-        site_mask: base_params.site_mask = DEFAULT,
+        site_mask: Optional[base_params.site_mask] = base_params.DEFAULT,
         cohort_size: Optional[base_params.cohort_size] = fst_params.cohort_size_default,
         min_cohort_size: Optional[
             base_params.min_cohort_size
@@ -262,7 +261,7 @@ def plot_fst_gwss(
         cohort1_query: base_params.sample_query,
         cohort2_query: base_params.sample_query,
         sample_sets: Optional[base_params.sample_sets] = None,
-        site_mask: base_params.site_mask = DEFAULT,
+        site_mask: Optional[base_params.site_mask] = base_params.DEFAULT,
         cohort_size: Optional[base_params.cohort_size] = fst_params.cohort_size_default,
         min_cohort_size: Optional[
             base_params.min_cohort_size
@@ -350,7 +349,7 @@ def average_fst(
             base_params.max_cohort_size
         ] = fst_params.max_cohort_size_default,
         n_jack: base_params.n_jack = 200,
-        site_mask: base_params.site_mask = DEFAULT,
+        site_mask: Optional[base_params.site_mask] = base_params.DEFAULT,
         site_class: Optional[base_params.site_class] = None,
         random_seed: base_params.random_seed = 42,
     ) -> Tuple[float, float]:
@@ -416,7 +415,7 @@ def pairwise_average_fst(
             base_params.max_cohort_size
         ] = fst_params.max_cohort_size_default,
         n_jack: base_params.n_jack = 200,
-        site_mask: base_params.site_mask = DEFAULT,
+        site_mask: Optional[base_params.site_mask] = base_params.DEFAULT,
         site_class: Optional[base_params.site_class] = None,
         random_seed: base_params.random_seed = 42,
     ) -> fst_params.df_pairwise_fst:

diff --git a/malariagen_data/anoph/g123.py b/malariagen_data/anoph/g123.py
@@ -10,7 +10,6 @@
 from .hap_data import AnophelesHapData
 from ..util import hash_columns, check_types, CacheMiss
 from . import base_params
-from .base_params import DEFAULT
 from . import g123_params, gplt_params
 
 
@@ -150,8 +149,8 @@ def g123_gwss(
         self,
         contig: base_params.contig,
         window_size: g123_params.window_size,
-        sites: g123_params.sites = DEFAULT,
-        site_mask: Optional[base_params.site_mask] = DEFAULT,
+        sites: g123_params.sites = base_params.DEFAULT,
+        site_mask: Optional[base_params.site_mask] = base_params.DEFAULT,
         sample_sets: Optional[base_params.sample_sets] = None,
         sample_query: Optional[base_params.sample_query] = None,
         min_cohort_size: Optional[
@@ -168,7 +167,7 @@ def g123_gwss(
         # invalidate any previously cached data.
         name = "g123_gwss_v1"
 
-        if sites == DEFAULT:
+        if sites == base_params.DEFAULT:
             assert self._default_phasing_analysis is not None
             sites = self._default_phasing_analysis
         valid_sites = self.phasing_analysis_ids + ("all", "segregating")
@@ -252,8 +251,8 @@ def _g123_calibration(
     def g123_calibration(
         self,
         contig: base_params.contig,
-        sites: g123_params.sites = DEFAULT,
-        site_mask: Optional[base_params.site_mask] = DEFAULT,
+        sites: g123_params.sites = base_params.DEFAULT,
+        site_mask: Optional[base_params.site_mask] = base_params.DEFAULT,
         sample_query: Optional[base_params.sample_query] = None,
         sample_sets: Optional[base_params.sample_sets] = None,
         min_cohort_size: Optional[
@@ -305,8 +304,8 @@ def plot_g123_gwss_track(
         self,
         contig: base_params.contig,
         window_size: g123_params.window_size,
-        sites: g123_params.sites = DEFAULT,
-        site_mask: Optional[base_params.site_mask] = DEFAULT,
+        sites: g123_params.sites = base_params.DEFAULT,
+        site_mask: Optional[base_params.site_mask] = base_params.DEFAULT,
         sample_sets: Optional[base_params.sample_sets] = None,
         sample_query: Optional[base_params.sample_query] = None,
         min_cohort_size: Optional[
@@ -406,8 +405,8 @@ def plot_g123_gwss(
         self,
         contig: base_params.contig,
         window_size: g123_params.window_size,
-        sites: g123_params.sites = DEFAULT,
-        site_mask: Optional[base_params.site_mask] = DEFAULT,
+        sites: g123_params.sites = base_params.DEFAULT,
+        site_mask: Optional[base_params.site_mask] = base_params.DEFAULT,
         sample_sets: Optional[base_params.sample_sets] = None,
         sample_query: Optional[base_params.sample_query] = None,
         min_cohort_size: Optional[
@@ -484,7 +483,7 @@ def plot_g123_calibration(
         self,
         contig: base_params.contig,
         sites: g123_params.sites,
-        site_mask: Optional[base_params.site_mask] = DEFAULT,
+        site_mask: Optional[base_params.site_mask] = base_params.DEFAULT,
         sample_query: Optional[base_params.sample_query] = None,
         sample_sets: Optional[base_params.sample_sets] = None,
         min_cohort_size: Optional[

