fix: restore files incorrectly modified during master merge conflict resolution

Author: suhr25

malariagen_data/anoph/aim_data.py

@@ -254,14 +254,24 @@ def plot_aim_heatmap(
             gn = np.take(gn, ix_sorted, axis=1)
             samples = np.take(samples, ix_sorted, axis=0)
 
+        species = aims.split("_vs_")
+
         # Set up colors for genotypes
         if palette is None:
-            assert self._aim_palettes is not None
+            if self._aim_palettes is None:
+                raise RuntimeError(
+                    "AIM palettes are not available for this data resource. "
+                    "Please provide the 'palette' parameter explicitly (4 colors)."
+                )
             palette = self._aim_palettes[aims]
-            assert len(palette) == 4
+            if len(palette) != 4:
+                raise RuntimeError(
+                    "Expected AIM palette to have 4 colors "
+                    f"(missing, {species[0]}/{species[0]}, {species[0]}/{species[1]}, {species[1]}/{species[1]}), "
+                    f"got {len(palette)}"
+                )
             # Expect 4 colors, in the order:
             # missing, hom taxon 1, het, hom taxon 2
-        species = aims.split("_vs_")
 
         # Create subplots.
         fig = go_make_subplots(

malariagen_data/anoph/cnv_frq.py

@@ -597,7 +597,11 @@ def _gene_cnv_frequencies_advanced(
             if nobs_mode == "called":
                 nobs[:, cohort_index] = np.repeat(cohort_n_called, 2)
             else:
-                assert nobs_mode == "fixed"
+                if nobs_mode != "fixed":
+                    raise RuntimeError(
+                        f"Internal error: expected nobs_mode='fixed', got {nobs_mode!r}. "
+                        "This should not happen; please open a GitHub issue."
+                    )
                 nobs[:, cohort_index] = cohort.size
 
         debug("compute frequency")

malariagen_data/anoph/frq_base.py

@@ -417,14 +417,6 @@ def plot_frequencies_heatmap(
                 `aa_allele_frequencies_advanced()` or
                 `gene_cnv_frequencies_advanced()`.
             """,
-            taxa="""
-                Taxon or list of taxa to include in the plot. If None,
-                all taxa are shown.
-            """,
-            areas="""
-                Area or list of areas to include in the plot. If None,
-                all areas are shown.
-            """,
             kwargs="Passed through to `px.line()`.",
         ),
         returns="""

malariagen_data/anoph/genome_features.py

@@ -110,7 +110,11 @@ def _genome_features_for_contig(self, *, contig: str, attributes: Tuple[str, ...
 
         # Handle normal contigs in the reference genome.
         else:
-            assert contig in self.contigs
+            if contig not in self.contigs:
+                raise ValueError(
+                    f"Contig {contig!r} not found. "
+                    f"Available contigs: {self.contigs}"
+                )
             df = self._genome_features(attributes=attributes)
 
             # Apply contig query.
@@ -561,7 +565,8 @@ def plot_genes(
 
             # Increase the figure height by a certain factor, to accommodate labels.
             height_increase_factor = 1.3
-            assert fig.height is not None
+            if fig.height is None:
+                raise RuntimeError("Figure height is unexpectedly None")
             fig.height = int(fig.height * height_increase_factor)
 
             # Get the original y_range.

malariagen_data/anoph/genome_sequence.py

@@ -86,7 +86,11 @@ def _genome_sequence_for_contig(self, *, contig, inline_array, chunks):
 
         # Handle normal contigs in the reference genome.
         else:
-            assert contig in self.contigs
+            if contig not in self.contigs:
+                raise ValueError(
+                    f"Contig {contig!r} not found. "
+                    f"Available contigs: {self.contigs}"
+                )
             root = self.open_genome()
             z = root[contig]
             d = _da_from_zarr(z, inline_array=inline_array, chunks=chunks)

malariagen_data/anoph/h1x.py

@@ -403,8 +403,17 @@ def _moving_h1x(ha, hb, size, start=0, stop=None, step=None):
         H1X values (sum of squares of joint haplotype frequencies).
     """
 
-    assert ha.ndim == hb.ndim == 2
-    assert ha.shape[0] == hb.shape[0]
+    if ha.ndim != 2 or hb.ndim != 2:
+        raise ValueError(
+            "Expected both haplotype arrays to be 2-dimensional "
+            "(n_variants, n_haplotypes), "
+            f"got ndim=({ha.ndim}, {hb.ndim})"
+        )
+    if ha.shape[0] != hb.shape[0]:
+        raise ValueError(
+            "Expected both haplotype arrays to have the same number of variants "
+            f"(axis 0), got ({ha.shape[0]}, {hb.shape[0]})"
+        )
 
