library to explain models for Entity Resolution
Project description
ExplainER
ERExplain is a package to explain any Entity Resolution model, using a Black-Box approach
Key Features
The explanations can be provided into two different ways:
- Attribute-Level: the system shows to the user a histogram reporting the importance of the attributes with respect to the prediction. The importance is a number in [0,1]
- Value-level: the system shows to the user, for each chosen attribute set/single attribute A, the most influential values for A, with respect to the prediction
Tech
Dillinger uses some well-know libraries:
Installation
To install the package simply run
$ pip install erexplain
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
erexplain-0.1.2.tar.gz
(4.7 kB
view hashes)
Built Distribution
erexplain-0.1.2-py3-none-any.whl
(10.1 kB
view hashes)
Close
Hashes for erexplain-0.1.2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 2cf266ebad30e36c3b825642f336950184d8e92a477b86372dad9ff9b22aa387 |
|
MD5 | ba6bb8e7229257bbd60a806986f9e79e |
|
BLAKE2b-256 | 5cef331a578f3e43edd913654374a062f76199d99484354143be5eabf7782517 |