ngram.py - Uni/Bi-gram finder and sentence generator Run from the command line using the following command python ngram.py -f <filename> [options] <filename> is the path to the corpus file you would like to parse Options: -s enables stemming default: disabled python ngram.py -f Dataset3/train.txt -s -f <filename> adds <filename> to the train set python ngram.py -f Dataset3/Train.txt -f Dataset3/Test.txt -pp <filename> calculates the perplexity of the model given <filename> as test data python ngram.py -f Dataset3/Train.txt -pp Dataset3/Test.txt -w <word> sets <word> as the first word in the sentence generator, otherwise chosen randomly default: random word from corpus python ngram.py -f Dataset3/Train.txt -w once -l <length> sets the minimum sentence length to the number <length> default: 20 -p <length> sets the passage length to the number <length> default: 100 Example: python ngram.py -f Dataset3/Train.txt -f Dataset3/Test.txt -w the -l 15 -p 5 -s