Topic modeling with text networks
Project description
Topic Network - topic modeling with text networks
This package introduces a novel method for topic modeling using community detection in complex networks. The algorithms included in the package first create a network of collocated terms, filter out unimportant words based on centrality measures, and then use community detection to reveal the topic groups in the network.
The methods used are language-agnostic, meaning that you can perform the topic modeling on any text in any language.
It is an early version, hence there might be performance issues when modeling big corpora. These are to be resolved in upcoming updates.
Installation
To install the current version of the package, use:
pip install topicnetwork
Use
To find the topics, simply use:
import topicnetwork
topics = topicnetwork.find_topics(list_of_strings)
For best results, use a text without punctuation and stopwords, and words converted to lowercase. You can perform the cleaning on your English texts with:
text = topicnetwork.clean(list_of_strings)
Notes
Package written and maintained by Michal Pikusa (pikusa.michal@gmail.com)
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file topicnetwork-0.1.4.tar.gz
.
File metadata
- Download URL: topicnetwork-0.1.4.tar.gz
- Upload date:
- Size: 2.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/1.12.1 pkginfo/1.4.2 requests/2.18.4 setuptools/39.1.0 requests-toolbelt/0.8.0 tqdm/4.26.0 CPython/3.6.5
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 6aadfcb16cd61f0affd93e911e757d4fdf0ebf943db6f752cce51fa0a5946655 |
|
MD5 | 14b5d86b50566c0de6dd0e40c4ddb2f0 |
|
BLAKE2b-256 | 20e48126d0c902d811920accfa1084249daa78664a7af753055f9d22e73ece4d |
File details
Details for the file topicnetwork-0.1.4-py3-none-any.whl
.
File metadata
- Download URL: topicnetwork-0.1.4-py3-none-any.whl
- Upload date:
- Size: 2.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/1.12.1 pkginfo/1.4.2 requests/2.18.4 setuptools/39.1.0 requests-toolbelt/0.8.0 tqdm/4.26.0 CPython/3.6.5
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 43adb145ad867403d351dec2711165aff657ed9b8ab2213ff2dadff6f845d9b7 |
|
MD5 | d4c3ca9fe09bf2dcda31fc08788c73bc |
|
BLAKE2b-256 | 73f8eb07053e3034646c02d3be4394eddfa1a4792d253857ab96984495f85702 |