https://github.com/gelbpunkt/bookgen

Generates books based on other books using nltk
https://github.com/gelbpunkt/bookgen

Last synced: 5 days ago
JSON representation

Generates books based on other books using nltk

• Host: GitHub
• URL: https://github.com/gelbpunkt/bookgen
• Owner: Gelbpunkt
• License: mit
• Created: 2019-01-10T18:07:37.000Z (about 6 years ago)
• Default Branch: master
• Last Pushed: 2019-01-10T18:25:51.000Z (about 6 years ago)
• Last Synced: 2024-08-09T23:48:46.262Z (5 months ago)
• Language: Python
• Size: 4.88 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# bookgen

A python library using nltk to analyse two books and generate a new one.

## Installation

`pip install bookgen`

## Usage

```py

from bookgen import BookGen

book = BookGen("word_base_book.txt", "sentence_base_book.txt")

# book.download() will download the nltk extras required, only needed once

print(book.run())

```

## Explanation

BookGen will parse word classes from the first specified book, looking like this:

`{"NOUN": ["Mountain", "Valley"], "VERB": ["take", "went"]}`

These are sorted by the nltk universal tagset.

The second book serves as sentence base. It will be parsed into a list of word types that represent the whole book.

`["NOUN", "VERB", "PREP", "NOUN", "CONJ", "VERB", "."]`

Then, it generates a list of words from the words of the first book based on the second book.

`["Nathan", "went", "to", "Valley", "and", "peed", "."]`

This is joined with some capitalization fixes and returned.