diff --git a/malariagen_data/anoph/genome_features.py b/malariagen_data/anoph/genome_features.py
@@ -16,7 +16,6 @@
     unpack_gff3_attributes,
 )
 from . import base_params, gplt_params
-from .base_params import DEFAULT
 from .genome_sequence import AnophelesGenomeSequenceData
 
 
@@ -109,7 +108,7 @@ def _prep_gff_attributes(
     ) -> Tuple[str, ...]:
         if attributes is None:
             attributes_normed: Tuple[str, ...] = ()
-        elif attributes == DEFAULT:
+        elif attributes == base_params.DEFAULT:
             attributes_normed = self._gff_default_attributes
         elif isinstance(attributes, str):
             attributes_normed = (attributes,)
@@ -125,7 +124,7 @@ def _prep_gff_attributes(
     def genome_features(
         self,
         region: Optional[base_params.regions] = None,
-        attributes: base_params.gff_attributes = DEFAULT,
+        attributes: base_params.gff_attributes = base_params.DEFAULT,
     ) -> pd.DataFrame:
         debug = self._log.debug
 
@@ -159,7 +158,7 @@ def genome_features(
             )
 
     def genome_feature_children(
-        self, parent: str, attributes: base_params.gff_attributes = DEFAULT
+        self, parent: str, attributes: base_params.gff_attributes = base_params.DEFAULT
     ) -> pd.DataFrame:
         # Normalise attributes and ensure Parent is included.
         attributes_normed = self._prep_gff_attributes(attributes)

diff --git a/malariagen_data/anoph/h12.py b/malariagen_data/anoph/h12.py
@@ -9,7 +9,6 @@
 from .hap_data import AnophelesHapData
 from ..util import hash_columns, check_types, CacheMiss
 from . import base_params
-from .base_params import DEFAULT
 from . import h12_params, gplt_params, hap_params
 
