Bar Chart of Frequency of modals in different sections of the Brown Corpus

Natural Language Processing with Python

Chapter 4.8

 colors = 'rgbcmyk' # red, green, blue, cyan, magenta, yellow, black

 def bar_chart(categories, words, counts):
     "Plot a bar chart showing counts for each word by category"
     import pylab

     ind = pylab.arange(len(words))
     width = 0.1*1 / (len(categories) + 1)*10
     bar_groups = []
     for c in range(len(categories)):
         bars = pylab.bar(ind+c*width, counts[categories[c]], width,
                         color=colors[c % len(colors)])
         bar_groups.append(bars)
     pylab.xticks(ind+width, words)
     pylab.legend([b[0] for b in bar_groups], categories, loc='upper left')
     pylab.ylabel('Frequency')
     pylab.title('Frequency of Six Modal Verbs by Genre')
     pylab.show()

 def test_bar_char():
     genres = ['news', 'religion', 'hobbies', 'government', 'adventure']
     modals = ['can', 'could', 'may', 'might', 'must', 'will']
     cfdist = nltk.ConditionalFreqDist(
                 (genre, word)
                 for genre in genres
                 for word in nltk.corpus.brown.words(categories=genre)
                 if word in modals)
     counts = {}
     for genre in genres:
         counts[genre] = [cfdist[genre][word] for word in modals]
     bar_chart(genres, modals, counts)

修改了width,结果为：