Merge branch 'master' into GH903-api-introspection

Author: jonbrenas

malariagen_data/anoph/dipclust.py

@@ -542,10 +542,10 @@ def _dipclust_concat_subplots(
             if isinstance(figure, go.Figure):
                 # This is a figure, access the traces within it.
                 for trace in range(len(figure["data"])):
-                    fig.append_trace(figure["data"][trace], row=i + 1, col=1)
+                    fig.add_trace(figure["data"][trace], row=i + 1, col=1)
             else:
                 # Assume this is a trace, add directly.
-                fig.append_trace(figure, row=i + 1, col=1)
+                fig.add_trace(figure, row=i + 1, col=1)
 
         fig.update_xaxes(visible=False)
         fig.update_layout(

malariagen_data/anoph/sample_metadata.py

@@ -1569,11 +1569,11 @@ def plot_sample_location_mapbox(
         # Sort by `color` column by default, which can be overridden via category_orders.
         df_locations = df_samples[location_columns].drop_duplicates().sort_values(color)
 
-        fig = px.scatter_mapbox(
+        fig = px.scatter_map(
             df_locations,
             lat="latitude",
             lon="longitude",
-            mapbox_style="open-street-map",
+            map_style="open-street-map",
             zoom=zoom,
             color=color,
             category_orders=category_orders,

malariagen_data/plasmodium.py

@@ -1,5 +1,6 @@
 import json
 
+import os
 import dask.array as da
 import pandas as pd
 import xarray
@@ -59,7 +60,7 @@ def sample_metadata(self):
             One row per sample.
         """
         if self._cache_sample_metadata is None:
-            path = f"{self._path}/{self.CONF['metadata_path']}"
+            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
@@ -74,7 +75,7 @@ def _open_variant_calls_zarr(self):
 
         """
         if self._cache_variant_calls_zarr is None:
-            path = f"{self._path}/{self.CONF['variant_calls_zarr_path']}"
+            path = os.path.join(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
@@ -204,7 +205,7 @@ def open_genome(self):
 
         """
         if self._cache_genome is None:
-            path = f"{self._path}/{self.CONF['reference_path']}"
+            path = os.path.join(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
@@ -316,7 +317,7 @@ def genome_features(self, attributes=("ID", "Parent", "Name")):
         try:
             df = self._cache_genome_features[attributes]
         except KeyError:
-            path = f"{self._path}/{self.CONF['annotations_path']}"
+            path = os.path.join(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:

pyproject.toml

@@ -6,15 +6,10 @@ readme = "README.md"
 documentation = "https://malariagen.github.io/malariagen-data-python/latest/"
 repository = "https://github.com/malariagen/malariagen-data-python"
 authors = [
-    "Alistair Miles <alistair.miles@sanger.ac.uk>",
-    "Chris Clarkson <chris.clarkson@sanger.ac.uk>",
-    "Anastasia Hernandez-Koutoucheva <ah32@sanger.ac.uk>",
-    "Lee Hart <lee.hart@sanger.ac.uk>",
-    "Kathryn Murie <km22@sanger.ac.uk>",
-    "Nace Kranjc <n.kranjc@imperial.ac.uk>",
-    "Kelly Bennett <kb25@sanger.ac.uk>",
-    "Jon Brenas <jb52@sanger.ac.uk>",
-    "Sanjay Nagi <sanjay.nagi@lstmed.ac.uk>",
+    "Chris Clarkson <Chris.Clarkson@lstmed.ac.uk>",
+    "Anastasia Hernandez-Koutoucheva <Anastasia.Hernandez-Koutoucheva@lstmed.ac.uk>",
+    "Kelly Bennett <Kelly.Bennett@lstmed.ac.uk>",
+    "Jon Brenas <Jon.Brenas@lstmed.ac.uk>",
     "Tristan Dennis <Tristan.Dennis@lstmed.ac.uk>",
 ]
 license = "MIT"

tests/anoph/test_dipclust.py

@@ -80,10 +80,11 @@ def case_af1_sim(af1_sim_fixture, af1_sim_api):
     return af1_sim_fixture, af1_sim_api
 
 
+@pytest.mark.parametrize("sample_query", [None, "sex_call == 'F'"])
 @pytest.mark.parametrize("distance_metric", ["cityblock", "euclidean"])
 @parametrize_with_cases("fixture,api", cases=".")
 def test_plot_diplotype_clustering(
-    fixture, api: AnophelesDipClustAnalysis, distance_metric
+    fixture, api: AnophelesDipClustAnalysis, distance_metric, sample_query
 ):
     # Set up test parameters.
     all_sample_sets = api.sample_sets()["sample_set"].to_list()
@@ -96,24 +97,32 @@ def test_plot_diplotype_clustering(
         "median",
         "ward",
     )
-    sample_queries = (None, "sex_call == 'F'")
     dipclust_params = dict(
         region=fixture.random_region_str(region_size=5000),
         sample_sets=[random.choice(all_sample_sets)],
         linkage_method=random.choice(linkage_methods),
         distance_metric=distance_metric,
-        sample_query=random.choice(sample_queries),
+        sample_query=sample_query,
         show=False,
     )
 
