| Name | znslice JSON |
| Version |
0.1.2
JSON |
| download |
| home_page | |
| Summary | Cache, advanced slicing and lazy loading for __getitem__ |
| upload_time | 2023-02-06 13:16:12 |
| maintainer | |
| docs_url | None |
| author | zincwarecode |
| requires_python | >=3.8,<4.0 |
| license | Apache-2.0 |
| keywords |
|
| VCS |
|
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
[](https://badge.fury.io/py/znslice)
[](https://coveralls.io/github/zincware/ZnSlice?branch=main)
[](https://github.com/zincware)
# ZnSlice
A lightweight library (without external dependencies) for:
- advanced slicing.
- cache `__getitem__(self, item)`
- lazy load `__getitem__(self, item)`
# Installation
```bash
pip install znslice
```
# Usage
## Advanced Slicing and Cache
Convert List to `znslice.LazySequence` to allow advanced slicing.
```python
import znslice
lst = znslice.LazySequence.from_obj([1, 2, 3], indices=[0, 2])
print(lst[[0, 1]].tolist()) # [1, 3]
```
```python
import znslice
import collections.abc
class MapList(collections.abc.Sequence):
def __init__(self, data, func):
self.data = data
self.func = func
@znslice.znslice
def __getitem__(self, item: int):
print(f"Loading item = {item}")
return self.func(self.data[item])
def __len__(self):
return len(self.data)
data = MapList([0, 1, 2, 3, 4], lambda x: x ** 2)
assert data[0] == 0
assert data[[1, 2, 3]] == [1, 4, 9]
# calling data[:] will now only compute data[4] and load the remaining data from cache
assert data[:] == [0, 1, 4, 9, 16]
```
## Lazy Database Loading
You can use `znslice` to lazy load data from a database. This is useful if you have a large database and only want to load a small subset of the data.
In the following we will use the `ase` package to generate `Atoms` objects stored in a database and load them lazily.
```python
import ase.io
import ase.db
import znslice
import tqdm
import random
# create a database
with ase.db.connect("data.db", append=False) as db:
for _ in range(10):
atoms = ase.Atoms('CO', positions=[(0, 0, 0), (0, 0, random.random())])
db.write(atoms, group="data")
# load the database lazily
class ReadASEDB:
def __init__(self, file):
self.file = file
@znslice.znslice(
advanced_slicing=True, # this getitem supports advanced slicingn
lazy=True # we want to lazy load the data
)
def __getitem__(self, item):
data = []
with ase.db.connect(self.file) as database:
if isinstance(item, int):
print(f"get {item = }")
return database[item + 1].toatoms()
for idx in tqdm.tqdm(item):
data.append(database[idx + 1].toatoms())
return data
def __len__(self):
with ase.db.connect(self.file) as db:
return len(db)
db = ReadASEDB("data.db")
data = db[::2] # LazySequence([<__main__.ReadASEDB>], [[0, 2, 4, 6, 8]])
data.tolist() # list[ase.Atoms]
