Skip to main content

A library for pair probability prediction using machine learning.

Project description

XMFlib

XMFlib 是一个基于机器学习的位点对概率预测库,适用于表面科学和材料模拟领域。它通过预训练的神经网络模型,能够根据输入的相互作用能、温度和覆盖度,快速预测不同类型的配对概率。


特性

  • 支持多种表面类型(如 100, 111 晶面)
  • 内置多层感知机(MLP)模型,推理高效
  • 简单易用的 API,便于集成到科研和工程项目
  • 兼容 PyTorch,易于扩展和自定义模型

安装

pip install XMFlib

使用示例

from XMFlib.PairProbML import PairProbPredictor

predictor = PairProbPredictor()
result = predictor.predict(
    facet=100,                  # 晶面类型,可选 '100' 或 '111'
    interaction_energy=0.2,    # 相互作用能 (eV)
    temperature=400,            # 温度 (K)
    main_coverage=0.5           # 主组分覆盖度 (0~1)
)
print(result)
# 输出示例: {'vacancy_pair': 0.12, 'species_pair': 0.34, 'species_vacancy_pair': 0.54}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

xmflib-0.1.4.tar.gz (56.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

xmflib-0.1.4-py3-none-any.whl (54.9 kB view details)

Uploaded Python 3

File details

Details for the file xmflib-0.1.4.tar.gz.

File metadata

  • Download URL: xmflib-0.1.4.tar.gz
  • Upload date:
  • Size: 56.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.9.21

File hashes

Hashes for xmflib-0.1.4.tar.gz
Algorithm Hash digest
SHA256 70f67718901134f40ad23874c10ae48a973921b2fee85389fa800c3a42f79893
MD5 d7a1e2b8e4d4881a55c05cbeff46d4cc
BLAKE2b-256 d2783d3dfc3024f85e11fb5f97ffed5dfddf9f0d1f8e36f61dcf06cdcf7cefc8

See more details on using hashes here.

File details

Details for the file xmflib-0.1.4-py3-none-any.whl.

File metadata

  • Download URL: xmflib-0.1.4-py3-none-any.whl
  • Upload date:
  • Size: 54.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.9.21

File hashes

Hashes for xmflib-0.1.4-py3-none-any.whl
Algorithm Hash digest
SHA256 6c1fad79cb4db21791de47a135af51906fdf1504a02bc9c846f263f5fbcb2f54
MD5 55357b40dc9c0a1e42f480b5871adb61
BLAKE2b-256 c7cdee502a163642cc92387ec32435b9af5eb7c7daf91996e8ec19408901e8c0

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page