tabmat 4.1.5__cp310-cp310-win_amd64.whl → 4.2.1__cp310-cp310-win_amd64.whl

tabmat/benchmark/generate_matrices.py

@@ -13,7 +13,7 @@ def make_dense_matrices(n_rows: int, n_cols: int) -> dict:
     dense_matrices = {"numpy_C": np.random.random((n_rows, n_cols))}
     dense_matrices["numpy_F"] = dense_matrices["numpy_C"].copy(order="F")
     assert dense_matrices["numpy_F"].flags["F_CONTIGUOUS"]
-    dense_matrices["tabmat"] = tm.DenseMatrix(dense_matrices["numpy_C"])
+    dense_matrices["tabmat"] = tm.DenseMatrix(dense_matrices["numpy_C"])  # type: ignore
     return dense_matrices
 
 

tabmat/categorical_matrix.py

@@ -240,7 +240,13 @@ def _extract_codes_and_categories_pandas(cat_vec) -> tuple[np.ndarray, np.ndarra
 
 
 def _extract_codes_and_categories_polars(cat_vec) -> tuple[np.ndarray, np.ndarray]:
-    if not isinstance(cat_vec.dtype, (pl.Categorical, pl.Enum)):
+    dtype = cat_vec.dtype
+    if isinstance(dtype, pl.Enum):
+        categories = cat_vec.cat.get_categories().to_numpy()
+        indices = cat_vec.to_physical().fill_null(-1).to_numpy()
+        return indices, categories
+
+    if not isinstance(cat_vec.dtype, pl.Categorical):
         cat_vec = cat_vec.cast(pl.Categorical)
     # as of polars 1.32, `get_categories()` won't yield a useful result as
     # this is "not per column" anymore.
@@ -300,7 +306,7 @@ def _row_col_indexing(
     is_col_indexed = not (cols is None or len(cols) == arr.shape[1])
 
     if is_row_indexed and is_col_indexed:
-        return arr[np.ix_(rows, cols)]
+        return arr[np.ix_(rows, cols)]  # type: ignore
     elif is_row_indexed:
         return arr[rows]
     elif is_col_indexed:
@@ -691,7 +697,7 @@ class CategoricalMatrix(MatrixBase):
             )
 
         # TODO: data should be uint8
-        data = np.ones(self.shape[0], dtype=int)
+        data: np.ndarray = np.ones(self.shape[0], dtype=int)
         return sps.csr_matrix(
             (data, self.indices, np.arange(self.shape[0] + 1, dtype=int)),
             shape=self.shape,

tabmat/constructor.py

@@ -396,7 +396,7 @@ def from_formula(
     )
     result = materializer.get_model_matrix(spec)
 
-    term_names = np.zeros(len(result.term_names), dtype="object")
+    term_names: np.ndarray = np.zeros(len(result.term_names), dtype="object")
     for term, indices in result.model_spec.term_indices.items():
         term_names[indices] = str(term)
     result.term_names = term_names.tolist()

tabmat/formula.py

@@ -5,19 +5,21 @@ from collections import OrderedDict
 from collections.abc import Iterable
 from typing import Any, Optional, Union
 
+import narwhals.stable.v2 as nw
 import numpy as np
 import numpy.typing
 import pandas as pd
 from formulaic import ModelMatrix, ModelSpec
 from formulaic.errors import FactorEncodingError
 from formulaic.materializers import FormulaMaterializer
-from formulaic.materializers.types import FactorValues, NAAction, ScopedTerm
+from formulaic.materializers.types import FactorValues, ScopedTerm
 from formulaic.parser.types import Term
 from formulaic.transforms import stateful_transform
+from formulaic.utils.null_handling import drop_rows as drop_nulls
 from interface_meta import override
 from scipy import sparse as sps
 
-from .categorical_matrix import CategoricalMatrix
+from .categorical_matrix import CategoricalMatrix, _extract_codes_and_categories
 from .constructor_util import _split_sparse_and_dense_parts
 from .dense_matrix import DenseMatrix
 from .matrix_base import MatrixBase
@@ -53,34 +55,24 @@ class TabmatMaterializer(FormulaMaterializer):
         self.cat_missing_method = self.params.get("cat_missing_method", "fail")
         self.cat_missing_name = self.params.get("cat_missing_name", "(MISSING)")
 
