Merge branch 'master' into fix/issue-484-pydantic-validate-call

Author: 31puneet

.gitignore

@@ -1,6 +1,7 @@
 .idea
 .vscode
 __pycache__
+.mypy_cache
 *.pyc
 dist
 .venv/

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)
+- [Windows setup guide](WINDOWS_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).
 

WINDOWS_SETUP.md

@@ -0,0 +1,90 @@
+# Windows Setup Guide
+
+To get setup for development on Windows, see
+[this video if you prefer VS Code](https://youtu.be/zddl3n1DCFM),
+or [this older video if you prefer PyCharm](https://youtu.be/QniQi-Hoo9A),
+and the instructions below.
+
+## 1. Fork and clone this repo
+```bash
+git clone https://github.com/[username]/malariagen-data-python.git
+cd malariagen-data-python
+```
+
+## 2. Install Python
+
+Download and install Python 3.10 from the official website:
+https://www.python.org/downloads/windows/
+
+During installation, check the box that says Add Python to PATH
+before clicking Install.
+
+Verify the installation worked:
+```bash
+python --version
+```
+
+## 3. Install pipx and poetry
+```bash
+python -m pip install --user pipx
+python -m pipx ensurepath
+pipx install poetry
+```
+
+After running ensurepath, close and reopen PowerShell before continuing.
+
+## 4. Create and activate development environment
+```bash
+poetry install
+poetry shell
+```
+
+## 5. Install pre-commit hooks
+```bash
+pipx install pre-commit
+pre-commit install
+```
+
+## 6. Add upstream remote and get latest code
+```bash
+git remote add upstream https://github.com/malariagen/malariagen-data-python
+git pull upstream master
+```
+
+Note: On Windows the default branch is called master, not main.
+
+## 7. Verify everything works
+```bash
+python -c "import malariagen_data; print('Setup successful!')"
+```
+
+## Common Issues on Windows
+
+**poetry not found after install**
+
+Close and reopen PowerShell, then try again.
+
+**git not recognized**
+
+Install Git from https://git-scm.com/download/win
+and restart PowerShell.
+
+**python not recognized**
+
+Reinstall Python and make sure to check
+Add Python to PATH during installation.
+
+**fatal: not a git repository**
+
+Make sure you are inside the malariagen-data-python
+folder before running any git commands.
+```bash
+cd malariagen-data-python
+```
+
+**error: pathspec main did not match**
+
+On Windows use master instead of main.
+```bash
+git checkout master
+```

malariagen_data/adar1.py

@@ -130,7 +130,6 @@ def __init__(
             tqdm_class=tqdm_class,
             taxon_colors=TAXON_COLORS,
             virtual_contigs=None,
-            gene_names=None,
             inversion_tag_path=None,
             unrestricted_use_only=unrestricted_use_only,
             surveillance_use_only=surveillance_use_only,

malariagen_data/adir1.py

@@ -130,7 +130,6 @@ def __init__(
             tqdm_class=tqdm_class,
             taxon_colors=TAXON_COLORS,
             virtual_contigs=None,
-            gene_names=None,
             inversion_tag_path=None,
             unrestricted_use_only=unrestricted_use_only,
             surveillance_use_only=surveillance_use_only,

malariagen_data/af1.py

@@ -132,7 +132,6 @@ def __init__(
             tqdm_class=tqdm_class,
             taxon_colors=TAXON_COLORS,
             virtual_contigs=None,
-            gene_names=None,
             inversion_tag_path=None,
             unrestricted_use_only=unrestricted_use_only,
             surveillance_use_only=surveillance_use_only,

malariagen_data/amin1.py

@@ -130,7 +130,6 @@ def __init__(
             tqdm_class=tqdm_class,
             taxon_colors=TAXON_COLORS,
             virtual_contigs=None,
-            gene_names=None,
             inversion_tag_path=None,
             unrestricted_use_only=unrestricted_use_only,
             surveillance_use_only=surveillance_use_only,

malariagen_data/anoph/aim_data.py

@@ -40,10 +40,24 @@ def __init__(
         # to the superclass constructor.
         super().__init__(**kwargs)
 
-        # Store possible values for the `aims` parameter.
-        # TODO Consider moving this to data resource configuration.
-        self._aim_ids = aim_ids
-        self._aim_palettes = aim_palettes
+        # Read AIM parameters from the JSON config, falling back to
+        # constructor args for backward compatibility.
+        config = self.config
+        _aim_ids = config.get("AIM_IDS", None)
+        if _aim_ids is not None:
+            self._aim_ids: Optional[aim_params.aim_ids] = tuple(_aim_ids)
+        else:
+            self._aim_ids = aim_ids
+
+        _aim_palettes = config.get("AIM_PALETTES", None)
+        if _aim_palettes is not None:
+            # Convert lists to tuples for each palette entry.
+            self._aim_palettes: Optional[aim_params.aim_palettes] = {
+                k: tuple(v)
+                for k, v in _aim_palettes.items()  # type: ignore
+            }
+        else:
+            self._aim_palettes = aim_palettes
 
         # Set up caches.
         self._cache_aim_variants: Dict[str, xr.Dataset] = dict()

malariagen_data/anoph/base_params.py

@@ -189,6 +189,14 @@ def _validate_sample_selection_params(
     "Random seed used for reproducible down-sampling.",
 ]
 
+gene: TypeAlias = Annotated[
+    str,
+    """
+    Gene identifier. Can be either a gene ID or gene name.
+    Gene names are matched case-insensitively.
+    """,
+]
+
 transcript: TypeAlias = Annotated[
     str,
     "Gene transcript identifier.",

malariagen_data/anoph/cnv_frq.py

@@ -90,7 +90,11 @@ def _gene_cnv(
         inline_array,
     ):
         # Sanity check.
-        assert isinstance(region, Region)
+        if not isinstance(region, Region):
+            raise TypeError(
+                f"Expected region to be a Region object, "
+                f"got {type(region).__name__}: {region!r}"
+            )
 
         # Access genes within the region of interest.
         df_genome_features = self.genome_features(region=region)
@@ -260,7 +264,11 @@ def _gene_cnv_frequencies(
         debug = self._log.debug
 
         debug("sanity check - this function is one region at a time")
-        assert isinstance(region, Region)
+        if not isinstance(region, Region):
+            raise TypeError(
+                f"Expected region to be a Region object, "
+                f"got {type(region).__name__}: {region!r}"
+            )
 
         debug("get gene copy number data")
         ds_cnv = self.gene_cnv(
@@ -504,7 +512,11 @@ def _gene_cnv_frequencies_advanced(
         debug = self._log.debug
 
         debug("sanity check - here we deal with one region only")
-        assert isinstance(region, Region)
+        if not isinstance(region, Region):
+            raise TypeError(
+                f"Expected region to be a Region object, "
+                f"got {type(region).__name__}: {region!r}"
+            )
 
         debug("access gene CNV calls")
         ds_cnv = self.gene_cnv(