Automatically Assigning Industry Classifications to Company Descriptions – An Entailment Based Approach
Description
naicskit is a Python package which assigns industry classification codes to descriptions of companies. This model leverages the Huggingface library and an entailment-based approach for assigning taxonomy codes with the hopes that this will make the model robust with unseen taxonomies. Based on initial results, the model has an 87% accuracy on taxonomies it was trained on and 81% accuracy on unseen taxonomies.
How To Use naicskit
from naicskit.coder import IndustryCoder
description = '...'
coder = IndustryCoder('naics.2022','2')
results = coder.code_records(description)
Supported Taxonomies
- International Standard of Industrial Classification Rev 5.0 (ISIC 2024)
isic.2024 - International Standard of Industrial Classification Rev 4.0 (ISIC 2006)
isic.2006 - International Standard of Industrial Classification Rev 3.1 (ISIC 2002)
isic.2002 - International Standard of Industrial Classification Rev 3.0 (ISIC 1989)
isic.1989 - International Standard of Industrial Classification Rev 2.0 (ISIC 1968)
isic.1968 - North American Industry Classification System 2022 (NAICS 2022)
naics.2022 - North American Industry Classification System 2017 (NAICS 2017)
naics.2017 - North American Industry Classification System 2012 (NAICS 2012)
naics.2012 - North American Industry Classification System 2007 (NAICS 2007)
naics.2007 - Standard Industrial Classification (SIC 1987)
sic.1987
Release files for naicskit 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| naicskit-0.1.0.tar.gz | 203.6 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| naicskit-0.1.0-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 416.8 kB
Release files / naicskit-0.1.0.tar.gz
| Download URL | naicskit-0.1.0.tar.gz |
|---|---|
| Size | 203.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
5d46e2cdbf5c0edb08a45361a5b337cf9efcfc6e8102e7fc44979cb484c555bf
|
|
BLAKE2b-256 checksum How to use checksums |
d038c39dc8cc03848fb9fcd04f8183ce3c323d23680108d2d9cbc6dab1596609
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.6.1 CPython/3.11.4 Darwin/22.4.0
|
Release files / naicskit-0.1.0-py3-none-any.whl
| Download URL | naicskit-0.1.0-py3-none-any.whl |
|---|---|
| Size | 213.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
a11477dcf100f86758d33c4465923a2b34632eea656369f99bea7c8362d5c47c
|
|
BLAKE2b-256 checksum How to use checksums |
1b6194d04662266280523ca49b097cf65f7da5500c1fb28a201b1f9fa35f6752
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
poetry/1.6.1 CPython/3.11.4 Darwin/22.4.0
|