 
@@ -70,7 +69,7 @@ def _h12_calibration(
     def h12_calibration(
         self,
         contig: base_params.contig,
-        analysis: hap_params.analysis = DEFAULT,
+        analysis: hap_params.analysis = base_params.DEFAULT,
         sample_query: Optional[base_params.sample_query] = None,
         sample_sets: Optional[base_params.sample_sets] = None,
         cohort_size: Optional[base_params.cohort_size] = h12_params.cohort_size_default,
@@ -122,7 +121,7 @@ def h12_calibration(
     def plot_h12_calibration(
         self,
         contig: base_params.contig,
-        analysis: hap_params.analysis = DEFAULT,
+        analysis: hap_params.analysis = base_params.DEFAULT,
         sample_query: Optional[base_params.sample_query] = None,
         sample_sets: Optional[base_params.sample_sets] = None,
         cohort_size: Optional[base_params.cohort_size] = h12_params.cohort_size_default,
@@ -260,7 +259,7 @@ def h12_gwss(
         self,
         contig: base_params.contig,
         window_size: h12_params.window_size,
-        analysis: hap_params.analysis = DEFAULT,
+        analysis: hap_params.analysis = base_params.DEFAULT,
         sample_query: Optional[base_params.sample_query] = None,
         sample_sets: Optional[base_params.sample_sets] = None,
         cohort_size: Optional[base_params.cohort_size] = h12_params.cohort_size_default,
@@ -311,7 +310,7 @@ def plot_h12_gwss_track(
         self,
         contig: base_params.contig,
         window_size: h12_params.window_size,
-        analysis: hap_params.analysis = DEFAULT,
+        analysis: hap_params.analysis = base_params.DEFAULT,
         sample_sets: Optional[base_params.sample_sets] = None,
         sample_query: Optional[base_params.sample_query] = None,
         cohort_size: Optional[base_params.cohort_size] = h12_params.cohort_size_default,
@@ -408,7 +407,7 @@ def plot_h12_gwss(
         self,
         contig: base_params.contig,
         window_size: h12_params.window_size,
-        analysis: hap_params.analysis = DEFAULT,
+        analysis: hap_params.analysis = base_params.DEFAULT,
         sample_sets: Optional[base_params.sample_sets] = None,
         sample_query: Optional[base_params.sample_query] = None,
         cohort_size: Optional[base_params.cohort_size] = h12_params.cohort_size_default,

diff --git a/malariagen_data/anoph/h1x.py b/malariagen_data/anoph/h1x.py
@@ -8,7 +8,6 @@
 from .hap_data import AnophelesHapData
 from ..util import check_types, CacheMiss
 from . import base_params
-from .base_params import DEFAULT
 from . import h12_params, gplt_params, hap_params
 from .h12 import haplotype_frequencies
 
@@ -97,7 +96,7 @@ def h1x_gwss(
         window_size: h12_params.window_size,
         cohort1_query: base_params.sample_query,
         cohort2_query: base_params.sample_query,
-        analysis: hap_params.analysis = DEFAULT,
+        analysis: hap_params.analysis = base_params.DEFAULT,
         sample_sets: Optional[base_params.sample_sets] = None,
         cohort_size: Optional[base_params.cohort_size] = h12_params.cohort_size_default,
         min_cohort_size: Optional[
@@ -153,7 +152,7 @@ def plot_h1x_gwss_track(
         window_size: h12_params.window_size,
         cohort1_query: base_params.cohort1_query,
         cohort2_query: base_params.cohort2_query,
-        analysis: hap_params.analysis = DEFAULT,
+        analysis: hap_params.analysis = base_params.DEFAULT,
         sample_sets: Optional[base_params.sample_sets] = None,
         cohort_size: Optional[base_params.cohort_size] = h12_params.cohort_size_default,
         min_cohort_size: Optional[
@@ -255,7 +254,7 @@ def plot_h1x_gwss(
         window_size: h12_params.window_size,
         cohort1_query: base_params.cohort1_query,
         cohort2_query: base_params.cohort2_query,
-        analysis: hap_params.analysis = DEFAULT,
+        analysis: hap_params.analysis = base_params.DEFAULT,
         sample_sets: Optional[base_params.sample_sets] = None,
         cohort_size: Optional[base_params.cohort_size] = h12_params.cohort_size_default,
         min_cohort_size: Optional[

diff --git a/malariagen_data/anoph/hap_data.py b/malariagen_data/anoph/hap_data.py
@@ -21,7 +21,6 @@
     simple_xarray_concat,
 )
 from . import base_params, hap_params
-from .base_params import DEFAULT
 from .genome_features import AnophelesGenomeFeaturesData
 from .genome_sequence import AnophelesGenomeSequenceData
 from .sample_metadata import AnophelesSampleMetadata
@@ -57,7 +56,7 @@ def phasing_analysis_ids(self) -> Tuple[str, ...]:
         return tuple(self.config.get("PHASING_ANALYSIS_IDS", ()))  # ensure tuple
 
