A package for training and evaluating knowledge graph embeddings
Project description
PyKEEN (Python KnowlEdge EmbeddiNgs) is a package for training and evaluating knowledge graph embeddings.
The system has a modular architecture, and can be configured by the user through the command line interface.
Currently, the framework is under development.
Installation
PyKEEN can be installed with the following commands:
python3 -m pip install git+https://github.com/SmartDataAnalytics/PyKEEN.git@master
or in editable mode with:
$ git clone https://github.com/SmartDataAnalytics/PyKEEN.git pykeen
$ cd pykeen
$ python3 -m pip install -e .
How to Use
To start PyKEEN, please run the following command:
pykeen
or alternatively:
python3 -m pykeen
then the command line interface will assist you to configure your experiments.
To start PyKEEN with an existing configuration file, please run the following command:
pykeen -c /path/to/config.json
or alternatively:
python3 -m pykeen -c /path/to/config.json
then the command line interface won’t be called, instead the pipeline will be started immediately.
Starting PyKEEN’s prediction pipeline
To make prediction based on a trained model, please run following command:
pykeen-predict -m /path/to/model/directory -d /path/to/data/directory
or alternatively:
python3 -m pykeen-predict -m /path/to/model/directory -d /path/to/data/directory
Summarize the results of all experiments
To summarize the results of all experiments, please switch to root directory containing the directories for each experiment, and run following command:
pykeen-summarize
or alternatively:
python3 -m pykeen-summarize
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
File details
Details for the file pykeen-0.0.10.tar.gz
.
File metadata
- Download URL: pykeen-0.0.10.tar.gz
- Upload date:
- Size: 59.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/1.12.1 pkginfo/1.4.2 requests/2.19.1 setuptools/40.4.3 requests-toolbelt/0.8.0 tqdm/4.26.0 CPython/3.6.4
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 7f3e5216ba04d7c1729c26715b0b5ad731472fb6ccfbf8a40d39c365abee3994 |
|
MD5 | 42846a9660ade9bd4b9edb30541ffa79 |
|
BLAKE2b-256 | fa16e08d9d044ac2a140e4c472d4cf6940cc7dbf745c58405e1f368a7bd8ca79 |
Provenance
File details
Details for the file pykeen-0.0.10-py3-none-any.whl
.
File metadata
- Download URL: pykeen-0.0.10-py3-none-any.whl
- Upload date:
- Size: 104.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/1.12.1 pkginfo/1.4.2 requests/2.19.1 setuptools/40.4.3 requests-toolbelt/0.8.0 tqdm/4.26.0 CPython/3.6.4
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | aa66a11b645e58c5ac80e4253b1eee64c685a93bdb81fa871f5c2389cc69cac5 |
|
MD5 | 42c746965f928c7929a5ce14e6f6c25b |
|
BLAKE2b-256 | cbc43c91b79193de655d37986db928e88753a909ec3adce314a5597bd2e5ccf8 |