Merge branch 'master' into GH1223-seed-random

Author: jonbrenas

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/util.py

@@ -570,6 +570,9 @@ def __eq__(self, other):
             and (self.end == other.end)
         )
 
+    def __repr__(self):
+        return f"Region({self._contig!r}, {self._start!r}, {self._end!r})"
+
     def __str__(self):
         out = self._contig
         if self._start is not None or self._end is not None:
@@ -927,7 +930,20 @@ def _jitter(a, fraction, random_state=np.random):
 
 
 class CacheMiss(Exception):
-    pass
+    """Raised when a requested item is not present in the cache."""
+
+    def __init__(self, key=None):
+        self.key = key
+        if key is not None:
+            message = f"Cache miss for key: {key!r}"
+        else:
+            message = "Cache miss: requested item not found in cache."
+        super().__init__(message)
+
+    def __repr__(self):
+        if self.key is not None:
+            return f"CacheMiss({self.key!r})"
+        return "CacheMiss()"
 
 
 class LoggingHelper:
@@ -1531,12 +1547,10 @@ def _apply_allele_mapping(x, mapping, max_allele):
 
 def _dask_apply_allele_mapping(v, mapping, max_allele):
     if not isinstance(v, da.Array):
-        raise TypeError(
-            f"Expected v to be a dask.array.Array, " f"got {type(v).__name__}"
-        )
+        raise TypeError(f"Expected v to be a dask.array.Array, got {type(v).__name__}")
     if not isinstance(mapping, np.ndarray):
         raise TypeError(
-            f"Expected mapping to be a numpy.ndarray, " f"got {type(mapping).__name__}"
+            f"Expected mapping to be a numpy.ndarray, got {type(mapping).__name__}"
         )
     assert v.ndim == 2
     assert mapping.ndim == 2
@@ -1558,12 +1572,10 @@ def _genotype_array_map_alleles(gt, mapping):
     # N.B., scikit-allel does not handle empty blocks well, so we
     # include some extra logic to handle that better.
     if not isinstance(gt, np.ndarray):
-        raise TypeError(
-            f"Expected gt to be a numpy.ndarray, " f"got {type(gt).__name__}"
-        )
+        raise TypeError(f"Expected gt to be a numpy.ndarray, got {type(gt).__name__}")
     if not isinstance(mapping, np.ndarray):
         raise TypeError(
-            f"Expected mapping to be a numpy.ndarray, " f"got {type(mapping).__name__}"
+            f"Expected mapping to be a numpy.ndarray, got {type(mapping).__name__}"
         )
     assert gt.ndim == 3
     assert mapping.ndim == 3
@@ -1585,11 +1597,11 @@ def _genotype_array_map_alleles(gt, mapping):
 def _dask_genotype_array_map_alleles(gt, mapping):
     if not isinstance(gt, da.Array):
         raise TypeError(
-            f"Expected gt to be a dask.array.Array, " f"got {type(gt).__name__}"
+            f"Expected gt to be a dask.array.Array, got {type(gt).__name__}"
         )
     if not isinstance(mapping, np.ndarray):
         raise TypeError(
-            f"Expected mapping to be a numpy.ndarray, " f"got {type(mapping).__name__}"
+            f"Expected mapping to be a numpy.ndarray, got {type(mapping).__name__}"
         )
     assert gt.ndim == 3
     assert mapping.ndim == 2

tests/conftest.py

@@ -1,9 +1,7 @@
-import random
 import numpy as np
 import pytest
 
 
 @pytest.fixture(autouse=True, scope="session")
 def seed_random():
-    random.seed(42)
     np.random.seed(42)

tests/test_util.py

@@ -0,0 +1,63 @@
+"""Tests for Region.__repr__ and CacheMiss.__repr__ / default message."""
+
+import pytest
+
+from malariagen_data.util import CacheMiss, Region
+
+
+# ---------------------------------------------------------------------------
+# Region
+# ---------------------------------------------------------------------------
+
+
+def test_region_repr_contig_only():
+    r = Region("2L")
+    assert repr(r) == "Region('2L', None, None)"
+    assert str(r) == "2L"
+
+
+def test_region_repr_with_coords():
+    r = Region("2L", 100_000, 200_000)
+    assert repr(r) == "Region('2L', 100000, 200000)"
+    assert str(r) == "2L:100,000-200,000"
+
+
+def test_region_repr_in_list():
+    regions = [Region("2L", 10, 20), Region("3R", 30, 40)]
+    assert repr(regions) == "[Region('2L', 10, 20), Region('3R', 30, 40)]"
+
+
+def test_region_repr_start_only():
+    r = Region("X", start=500, end=None)
+    assert repr(r) == "Region('X', 500, None)"
+    assert str(r) == "X:500-"
+
+
+# ---------------------------------------------------------------------------
+# CacheMiss
+# ---------------------------------------------------------------------------
+
+
+def test_cache_miss_no_key():
+    cm = CacheMiss()
+    assert repr(cm) == "CacheMiss()"
+    assert "Cache miss" in str(cm)
+
+
+def test_cache_miss_string_key():
+    cm = CacheMiss("my_key")
+    assert repr(cm) == "CacheMiss('my_key')"
+    assert "my_key" in str(cm)
+
+
+def test_cache_miss_tuple_key():
+    cm = CacheMiss(("contig", 100))
+    assert repr(cm) == "CacheMiss(('contig', 100))"
+    assert "('contig', 100)" in str(cm)
+
+
+def test_cache_miss_is_exception():
+    with pytest.raises(CacheMiss) as exc_info:
+        raise CacheMiss("lookup_key")
+    assert "lookup_key" in str(exc_info.value)
+    assert repr(exc_info.value) == "CacheMiss('lookup_key')"