Explainable Leaderboards for Natural Language Processing
Project description
ExplainaBoard SDK
Reconstruct ExplainaBoard into OOP Version
Installation
- for SDK users:
pip install explainaboard
- for SDK developers: clone repo and run
pip install .
inside the repo- use
pip install -e .
for developer install. This is only useful in certain situations. Please see python documentation for this option.
- use
How to use SDK
from explainaboard import TaskType, get_loader, get_processor
path_data = "./explainaboard/tests/artifacts/test-summ.tsv"
loader = get_loader(TaskType.summarization, data = path_data)
data = loader.load()
processor = get_processor(TaskType.summarization, data = data)
analysis = processor.process()
analysis.write_to_directory("./")
Existing Support More
TaskType.text_classification
FileType.tsv
TaskType.named_entity_recognition
FileType.conll
TaskType.summarization
FileType.tsv
TaskType.extractive_qa
FileType.json
(same format with squad)
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
explainaboard-0.4.2.tar.gz
(509.7 kB
view details)
Built Distribution
File details
Details for the file explainaboard-0.4.2.tar.gz
.
File metadata
- Download URL: explainaboard-0.4.2.tar.gz
- Upload date:
- Size: 509.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.7.1 importlib_metadata/4.10.0 pkginfo/1.8.2 requests/2.27.1 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.9.9
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 15a657af181cac353ab86da3ac9c929ba35e39362cbcfd3077142d1ecd2de648 |
|
MD5 | 41b5a044efb612e28d0b96c2c14d9b03 |
|
BLAKE2b-256 | 9ee731e48e79f11641d6880cc567bea3bed4c89c0b0bb57c7b92d82e7b6ea6cb |
File details
Details for the file explainaboard-0.4.2-py2.py3-none-any.whl
.
File metadata
- Download URL: explainaboard-0.4.2-py2.py3-none-any.whl
- Upload date:
- Size: 529.2 kB
- Tags: Python 2, Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.7.1 importlib_metadata/4.10.0 pkginfo/1.8.2 requests/2.27.1 requests-toolbelt/0.9.1 tqdm/4.62.3 CPython/3.9.9
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 9076e158330084a4d409b980dc634d950b30f0aa089136335be5e33058881b6e |
|
MD5 | 6db62dded7c1b1b386ea1f1945ef5b01 |
|
BLAKE2b-256 | d68c655613dd32923a4ac4601ae6cb2ce5dedb8b6833cc86e30a3417c206b337 |