SOMA-component dataframe/schema accessors

apis/python/src/tiledbsc/annotation_dataframe.py

@@ -78,6 +78,14 @@ def dim_select(self, ids):
             with tiledb.open(self.uri) as A:  # TODO: with self.open
                 return A.df[ids]
 
+    # ----------------------------------------------------------------
+    def df(self, ids=None) -> pd.DataFrame:
+        """
+        Keystroke-saving alias for `.dim_select()`. If `ids` are provided, they're used
+        to subselect; if not, the entire dataframe is returned.
+        """
+        return self.dim_select(ids)
+
     # ----------------------------------------------------------------
     # TODO: this is a v1 for prototype/demo timeframe -- needs expanding.
     def attribute_filter(self, query_string, col_names_to_keep):

apis/python/src/tiledbsc/annotation_matrix.py

@@ -43,6 +43,14 @@ def dim_select(self, ids):
             with tiledb.open(self.uri) as A:  # TODO: with self.open
                 return A.df[ids]
 
+    # ----------------------------------------------------------------
+    def df(self, ids=None) -> pd.DataFrame:
+        """
+        Keystroke-saving alias for `.dim_select()`. If `ids` are provided, they're used
+        to subselect; if not, the entire dataframe is returned.
+        """
+        return self.dim_select(ids)
+
     # ----------------------------------------------------------------
     def shape(self):
         """

apis/python/src/tiledbsc/annotation_pairwise_matrix.py

@@ -60,6 +60,14 @@ def dim_select(self, ids):
             with tiledb.open(self.uri) as A:  # TODO: with self.open
                 return A.df[ids, ids]
 
+    # ----------------------------------------------------------------
+    def df(self, ids=None) -> pd.DataFrame:
+        """
+        Keystroke-saving alias for `.dim_select()`. If `ids` are provided, they're used
+        to subselect; if not, the entire dataframe is returned.
+        """
+        return self.dim_select(ids)
+
     # ----------------------------------------------------------------
     def from_anndata(self, matrix, dim_values):
         """

apis/python/src/tiledbsc/assay_matrix.py

@@ -7,6 +7,7 @@
 
 import scipy
 import numpy as np
+import pandas as pd
 
 from typing import Optional
 import time
@@ -44,6 +45,13 @@ def __init__(
     # We don't have a .shape() method since X is sparse. One should
     # instead use the row-counts for the soma's obs and var.
 
+    # ----------------------------------------------------------------
+    def dim_names(self):
+        """
+        Keystroke-saving accessor for `row_dim_name` and `col_dim_name`.
+        """
+        return (self.row_dim_name, self.col_dim_name)
+
     # ----------------------------------------------------------------
     def dim_select(self, obs_ids, var_ids):
         """
@@ -63,6 +71,14 @@ def dim_select(self, obs_ids, var_ids):
                 else:
                     return A.df[obs_ids, var_ids]
 
+    # ----------------------------------------------------------------
+    def df(self, obs_ids=None, var_ids=None) -> pd.DataFrame:
+        """
+        Keystroke-saving alias for `.dim_select()`. If either of `obs_ids` or `var_ids`
+        are provided, they're used to subselect; if not, the entire dataframe is returned.
+        """
+        return self.dim_select(obs_ids, var_ids)
+
     # ----------------------------------------------------------------
     def from_matrix(self, matrix, row_names, col_names) -> None:
         """

apis/python/tests/test_soma_group_indexing.py

@@ -2,6 +2,8 @@
 import tiledb
 import tiledbsc
 
+import numpy as np
+
 import pytest
 import tempfile
 import os
@@ -51,6 +53,16 @@ def test_soma_group_indexing(h5ad_file):
     assert soma.X.data.get_dim_names() == ["obs_id", "var_id"]
 
     assert soma.obs.get_dim_names() == ["obs_id"]
+    assert soma.obs.dim_name == "obs_id"
+    assert soma.obs.keys() == [
+        "orig.ident",
+        "nCount_RNA",
+        "nFeature_RNA",
+        "RNA_snn_res.0.8",
+        "letter.idents",
+        "groups",
+        "RNA_snn_res.1",
+    ]
     assert set(soma.obs.ids()) == set(
         [
             b"AAATTCGAATCACG",
@@ -135,8 +147,27 @@ def test_soma_group_indexing(h5ad_file):
             b"TTTAGCTGTACTCT",
         ]
     )
+    assert soma.obs.df().shape == (80, 7)
+    assert soma.obs.df(["AAGCAAGAGCTTAG", "TTGGTACTGAATCC"]).shape == (2, 7)
+    assert list(soma.obs.df().dtypes) == [
+        np.dtype("int32"),
+        np.dtype("float64"),
+        np.dtype("int32"),
+        np.dtype("int32"),
+        np.dtype("int32"),
+        np.dtype("O"),
+        np.dtype("int32"),
+    ]
 
     assert soma.var.get_dim_names() == ["var_id"]
+    assert soma.obs.dim_name == "obs_id"
+    assert soma.var.keys() == [
+        "vst.mean",
+        "vst.variance",
+        "vst.variance.expected",
+        "vst.variance.standardized",
+        "vst.variable",
+    ]
     assert set(soma.var.ids()) == set(
         [
             b"AKR1C3",
@@ -161,11 +192,44 @@ def test_soma_group_indexing(h5ad_file):
             b"VDAC3",
         ]
     )
+    assert soma.var.shape() == (20, 5)
+    assert soma.var.df(["RUFY1", "AKR1C3"]).shape == (2, 5)
+    assert list(soma.var.df().dtypes) == [
+        np.dtype("float64"),
+        np.dtype("float64"),
+        np.dtype("float64"),
+        np.dtype("float64"),
+        np.dtype("int32"),
+    ]
 
     assert set(soma.obsm.get_member_names()) == set(["X_pca", "X_tsne"])
+    assert set(soma.obsm.keys()) == set(["X_pca", "X_tsne"])
     assert isinstance(soma.obsm["X_pca"], tiledbsc.AnnotationMatrix)
     assert soma.obsm["nonesuch"] is None
     assert soma.obsm["X_pca"].get_dim_names() == ["obs_id"]
+    assert soma.obsm["X_pca"].df().shape == (80, 20)
+    assert list(soma.obsm["X_pca"].df().dtypes) == [
+        np.dtype("O"),
+        np.dtype("float64"),
+        np.dtype("float64"),
+        np.dtype("float64"),
+        np.dtype("float64"),
+        np.dtype("float64"),
+        np.dtype("float64"),
+        np.dtype("float64"),
+        np.dtype("float64"),
+        np.dtype("float64"),
+        np.dtype("float64"),
+        np.dtype("float64"),
+        np.dtype("float64"),
+        np.dtype("float64"),
+        np.dtype("float64"),
+        np.dtype("float64"),
+        np.dtype("float64"),
+        np.dtype("float64"),
+        np.dtype("float64"),
+        np.dtype("float64"),
+    ]
 
     assert set(soma.varm.get_member_names()) == set(["PCs"])
     assert isinstance(soma.varm["PCs"], tiledbsc.AnnotationMatrix)