+        # Always convert input to narwhals DataFrame
+        self.__narwhals_data = nw.from_native(self.data, eager_only=True)
+        self.__data_context = self.__narwhals_data.to_dict()
+
         # We can override formulaic's C() function here
         self.context["C"] = _C
 
-    @override
-    def _is_categorical(self, values):
-        if isinstance(values, (pd.Series, pd.Categorical)):
-            return values.dtype == object or isinstance(
-                values.dtype, (pd.CategoricalDtype, pd.StringDtype)
-            )
-        return super()._is_categorical(values)
+    @override  # type: ignore
+    @property
+    def data_context(self):
+        return self.__data_context
 
     @override
-    def _check_for_nulls(self, name, values, na_action, drop_rows):
-        if na_action is NAAction.IGNORE:
-            return
-
-        if na_action is NAAction.RAISE:
-            if isinstance(values, pd.Series) and values.isnull().values.any():
-                raise ValueError(f"`{name}` contains null values after evaluation.")
-
-        elif na_action is NAAction.DROP:
-            if isinstance(values, pd.Series):
-                drop_rows.update(np.flatnonzero(values.isnull().values))
-
-        else:
-            raise ValueError(
-                f"Do not know how to interpret `na_action` = {repr(na_action)}."
-            )
+    def _is_categorical(self, values: Any) -> bool:
+        if nw.dependencies.is_narwhals_series(values):
+            if not values.dtype.is_numeric():
+                return True
+        return super()._is_categorical(values)
 
     @override
     def _encode_constant(self, value, metadata, encoder_state, spec, drop_rows):
@@ -90,9 +82,9 @@ class TabmatMaterializer(FormulaMaterializer):
     @override
     def _encode_numerical(self, values, metadata, encoder_state, spec, drop_rows):
         if drop_rows:
-            values = values.drop(index=values.index[drop_rows])
-        if isinstance(values, pd.Series):
-            values = values.to_numpy().astype(self.dtype, copy=False)
+            values = drop_nulls(values, indices=drop_rows)
+        if isinstance(values, nw.Series):
+            values = values.to_numpy().astype(self.dtype)
         if (values != 0).mean() <= self.sparse_threshold:
             return _InteractableSparseVector(sps.csc_matrix(values[:, np.newaxis]))
         else:
@@ -104,7 +96,7 @@ class TabmatMaterializer(FormulaMaterializer):
     ):
         # We do not do any encoding here as it is handled by tabmat
         if drop_rows:
-            values = values.drop(index=values.index[drop_rows])
+            values = drop_nulls(values, indices=drop_rows)
         return encode_contrasts(
             values,
             reduced_rank=reduced_rank,
@@ -428,17 +420,22 @@ class _InteractableCategoricalVector(_InteractableVector):
         self.name = name
 
     @classmethod
-    def from_categorical(
+    def from_codes(
         cls,
-        cat: pd.Categorical,
+        codes: np.ndarray,
+        categories: list,
         reduced_rank: bool,
         missing_method: str = "fail",
         missing_name: str = "(MISSING)",
         add_missing_category: bool = False,
     ) -> "_InteractableCategoricalVector":
-        """Create an interactable categorical vector from a pandas categorical."""
-        categories = cat.categories.tolist()
-        codes = cat.codes.copy().astype(np.int64)
+        """Create an interactable categorical vector from integer codes and categories.
+
+        The `codes` array is expected to contain integer category codes, using
+        -1 for missing values and -2 for rows that should be dropped.
+        """
+        codes = codes.copy().astype(np.int64)
+        categories = categories.copy()
 
         if reduced_rank:
             codes[codes == 0] = -2
@@ -458,7 +455,7 @@ class _InteractableCategoricalVector(_InteractableVector):
         return cls(
             codes=codes,
             categories=categories,
-            multipliers=np.ones(len(cat.codes)),
+            multipliers=np.ones(len(codes)),
         )
 