     def _prep_phasing_analysis_param(self, *, analysis: hap_params.analysis) -> str:
-        if analysis == DEFAULT:
+        if analysis == base_params.DEFAULT:
             # Use whatever is the default phasing analysis for this data resource.
             assert self._default_phasing_analysis is not None
             return self._default_phasing_analysis
@@ -74,7 +73,7 @@ def _prep_phasing_analysis_param(self, *, analysis: hap_params.analysis) -> str:
         returns="Zarr hierarchy.",
     )
     def open_haplotype_sites(
-        self, analysis: hap_params.analysis = DEFAULT
+        self, analysis: hap_params.analysis = base_params.DEFAULT
     ) -> zarr.hierarchy.Group:
         analysis = self._prep_phasing_analysis_param(analysis=analysis)
         try:
@@ -172,7 +171,7 @@ def haplotype_sites(
         self,
         region: base_params.regions,
         field: base_params.field,
-        analysis: hap_params.analysis = DEFAULT,
+        analysis: hap_params.analysis = base_params.DEFAULT,
         inline_array: base_params.inline_array = base_params.inline_array_default,
         chunks: base_params.chunks = base_params.chunks_default,
     ) -> da.Array:
@@ -205,7 +204,7 @@ def haplotype_sites(
     def open_haplotypes(
         self,
         sample_set: base_params.sample_set,
-        analysis: hap_params.analysis = DEFAULT,
+        analysis: hap_params.analysis = base_params.DEFAULT,
     ) -> Optional[zarr.hierarchy.Group]:
         analysis = self._prep_phasing_analysis_param(analysis=analysis)
         try:
@@ -327,7 +326,7 @@ def _haplotypes_for_contig(
     def haplotypes(
         self,
         region: base_params.regions,
-        analysis: hap_params.analysis = DEFAULT,
+        analysis: hap_params.analysis = base_params.DEFAULT,
         sample_sets: Optional[base_params.sample_sets] = None,
         sample_query: Optional[base_params.sample_query] = None,
         inline_array: base_params.inline_array = base_params.inline_array_default,

diff --git a/malariagen_data/anoph/hapclust.py b/malariagen_data/anoph/hapclust.py
@@ -8,7 +8,6 @@
 from ..util import CacheMiss, check_types, pdist_abs_hamming
 from ..plotly_dendrogram import plot_dendrogram
 from . import base_params, plotly_params, tree_params, hap_params, hapclust_params
-from .base_params import DEFAULT
 from .snp_data import AnophelesSnpData
 from .hap_data import AnophelesHapData
 
@@ -35,7 +34,7 @@ def __init__(
     def plot_haplotype_clustering(
         self,
         region: base_params.regions,
-        analysis: hap_params.analysis = DEFAULT,
+        analysis: hap_params.analysis = base_params.DEFAULT,
         sample_sets: Optional[base_params.sample_sets] = None,
         sample_query: Optional[base_params.sample_query] = None,
         cohort_size: Optional[base_params.cohort_size] = None,
@@ -186,7 +185,7 @@ def plot_haplotype_clustering(
     def haplotype_pairwise_distances(
         self,
         region: base_params.regions,
-        analysis: hap_params.analysis = DEFAULT,
+        analysis: hap_params.analysis = base_params.DEFAULT,
         sample_sets: Optional[base_params.sample_sets] = None,
         sample_query: Optional[base_params.sample_query] = None,
         cohort_size: Optional[base_params.cohort_size] = None,

diff --git a/malariagen_data/anoph/pca.py b/malariagen_data/anoph/pca.py
@@ -60,7 +60,7 @@ def pca(
         sample_sets: Optional[base_params.sample_sets] = None,
         sample_query: Optional[base_params.sample_query] = None,
         sample_indices: Optional[base_params.sample_indices] = None,
-        site_mask: Optional[base_params.site_mask] = None,
+        site_mask: Optional[base_params.site_mask] = base_params.DEFAULT,
         site_class: Optional[base_params.site_class] = None,
         min_minor_ac: Optional[base_params.min_minor_ac] = None,
         max_missing_an: Optional[base_params.max_missing_an] = None,