PWACT is an open-source automated active learning platform based on PWMLFF for efficient data sampling.
Project description
Dependencies
Please refer to the user manual
-
AL-PWMLFF job scheduling uses the SLURM cluster management and job scheduling system. SLURM must be installed on your computing cluster.
-
DFT calculations in AL-PWMLFF support PWmat, VASP, CP2K and DFTB. We have integrated DFTB in PWmat. You can find detailed usage instructions in the
DFTB_DETAIL sectionof thePWmat Manual. -
AL-PWMLFF model training is based on
PWMLFF. Refer to thePWMLFF documentationfor installation instructions (Download address for PWmat version integrated with DFTB). -
AL-PWMLFF Lammps molecular dynamics simulation is based on Lammps_for_pwmlff. Refer to the
Lammps_for_pwmlff documentationfor installation instructions.
Installation Process
You can install it through the pip command or the github source code installation.
install by pip
pip install pwact
from github
Code Download
git clone https://github.com/LonxunQuantum/PWact.git
Then import environment variable.
export PATH=/data/home/wuxingxing/codespace/al_pwmlff/bin:$PATH
AL-PWMLFF is developed in Python and supports Python 3.9 and above. It is recommended to use the Python runtime environment provided by PWMLFF.
If you need to create a virtual environment for AL-PWMLFF separately, you only need to install the following dependent packages (compatible with your Python version, Python >= 3.9).
pip install numpy pandas tqdm pwdata
Command List
AL-PWMLFF includes the following commands, which are not case sensitive. The starting command is pwact
1. Display the available command list
pwact [ -h / --help / help ]
2. Display the parameter list for cmd_name:
pwact cmd_name -h
3. Initial Training Set Preparation
pwact init_bulk param.json resource.json
4. Active Learning
pwact run param.json resource.json
For the 3-th and 4-th command above, the names of the JSON files can be modified by the user, but it is required that the input order of param.json and resouce.json cannot be changed.
5. Tool Commands
Convert MOVEMENT or OUTCAR to PWdata format
pwact to_pwdata
Search for labeled datasets in the active learning directory
pwact gather_pwdata
examples download
from github
https://github.com/LonxunQuantum/PWact/tree/main/pwact/example
from BaiduNetdisk included the calculation results of examples
https://pan.baidu.com/s/14E0u_7cpntiBZgg-C1S5XA?pwd=pwmt
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file pwact-0.1.10.tar.gz.
File metadata
- Download URL: pwact-0.1.10.tar.gz
- Upload date:
- Size: 93.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.0.0 CPython/3.10.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d369012f34e5dd327d57239eeb96e17b391e2c856458bb2de11ceae025dc7a13
|
|
| MD5 |
c3af80a2944e9c4570e88c73593e56e2
|
|
| BLAKE2b-256 |
d1d2890154fcf2f1045a5a08d7a3da9208ababed79482e4fe01212b3861ab188
|
File details
Details for the file pwact-0.1.10-py3-none-any.whl.
File metadata
- Download URL: pwact-0.1.10-py3-none-any.whl
- Upload date:
- Size: 112.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/5.0.0 CPython/3.10.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e6bcf2edba58eaff2978843625526658b1ae9ce8e92fbeff9767a5eee0f0db2e
|
|
| MD5 |
4835881d8e7e1d9bb74e21034d6b22f7
|
|
| BLAKE2b-256 |
4f1aeb22d6e9c3fc1f66ab78e9fa26a70dda65e4c83a0995f39883435a44f929
|