Source code for sussex_nltk.util

'''
.. codeauthor::
    Matti Lyra
'''

import random
import matplotlib.pyplot as plt


def lexical_diversity(text):
    return len(text) / (len(set(text)) + 0.0)

def percentage(count, total):
    return 100 * count / (total + 0.0)

def sample_from_corpus(corpus,sample_size):
    n = corpus.enumerate_sents()
    sample_indices = set(random.sample(xrange(n),sample_size))
    return [sent for i,sent in enumerate(corpus.sents()) if i in sample_indices]

def zipf_dist(freqdist,num_of_ranks=50,show_values=True):
    '''
    Given a frequency distribution object, rank all types
    in order of frequency of occurrence (where rank 1 is most
    frequent word), and plot the ranks against the frequency
    of occurrence. If num_of_ranks=20, then 20 types will
    be plotted.
    If show_values = True, then display the bar values above them.
    '''
    x = range(1,num_of_ranks+1)                #x values are the ranks of types
    y = freqdist.values()[:num_of_ranks]       #y values are the frequencies of the ranked types
    plt.bar(x,y,color="#1AADA4")            #plot a bar graph of x and y
    plt.xlabel("Rank of types ordered by frequency of occurrence")
    plt.ylabel("Frequency of occurrence")   #set the label of the y axis
    plt.grid(True)                          #display grid on graph
    plt.xticks(range(1,num_of_ranks+1,2),range(1,num_of_ranks+1,2))  #set what values appears on the x axis
    plt.xlim([0,num_of_ranks+2])            #limit the display on the x axis
    if show_values:                            #if show_values is True, then show the y values on the bars
        for xi,yi in zip(x,y):
            plt.text(xi+0.25,yi+50,yi,verticalalignment="bottom",rotation=55,fontsize="small")
    plt.show()                              #display the graph
    print "Plot complete."