# comment out lines dependent on methods that you haven't yet implemented
print "Statistics for", self.filename
print self.numsents, "sentences"
print self.numtokens, "word tokens"
print self.numtypes, "word types"
print '{0:.2f} average tokens per type'.format(self.numtokens/self.numtypes)
print '{0:.2f} average sentence length'.format(self.numtokens/self.numsents)
print '{0:.2f} average word token length'.format(expectation(self.token_lengths))
print '{0:.2f} average word type length'.format(expectation(self.type_lengths))
print "Hapax legomena comprise {0:.2%} of the types".format(num_hapaxes(self.word_counts)/self.numtypes)
#self.plot_freq(self.filename+'_freq.png')
#self.plot_lengths(self.filename+'_lengths.png')
if __name__=='__main__':
filename = sys.argv[1]
corpus = Corpus(filename, casefold=True)
corpus.display_stats()
print
word_model = NGram(1, 'word', corpus.word_counts)
word_model.display_stats()
print
char_model = NGram(1, 'character', corpus.char_counts)
char_model.display_stats()
print '{0:.2f} average tokens per type'.format(self.numtokens /
self.numtypes)
print '{0:.2f} average sentence length'.format(self.numtokens /
self.numsents)
print '{0:.2f} average word token length'.format(
expectation(self.token_lengths))
print '{0:.2f} average word type length'.format(
expectation(self.type_lengths))
print "Hapax legomena comprise {0:.2%} of the types".format(
num_hapaxes(self.word_counts) / self.numtypes)
#self.plot_freq(self.filename+'_freq.png')
#self.plot_lengths(self.filename+'_lengths.png')
if __name__ == '__main__':
filename = sys.argv[1]
corpus = Corpus(filename, casefold=True)
corpus.display_stats()
print
word_model = NGram(1, 'word', corpus.word_counts)
word_model.display_stats()
print
char_model = NGram(1, 'character', corpus.char_counts)
char_model.display_stats()
