Parsernaam: Predict First and Last Name
-----------------------------------------
.. image:: https://github.com/appeler/parsernaam/actions/workflows/python-package.yml/badge.svg
:target: https://github.com/appeler/parsernaam/actions?query=workflow%3A%22Python+package%22
.. image:: https://img.shields.io/pypi/v/parsernaam.svg
:target: https://pypi.python.org/pypi/parsernaam
.. image:: https://static.pepy.tech/badge/parsernaam
:target: https://pepy.tech/project/parsernaam
Most common name parsers use crude pattern matching and the sequence of strings, e.g., the last word is the last name, to parse names. This approach is limited and fragile, especially for Indian names. We take a machine-learning approach to the problem. Using the large voter registration data in India and US, we build machine-learning-based name parsers that predict whether the string is a first or last name.
For Indian electoral rolls, we assume the last name is the word in the name that is shared by multiple family members. (We table the expansion to include compound last names---extremely rare in India---till the next iteration.)
Gradio App.
-----------
`parsernaam on HF <https://huggingface.co/spaces/sixtyfold/parsernaam>`_
Installation
------------
.. code-block:: bash
pip install parsernaam
General API
-----------
The general API is as follows:
::
# Import the library
from parsernaam.parsernaam import ParseNames
positional arguments:
df dataframe with Names to parse (with column name 'name')
# example
df = pd.DataFrame({'name': ['Jan', 'Nicholas Turner', 'Petersen', 'Nichols Richard', 'Piet',
'John Smith', 'Janssen', 'Kim Yeon']})
df = ParseNames.parse(df)
print(df.to_markdown())
::
| | name | parsed_name |
|---:|:----------------|:------------------------------------------------------------------------------|
| 0 | Jan | {'name': 'Jan', 'type': 'first', 'prob': 0.6769440174102783} |
| 1 | Nicholas Turner | {'name': 'Nicholas Turner', 'type': 'first_last', 'prob': 0.9990382194519043} |
| 2 | Petersen | {'name': 'Petersen', 'type': 'last', 'prob': 0.5342262387275696} |
| 3 | Nichols Richard | {'name': 'Nichols Richard', 'type': 'last_first', 'prob': 0.9998832941055298} |
| 4 | Piet | {'name': 'Piet', 'type': 'first', 'prob': 0.5381495952606201} |
| 5 | John Smith | {'name': 'John Smith', 'type': 'first_last', 'prob': 0.9975730776786804} |
| 6 | Janssen | {'name': 'Janssen', 'type': 'first', 'prob': 0.5929554104804993} |
| 7 | Kim Yeon | {'name': 'Kim Yeon', 'type': 'last_first', 'prob': 0.9987115859985352} |
Data
----
The model is trained on names from the Florida Voter Registration Data from early 2022.
The data are available on the `Harvard Dataverse <http://dx.doi.org/10.7910/DVN/UBIG3F>`__
Authors
-------
Rajashekar Chintalapati and Gaurav Sood
Contributing
------------
Contributions are welcome. Please open an issue if you find a bug or have a feature request.
License
-------
The package is released under the `MIT License <https://opensource.org/licenses/MIT>`_.
Raw data
{
"_id": null,
"home_page": "https://github.com/appeler/parsernaam",
"name": "parsernaam",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "parse names",
"author": "Rajashekar Chintalapati, Gaurav Sood",
"author_email": "rajshekar.ch@gmail.com, gsood07@gmail.com",
"download_url": "https://files.pythonhosted.org/packages/2c/eb/599dd959b7b709b8e3307f70dcec70f954c195ca8f951a8d14058ec96438/parsernaam-0.0.4.tar.gz",
"platform": null,
"description": "Parsernaam: Predict First and Last Name\n-----------------------------------------\n\n.. image:: https://github.com/appeler/parsernaam/actions/workflows/python-package.yml/badge.svg\n :target: https://github.com/appeler/parsernaam/actions?query=workflow%3A%22Python+package%22\n.. image:: https://img.shields.io/pypi/v/parsernaam.svg\n :target: https://pypi.python.org/pypi/parsernaam\n.. image:: https://static.pepy.tech/badge/parsernaam\n :target: https://pepy.tech/project/parsernaam\n\nMost common name parsers use crude pattern matching and the sequence of strings, e.g., the last word is the last name, to parse names. This approach is limited and fragile, especially for Indian names. We take a machine-learning approach to the problem. Using the large voter registration data in India and US, we build machine-learning-based name parsers that predict whether the string is a first or last name. \n\nFor Indian electoral rolls, we assume the last name is the word in the name that is shared by multiple family members. (We table the expansion to include compound last names---extremely rare in India---till the next iteration.)