     def __rmul__(self, other):
@@ -674,7 +671,7 @@ def _C(
     data,
     *,
     levels: Optional[Iterable[str]] = None,
-    missing_method: str = "fail",
+    missing_method: Optional[str] = None,
     missing_name: str = "(MISSING)",
     spans_intercept: bool = True,
 ):
@@ -694,12 +691,13 @@ def _C(
         model_spec: ModelSpec,
     ):
         if drop_rows:
-            values = values.drop(index=values.index[drop_rows])
+            values = drop_nulls(values, indices=drop_rows)
         return encode_contrasts(
             values,
             levels=levels,
             reduced_rank=reduced_rank,
-            missing_method=missing_method,
+            missing_method=missing_method
+            or model_spec.materializer_params.get("cat_missing_method", "fail"),  # type: ignore
             missing_name=missing_name,
             _state=encoder_state,
             _spec=model_spec,
@@ -715,14 +713,14 @@ def _C(
 
 @stateful_transform
 def encode_contrasts(
-    data,
+    data: nw.Series,
     *,
     levels: Optional[Iterable[str]] = None,
     missing_method: str = "fail",
     missing_name: str = "(MISSING)",
     reduced_rank: bool = False,
-    _state=None,
-    _spec=None,
+    _state: dict[str, Any] = {},
+    _spec: Optional[ModelSpec] = None,
 ) -> FactorValues[_InteractableCategoricalVector]:
     """
     Encode a categorical dataset into one an _InteractableCategoricalVector
@@ -738,6 +736,13 @@ def encode_contrasts(
     levels = levels if levels is not None else _state.get("categories")
     add_missing_category = _state.get("add_missing_category", False)
 
+    if data.dtype.is_numeric():
+        # Polars enums only support string values
+        data = data.cast(nw.String)
+        # Convert levels to strings as well to match data type
+        if levels is not None:
+            levels = [str(level) for level in levels]
+
     # Check for unseen categories when levels are specified
     if levels is not None:
         if missing_method == "convert" and not add_missing_category:
@@ -746,21 +751,28 @@ def encode_contrasts(
             #  - missings are no problem in the other cases
             unseen_categories = set(data.unique()) - set(levels)
         else:
-            unseen_categories = set(data.dropna().unique()) - set(levels)
+            unseen_categories = set(data.drop_nulls().unique()) - set(levels)
 
         if unseen_categories:
             raise ValueError(
                 f"Column {data.name} contains unseen categories: {unseen_categories}."
             )
+    else:
+        # Not super efficient as we do it again in _extract_codes_and_categories
+        levels = list(data.drop_nulls().unique().sort())
+
+    cat = data.cast(nw.Enum(levels))
+    codes, categories = _extract_codes_and_categories(cat)
+    categories = list(categories)
 
-    cat = pd.Categorical(data._values, categories=levels)
-    _state["categories"] = cat.categories
-    _state["add_missing_category"] = add_missing_category or (
-        missing_method == "convert" and cat.isna().any()
+    _state["categories"] = categories
+    _state["add_missing_category"] = add_missing_category or bool(
+        missing_method == "convert" and cat.is_null().any()
     )
 
-    return _InteractableCategoricalVector.from_categorical(
-        cat,
+    return _InteractableCategoricalVector.from_codes(
+        codes=codes,
+        categories=categories,
         reduced_rank=reduced_rank,
         missing_method=missing_method,
         missing_name=missing_name,

tabmat/split_matrix.py

@@ -527,7 +527,7 @@ class SplitMatrix(MatrixBase):
         list[Optional[str]]
             Column names.
         """
-        names = np.empty(self.shape[1], dtype=object)
+        names: np.ndarray = np.empty(self.shape[1], dtype=object)
         for idx, mat in zip(self.indices, self.matrices):
             names[idx] = mat.get_names(type, missing_prefix, idx)
         return names.tolist()

{tabmat-4.1.5.dist-info → tabmat-4.2.1.dist-info}/METADATA

@@ -1,20 +1,19 @@
 Metadata-Version: 2.4
 Name: tabmat
-Version: 4.1.5
+Version: 4.2.1
 Summary: Efficient matrix representations for working with tabular data.
 Home-page: https://github.com/Quantco/tabmat
 Author: QuantCo, Inc.
 Author-email: noreply@quantco.com
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
-Requires-Python: >=3.9
+Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
-Requires-Dist: formulaic>=0.6
+Requires-Dist: formulaic>=1.2
 Requires-Dist: narwhals
 Requires-Dist: numpy
 Requires-Dist: scipy

