Rename to _check_types, update uses

Author: leehart

malariagen_data/anoph/aim_data.py

@@ -10,7 +10,7 @@
 
 from malariagen_data.anoph import plotly_params
 
-from ..util import DIM_SAMPLE, check_types, _init_zarr_store, _simple_xarray_concat
+from ..util import DIM_SAMPLE, _check_types, _init_zarr_store, _simple_xarray_concat
 from . import aim_params, base_params
 from .genome_features import AnophelesGenomeFeaturesData
 from .genome_sequence import AnophelesGenomeSequenceData
@@ -62,7 +62,7 @@ def _prep_aims_param(self, *, aims: aim_params.aims) -> str:
         else:
             raise ValueError(f"Invalid aims parameter, must be one of {self.aim_ids}.")
 
-    @check_types
+    @_check_types
     @doc(
         summary="Access ancestry informative marker variants.",
         returns="""
@@ -110,7 +110,7 @@ def _aim_calls_dataset(self, *, aims, sample_set):
         ds = ds.set_coords(["variant_contig", "variant_position", "sample_id"])
         return ds
 
-    @check_types
+    @_check_types
     @doc(
         summary="""
             Access ancestry informative marker SNP sites, alleles and genotype

malariagen_data/anoph/base.py

@@ -34,7 +34,7 @@
     CacheMiss,
     LoggingHelper,
     _check_colab_location,
-    check_types,
+    _check_types,
     _distributed_client,
     _get_gcp_region,
     _hash_params,
@@ -222,12 +222,12 @@ def _spinner(
         else:
             return nullcontext()
 
-    @check_types
+    @_check_types
     def open_file(self, path: str) -> IO:
         full_path = f"{self._base_path}/{path}"
         return self._fs.open(full_path)
 
-    @check_types
+    @_check_types
     def read_files(
         self,
         paths: Iterable[str],
@@ -608,7 +608,7 @@ def _read_sample_sets_manifest(self, *, single_release: str):
 
         return df
 
-    @check_types
+    @_check_types
     @doc(
         summary="Access a dataframe of sample sets",
         returns="""A dataframe of sample sets, one row per sample set. It contains five columns:
@@ -630,7 +630,7 @@ def sample_sets(
     ) -> pd.DataFrame:
         return self._relevant_sample_sets(release=release)
 
-    @check_types
+    @_check_types
     @doc(
         summary="Access a dataframe of available sample sets",
         returns="""A dataframe of available sample sets, one row per sample set. It contains five columns:
@@ -685,7 +685,7 @@ def _available_sample_sets(
         # Return copy to ensure cached dataframes aren't modified by user.
         return df.copy()
 
-    @check_types
+    @_check_types
     @doc(
         summary="Access a dataframe of relevant sample sets",
         returns="""A dataframe of relevant sample sets, one row per sample set. It contains five columns:
@@ -767,7 +767,7 @@ def _relevant_sample_sets(
         # Return copy to ensure cached dataframes aren't modified by user.
         return df.copy()
 
-    @check_types
+    @_check_types
     @doc(
         summary="Find which release a sample set was included in.",
         returns="The release the sample set is part of.",
@@ -784,7 +784,7 @@ def lookup_release(self, sample_set: base_params.sample_set) -> str:
                 f"No release found for sample set {sample_set!r}. This sample set might be unavailable or irrelevant with respect to settings."
             ) from e
 
-    @check_types
+    @_check_types
     @doc(
         summary="Find which study a sample set belongs to.",
         returns="The study the sample set belongs to.",
@@ -798,7 +798,7 @@ def lookup_study(self, sample_set: base_params.sample_set) -> str:
         except KeyError as e:
             raise ValueError(f"No study ID found for sample set {sample_set!r}") from e
 
-    @check_types
+    @_check_types
     @doc(
         summary="Find the study info for a sample set.",
         returns="The info for the study the sample set belongs to.",
@@ -816,7 +816,7 @@ def lookup_study_info(self, sample_set: base_params.sample_set) -> dict:
                 f"No study info found for sample set {sample_set!r}"
             ) from e
 
