NLTK Lexical Dispersion Plot - word offset to percentile in the x-axis

• cheatsheets

  126 7,256 7.0 Python

  Official Matplotlib cheat sheets (by matplotlib)

  

# Natural Language Toolkit: Dispersion Plots # # Copyright (C) 2001-2022 NLTK Project # Author: Steven Bird # URL: # For license information, see LICENSE.TXT import numpy as np """ A utility for displaying lexical dispersion. """ def dispersion_plot(text, words, ignore_case=False, title="Lexical Dispersion Plot"): """ Generate a lexical dispersion plot. :param text: The source text :type text: list(str) or enum(str) :param words: The target words :type words: list of str :param ignore_case: flag to set if case should be ignored when searching text :type ignore_case: bool """ try: from matplotlib import pylab except ImportError as e: raise ValueError( "The plot function requires matplotlib to be installed." "See https://matplotlib.org/" ) from e text = list(text) words.reverse() if ignore_case: words_to_comp = list(map(str.lower, words)) text_to_comp = list(map(str.lower, text)) else: words_to_comp = words text_to_comp = text points = [ (x, y) for x in range(len(text_to_comp)) for y in range(len(words_to_comp)) if text_to_comp[x] == words_to_comp[y] ] if points: x, y = list(zip(*points)) else: x = y = () pylab.plot(x, y, "b|", scalex=0.1) pylab.yticks(list(range(len(words))), words, color="b") pylab.title(title) pylab.xlabel("Word Offset") pylab.show() if __name__ == "__main__": from nltk.corpus import gutenberg words = ["Elinor", "Marianne", "Edward", "Willoughby"] dispersion_plot(gutenberg.words("austen-sense.txt"), words

• InfluxDB

  www.influxdata.com featured

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

Suggest a related project