Merge branch 'master' into fix/empty-cohort-queries-guard

Author: jonbrenas

.gitignore

@@ -3,6 +3,7 @@
 __pycache__
 *.pyc
 dist
+.venv/
 .coverage
 coverage.xml
 .ipynb_checkpoints/

README.md

@@ -49,6 +49,7 @@ To get setup for development, see [this video if you prefer VS Code](https://you
 For detailed setup instructions, see:
 - [Linux setup guide](LINUX_SETUP.md)
 - [macOS setup guide](MACOS_SETUP.md)
+- [Google Colab (TPU) setup guide](docs/source/colab_tpu_runtime.rst)
 Detailed instructions can be found in the [Contributors guide](https://github.com/malariagen/malariagen-data-python/blob/master/CONTRIBUTING.md).
 
 ## AI use policy and guidelines

docs/source/colab_tpu_runtime.rst

@@ -0,0 +1,111 @@
+Google Colab Installation Guide
+===============================
+Prerequisites
+-------------
+
+Before installing the package, configure the runtime environment
+correctly:
+
+1. Open a new notebook in Google Colab.
+2. Navigate to ``Runtime → Change runtime type``.
+3. Set the runtime configuration as follows:
+
+   - **Runtime type:** Python 3
+   - **Hardware accelerator:** TPU
+   - **TPU type:** v2-8
+
+4. Click **Save** to apply the configuration.
+
+Using the recommended TPU configuration ensures compatibility with
+workflows that may require TPU-based computation.
+
+
+Installation Procedure
+----------------------
+
+In a new notebook cell, install the package:
+
+.. code-block:: bash
+
+   !pip install malariagen_data
+
+After installation completes, verify that the package is available:
+
+.. code-block:: python
+
+   import malariagen_data
+
+If the import executes without errors, the installation was successful.
+
+If dependency-related warnings or conflicts occur, follow one of the
+resolution options described below.
+
+
+Resolution Options
+------------------
+
+Resolution Option 1: Uninstall Panel
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+If your notebook does not require ``panel``, uninstall it before
+installing ``malariagen_data``.
+
+.. code-block:: bash
+
+   !pip uninstall -y panel
+   !pip install malariagen_data
+
+Verify installation:
+
+.. code-block:: python
+
+   import malariagen_data
+
+
+Resolution Option 2: Install Compatible Panel Version
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+If your workflow depends on ``panel``, install a compatible version:
+
+.. code-block:: bash
+
+   !pip install panel==1.7.0
+   !pip install malariagen_data
+
+Restart the runtime:
+
+``Runtime → Restart runtime``
+
+Then verify:
+
+.. code-block:: python
+
+   import malariagen_data
+
+
+Resolution Option 3: Install Required Blinker Version
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+If a ``blinker`` version conflict occurs:
+
+.. code-block:: bash
+
+   !pip install blinker==1.9.0 --ignore-installed
+   !pip install malariagen_data
+
+Restart the runtime and verify:
+
+.. code-block:: python
+
+   import malariagen_data
+
+
+Final Verification
+------------------
+
+After completing any of the procedures above:
+
+- Ensure that ``malariagen_data`` installs without dependency errors.
+- Confirm that ``import malariagen_data`` runs successfully.
+- Restart the runtime whenever core dependencies are modified.
+- Avoid mixing incompatible package versions within the same Colab session.

malariagen_data/anoph/aim_data.py

@@ -341,6 +341,4 @@ def plot_aim_heatmap(
 
         if show:  # pragma: no cover
             fig.show(renderer=renderer)
-            return None
-        else:
-            return fig
+        return fig

malariagen_data/anoph/base.py

@@ -607,9 +607,9 @@ def _read_sample_sets_manifest(self, *, single_release: str):
             # Get today's date in ISO format
             today_date_iso = date.today().isoformat()
             # Add an "unrestricted_use" column, set to True if terms-of-use expiry date <= today's date.
-            df["unrestricted_use"] = df[terms_of_use_expiry_date_column].apply(
-                lambda d: True if pd.isna(d) else (d <= today_date_iso)
-            )
+            # Vectorized operation: True if NaN, else (d <= today_date_iso)
+            s = df[terms_of_use_expiry_date_column]
+            df["unrestricted_use"] = s.isna() | (s <= today_date_iso)
             # Make the "unrestricted_use" column a nullable boolean, to allow missing data.
             df["unrestricted_use"] = df["unrestricted_use"].astype(pd.BooleanDtype())
 

malariagen_data/anoph/cnv_data.py

@@ -810,9 +810,7 @@ def plot_cnv_hmm_coverage_track(
 
         if show:
             bkplt.show(fig)
-            return None
-        else:
-            return fig
+        return fig
 
     @_check_types
     @doc(
@@ -884,9 +882,7 @@ def plot_cnv_hmm_coverage(
 
         if show:
             bkplt.show(fig)
-            return None
-        else:
-            return fig
+        return fig
 
     @_check_types
     @doc(
@@ -1028,9 +1024,7 @@ def plot_cnv_hmm_heatmap_track(
 
         if show:
             bkplt.show(fig)
-            return None
-        else:
-            return fig
+        return fig
 
     @_check_types
     @doc(
@@ -1100,6 +1094,4 @@ def plot_cnv_hmm_heatmap(
 
         if show:
             bkplt.show(fig)
-            return None
-        else:
-            return fig
+        return fig

malariagen_data/anoph/dipclust.py

@@ -1,3 +1,4 @@
+import warnings
 from typing import Optional, Tuple
 
 import allel  # type: ignore
@@ -188,13 +189,11 @@ def plot_diplotype_clustering(
 
         if show:  # pragma: no cover
             fig.show(renderer=renderer)
-            return None
-        else:
-            return {
-                "figure": fig,
-                "dendro_sample_id_order": np.asarray(leaf_data["sample_id"].to_list()),
-                "n_snps": n_snps_used,
-            }
+        return {
+            "figure": fig,
+            "dendro_sample_id_order": np.asarray(leaf_data["sample_id"].to_list()),
+            "n_snps": n_snps_used,
+        }
 
     def diplotype_pairwise_distances(
         self,
@@ -540,8 +539,9 @@ def _insert_dipclust_snp_trace(
             figures.append(snp_trace)
             subplot_heights.append(snp_row_height * n_snps_transcript)
         else:
-            print(
-                f"No SNPs were found below {snp_filter_min_maf} allele frequency. Omitting SNP genotype plot."
+            warnings.warn(
+                f"No SNPs were found below {snp_filter_min_maf} allele frequency. Omitting SNP genotype plot.",
+                stacklevel=2,
             )
         return figures, subplot_heights, n_snps_transcript
 
@@ -607,8 +607,9 @@ def plot_diplotype_clustering_advanced(
             cnv_colorscale = cnv_params.colorscale_default
         if cohort_size and snp_transcript:
             cohort_size = None
-            print(
-                "Cohort size is not supported with amino acid heatmap. Overriding cohort size to None."
+            warnings.warn(
+                "Cohort size is not supported with amino acid heatmap. Overriding cohort size to None.",
+                stacklevel=2,
             )
 
         res = self.plot_diplotype_clustering(
@@ -797,6 +798,4 @@ def plot_diplotype_clustering_advanced(
 
         if show:
             fig.show(renderer=renderer)
-            return None
-        else:
-            return fig
+        return fig

malariagen_data/anoph/distance.py

@@ -614,6 +614,4 @@ def plot_njt(
 
         if show:  # pragma: no cover
             fig.show(renderer=renderer)
-            return None
-        else:
-            return fig
+        return fig