Neer Match Utilities
neermatch is a framework for entity matching that supports deep
learning, symbolic learning, and hybrid approaches, using neural
networks, gradient boosting, logit, or probit as classifiers. It is
tailored to the needs of economic historians and quantitative
economists, but generalizes to any domain requiring entity matching.
The neermatch framework encompasses three packages:
py-neer-match: ThePythonimplementation of the basic functionalities (ANNs only). Learn morepy-neer-utilities: APythonpackage that provides additional models and functionalities to streamline and support the entity matching workflow. (this project)r-neer-match: TheRimplementation of the basic functionalites. Learn more
The project is financially supported by the Deutsche
Forschungsgemeinschaft (DFG) under Grant
539465691 as part of the Infrastructure Priority Programme New Data
Spaces for the Social Sciences
(SPP 2431). Reading the article Karapanagiotis and Liebald
(2023)
helps to understand the theoretical foundation and design of neermatch
(note that the article refers to an earlier version of the framework,
previously labeled as mlmatch).
The documentation provides examples of how neermatch may be used. The
data used in these examples are available in this
folder
of the GitHub repository.
Contributors
Marius Liebald (maintainer)
Pantelis Karapanagiotis (contributor)
Erik Hellberg (contributor)
Installation
pip install neer-match
pip install neer-match-utilities
Official Documentation
The documentation is hosted under https://www.marius-liebald.com/py-neer-utilities/index.html
License
The package is distributed under the MIT license.
References
Gram, Dennis, Pantelis Karapanagiotis, Marius Liebald, and Uwe Walz. 2022. “Design and Implementation of a Historical German Firm-Level Financial Database.” ACM Journal of Data and Information Quality (JDIQ) 14 (3): 1–22. https://doi.org/10.1145/3531533.
Karapanagiotis, Pantelis, and Marius Liebald. 2023. Entity Matching with Similarity Encoding: A Supervised Learning Recommendation Framework for Linking (Big) Data. http://dx.doi.org/10.2139/ssrn.4541376.
Karapanagiotis, Pantelis, and Marius Liebald. 2024a. NEural-symbolic Entity Reasoning and Matching (Python Neer Match). https://github.com/pi-kappa-devel/py-neer-match.
Karapanagiotis, Pantelis, and Marius Liebald. 2024b. NEural-symbolic Entity Reasoning and Matching (R Neer Match). https://github.com/pi-kappa-devel/r-neer-match.
Lin, Tsung-Yi, Priya Goyal, Ross Girshick, Kaiming He, and Piotr Dollár. 2017. “Focal Loss for Dense Object Detection.” Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2980–88. https://doi.org/10.1109/ICCV.2017.324.
Lipton, Zachary C., Charles Elkan, and Balakrishnan Naryanaswamy. 2014. “Optimal Thresholding of Classifiers to Maximize F1 Measure.” ECML PKDD 2014.
1 maintainer
Metadata
1 maintainer
Release files for neer-match-utilities 1.2.6
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| neer_match_utilities-1.2.6.tar.gz | 108.1 kB | Without provenance | Details for neer_match_utilities-1.2.6.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| neer_match_utilities-1.2.6-py3-none-any.whl | Python 3 | none | any | Details for neer_match_utilities-1.2.6-py3-none-any.whl |
Total release size: 195.0 kB
Release files / neer_match_utilities-1.2.6.tar.gz
| Download URL | neer_match_utilities-1.2.6.tar.gz |
|---|---|
| Size | 108.1 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
dab2d36e096d7a3a9b1860c92975ba2fa0663dd006eebba22c17b0755a4213a5
|
|
BLAKE2b-256 checksum How to use checksums |
e8d8cac111c6ba1f3727cc7c3318d25e6c838cce8e63748adf34cb0fe1ecb057
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.18
|
Release files / neer_match_utilities-1.2.6-py3-none-any.whl
| Download URL | neer_match_utilities-1.2.6-py3-none-any.whl |
|---|---|
| Size | 86.9 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
0c42073478a344cc316c094721deec917ee6ef40c851eb94577975478182e7cd
|
|
BLAKE2b-256 checksum How to use checksums |
faa04392dfc36beddb3248161789c571bcb92b3245e9b4217dd3a7541d01ff2d
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.11.18
|
Security for neer-match-utilities 1.2.6
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
