Skip to main content

Module for conversational and text summarization and much more

Project description

A python module for conversation and text summarization and much more exciting features.

Features provided by this module:

  • Text Segmentation using:

    • TextTiling with Block Score

    • TextTiling with Vocabulary introduction

  • Conversational summarization using:

    • Cluster Rank

  • Text summarization using :

    • TextRank

    • Random

Installation

Make sure you have Python 2.7/3.3+ and pip(Windows, Linux) installed. Run simply (preferred way):

$ [sudo] pip install readless

Or for the latest version in development:

$ [sudo] pip install git+git://github.com/adichat/read-less.git

ReadLess API

You can use readless like a library in your project.

For quickly summarizing a conversation using ClusterRank algorithm:

# -*- coding: utf8 -*-

from readless.Summarization import clusterrank
summarizer = clusterrank.ClusterRank()
pathToFile = "C:/conversation.in"
summary = summarizer.summarizeFile(pathToFile)

For segmenting a text using TextTiling algorithm:

# -*- coding: utf8 -*-

from readless.Segmentation import texttiling
segmentation = texttiling.TextTiling()
pathToFile = "C:/conversation.in"
segmentedText = segmentation.segmentFile(pathToFile)

For a detailed list of other API functionalities, see **ReadLess Documentation**.

Contributions

All contributions are welcomed. This module is in development and there are several scopes of improvement. Tests are to be implemented along with other Summarization algorithms with support for web page summarization. For upcoming features, see Future developments.

LICENSE

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

readless-1.0.17.zip (14.2 kB view details)

Uploaded Source

File details

Details for the file readless-1.0.17.zip.

File metadata

  • Download URL: readless-1.0.17.zip
  • Upload date:
  • Size: 14.2 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No

File hashes

Hashes for readless-1.0.17.zip
Algorithm Hash digest
SHA256 6d10f151f531136ac8cf0a15b23f659691454ac16b3ee4d948230fd7b460041f
MD5 f829132f5acc31f8932bfb579feec505
BLAKE2b-256 4b4f9805168a38944990be1f5d9f43c092fdd92228d63abab1fe87e9c8ff0aea

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page