Unsupervised automatic keyphrase extraction

Project description

SemCluster

Unsupervised Automatic Keyphrase Extraction Using Affinity Propagation

Installation

Clone this Repo and its submodules using

git clone --recurse-submodules git@code.siemens.com:palle.klewitz/semcluster.git

Install esa-wiki

cd ESA-Wiki
python3 setup.py sdist bdist_wheel
pip3 install dist/wiki_esa-0.0.1-py3-none-any.whl
cd ..

Install semcluster

python3 setup.py sdist bdist_wheel
pip3 install dist/semcluster-0.0.1-py3-none-any.whl

Usage

from semcluster import SemClusterKeywordExtractor

text = "The quick brown fox jumps over the lazy dog."

# Instantiate extractor
e = SemClusterKeywordExtractor()

# Extract phrases
keyphrases = e.extract_keyphrases(text, seed_threshold=0.7, verbose=True)

Project details

Release history Release notifications | RSS feed

This version

0.0.1

Mar 4, 2019

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

semcluster-0.0.1.tar.gz (34.6 MB view details)

Uploaded Mar 4, 2019 Source

Built Distribution

semcluster-0.0.1-py3-none-any.whl (35.1 MB view details)

Uploaded Mar 4, 2019 Python 3

File details

Details for the file semcluster-0.0.1.tar.gz.

File metadata

Download URL: semcluster-0.0.1.tar.gz
Upload date: Mar 4, 2019
Size: 34.6 MB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: twine/1.12.1 pkginfo/1.5.0.1 requests/2.18.4 setuptools/40.8.0 requests-toolbelt/0.9.1 tqdm/4.23.3 CPython/3.6.5

File hashes

Hashes for semcluster-0.0.1.tar.gz
Algorithm	Hash digest
SHA256	`43b5d31fa6360f26e173995ba7664ec06991ff618a4de792e4a53788dfc80d31`
MD5	`a8d0030b6b2330b40b0b96c48522608a`
BLAKE2b-256	`92a447a949950c05458dd09fdc43c457061941c27fdf8bf1f14c1e903761b241`

See more details on using hashes here.

File details

Details for the file semcluster-0.0.1-py3-none-any.whl.

File metadata

Download URL: semcluster-0.0.1-py3-none-any.whl
Upload date: Mar 4, 2019
Size: 35.1 MB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: twine/1.12.1 pkginfo/1.5.0.1 requests/2.18.4 setuptools/40.8.0 requests-toolbelt/0.9.1 tqdm/4.23.3 CPython/3.6.5

File hashes

Hashes for semcluster-0.0.1-py3-none-any.whl
Algorithm	Hash digest
SHA256	`ac29f4ec9c3e8f9fe674b214abaae9bd44e066d1f452705096b70f329aa2060e`
MD5	`0f49113b1760596f9c3e88d69424b60c`
BLAKE2b-256	`34006d0a7bb2c325ce3a29346a2f76ee99994aeff25ad5f64274658fb96da236`