cellarr-array 0.0.1__tar.gz → 0.0.2__tar.gz

{cellarr_array-0.0.1 → cellarr_array-0.0.2}/CHANGELOG.md

@@ -1,5 +1,9 @@
 # Changelog
 
+## Version 0.0.2
+
+- Support in-memory tiledb objects. Updated tests and documentation.
+
 ## Version 0.0.1
 
 Initial implementation of the sparse and dense arrays backed by TileDB. 

{cellarr_array-0.0.1 → cellarr_array-0.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: cellarr-array
-Version: 0.0.1
+Version: 0.0.2
 Summary: Base class for handling TileDB backed arrays.
 Home-page: https://github.com/cellarr/cellarr-array
 Author: Jayaram Kancherla
@@ -26,7 +26,7 @@ Requires-Dist: pytest-cov; extra == "testing"
 
 # cellarr-array
 
-This package provided high-level wrappers for TileDB arrays optimized for handling genomic data matrices.
+This package provided high-level wrappers for TileDB arrays, for handling genomic data matrices.
 
 ## Install
 
@@ -116,24 +116,43 @@ subset = dense_array[100:200, genes]
 ### Working with Sparse Arrays
 
 ```python
-# Create a sparse array with COO output format
-coo_array = SparseCellArray(
+from cellarr_array import SparseCellArray
+
+# Create a sparse array with CSR output format
+csr_array = SparseCellArray(
     uri="sparse_matrix.tdb",
-    return_coo=True
+    return_sparse=True
 )
 
-# Get result as COO matrix
-result = coo_array[100:200, 500:1000]
+# Get result as CSR matrix
+result = csr_array[100:200, 500:1000]
 
 # Result is scipy.sparse.coo_matrix
-assert sparse.isspmatrix_coo(result)
+assert sparse.isspmatrix_csr(result)
 
 # Perform sparse operations
 nnz = result.nnz
 density = result.nnz / (result.shape[0] * result.shape[1])
 
 # Convert to other sparse formats if needed
-result_csr = result.tocsr()
+result_csc = result.tocsc()
+```
+
+Likewise create a CSC output format
+
+```python
+from scipy import sparse
+
+# Create a sparse array with CSC output format
+csc_array = SparseCellArray(
+    uri="sparse_matrix.tdb",
+    return_sparse=True,
+    sparse_coerce=sparse.csc_matrix
+)
+
+# Get result as CSR matrix
+result = csc_array[100:200, 500:1000]
+print(result)
 ```
 
 ### Array Maintenance
@@ -144,7 +163,7 @@ array.consolidate()
 
 # Custom consolidation
 config = ConsolidationConfig(
-    steps=["fragment"],
+    steps=2,
     vacuum_after=True
 )
 array.consolidate(config)

{cellarr_array-0.0.1 → cellarr_array-0.0.2}/README.md

@@ -3,7 +3,7 @@
 
 # cellarr-array
 
-This package provided high-level wrappers for TileDB arrays optimized for handling genomic data matrices.
+This package provided high-level wrappers for TileDB arrays, for handling genomic data matrices.
 
 ## Install
 
@@ -93,24 +93,43 @@ subset = dense_array[100:200, genes]
 ### Working with Sparse Arrays
 
 ```python
-# Create a sparse array with COO output format
-coo_array = SparseCellArray(
+from cellarr_array import SparseCellArray
+
+# Create a sparse array with CSR output format
+csr_array = SparseCellArray(
     uri="sparse_matrix.tdb",
-    return_coo=True
+    return_sparse=True
 )
 
-# Get result as COO matrix
-result = coo_array[100:200, 500:1000]
+# Get result as CSR matrix
+result = csr_array[100:200, 500:1000]
 
 # Result is scipy.sparse.coo_matrix
-assert sparse.isspmatrix_coo(result)
+assert sparse.isspmatrix_csr(result)
 
 # Perform sparse operations
 nnz = result.nnz
 density = result.nnz / (result.shape[0] * result.shape[1])
 
 # Convert to other sparse formats if needed
-result_csr = result.tocsr()
+result_csc = result.tocsc()
+```
+
+Likewise create a CSC output format
+
+```python
+from scipy import sparse
+
+# Create a sparse array with CSC output format
+csc_array = SparseCellArray(
+    uri="sparse_matrix.tdb",
+    return_sparse=True,
+    sparse_coerce=sparse.csc_matrix
+)
+
+# Get result as CSR matrix
+result = csc_array[100:200, 500:1000]
+print(result)
 ```
 
 ### Array Maintenance
@@ -121,7 +140,7 @@ array.consolidate()
 
 # Custom consolidation
 config = ConsolidationConfig(
-    steps=["fragment"],
+    steps=2,
     vacuum_after=True
 )
 array.consolidate(config)

{cellarr_array-0.0.1 → cellarr_array-0.0.2}/docs/conf.py

@@ -311,7 +311,7 @@ extensions.remove('myst_parser')
 extensions.append('myst_nb')
 
 # Less verbose api documentation
-# extensions.append('sphinx_autodoc_typehints')
+extensions.append('sphinx_autodoc_typehints')
 
 autodoc_default_options = {
     "special-members": True,

{cellarr_array-0.0.1 → cellarr_array-0.0.2}/docs/index.md

@@ -1,17 +1,6 @@
 # cellarr-array
 
-Add a short description here!
-
-
-## Note
-
-> This is the main page of your project's [Sphinx] documentation. It is
-> formatted in [Markdown]. Add additional pages by creating md-files in
-> `docs` or rst-files (formatted in [reStructuredText]) and adding links to
-> them in the `Contents` section below.
->
-> Please check [Sphinx] and [MyST] for more information
-> about how to document your project and how to configure your preferences.
+This package provided high-level wrappers for TileDB arrays optimized for handling genomic data matrices.
 
