Initialize from a NamedList& wrappers for combine and merge operati…

…ons (#118)

* Initialize from a `NamedList`
* Update tests and changelog

.github/workflows/pypi-publish.yml → .github/workflows/publish-pypi.yml

@@ -13,6 +13,7 @@ jobs:
 
     steps:
       - uses: actions/checkout@v4
+
       - name: Set up Python 3.11
         uses: actions/setup-python@v5
         with:
@@ -21,36 +22,31 @@ jobs:
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
-          pip install flake8 pytest tox
-
-      # - name: Lint with flake8
-      #   run: |
-      #     # stop the build if there are Python syntax errors or undefined names
-      #     flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
-      #     # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
-      #     # flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+          pip install tox
 
       - name: Test with tox
-        run: tox
+        run: |
+          tox
 
       - name: Build docs
-        run: tox -e docs
+        run: |
+          tox -e docs
 
-      - name: Add nojekyll file
-        run: touch ./docs/_build/html/.nojekyll
+      - run: touch ./docs/_build/html/.nojekyll
 
       - name: GH Pages Deployment
-        uses: JamesIves/github-pages-deploy-action@4.1.3
+        uses: JamesIves/github-pages-deploy-action@v4
         with:
           branch: gh-pages # The branch the action should deploy to.
           folder: ./docs/_build/html
           clean: true # Automatically remove deleted files from the deploy branch
 
       - name: Build Project and Publish
-        run: python -m tox -e clean,build
+        run: |
+          python -m tox -e clean,build
 
       - name: Publish package
-        uses: pypa/gh-action-pypi-publish@27b31702a0e7fc50959f5ad993c78deac1bdfc29
+        uses: pypa/gh-action-pypi-publish@v1.12.2
         with:
           user: __token__
           password: ${{ secrets.PYPI_PASSWORD }}

.github/workflows/run-tests.yml

@@ -0,0 +1,32 @@
+name: Run tests
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version: ["3.9", "3.10", "3.11", "3.12", "3.13"]
+
+    name: Python ${{ matrix.python-version }}
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: "pip"
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install tox
+
+      - name: Test with tox
+        run: |
+          tox

CHANGELOG.md

@@ -1,5 +1,11 @@
 # Changelog
 
+## Version 0.6.1
+
+- Implement wrapper methods within the `BiocFrame` class for merge and combine operations.
+- Initialize `BiocFrame` from a `NamedList`.
+- Renaming GitHub actions for consistency with other packages.
+
 ## Version 0.6.0
 
 - chore: Remove Python 3.8 (EOL)

README.md

@@ -12,7 +12,7 @@
 
 [![Project generated with PyScaffold](https://img.shields.io/badge/-PyScaffold-005CA0?logo=pyscaffold)](https://pyscaffold.org/)
 [![PyPI-Server](https://img.shields.io/pypi/v/BiocFrame.svg)](https://pypi.org/project/BiocFrame/)
-![Unit tests](https://github.com/BiocPy/BiocFrame/actions/workflows/pypi-test.yml/badge.svg)
+![Unit tests](https://github.com/BiocPy/BiocFrame/actions/workflows/run-tests.yml/badge.svg)
 
 # Bioconductor-like data frames
 

src/biocframe/BiocFrame.py

@@ -1,6 +1,6 @@
-from collections import OrderedDict
+from collections import OrderedDict, abc
 from copy import copy
-from typing import Any, Dict, List, Literal, Optional, Sequence, Tuple, Union
+from typing import Any, Dict, List, Literal, Mapping, Optional, Sequence, Tuple, Union
 from warnings import warn
 
 import biocutils as ut
@@ -122,7 +122,7 @@ class BiocFrame:
 
     def __init__(
         self,
-        data: Optional[Dict[str, Any]] = None,
+        data: Mapping = None,
         number_of_rows: Optional[int] = None,
         row_names: Optional[List] = None,
         column_names: Optional[List[str]] = None,
@@ -138,6 +138,10 @@ def __init__(
                 columns must have the same length. Defaults to an empty
                 dictionary.
 