-    @check_types
+    @_check_types
     @doc(
         summary="Find the terms-of-use info for a sample set.",
         returns="The terms-of-use info for the sample set.",
@@ -980,7 +980,7 @@ def _results_cache_add_analysis_params(self, params: dict):
         # Expect sub-classes will override to add any analysis parameters.
         pass
 
-    @check_types
+    @_check_types
     def results_cache_get(
         self, *, name: str, params: Dict[str, Any]
     ) -> Mapping[str, np.ndarray]:
@@ -1004,7 +1004,7 @@ def results_cache_get(
 
         raise CacheMiss
 
-    @check_types
+    @_check_types
     def results_cache_set(
         self, *, name: str, params: Dict[str, Any], results: Mapping[str, np.ndarray]
     ):

malariagen_data/anoph/cnv_data.py

@@ -11,7 +11,7 @@
     DIM_SAMPLE,
     DIM_VARIANT,
     Region,
-    check_types,
+    _check_types,
     _da_from_zarr,
     _init_zarr_store,
     _parse_multi_region,
@@ -68,7 +68,7 @@ def coverage_calls_analysis_ids(self) -> Tuple[str, ...]:
         """
         return tuple(self.config.get("COVERAGE_CALLS_ANALYSIS_IDS", ()))  # ensure tuple
 
-    @check_types
+    @_check_types
     @doc(
         summary="Open CNV HMM zarr.",
         returns="Zarr hierarchy or None.",
@@ -167,7 +167,7 @@ def _cnv_hmm_dataset(self, *, contig, sample_set, inline_array, chunks):
 
         return ds
 
-    @check_types
+    @_check_types
     @doc(
         summary="Access CNV HMM data from CNV calling.",
         returns="""A dataset with 2 dimensions:
@@ -271,7 +271,7 @@ def cnv_hmm(
 
         return ds
 
-    @check_types
+    @_check_types
     @doc(
         summary="Open CNV coverage calls zarr.",
         returns="Zarr hierarchy.",
@@ -386,7 +386,7 @@ def _cnv_coverage_calls_dataset(
 
         return ds
 
-    @check_types
+    @_check_types
     @doc(
         summary="Access CNV HMM data from genome-wide CNV discovery and filtering.",
         returns="""A dataset with 2 dimensions:
@@ -469,7 +469,7 @@ def cnv_coverage_calls(
 
         return ds
 
-    @check_types
+    @_check_types
     @doc(
         summary="Open CNV discordant read calls zarr.",
         returns="Zarr hierarchy.",
@@ -575,7 +575,7 @@ def _cnv_discordant_read_calls_dataset(
 
         return ds
 
-    @check_types
+    @_check_types
     @doc(
         summary="Access CNV discordant read calls data.",
         returns="""A dataset with 2 dimensions:
@@ -665,7 +665,7 @@ def cnv_discordant_read_calls(
 
         return ds
 
-    @check_types
+    @_check_types
     @doc(
         summary="Plot CNV HMM data for a single sample, using bokeh.",
         returns="Bokeh figure.",
@@ -790,7 +790,7 @@ def plot_cnv_hmm_coverage_track(
         else:
             return fig
 
-    @check_types
+    @_check_types
     @doc(
         summary="Plot CNV HMM data for a single sample, together with a genes track, using bokeh.",
         returns="Bokeh figure.",
@@ -864,7 +864,7 @@ def plot_cnv_hmm_coverage(
         else:
             return fig
 
-    @check_types
+    @_check_types
     @doc(
         summary="Plot CNV HMM data for multiple samples as a heatmap, using bokeh.",
         returns="Bokeh figure.",
@@ -1006,7 +1006,7 @@ def plot_cnv_hmm_heatmap_track(
         else:
             return fig
 
