Tabmat v4 alpha

CHANGELOG.rst

@@ -10,6 +10,13 @@ Changelog
 Unreleased
 ----------
 
+**New features:**
+
+- Added column name and term name metadata to ``MatrixBase`` objects. These are automatically populated when initializing a ``MatrixBase`` from a ``pandas.DataFrame``. In addition, they can be accessed and modified via the ``column_names`` and ``term_names`` properties.
+- Added a formula interface for creating tabmat matrices from pandas data frames. See :func:`tabmat.from_formula` for details.
+- Added support for missing values in ``CategoricalMatrix`` by either creating a separate category for them or treating them as all-zero rows.
+- Added support for handling missing categorical values in pandas data frames.
+
 **Bug fix:**
 
 - Added cython compiler directive legacy_implicit_noexcept = True to fix performance regression with cython 3.

conda.recipe/meta.yaml

@@ -38,6 +38,7 @@ requirements:
     - {{ pin_compatible('numpy') }}
     - pandas
     - scipy
+    - formulaic>=0.6
 
 test:
   requires:

environment-win.yml

@@ -5,6 +5,7 @@ channels:
 dependencies:
   - libblas>=0=*mkl
   - pandas
+  - formulaic>=0.6
 
   # development tools
   - click

environment.yml

@@ -4,6 +4,7 @@ channels:
   - nodefaults
 dependencies:
   - pandas
+  - formulaic>=0.6
 
   # development tools
   - click

pyproject.toml

@@ -33,6 +33,7 @@ python_version = '3.9'
 
 [tool.cibuildwheel]
 skip = [
+  "cp36-*",
   "*-win32",
   "*-manylinux_i686",
   "pp*", 

setup.py

@@ -54,7 +54,7 @@
 print(f"Debug Build: {debug_build}")
 
 if sys.platform == "win32":
-    allocator_libs = []
+    allocator_libs = []  # type: ignore
     extra_compile_args = ["/openmp", "/O2"]
     extra_link_args = ["/openmp"]
     # make sure we can find xsimd headers
@@ -157,7 +157,7 @@
     ],
     package_dir={"": "src"},
     packages=find_packages(where="src"),
-    install_requires=["numpy", "pandas", "scipy"],
+    install_requires=["numpy", "pandas", "scipy", "formulaic>=0.6"],
     python_requires=">=3.9",
     ext_modules=cythonize(
         ext_modules,

src/tabmat/__init__.py

@@ -1,11 +1,11 @@
 import importlib.metadata
 
 from .categorical_matrix import CategoricalMatrix
-from .constructor import from_csc, from_pandas
+from .constructor import from_csc, from_formula, from_pandas
 from .dense_matrix import DenseMatrix
 from .matrix_base import MatrixBase
 from .sparse_matrix import SparseMatrix
-from .split_matrix import SplitMatrix
+from .split_matrix import SplitMatrix, as_tabmat, hstack
 from .standardized_mat import StandardizedMatrix
 
 try:
@@ -21,5 +21,8 @@
     "SplitMatrix",
     "CategoricalMatrix",
     "from_csc",
+    "from_formula",
     "from_pandas",
+    "as_tabmat",
+    "hstack",
 ]