texta-bert-tagger

Name	texta-bert-tagger JSON
Version	3.0.1 JSON
	download
home_page	https://git.texta.ee/texta/texta-bert-tagger-python
Summary	texta-bert-tagger
upload_time	2023-04-25 13:52:46
maintainer
docs_url	None
author	TEXTA
requires_python
license	GPLv3
keywords
VCS
bugtrack_url
requirements	No requirements were recorded.
Travis-CI	No Travis.
coveralls test coverage	No coveralls.

            # TEXTA Bert Tagger

![Py3.8](https://img.shields.io/badge/python-3.8-green.svg)
![Py3.9](https://img.shields.io/badge/python-3.9-green.svg)

## Installation

##### Using built package
`pip install texta-bert-tagger`

##### Using Git
`pip install git+https://git.texta.ee/texta/texta-bert-tagger-python.git`

### Testing

`python -m pytest -v tests`

### Documentation

Documentation for version 1.* is available [here](https://git.texta.ee/texta/texta-bert-tagger-python/-/wikis/Documentation-v1.*).

Documentation for version 2.* is available [here](https://git.texta.ee/texta/texta-bert-tagger-python/-/wikis/Documentation-v2.*).

Documentation for version 3.* is available [here](https://git.texta.ee/texta/texta-bert-tagger-python/-/wikis/Documentation-v3.*).

## Usage (for versions >=3.*.*)

### Fine-tune BERT model

```python
from texta_bert_tagger.tagger import BertTagger
bert_tagger = BertTagger()

data_sample = {"good": ["It was a nice day.", "All was well."], "bad": ["It was horrible.", "What a disaster."]}

# Train a model

# pos_label - used in metrics (precision, recall, f1-score etc) calculations as true label
bert_tagger.train(data_sample, pos_label="bad", n_epochs=2)

# Predict
result = bert_tagger.tag_text("How awful!")
print(result)
```

#### Output

```
[{"prediction": "bad", "probability": 0.55200404, "attributions": []}]
```

            

Raw data

            {
    "_id": null,
    "home_page": "https://git.texta.ee/texta/texta-bert-tagger-python",
    "name": "texta-bert-tagger",
    "maintainer": "",
    "docs_url": null,
    "requires_python": "",
    "maintainer_email": "",
    "keywords": "",
    "author": "TEXTA",
    "author_email": "info@texta.ee",
    "download_url": "https://files.pythonhosted.org/packages/bc/42/f31bf0b0f6b2b6ebfebb0a91dd8be54156dd908013658d817848d4d86bd1/texta-bert-tagger-3.0.1.tar.gz",
    "platform": null,
    "description": "# TEXTA Bert Tagger\n\n![Py3.8](https://img.shields.io/badge/python-3.8-green.svg)\n![Py3.9](https://img.shields.io/badge/python-3.9-green.svg)\n\n## Installation\n\n##### Using built package\n`pip install texta-bert-tagger`\n\n##### Using Git\n`pip install git+https://git.texta.ee/texta/texta-bert-tagger-python.git`\n\n### Testing\n\n`python -m pytest -v tests`\n\n### Documentation\n\nDocumentation for version 1.* is available [here](https://git.texta.ee/texta/texta-bert-tagger-python/-/wikis/Documentation-v1.*).\n\nDocumentation for version 2.* is available [here](https://git.texta.ee/texta/texta-bert-tagger-python/-/wikis/Documentation-v2.*).\n\nDocumentation for version 3.* is available [here](https://git.texta.ee/texta/texta-bert-tagger-python/-/wikis/Documentation-v3.*).\n\n## Usage (for versions >=3.*.*)\n\n### Fine-tune BERT model\n\n```python\nfrom texta_bert_tagger.tagger import BertTagger\nbert_tagger = BertTagger()\n\ndata_sample = {\"good\": [\"It was a nice day.\", \"All was well.\"], \"bad\": [\"It was horrible.\", \"What a disaster.\"]}\n\n# Train a model\n\n# pos_label - used in metrics (precision, recall, f1-score etc) calculations as true label\nbert_tagger.train(data_sample, pos_label=\"bad\", n_epochs=2)\n\n# Predict\nresult = bert_tagger.tag_text(\"How awful!\")\nprint(result)\n```\n\n#### Output\n\n```\n[{\"prediction\": \"bad\", \"probability\": 0.55200404, \"attributions\": []}]\n```\n",
    "bugtrack_url": null,
    "license": "GPLv3",
    "summary": "texta-bert-tagger",
    "version": "3.0.1",
    "split_keywords": [],
    "urls": [
        {
            "comment_text": "",
            "digests": {
                "blake2b_256": "bc42f31bf0b0f6b2b6ebfebb0a91dd8be54156dd908013658d817848d4d86bd1",
                "md5": "800f5ffa75a5232d84ab78a5c080f25e",
                "sha256": "9f69f687edbf40a3401b3c0372b98ef93fd1ad4763ca263903aae60688d3f80c"
            },
            "downloads": -1,
            "filename": "texta-bert-tagger-3.0.1.tar.gz",
            "has_sig": false,
            "md5_digest": "800f5ffa75a5232d84ab78a5c080f25e",
            "packagetype": "sdist",
            "python_version": "source",
            "requires_python": null,
            "size": 30515,
            "upload_time": "2023-04-25T13:52:46",
            "upload_time_iso_8601": "2023-04-25T13:52:46.436248Z",
            "url": "https://files.pythonhosted.org/packages/bc/42/f31bf0b0f6b2b6ebfebb0a91dd8be54156dd908013658d817848d4d86bd1/texta-bert-tagger-3.0.1.tar.gz",
            "yanked": false,
            "yanked_reason": null
        }
    ],
    "upload_time": "2023-04-25 13:52:46",
    "github": false,
    "gitlab": false,
    "bitbucket": false,
    "lcname": "texta-bert-tagger"
}