+                Alternatively may provide a `Mapping` object, for example
+                a :py:class:`~biocutils.NamedList` that can be coerced into
+                a dictionary.
+
             number_of_rows:
                 Number of rows. If not specified, inferred from ``data``. This
                 needs to be provided if ``data`` is empty and ``row_names`` are
@@ -161,7 +165,18 @@ def __init__(
             validate:
                 Internal use only.
         """
-        self._data = {} if data is None else data
+        if data is None:
+            data = {}
+
+        if isinstance(data, ut.NamedList):
+            data = data.as_dict()
+            # making sure all column values are lists
+            for k, v in data.items():
+                if not isinstance(v, list):
+                    # if its a scalar, make a list else corce to list
+                    data[k] = list(v) if isinstance(v, abc.Sequence) else [v]
+
+        self._data = data
         if row_names is not None and not isinstance(row_names, ut.Names):
             row_names = ut.Names(row_names)
         self._row_names = row_names
@@ -1243,10 +1258,6 @@ def flatten(self, as_type: Literal["dict", "biocframe"] = "dict", delim: str = "
 
         return _data_copy
 
-    def combine(self, *other):
-        """Wrapper around :py:func:`~relaxed_combine_rows`, provided for back-compatibility only."""
-        return relaxed_combine_rows([self] + other)
-
     # TODO: very primitive implementation, needs very robust testing
     # TODO: implement in-place, view
     def __array_ufunc__(self, func, method, *inputs, **kwargs) -> "BiocFrame":
@@ -1274,6 +1285,40 @@ def __array_ufunc__(self, func, method, *inputs, **kwargs) -> "BiocFrame":
 
         return input
 
+    #############################
+    ######>> Combine Ops <<######
+    #############################
+
+    def combine(self, *other):
+        """Wrapper around :py:func:`~relaxed_combine_rows`, provided for back-compatibility only."""
+        return relaxed_combine_rows(self, *other)
+
+    def relaxed_combine_rows(self, *other):
+        """Wrapper around :py:func:`~relaxed_combine_rows`."""
+        return relaxed_combine_rows(self, *other)
+
+    def relaxed_combine_columns(self, *other):
+        """Wrapper around :py:func:`~relaxed_combine_columns`."""
+        return relaxed_combine_columns(self, *other)
+
+    def combine_rows(self, *other):
+        """Wrapper around :py:func:`~biocutils.combine_rows`."""
+        return _combine_rows_bframes(self, *other)
+
+    def combine_columns(self, *other):
+        """Wrapper around :py:func:`~biocutils.combine_columns`."""
+        return _combine_cols_bframes(self, *other)
+
+    def merge(
+        self,
+        *other: Sequence["BiocFrame"],
+        by: Union[None, str, Sequence] = None,
+        join: Literal["inner", "left", "right", "outer"] = "left",
+        rename_duplicate_columns: bool = False,
+    ):
+        """Wrapper around :py:func:`merge`."""
+        return merge([self] + list(other), by=by, join=join, rename_duplicate_columns=rename_duplicate_columns)
+
 
 ############################
 

tests/test_combine.py

@@ -30,6 +30,12 @@ def test_basic():
     assert merged.shape[0] == obj1.shape[0] + obj2.shape[0]
     assert merged.shape[1] == 2
 
+    merged2 = obj1.combine(obj2)
+
+    assert isinstance(merged2, BiocFrame)
+    assert merged2.shape[0] == obj1.shape[0] + obj2.shape[0]
+    assert merged2.shape[1] == 2
+
 
 def test_multiple():
     merged = combine(obj1, obj2, obj1)
@@ -38,6 +44,12 @@ def test_multiple():
     assert merged.shape[0] == 2 * obj1.shape[0] + obj2.shape[0]
     assert merged.shape[1] == 2
 
+    merged2 = obj1.combine(obj2, obj1)
+
+    assert isinstance(merged2, BiocFrame)
+    assert merged2.shape[0] == 2 * obj1.shape[0] + obj2.shape[0]
+    assert merged2.shape[1] == 2
+
 
 def test_empty():
     o1 = BiocFrame(number_of_rows=10)
@@ -49,6 +61,11 @@ def test_empty():
     assert merged.shape[0] == 15
     assert merged.shape[1] == 0
 