+    # Check if any samples match the query.
+    if sample_query is not None:
+        df_samples = api.sample_metadata().query(sample_query)
+        if len(df_samples) == 0:
+            with pytest.raises(ValueError):
+                api.plot_diplotype_clustering(**dipclust_params)
+            return
+
     # Run checks.
     api.plot_diplotype_clustering(**dipclust_params)
 
 
+@pytest.mark.parametrize("sample_query", [None, "sex_call == 'F'"])
 @pytest.mark.parametrize("distance_metric", ["cityblock", "euclidean"])
 @parametrize_with_cases("fixture,api", cases=".")
 def test_plot_diplotype_clustering_advanced(
-    fixture, api: AnophelesDipClustAnalysis, distance_metric
+    fixture, api: AnophelesDipClustAnalysis, distance_metric, sample_query
 ):
     # Set up test parameters.
     all_sample_sets = api.sample_sets()["sample_set"].to_list()
@@ -126,24 +135,32 @@ def test_plot_diplotype_clustering_advanced(
         "median",
         "ward",
     )
-    sample_queries = (None, "sex_call == 'F'")
     dipclust_params = dict(
         region=fixture.random_region_str(region_size=5000),
         sample_sets=[random.choice(all_sample_sets)],
         linkage_method=random.choice(linkage_methods),
         distance_metric=distance_metric,
-        sample_query=random.choice(sample_queries),
+        sample_query=sample_query,
         show=False,
     )
 
+    # Check if any samples match the query.
+    if sample_query is not None:
+        df_samples = api.sample_metadata().query(sample_query)
+        if len(df_samples) == 0:
+            with pytest.raises(ValueError):
+                api.plot_diplotype_clustering_advanced(**dipclust_params)
+            return
+
     # Run checks.
     api.plot_diplotype_clustering_advanced(**dipclust_params)
 
 
+@pytest.mark.parametrize("sample_query", [None, "sex_call == 'F'"])
 @pytest.mark.parametrize("n", [1, 2])
 @parametrize_with_cases("fixture,api", cases=".")
 def test_plot_diplotype_clustering_advanced_with_transcript(
-    fixture, api: AnophelesDipClustAnalysis, n
+    fixture, api: AnophelesDipClustAnalysis, n, sample_query
 ):
     # Set up test parameters.
     contig = fixture.random_contig()
@@ -158,24 +175,32 @@ def test_plot_diplotype_clustering_advanced_with_transcript(
         "median",
         "ward",
     )
-    sample_queries = (None, "sex_call == 'F'")
     dipclust_params = dict(
         region=contig,
         snp_transcript=transcripts,
         sample_sets=[random.choice(all_sample_sets)],
         linkage_method=random.choice(linkage_methods),
         distance_metric="cityblock",
-        sample_query=random.choice(sample_queries),
+        sample_query=sample_query,
         show=False,
     )
 
+    # Check if any samples match the query.
+    if sample_query is not None:
+        df_samples = api.sample_metadata().query(sample_query)
+        if len(df_samples) == 0:
+            with pytest.raises(ValueError):
+                api.plot_diplotype_clustering_advanced(**dipclust_params)
+            return
+
     # Run checks.
     api.plot_diplotype_clustering_advanced(**dipclust_params)
 
 
+@pytest.mark.parametrize("sample_query", [None, "sex_call == 'F'"])
 @parametrize_with_cases("fixture,api", cases=".")
 def test_plot_diplotype_clustering_advanced_with_cnv_region(
-    fixture, api: AnophelesDipClustAnalysis
+    fixture, api: AnophelesDipClustAnalysis, sample_query
 ):
     # Set up test parameters.
     region = fixture.random_region_str(region_size=5000)
@@ -189,16 +214,23 @@ def test_plot_diplotype_clustering_advanced_with_cnv_region(
         "median",
         "ward",
     )
-    sample_queries = (None, "sex_call == 'F'")
     dipclust_params = dict(
         region=region,
         cnv_region=region,
         sample_sets=[random.choice(all_sample_sets)],
         linkage_method=random.choice(linkage_methods),
         distance_metric="cityblock",
-        sample_query=random.choice(sample_queries),
+        sample_query=sample_query,
         show=False,
     )
 
+    # Check if any samples match the query.
+    if sample_query is not None:
+        df_samples = api.sample_metadata().query(sample_query)
+        if len(df_samples) == 0:
+            with pytest.raises(ValueError):
+                api.plot_diplotype_clustering_advanced(**dipclust_params)
+            return
+
     # Run checks.
     api.plot_diplotype_clustering_advanced(**dipclust_params)