tabmat-4.2.1.dist-info/RECORD

@@ -0,0 +1,26 @@
+tabmat/__init__.py,sha256=uvBIwdxTmQCtfs3kfX75sMYGg0wBRNe0rUyQ3cvhU7M,759
+tabmat/categorical_matrix.py,sha256=MaFcyO7LmIuXRpyIjuCgbEI6ScZBL-0fibOGslGqZvU,33170
+tabmat/constructor.py,sha256=YO_8SRP8sZlxx4ELgcpZ5sRYW30lex6kujejQVcozaY,16582
+tabmat/constructor_util.py,sha256=IRtDJ0EQKiZVPH2aUvOuftPpgQog-kmq6dItGx8TPf8,1753
+tabmat/dense_matrix.py,sha256=-iQseyKovWyXHvPWg1w2URYNJbTKAOEVy34fHGRtnBU,12375
+tabmat/formula.py,sha256=lor2w9iswrfwKzw2qINAS-kCVelVVXhkR2pbfWXs5ho,29292
+tabmat/matrix_base.py,sha256=NIbL5myAyVDoL5RQhSod8BKX9kbVGTunggN7uMBLjD4,8192
+tabmat/sparse_matrix.py,sha256=wVgz7w8QWPskSzJyMSKo8O0B5NkC8h027BXgpmbToCc,14377
+tabmat/split_matrix.py,sha256=jRjnX0JU_KA29_Cm2fZWmRxgq7vueGDf6vX2UuaY5qI,21593
+tabmat/standardized_mat.py,sha256=ogrHF2vG6Es0WSNgcMNukDAlYq7R4yzB4-HuoovUnCE,13514
+tabmat/util.py,sha256=xxX5S5-m4Jy8Nr56T7IuLibZZcgUc8-xlU84N5xQZNA,4175
+tabmat/benchmark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+tabmat/benchmark/generate_matrices.py,sha256=1H-Y3SngnM7HgUT_YkOezPfnSdD9NwlvlJviKF4Aq1E,4923
+tabmat/benchmark/main.py,sha256=auwBIbBXM8nOtDkbLV95Da52Wk52Jw5ayJbX_Z6FK8Q,12420
+tabmat/benchmark/memory_tools.py,sha256=mFO-86Shxs1WmDf2--Xbxa3z3hTz4WmbKbFdrb3bxA8,1385
+tabmat/benchmark/visualize_benchmarks.py,sha256=-fr4rDOKtmCHsXTvuk_aF_m3egUR7z_ac3OiG4ebx-Q,5922
+tabmat/ext/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+tabmat/ext/categorical.cp310-win_amd64.pyd,sha256=-qLSl_fI-wKm3aPyYaHOao-gYgqBPaRkRYugWGu5r70,310784
+tabmat/ext/dense.cp310-win_amd64.pyd,sha256=nfF1ZeHf4wmrNCULKrl2XqwPp77CnlxfmCFBj8iUFs4,262144
+tabmat/ext/sparse.cp310-win_amd64.pyd,sha256=bak26vu4dDLWJg7ERsPylWNfGlR5P27gEk50itsT4Sg,672256
+tabmat/ext/split.cp310-win_amd64.pyd,sha256=RGkDFGCM7TQ447jE53Ds9GBx-4chePwaM116acksjLo,245248
+tabmat-4.2.1.dist-info/licenses/LICENSE,sha256=5NI6VxMb_AfgPHL2nQttFTurJZWQ8ks5UWTpNEsD9K0,1472
+tabmat-4.2.1.dist-info/METADATA,sha256=2neapQHbY3HbdtA0GGICTdkWDwo4DV2oJ-h3fqfZVM0,6227
+tabmat-4.2.1.dist-info/WHEEL,sha256=lVtJYX4SZwMxwg8oP4kB_UdF4VQRXLlqu7hUy_2nnAE,102
+tabmat-4.2.1.dist-info/top_level.txt,sha256=dAA5sdRVvDsNOvJd8hxwmetHTmRhp_Y08al7_gHqs9c,7
+tabmat-4.2.1.dist-info/RECORD,,