-    @check_types
+    @_check_types
     @doc(
         summary="Plot CNV HMM data for multiple samples as a heatmap, with a genes track, using bokeh.",
         returns="Bokeh figure.",

malariagen_data/anoph/cnv_frq.py

@@ -16,7 +16,7 @@
     _add_frequency_ci,
 )
 from ..util import (
-    check_types,
+    _check_types,
     _pandas_apply,
     Region,
     _parse_multi_region,
@@ -38,7 +38,7 @@ def __init__(
         # to the superclass constructor.
         super().__init__(**kwargs)
 
-    @check_types
+    @_check_types
     @doc(
         summary="""
         Compute modal copy number by gene, from HMM data.
@@ -183,7 +183,7 @@ def _gene_cnv(
 
         return ds_out
 
-    @check_types
+    @_check_types
     @doc(
         summary="""
         Compute modal copy number by gene, then compute the frequency of
@@ -412,7 +412,7 @@ def _gene_cnv_frequencies(
 
         return df
 
-    @check_types
+    @_check_types
     @doc(
         summary="""
         Group samples by taxon, area (space) and period (time), then compute

malariagen_data/anoph/dipclust.py

@@ -8,7 +8,7 @@
 
 from ..util import (
     CacheMiss,
-    check_types,
+    _check_types,
     _multiallelic_diplotype_pdist,
     _multiallelic_diplotype_mean_sqeuclidean,
     _multiallelic_diplotype_mean_cityblock,
@@ -42,7 +42,7 @@ def __init__(
         # to the superclass constructor.
         super().__init__(**kwargs)
 
-    @check_types
+    @_check_types
     @doc(
         summary=""""
         Hierarchically cluster diplotypes in region and produce an interactive plot.

malariagen_data/anoph/distance.py

@@ -10,7 +10,7 @@
 # Internal imports.
 from .snp_data import AnophelesSnpData
 from . import base_params, distance_params, plotly_params, pca_params, tree_params
-from ..util import _square_to_condensed, check_types, CacheMiss
+from ..util import _square_to_condensed, _check_types, CacheMiss
 
 
 @numba.njit(parallel=True)
@@ -81,7 +81,7 @@ def __init__(self, **kwargs):
         # to the superclass constructor.
         super().__init__(**kwargs)
 
-    @check_types
+    @_check_types
     @doc(
         summary="""
             Compute pairwise distances between samples using biallelic SNP genotypes.
@@ -240,7 +240,7 @@ def _biallelic_diplotype_pairwise_distances(
             ),  # ensure consistent behaviour to/from results cache
         )
 
-    @check_types
+    @_check_types
     @doc(
         summary="""
             Construct a neighbour-joining tree between samples using biallelic SNP genotypes.
@@ -409,7 +409,7 @@ def _njt(
             ),  # ensure consistent behaviour to/from results cache
         )
 
-    @check_types
+    @_check_types
     @doc(
         summary="""
             Plot an unrooted neighbour-joining tree, computed from pairwise distances

malariagen_data/anoph/frq_base.py

@@ -12,7 +12,7 @@
     frq_params,
     map_params,
 )
-from ..util import check_types
+from ..util import _check_types
 from .base import AnophelesBase
 
 
@@ -170,7 +170,7 @@ def __init__(
         # to the superclass constructor.
         super().__init__(**kwargs)
 
-    @check_types
+    @_check_types
     @doc(
         summary="""
             Plot a heatmap from a pandas DataFrame of frequencies, e.g., output
@@ -323,7 +323,7 @@ def plot_frequencies_heatmap(
         else:
             return fig
 
-    @check_types
+    @_check_types
     @doc(
         summary="Create a time series plot of variant frequencies using plotly.",
         parameters=dict(
@@ -461,7 +461,7 @@ def plot_frequencies_time_series(
         else:
             return fig
 
-    @check_types
+    @_check_types
     @doc(
         summary="""
             Plot markers on a map showing variant frequencies for cohorts grouped
@@ -552,7 +552,7 @@ def plot_frequencies_map_markers(
             )
             m.add(marker)
 
-    @check_types
+    @_check_types
     @doc(
         summary="""
             Create an interactive map with markers showing variant frequencies or