跳转到主要内容

一个用于在材料科学中应用机器学习的原子结构特征转换的Python包。

项目描述

Build status Coverage Status Ruff

DScribe是一个Python包,可以将原子结构转换为固定大小的数值指纹。这些指纹通常被称为“描述符”,它们可用于各种任务,包括机器学习、可视化、相似性分析等。

文档

有关更多详情和教程,请访问我们的文档: https://singroup.github.io/dscribe/

您可以在以下文章中找到更多详情

快速示例

import numpy as np
from ase.build import molecule
from dscribe.descriptors import SOAP
from dscribe.descriptors import CoulombMatrix

# Define atomic structures
samples = [molecule("H2O"), molecule("NO2"), molecule("CO2")]

# Setup descriptors
cm_desc = CoulombMatrix(n_atoms_max=3, permutation="sorted_l2")
soap_desc = SOAP(species=["C", "H", "O", "N"], r_cut=5, n_max=8, l_max=6, crossover=True)

# Create descriptors as numpy arrays or sparse arrays
water = samples[0]
coulomb_matrix = cm_desc.create(water)
soap = soap_desc.create(water, centers=[0])

# Easy to use also on multiple systems, can be parallelized across processes
coulomb_matrices = cm_desc.create(samples)
coulomb_matrices = cm_desc.create(samples, n_jobs=3)
oxygen_indices = [np.where(x.get_atomic_numbers() == 8)[0] for x in samples]
oxygen_soap = soap_desc.create(samples, oxygen_indices, n_jobs=3)

# Descriptors also allow calculating derivatives with respect to atomic
# positions
der, des = soap_desc.derivatives(samples, return_descriptor=True)

当前实现的描述符

描述符 导数
库仑矩阵 :heavy_check_mark :heavy_check_mark
正弦矩阵 :heavy_check_mark :heavy_check_mark
Ewald矩阵 :heavy_check_mark :heavy_check_mark
原子中心对称函数(ACSF) :heavy_check_mark :heavy_check_mark
原子位置平滑重叠(SOAP) :heavy_check_mark :heavy_check_mark
多体张量表示(MBTR) :heavy_check_mark :heavy_check_mark
局部多体张量表示(LMBTR) :heavy_check_mark :heavy_check_mark
Valle-Oganov描述符 :heavy_check_mark :heavy_check_mark

安装

详细的安装说明可以在文档中找到,但简而言之

pip

pip install dscribe

conda

conda install -c conda-forge dscribe

从源码

git clone https://github.com/SINGROUP/dscribe.git
cd dscribe
git submodule update --init
pip install .

项目详情


下载文件

下载适用于您平台的文件。如果您不确定选择哪一个,请了解更多关于安装包的信息。

源代码发行版

dscribe-2.1.1.tar.gz (1.2 MB 查看哈希值)

上传日期 源代码

构建发行版

dscribe-2.1.1-pp310-pypy310_pp73-win_amd64.whl (542.2 kB 查看哈希值)

上传日期 PyPy Windows x86-64

dscribe-2.1.1-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (724.0 kB 查看哈希值)

上传日期 PyPy manylinux: glibc 2.17+ x86-64

dscribe-2.1.1-pp310-pypy310_pp73-manylinux_2_17_i686.manylinux2014_i686.whl (707.1 kB 查看哈希值)

上传日期 PyPy manylinux: glibc 2.17+ i686

dscribe-2.1.1-pp310-pypy310_pp73-macosx_11_0_arm64.whl (669.7 kB 查看哈希值)

上传日期 PyPy macOS 11.0+ ARM64

dscribe-2.1.1-pp310-pypy310_pp73-macosx_10_9_x86_64.whl (708.0 kB 查看哈希值)

上传日期 PyPy macOS 10.9+ x86-64

dscribe-2.1.1-pp39-pypy39_pp73-win_amd64.whl (542.5 kB 查看哈希值)

上传于 PyPy Windows x86-64

dscribe-2.1.1-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (724.0 kB 查看哈希值)

上传于 PyPy manylinux: glibc 2.17+ x86-64

dscribe-2.1.1-pp39-pypy39_pp73-manylinux_2_17_i686.manylinux2014_i686.whl (707.0 kB 查看哈希值)

