TEXTA Tagger
Installation
Using built package
pip install texta-tagger
Using Git (for development)
pip install git+https://git.texta.ee/texta/texta-tagger.git
Usage
Predicting Using Zipped Model
Predicting without MLP & lemmatization
>>> from texta_tagger.tagger import Tagger
>>>
>>> t = Tagger()
>>> t.load_zip('test_data/tagger.zip')
True
>>> print('Tagger:', t)
Tagger: Eesti
>>> t.tag_text('eesti keel ja eesti meel')
{'prediction': True, 'probability': 0.9999999322365133}
Predicting with MLP & lemmatization
Predicting with lemmatization requires either a running MLP server or MLP Python package installed. In following example MLP from package is used:
>>> from texta_tagger.tagger import Tagger
>>> from texta_mlp.mlp import MLP
>>>
>>> mlp = MLP()
>>>
>>> t = Tagger(mlp=mlp)
>>> t.load_zip('test_data/tagger.zip')
True
>>> print('Tagger:', t)
Tagger: Eesti
>>> t.tag_text('eesti keel ja eesti meel')
{'prediction': True, 'probability': 0.9999999322365133}
In following example MLP server version is used:
>>> from texta_tagger.tagger import Tagger
>>> from texta_tagger.mlp_analyzer import get_mlp_analyzer
>>>
>>> mlp = get_mlp_analyzer(mlp_host="http://my-mlp-server:5000")
>>>
>>> t = Tagger(mlp=mlp)
>>> t.load_zip('test_data/tagger.zip')
True
>>> print('Tagger:', t)
Tagger: Eesti
>>> t.tag_text('eesti keel ja eesti meel')
{'prediction': True, 'probability': 0.9999999322365133}
Training
TODO
Environment Variables
- TEXTA_TAGGER_MLP_URL - MLP host used for lemmatization (e.g. http://mlp-dev.texta.ee:5000)
- TEXTA_TAGGER_MLP_MAJOR_VERSION - MLP major version (2/3).
1 maintainer
Release files for texta-tagger 3.3.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| texta-tagger-3.3.0.tar.gz | 23.1 kB | Details |
Release files / texta-tagger-3.3.0.tar.gz
| Download URL | texta-tagger-3.3.0.tar.gz |
|---|---|
| Size | 23.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
b493ab73164089feca3d2a51986b9fadaadc7fb4b49d07feeb31947911146da8
|
|
BLAKE2b-256 checksum How to use checksums |
09db0fde25633c8a87983d1e942794313ae755bc5538ff128a5224eabbf327ef
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.8.0 pkginfo/1.9.6 readme-renderer/34.0 requests/2.27.1 requests-toolbelt/0.10.1 urllib3/1.26.14 tqdm/4.64.1 importlib-metadata/4.8.3 keyring/23.4.1 rfc3986/1.5.0 colorama/0.4.5 CPython/3.6.14
|