{tabmat-4.1.5.dist-info → tabmat-4.2.1.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.9.0)
+Generator: setuptools (80.10.2)
 Root-Is-Purelib: false
 Tag: cp310-cp310-win_amd64
 

tabmat-4.1.5.dist-info/RECORD

@@ -1,26 +0,0 @@
-tabmat/__init__.py,sha256=uvBIwdxTmQCtfs3kfX75sMYGg0wBRNe0rUyQ3cvhU7M,759
-tabmat/categorical_matrix.py,sha256=Sl1Zkk_E3A5uKbUg4GXrQSPOAjbStPKAkKdsRuSiSEs,32924
-tabmat/constructor.py,sha256=MXquP1UfhZk6mZdmiigmMsvn8UMdKF05dU7HlggES9M,16570
-tabmat/constructor_util.py,sha256=IRtDJ0EQKiZVPH2aUvOuftPpgQog-kmq6dItGx8TPf8,1753
-tabmat/dense_matrix.py,sha256=-iQseyKovWyXHvPWg1w2URYNJbTKAOEVy34fHGRtnBU,12375
-tabmat/formula.py,sha256=lrciexxxcNl_imYMQY7GcNwmKq1GKCWgo-yPzmEk_Ps,28744
-tabmat/matrix_base.py,sha256=NIbL5myAyVDoL5RQhSod8BKX9kbVGTunggN7uMBLjD4,8192
-tabmat/sparse_matrix.py,sha256=wVgz7w8QWPskSzJyMSKo8O0B5NkC8h027BXgpmbToCc,14377
-tabmat/split_matrix.py,sha256=N-3XboRNN-pYsZuds74-ldxODDqexeHT5CL-9IxmjJ8,21581
-tabmat/standardized_mat.py,sha256=ogrHF2vG6Es0WSNgcMNukDAlYq7R4yzB4-HuoovUnCE,13514
-tabmat/util.py,sha256=xxX5S5-m4Jy8Nr56T7IuLibZZcgUc8-xlU84N5xQZNA,4175
-tabmat/benchmark/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tabmat/benchmark/generate_matrices.py,sha256=MlMwENeE26D22VvAAqowjHBOlaRnvdXXePlUw54L1pI,4907
-tabmat/benchmark/main.py,sha256=auwBIbBXM8nOtDkbLV95Da52Wk52Jw5ayJbX_Z6FK8Q,12420
-tabmat/benchmark/memory_tools.py,sha256=mFO-86Shxs1WmDf2--Xbxa3z3hTz4WmbKbFdrb3bxA8,1385
-tabmat/benchmark/visualize_benchmarks.py,sha256=-fr4rDOKtmCHsXTvuk_aF_m3egUR7z_ac3OiG4ebx-Q,5922
-tabmat/ext/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-tabmat/ext/categorical.cp310-win_amd64.pyd,sha256=G_RDdyQYtOPKg6HgPDMdx4MtymbgC6EiWKZYS3XWwI8,310784
-tabmat/ext/dense.cp310-win_amd64.pyd,sha256=_Sh2YfTvlIuuQLYMjJnaXPVlM4nx-uAgkS8i_wvmbcw,262656
-tabmat/ext/sparse.cp310-win_amd64.pyd,sha256=QE787ILvpsJJJnpmiZL7TIjcXoBM4TOMTsL8byAO-7Y,672256
-tabmat/ext/split.cp310-win_amd64.pyd,sha256=zBm1Whx0OQEmOz2kN9bBQO617i-koYTz8YTJAOG7mIQ,245248
-tabmat-4.1.5.dist-info/licenses/LICENSE,sha256=5NI6VxMb_AfgPHL2nQttFTurJZWQ8ks5UWTpNEsD9K0,1472
-tabmat-4.1.5.dist-info/METADATA,sha256=bfh1IMj4VTbXdgTvwc5gewg5b_8nI3IvmF3kbXmIVyU,6277
-tabmat-4.1.5.dist-info/WHEEL,sha256=KUuBC6lxAbHCKilKua8R9W_TM71_-9Sg5uEP3uDWcoU,101
-tabmat-4.1.5.dist-info/top_level.txt,sha256=dAA5sdRVvDsNOvJd8hxwmetHTmRhp_Y08al7_gHqs9c,7
-tabmat-4.1.5.dist-info/RECORD,,