Performs user classification into labels using a set of seed Twitter users with known labels andthe structure of the interaction network between them.
Project description
Performs user classification into labels using a set of seed Twitter users with known labels and the structure of the interaction network between them.
Features
Graph-based, multi-label user classification platform.
Implementation of the ARCTE (Absorbing Regularized Commute Times Embedding) algorithm for graph-based feature extraction.
Both python vanilla and cython-optimized versions.
Implementation of other feature extraction methods for graphs (Laplacian Eigenmaps, Louvain, MROC).
Evaluation score and time benchmarks.
Install
### Required packages - numpy - scipy - scikit-learn - Cython - h5py - python-louvain - [reveal-user-annotation](https://github.com/MKLab-ITI/reveal-user-annotation)
### Installation To install for all users on Unix/Linux:
python3.4 setup.py build sudo python3.4 setup.py install
Alternatively:
pip install reveal-user-classification
Reveal-FP7 Integration
There is one console entry point:
user_network_profile_classifier assessment_id
where assessment_id is the address of a MongoDB instance.
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
Hashes for reveal-user-classification-0.1.17.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 97a87a2de6858bc5d15d9bc40223de9bae6a8698676a45065f47ecea67b3c4d9 |
|
MD5 | e2c2de9c74aa3f347c8f0b8ffdc27159 |
|
BLAKE2b-256 | 94013c1c9071e41bdf1fa628239de599f36c9726b3229c889cd9394f3a8da06e |