     # Construct moving windows.
     windows = allel.index_windows(ha, size, start, stop, step)

malariagen_data/anoph/hap_data.py

@@ -58,7 +58,11 @@ def phasing_analysis_ids(self) -> Tuple[str, ...]:
     def _prep_phasing_analysis_param(self, *, analysis: hap_params.analysis) -> str:
         if analysis == base_params.DEFAULT:
             # Use whatever is the default phasing analysis for this data resource.
-            assert self._default_phasing_analysis is not None
+            if self._default_phasing_analysis is None:
+                raise RuntimeError(
+                    "No default phasing analysis configured. "
+                    "Please specify the 'analysis' parameter explicitly."
+                )
             return self._default_phasing_analysis
         elif analysis in self.phasing_analysis_ids:
             return analysis
@@ -118,7 +122,11 @@ def _haplotype_sites_for_contig(
 
         # Handle contig in the reference genome.
         else:
-            assert contig in self.contigs
+            if contig not in self.contigs:
+                raise ValueError(
+                    f"Contig {contig!r} not found. "
+                    f"Available contigs: {self.contigs}"
+                )
             root = self.open_haplotype_sites(analysis=analysis)
             z = root[f"{contig}/variants/{field}"]
             ret = _da_from_zarr(z, inline_array=inline_array, chunks=chunks)
@@ -251,7 +259,11 @@ def _haplotypes_for_contig(
 
         # Handle contig in the reference genome.
         else:
-            assert contig in self.contigs
+            if contig not in self.contigs:
+                raise ValueError(
+                    f"Contig {contig!r} not found. "
+                    f"Available contigs: {self.contigs}"
+                )
 
             # Open haplotypes zarr.
             root = self.open_haplotypes(sample_set=sample_set, analysis=analysis)

malariagen_data/anoph/hap_frq.py

@@ -100,7 +100,11 @@ def haplotypes_frequencies(
             hap_dict = {k: 0 for k in f_all.keys()}
 
             n_samples = np.count_nonzero(loc_coh)
-            assert n_samples >= min_cohort_size
+            if n_samples < min_cohort_size:
+                raise ValueError(
+                    f"Not enough samples ({n_samples}) for minimum "
+                    f"cohort size ({min_cohort_size})"
+                )
             gt_coh = gt.compress(loc_coh, axis=1)
             gt_hap = gt_coh.to_haplotypes()
             f, _, _ = _haplotype_frequencies(gt_hap)
@@ -224,7 +228,11 @@ def haplotypes_frequencies_advanced(
             hap_freq = {k: 0 for k in f_all.keys()}
             hap_count = {k: 0 for k in f_all.keys()}
             hap_nob = {k: 2 * n_samples for k in f_all.keys()}
-            assert n_samples >= min_cohort_size
+            if n_samples < min_cohort_size:
+                raise ValueError(
+                    f"Not enough samples ({n_samples}) for minimum "
+                    f"cohort size ({min_cohort_size})"
+                )
             sample_indices = group_samples_by_cohort.indices[cohort_key]
             gt_coh = gt.take(sample_indices, axis=1)
             gt_hap = gt_coh.to_haplotypes()

malariagen_data/anoph/sample_metadata.py

@@ -594,8 +594,16 @@ def _aim_analysis(self):
     def _parse_aim_metadata(
         self, sample_set: str, data: Union[bytes, Exception]
     ) -> pd.DataFrame:
-        assert self._aim_metadata_columns is not None
-        assert self._aim_metadata_dtype is not None
+        if self._aim_metadata_columns is None:
+            raise RuntimeError(
+                "Internal error: AIM metadata columns are not configured. "
+                "This should not happen; please open a GitHub issue."
+            )
+        if self._aim_metadata_dtype is None:
+            raise RuntimeError(
+                "Internal error: AIM metadata dtypes are not configured. "
+                "This should not happen; please open a GitHub issue."
+            )
         if isinstance(data, bytes):
             # Parse CSV data but don't apply the dtype yet.
             df = pd.read_csv(io.BytesIO(data), na_values="")
@@ -971,6 +979,8 @@ def plot_samples_interactive_map(
             fill_value=0,
         )
 
+        taxa = df_pivot.columns.dropna().sort_values().unique()
+
         # Append aggregations to pivot.
         df_location_aggs = df_samples.groupby(location_composite_key).agg(
             {
@@ -1015,7 +1025,6 @@ def plot_samples_interactive_map(
         samples_map.layout.width = width
 
         # Add markers.
-        count_factors = df_samples[count_by].dropna().sort_values().unique()
         for _, row in df_pivot.reset_index().iterrows():
             title = (
                 f"Location: {row.location} ({row.latitude:.3f}, {row.longitude:.3f})"
@@ -1028,13 +1037,13 @@ def plot_samples_interactive_map(
             title += f"\nContributors: {row.contributor}"
             title += "\nNo. specimens: "
             all_n = 0
-            for factor in count_factors:
+            for taxon in taxa:
                 # Get the number of samples in this taxon
-                n = row[factor]
+                n = int(row[taxon])
                 # Count the number of samples in all taxa
                 all_n += n
                 if n > 0:
-                    title += f"{n} {factor}; "
+                    title += f"{n} {taxon}; "
             # Only show a marker when there are enough samples
             if all_n >= min_samples:
                 marker = ipyleaflet.Marker(