+    merged2 = o1.combine(o2)
+
+    assert isinstance(merged2, BiocFrame)
+    assert merged2.shape[0] == 15
+    assert merged2.shape[1] == 0
 
 def test_with_rownames():
     obj1.row_names = ["a", "b", "c", "d", "e"]
@@ -155,6 +172,29 @@ def test_relaxed_combine_rows():
         None,
     ]
 
+    merged2 = obj1.relaxed_combine_rows(obj2, obj3)
+
+    assert merged2.get_column_names().as_list() == ["column1", "column2", "column3"]
+    assert merged2.column("column1") == [1, 2, 3, -1, -2, -3, None, None, None]
+    assert (
+        merged2.column("column2").mask
+        == np.ma.array([False, False, False, True, True, True, False, False, False])
+    ).all()
+    assert (
+        merged2.column("column2").data == np.ma.array([4, 5, 6, 0, 0, 0, -4, -5, -6])
+    ).all()
+    assert merged2.column("column3") == [
+        None,
+        None,
+        None,
+        "A",
+        "B",
+        "C",
+        None,
+        None,
+        None,
+    ]
+
 
 def test_combine_columns_basic():
     obj1 = BiocFrame(
@@ -185,6 +225,12 @@ def test_combine_columns_basic():
         combine_columns(obj1, obj2[1:4, :])
     assert str(ex.value).find("same number of rows") >= 0
 
+    merged2= obj1.combine_columns(obj2)
+    assert isinstance(merged2, BiocFrame)
+    assert merged2.get_column_names().as_list() == ["odd", "even", "foo", "bar"]
+    assert merged2.get_column("odd") == [1, 3, 5, 7, 9]
+    assert merged2.get_column("bar") == [0, 22, 44, 66, 88]
+
 
 def test_combine_columns_with_column_data():
     obj1 = BiocFrame(

tests/test_initialize.py

@@ -3,7 +3,7 @@
 
 import biocframe
 from biocframe import BiocFrame
-from biocutils import Names
+from biocutils import Names, NamedList
 
 __author__ = "jkanche"
 __copyright__ = "jkanche"
@@ -164,3 +164,12 @@ def test_with_add_deletions():
     del obj1["new_column"]
     assert obj1.shape == (3, 2)
     assert len(obj1.column_data) == 2
+
+def test_NamedList():
+    x = NamedList([1,2,3,4], names=["A", "B", "C", "D"])
+
+    frame = BiocFrame(x)
+    assert frame is not None
+    assert isinstance(frame, BiocFrame)
+    assert frame.shape == (1, 4)
+    assert list(frame.get_column_names()) == ["A", "B", "C", "D"]

tests/test_merge.py

@@ -170,3 +170,34 @@ def test_merge_BiocFrame_column_data():
     combined = merge([obj1, obj2], by="A", join="left")
     comcol = combined.get_column_data()
     assert comcol.column("foo") == [True, False, False]
+
+def test_merge_class_method():
+    # A simple case.
+    obj1 = BiocFrame({"B": [3, 4, 5, 6]}, row_names=[1, 2, 3, 4])
+    obj2 = BiocFrame(
+        {"C": ["A", "B"]},
+        row_names=[1, 3],
+    )
+
+    combined = merge([obj1, obj2], by=None, join="left")
+    assert combined.get_column_data() is None
+
+    obj1.set_column_data(BiocFrame({"foo": [True]}), in_place=True)
+    combined = merge([obj1, obj2], by=None, join="left")
+    comcol = combined.get_column_data()
+    assert combined.get_column_names().as_list() == ["B", "C"]
+    assert comcol.column("foo") == [True, None]
+
+    combined2 = obj1.merge(obj2, by=None, join="left")
+    comcol2 = combined2.get_column_data()
+    assert combined2.get_column_names().as_list() == ["B", "C"]
+    assert comcol2.column("foo") == [True, None]
+
+    obj2.set_column_data(BiocFrame({"foo": [False]}), in_place=True)
+    combined = merge([obj1, obj2], by=None, join="left")
+    comcol = combined.get_column_data()
+    assert comcol.column("foo") == [True, False]
+
+    combined2 = obj1.merge(obj2, by=None, join="left")
+    comcol2 = combined2.get_column_data()
+    assert comcol.column("foo") == [True, False]