cap-anndata 0.2.1__tar.gz → 0.3.0__tar.gz

cap_anndata-0.3.0/PKG-INFO

@@ -0,0 +1,54 @@
+Metadata-Version: 2.1
+Name: cap_anndata
+Version: 0.3.0
+Summary: Partial read/write of AnnData (h5ad) files for low-memory operations with large datasets.
+Home-page: https://github.com/cellannotation/cap-anndata
+Author: R. Mukhin, A. Isaev
+Author-email: roman@ebookapplications.com
+Project-URL: Bug Tracker, https://github.com/cellannotation/cap-anndata/issues
+Classifier: Programming Language :: Python :: 3.9
+Classifier: License :: OSI Approved :: BSD License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy>=1.23.5
+Requires-Dist: pandas>=2.2.0
+Requires-Dist: anndata>=0.10.0
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0.0; extra == "dev"
+Requires-Dist: setuptools~=69.1.1; extra == "dev"
+
+# CAP-AnnData: Partial I/O for AnnData (.h5ad) Files
+
+## Overview
+CAP-AnnData offering functionalities for selective reading and writing of [AnnData](https://pypi.org/project/anndata/) 
+file fields without the need for loading entire dataset (or even entire field) into memory. 
+For example, it allows to read and modify the single `obs` column taking nothing into memory except the column itself.
+Package eager to replicate the original AnnData API as much as possible, 
+while providing additional features for efficient data manipulation for heavy datasets.
+
+## Installation
+Install CAP-AnnData via pip:
+
+```commandline
+pip install -U cap-anndata
+```
+
+## Basic Example
+
+The example below displayes how to read a single `obs` column, create new obs column and propagate it to the `.h5ad` file.
+```python
+from cap_anndata import read_h5ad
+
+file_path = "your_data.h5ad"
+with read_h5ad(file_path=file_path, edit=True) as cap_adata:
+    print(cap_adata.obs_keys())  # ['a', 'b', 'c']
+    print(cap_adata.obs) # Empty DataFrame
+    cap_adata.read_obs(columns=['a'])
+    print(cap_adata.obs.columns) # ['a']
+    cap_adata.obs['new_col'] = cap_adata.obs['a']
+    cap_adata.overwrite(fields=['obs'])
+```
+
+More example can be found in the [How-TO](https://github.com/cellannotation/cap-anndata/blob/main/HOWTO.md) file. 

cap_anndata-0.3.0/README.md

@@ -0,0 +1,33 @@
+# CAP-AnnData: Partial I/O for AnnData (.h5ad) Files
+
+## Overview
+CAP-AnnData offering functionalities for selective reading and writing of [AnnData](https://pypi.org/project/anndata/) 
+file fields without the need for loading entire dataset (or even entire field) into memory. 
+For example, it allows to read and modify the single `obs` column taking nothing into memory except the column itself.
+Package eager to replicate the original AnnData API as much as possible, 
+while providing additional features for efficient data manipulation for heavy datasets.
+
+## Installation
+Install CAP-AnnData via pip:
+
+```commandline
+pip install -U cap-anndata
+```
+
+## Basic Example
+
+The example below displayes how to read a single `obs` column, create new obs column and propagate it to the `.h5ad` file.
+```python
+from cap_anndata import read_h5ad
+
+file_path = "your_data.h5ad"
+with read_h5ad(file_path=file_path, edit=True) as cap_adata:
+    print(cap_adata.obs_keys())  # ['a', 'b', 'c']
+    print(cap_adata.obs) # Empty DataFrame
+    cap_adata.read_obs(columns=['a'])
+    print(cap_adata.obs.columns) # ['a']
+    cap_adata.obs['new_col'] = cap_adata.obs['a']
+    cap_adata.overwrite(fields=['obs'])
+```
+
+More example can be found in the [How-TO](https://github.com/cellannotation/cap-anndata/blob/main/HOWTO.md) file. 

{cap_anndata-0.2.1 → cap_anndata-0.3.0}/cap_anndata/__init__.py

@@ -1,5 +1,5 @@
 from .backed_df import CapAnnDataDF
-from .backed_uns import CapAnnDataUns
+from .backed_dict import CapAnnDataDict
 from .cap_anndata import CapAnnData
 from .reader import (
     read_directly,

cap_anndata-0.3.0/cap_anndata/backed_dict.py

@@ -0,0 +1,34 @@
+from typing import Set, Any
+
+
+class CapAnnDataDict(dict):
+    __keys_to_remove: Set[str] = None
+
+    def __delitem__(self, __key: Any) -> None:
+        self.keys_to_remove.add(__key)
+        return super().__delitem__(__key)
+
+    def __setitem__(self, __key: Any, __value: Any) -> None:
+        if __value is not None:
+            if __key in self.keys_to_remove:
+                self.keys_to_remove.remove(__key)
+        else:
+            self.keys_to_remove.add(__key)
+        return super().__setitem__(__key, __value)
+
+    @property
+    def keys_to_remove(self) -> Set[str]:
+        if self.__keys_to_remove is None:
+            self.__keys_to_remove = set()
+        return self.__keys_to_remove
+
+    def pop(self, __key: Any, __default: Any = None) -> Any:
+        if __key in self:
+            self.keys_to_remove.add(__key)
+        return super().pop(__key, __default)
+
+    def popitem(self) -> Any:
+        item = super().popitem()
+        key = item[0]
+        self.keys_to_remove.add(key)
+        return item