 
 ## Contents

{cellarr_array-0.0.1 → cellarr_array-0.0.2}/src/cellarr_array/CellArray.py

@@ -42,7 +42,8 @@ class CellArray(ABC):
                 Defaults to None for automatic mode switching.
 
             config_or_context:
-                Config or context object.
+                Optional config or context object.
+
                 Defaults to None.
 
             validate:
@@ -53,14 +54,15 @@ class CellArray(ABC):
         self._mode = mode
 
         if config_or_context is None:
-            config_or_context = tiledb.Config()
-
-        if isinstance(config_or_context, tiledb.Config):
-            ctx = tiledb.Ctx(config_or_context)
-        elif isinstance(config_or_context, tiledb.Ctx):
-            ctx = config_or_context
+            # config_or_context = tiledb.Config()
+            ctx = None
         else:
-            raise TypeError("'config_or_context' must be either TileDB config or a context object.")
+            if isinstance(config_or_context, tiledb.Config):
+                ctx = tiledb.Ctx(config_or_context)
+            elif isinstance(config_or_context, tiledb.Ctx):
+                ctx = config_or_context
+            else:
+                raise TypeError("'config_or_context' must be either TileDB config or a context object.")
 
         self._ctx = ctx
         self._array = None

{cellarr_array-0.0.1 → cellarr_array-0.0.2}/src/cellarr_array.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: cellarr-array
-Version: 0.0.1
+Version: 0.0.2
 Summary: Base class for handling TileDB backed arrays.
 Home-page: https://github.com/cellarr/cellarr-array
 Author: Jayaram Kancherla
@@ -26,7 +26,7 @@ Requires-Dist: pytest-cov; extra == "testing"
 
 # cellarr-array
 
-This package provided high-level wrappers for TileDB arrays optimized for handling genomic data matrices.
+This package provided high-level wrappers for TileDB arrays, for handling genomic data matrices.
 
 ## Install
 
@@ -116,24 +116,43 @@ subset = dense_array[100:200, genes]
 ### Working with Sparse Arrays
 
 ```python
-# Create a sparse array with COO output format
-coo_array = SparseCellArray(
+from cellarr_array import SparseCellArray
+
+# Create a sparse array with CSR output format
+csr_array = SparseCellArray(
     uri="sparse_matrix.tdb",
-    return_coo=True
+    return_sparse=True
 )
 
-# Get result as COO matrix
-result = coo_array[100:200, 500:1000]
+# Get result as CSR matrix
+result = csr_array[100:200, 500:1000]
 
 # Result is scipy.sparse.coo_matrix
-assert sparse.isspmatrix_coo(result)
+assert sparse.isspmatrix_csr(result)
 
 # Perform sparse operations
 nnz = result.nnz
 density = result.nnz / (result.shape[0] * result.shape[1])
 
 # Convert to other sparse formats if needed
-result_csr = result.tocsr()
+result_csc = result.tocsc()
+```
+
+Likewise create a CSC output format
+
+```python
+from scipy import sparse
+
+# Create a sparse array with CSC output format
+csc_array = SparseCellArray(
+    uri="sparse_matrix.tdb",
+    return_sparse=True,
+    sparse_coerce=sparse.csc_matrix
+)
+
+# Get result as CSR matrix
+result = csc_array[100:200, 500:1000]
+print(result)
 ```
 
 ### Array Maintenance
@@ -144,7 +163,7 @@ array.consolidate()
 
 # Custom consolidation
 config = ConsolidationConfig(
-    steps=["fragment"],
+    steps=2,
     vacuum_after=True
 )
 array.consolidate(config)

{cellarr_array-0.0.1 → cellarr_array-0.0.2}/src/cellarr_array.egg-info/SOURCES.txt

@@ -39,4 +39,5 @@ tests/conftest.py
 tests/test_all.py
 tests/test_dense.py
 tests/test_helpers.py
+tests/test_inmemory.py
 tests/test_sparse.py

cellarr_array-0.0.2/tests/test_inmemory.py

@@ -0,0 +1,34 @@
+from pathlib import Path
+
+import numpy as np
+import pytest
+import scipy as sp
+
+from cellarr_array import DenseCellArray, create_cellarray
+
+__author__ = "Jayaram Kancherla"
+__copyright__ = "Jayaram Kancherla"
+__license__ = "MIT"
+
+
+def test_inmem_uri():
+    shape = (10_000, 10_000)
+    arr = np.arange(100_000_000).reshape(shape)
+    uri = "mem://dense"
+
+    dense_inmem = create_cellarray(uri, shape=(shape))
+    dense_inmem.write_batch(arr, start_row=0)
+
+    assert np.allclose(dense_inmem[:10, :10], arr[:10, :10])
+
+
+def test_inmem_uri_sparse():
+    shape = (1000, 1000)
+
+    s = sp.sparse.random(1000, 1000, density=0.25)
+    uri = "mem://sparse"
+
+    dense_inmem = create_cellarray(uri, shape=(shape), sparse=True)
+    dense_inmem.write_batch(s, start_row=0)
+
+    assert np.allclose(dense_inmem[:10, :10].toarray(), s.tocsr()[:10, :10].toarray())