\n\nGradio App.\n-----------\n`parsernaam on HF <https://huggingface.co/spaces/sixtyfold/parsernaam>`_\n\nInstallation\n------------\n.. code-block:: bash\n\n pip install parsernaam\n\nGeneral API\n-----------\n\nThe general API is as follows:\n\n::\n\n # Import the library\n from parsernaam.parsernaam import ParseNames\n\n positional arguments:\n df dataframe with Names to parse (with column name 'name')\n\n # example\n df = pd.DataFrame({'name': ['Jan', 'Nicholas Turner', 'Petersen', 'Nichols Richard', 'Piet',\n 'John Smith', 'Janssen', 'Kim Yeon']})\n df = ParseNames.parse(df)\n print(df.to_markdown())\n\n::\n\n | | name | parsed_name |\n |---:|:----------------|:------------------------------------------------------------------------------|\n | 0 | Jan | {'name': 'Jan', 'type': 'first', 'prob': 0.6769440174102783} |\n | 1 | Nicholas Turner | {'name': 'Nicholas Turner', 'type': 'first_last', 'prob': 0.9990382194519043} |\n | 2 | Petersen | {'name': 'Petersen', 'type': 'last', 'prob': 0.5342262387275696} |\n | 3 | Nichols Richard | {'name': 'Nichols Richard', 'type': 'last_first', 'prob': 0.9998832941055298} |\n | 4 | Piet | {'name': 'Piet', 'type': 'first', 'prob': 0.5381495952606201} |\n | 5 | John Smith | {'name': 'John Smith', 'type': 'first_last', 'prob': 0.9975730776786804} |\n | 6 | Janssen | {'name': 'Janssen', 'type': 'first', 'prob': 0.5929554104804993} |\n | 7 | Kim Yeon | {'name': 'Kim Yeon', 'type': 'last_first', 'prob': 0.9987115859985352} |\n\n\nData\n----\n\nThe model is trained on names from the Florida Voter Registration Data from early 2022.\nThe data are available on the `Harvard Dataverse <http://dx.doi.org/10.7910/DVN/UBIG3F>`__\n\n\nAuthors\n-------\n\nRajashekar Chintalapati and Gaurav Sood\n\nContributing\n------------\n\nContributions are welcome. Please open an issue if you find a bug or have a feature request.\n\nLicense\n-------\n\nThe package is released under the `MIT License <https://opensource.org/licenses/MIT>`_.\n\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Name parser",
"version": "0.0.4",
"project_urls": {
"Homepage": "https://github.com/appeler/parsernaam"
},
"split_keywords": [
"parse",
"names"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "69b04ef135b494af3ac44ad21acbb119a977116b1275aa4bf37c121ef52672ad",
"md5": "594ca673166a6ba5203c91d2ffd7f472",
"sha256": "d72c23879858bc906d09979a4a36cad4abcafa2bc9858921731d1afdb7736ccd"
},
"downloads": -1,
"filename": "parsernaam-0.0.4-py2.py3-none-any.whl",
"has_sig": false,
"md5_digest": "594ca673166a6ba5203c91d2ffd7f472",
"packagetype": "bdist_wheel",
"python_version": "py2.py3",
"requires_python": null,
"size": 8145924,
"upload_time": "2023-10-11T20:10:44",
"upload_time_iso_8601": "2023-10-11T20:10:44.942827Z",
"url": "https://files.pythonhosted.org/packages/69/b0/4ef135b494af3ac44ad21acbb119a977116b1275aa4bf37c121ef52672ad/parsernaam-0.0.4-py2.py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "2ceb599dd959b7b709b8e3307f70dcec70f954c195ca8f951a8d14058ec96438",
"md5": "cdffa8788c3ad171dc9018c4e8ba9132",
"sha256": "6e6904fdad9efbe96a78e99825bee37d3970d9730083cbb847fcef27dad14ae2"
},
"downloads": -1,
"filename": "parsernaam-0.0.4.tar.gz",
"has_sig": false,
"md5_digest": "cdffa8788c3ad171dc9018c4e8ba9132",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 8142688,
"upload_time": "2023-10-11T20:10:48",
"upload_time_iso_8601": "2023-10-11T20:10:48.400115Z",
"url": "https://files.pythonhosted.org/packages/2c/eb/599dd959b7b709b8e3307f70dcec70f954c195ca8f951a8d14058ec96438/parsernaam-0.0.4.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-10-11 20:10:48",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "appeler",
"github_project": "parsernaam",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"requirements": [],
"lcname": "parsernaam"
}
JSON