上传于 PyPy manylinux: glibc 2.17+ i686

dscribe-2.1.1-pp39-pypy39_pp73-macosx_11_0_arm64.whl (669.7 kB 查看哈希值)

上传于 PyPy macOS 11.0+ ARM64

dscribe-2.1.1-pp39-pypy39_pp73-macosx_10_9_x86_64.whl (708.0 kB 查看哈希值)

上传于 PyPy macOS 10.9+ x86-64

dscribe-2.1.1-pp38-pypy38_pp73-win_amd64.whl (542.4 kB 查看哈希值)

上传于 PyPy Windows x86-64

dscribe-2.1.1-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (723.9 kB 查看哈希值)

上传于 PyPy manylinux: glibc 2.17+ x86-64

dscribe-2.1.1-pp38-pypy38_pp73-manylinux_2_17_i686.manylinux2014_i686.whl (706.7 kB 查看哈希值)

上传于 PyPy manylinux: glibc 2.17+ i686

dscribe-2.1.1-pp38-pypy38_pp73-macosx_11_0_arm64.whl (669.7 kB 查看哈希值)

上传于 PyPy macOS 11.0+ ARM64

dscribe-2.1.1-pp38-pypy38_pp73-macosx_10_9_x86_64.whl (708.0 kB 查看哈希值)

上传于 PyPy macOS 10.9+ x86-64

dscribe-2.1.1-cp312-cp312-win_amd64.whl (544.2 kB 查看哈希值)

上传于 CPython 3.12 Windows x86-64

dscribe-2.1.1-cp312-cp312-win32.whl (508.1 kB 查看哈希值)

上传时间: CPython 3.12 Windows x86

dscribe-2.1.1-cp312-cp312-musllinux_1_2_x86_64.whl (13.4 MB 查看哈希值)

上传时间: CPython 3.12 musllinux: musl 1.2+ x86-64

dscribe-2.1.1-cp312-cp312-musllinux_1_2_i686.whl (13.2 MB 查看哈希值)

上传时间: CPython 3.12 musllinux: musl 1.2+ i686

dscribe-2.1.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (12.9 MB 查看哈希值)

上传时间: CPython 3.12 manylinux: glibc 2.17+ x86-64

dscribe-2.1.1-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl (12.3 MB 查看哈希值)

上传时间: CPython 3.12 manylinux: glibc 2.17+ i686

dscribe-2.1.1-cp312-cp312-macosx_11_0_arm64.whl (690.8 kB 查看哈希值)

上传时间: CPython 3.12 macOS 11.0+ ARM64

dscribe-2.1.1-cp312-cp312-macosx_10_9_x86_64.whl (726.0 kB 查看哈希值)

上传时间: CPython 3.12 macOS 10.9+ x86-64

dscribe-2.1.1-cp311-cp311-win_amd64.whl (544.1 kB 查看哈希值)

上传时间: CPython 3.11 Windows x86-64

dscribe-2.1.1-cp311-cp311-win32.whl (507.5 kB 查看哈希值)

上传时间: CPython 3.11 Windows x86

dscribe-2.1.1-cp311-cp311-musllinux_1_2_x86_64.whl (13.4 MB 查看哈希值)

上传时间: CPython 3.11 musllinux: musl 1.2+ x86-64

dscribe-2.1.1-cp311-cp311-musllinux_1_2_i686.whl (13.2 MB 查看哈希值)

上传时间: CPython 3.11 musllinux: musl 1.2+ i686

dscribe-2.1.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (12.8 MB 查看哈希值)

上传时间: CPython 3.11 manylinux: glibc 2.17+ x86-64

dscribe-2.1.1-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl (12.3 MB 查看哈希值)

上传时间: CPython 3.11 manylinux: glibc 2.17+ i686

dscribe-2.1.1-cp311-cp311-macosx_11_0_arm64.whl (691.9 kB 查看哈希值)

上传时间: CPython 3.11 macOS 11.0+ ARM64

dscribe-2.1.1-cp311-cp311-macosx_10_9_x86_64.whl (726.3 kB 查看哈希值)

上传时间: CPython 3.11 macOS 10.9+ x86-64

dscribe-2.1.1-cp310-cp310-win_amd64.whl (543.0 kB 查看哈希值)