# supports addition, advanced slicing, etc.
data = db[::2] + db[1::2]
```
Raw data
{
"_id": null,
"home_page": "",
"name": "znslice",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.8,<4.0",
"maintainer_email": "",
"keywords": "",
"author": "zincwarecode",
"author_email": "zincwarecode@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/ce/b8/c657c1317ec4143dc292231a8b2dd53b2d14e72477d0f7439978d26c3d0f/znslice-0.1.2.tar.gz",
"platform": null,
"description": "[](https://badge.fury.io/py/znslice)\n[](https://coveralls.io/github/zincware/ZnSlice?branch=main)\n[](https://github.com/zincware)\n# ZnSlice\n\nA lightweight library (without external dependencies) for:\n- advanced slicing.\n- cache `__getitem__(self, item)`\n- lazy load `__getitem__(self, item)`\n\n# Installation\n\n```bash\npip install znslice\n```\n\n# Usage\n\n## Advanced Slicing and Cache\nConvert List to `znslice.LazySequence` to allow advanced slicing.\n```python\nimport znslice\n\nlst = znslice.LazySequence.from_obj([1, 2, 3], indices=[0, 2])\nprint(lst[[0, 1]].tolist()) # [1, 3]\n```\n\n\n```python\nimport znslice\nimport collections.abc\n\nclass MapList(collections.abc.Sequence):\n def __init__(self, data, func):\n self.data = data\n self.func = func\n \n @znslice.znslice\n def __getitem__(self, item: int):\n print(f\"Loading item = {item}\")\n return self.func(self.data[item])\n \n def __len__(self):\n return len(self.data)\n\ndata = MapList([0, 1, 2, 3, 4], lambda x: x ** 2)\n\nassert data[0] == 0\nassert data[[1, 2, 3]] == [1, 4, 9]\n# calling data[:] will now only compute data[4] and load the remaining data from cache\nassert data[:] == [0, 1, 4, 9, 16]\n```\n\n## Lazy Database Loading\n\nYou can use `znslice` to lazy load data from a database. This is useful if you have a large database and only want to load a small subset of the data.\n\nIn the following we will use the `ase` package to generate `Atoms` objects stored in a database and load them lazily.\n\n```python \nimport ase.io\nimport ase.db\nimport znslice\nimport tqdm\nimport random\n\n# create a database\nwith ase.db.connect(\"data.db\", append=False) as db:\n for _ in range(10):\n atoms = ase.Atoms('CO', positions=[(0, 0, 0), (0, 0, random.random())])\n db.write(atoms, group=\"data\")\n \n# load the database lazily\nclass ReadASEDB:\n def __init__(self, file):\n self.file = file\n \n @znslice.znslice(\n advanced_slicing=True, # this getitem supports advanced slicingn\n lazy=True # we want to lazy load the data\n )\n def __getitem__(self, item):\n data = []\n with ase.db.connect(self.file) as database:\n if isinstance(item, int):\n print(f\"get {item = }\")\n return database[item + 1].toatoms()\n for idx in tqdm.tqdm(item):\n data.append(database[idx + 1].toatoms())\n return data\n \n def __len__(self):\n with ase.db.connect(self.file) as db:\n return len(db)\n\ndb = ReadASEDB(\"data.db\")\n\ndata = db[::2] # LazySequence([<__main__.ReadASEDB>], [[0, 2, 4, 6, 8]])\ndata.tolist() # list[ase.Atoms] \n\n# supports addition, advanced slicing, etc.\ndata = db[::2] + db[1::2]\n```\n",
"bugtrack_url": null,
"license": "Apache-2.0",
"summary": "Cache, advanced slicing and lazy loading for __getitem__",
"version": "0.1.2",
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "cf361b0bf380415cc07e53d86bd969a7cbd226ec6f73a535191f67396c68a1ae",
"md5": "d3b12557d0727dadc567a0205adb3ac9",
"sha256": "f07912398075d3967a7cc7ab1c00fcac1ca9a4389af8274a140dd00b04065b49"
},
"downloads": -1,
"filename": "znslice-0.1.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "d3b12557d0727dadc567a0205adb3ac9",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8,<4.0",
"size": 5417,
"upload_time": "2023-02-06T13:16:11",
"upload_time_iso_8601": "2023-02-06T13:16:11.015159Z",
"url": "https://files.pythonhosted.org/packages/cf/36/1b0bf380415cc07e53d86bd969a7cbd226ec6f73a535191f67396c68a1ae/znslice-0.1.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "ceb8c657c1317ec4143dc292231a8b2dd53b2d14e72477d0f7439978d26c3d0f",
"md5": "3ef3405d920da133a19b1a2a6499bc25",
"sha256": "c2edb2fe1cdf7ac52f42bd0cf63c74d25c8dbdce0ded3a9d245135641d175255"
},
"downloads": -1,
"filename": "znslice-0.1.2.tar.gz",
"has_sig": false,
"md5_digest": "3ef3405d920da133a19b1a2a6499bc25",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8,<4.0",
"size": 5435,
"upload_time": "2023-02-06T13:16:12",
"upload_time_iso_8601": "2023-02-06T13:16:12.662968Z",
"url": "https://files.pythonhosted.org/packages/ce/b8/c657c1317ec4143dc292231a8b2dd53b2d14e72477d0f7439978d26c3d0f/znslice-0.1.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-02-06 13:16:12",
"github": false,
"gitlab": false,
"bitbucket": false,
"lcname": "znslice"
}