上传时间: CPython 3.10 Windows x86-64

dscribe-2.1.1-cp310-cp310-win32.whl (507.0 kB 查看哈希值)

上传时间: CPython 3.10 Windows x86

dscribe-2.1.1-cp310-cp310-musllinux_1_2_x86_64.whl (13.2 MB 查看哈希值)

上传时间: CPython 3.10 musllinux: musl 1.2+ x86-64

dscribe-2.1.1-cp310-cp310-musllinux_1_2_i686.whl (13.0 MB 查看哈希值)

上传时间: CPython 3.10 musllinux: musl 1.2+ i686

dscribe-2.1.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (12.5 MB 查看哈希值)

上传时间: CPython 3.10 manylinux: glibc 2.17+ x86-64

dscribe-2.1.1-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl (12.2 MB 查看哈希值)

上传时间: CPython 3.10 manylinux: glibc 2.17+ i686

dscribe-2.1.1-cp310-cp310-macosx_11_0_arm64.whl (690.7 kB 查看哈希值)

上传时间: CPython 3.10 macOS 11.0+ ARM64

dscribe-2.1.1-cp310-cp310-macosx_10_9_x86_64.whl (725.3 kB 查看哈希值)

上传时间: CPython 3.10 macOS 10.9+ x86-64

dscribe-2.1.1-cp39-cp39-win_amd64.whl (543.2 kB 查看哈希值)

上传时间: CPython 3.9 Windows x86-64

dscribe-2.1.1-cp39-cp39-win32.whl (507.1 kB 查看哈希值)

上传时间: CPython 3.9 Windows x86

dscribe-2.1.1-cp39-cp39-musllinux_1_2_x86_64.whl (13.2 MB 查看哈希值)

上传时间: CPython 3.9 musllinux: musl 1.2+ x86-64

dscribe-2.1.1-cp39-cp39-musllinux_1_2_i686.whl (13.0 MB 查看哈希值)

上传时间: CPython 3.9 musllinux: musl 1.2+ i686

dscribe-2.1.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (12.5 MB 查看哈希值)

上传时间: CPython 3.9 manylinux: glibc 2.17+ x86-64

dscribe-2.1.1-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl (12.1 MB 查看哈希值)

上传时间: CPython 3.9 manylinux: glibc 2.17+ i686

dscribe-2.1.1-cp39-cp39-macosx_11_0_arm64.whl (690.9 kB 查看哈希值)

上传时间: CPython 3.9 macOS 11.0+ ARM64

dscribe-2.1.1-cp39-cp39-macosx_10_9_x86_64.whl (725.3 kB 查看哈希值)

上传时间: CPython 3.9 macOS 10.9+ x86-64

dscribe-2.1.1-cp38-cp38-win_amd64.whl (543.1 kB 查看哈希值)

上传于 CPython 3.8 Windows x86-64

dscribe-2.1.1-cp38-cp38-win32.whl (507.0 kB 查看哈希值)

上传于 CPython 3.8 Windows x86

dscribe-2.1.1-cp38-cp38-musllinux_1_2_x86_64.whl (13.2 MB 查看哈希值)

上传于 CPython 3.8 musllinux: musl 1.2+ x86-64

dscribe-2.1.1-cp38-cp38-musllinux_1_2_i686.whl (13.0 MB 查看哈希值)

上传于 CPython 3.8 musllinux: musl 1.2+ i686

dscribe-2.1.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (12.5 MB 查看哈希值)

上传于 CPython 3.8 manylinux: glibc 2.17+ x86-64

dscribe-2.1.1-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl (12.2 MB 查看哈希值)

上传于 CPython 3.8 manylinux: glibc 2.17+ i686

dscribe-2.1.1-cp38-cp38-macosx_11_0_arm64.whl (690.6 kB 查看哈希值)

上传于 CPython 3.8 macOS 11.0+ ARM64

dscribe-2.1.1-cp38-cp38-macosx_10_9_x86_64.whl (725.2 kB 查看哈希值)

上传于 CPython 3.8 macOS 10.9+ x86-64

支持者

AWS AWS 云计算和安全赞助商 Datadog Datadog 监控 Fastly Fastly CDN Google Google 下载分析 Microsoft Microsoft PSF 赞助商 Pingdom Pingdom 监控 Sentry Sentry 错误记录 StatusPage StatusPage 状态页面