nlp assignment 2

assignment2.py

import nltk
from nltk import PCFG, CFG
from nltk.draw.tree import draw_trees

# out cfg
cfg_grammar = CFG.fromstring("""
 S -> NP VP
 NP -> ART N | N N | N | NP PP
 VP -> V | V NP | V NP PP
 PP -> P NP
 ART -> 'a'
 N -> 'flower' | 'a' | 'blooms'
 V -> 'blooms' | 'flower'
 """)

# out pcfg
pcfg_grammar = PCFG.fromstring("""
 S -> NP VP [1.0]
 NP -> ART N [0.53] | N N [0.09] | N [0.14] | NP PP [0.24]
 VP -> V [0.386] | V NP [0.393] | V NP PP [0.22]
 PP -> P NP [1.0]
 ART -> 'a' [1.0]
 N -> 'flower' [0.8] | 'a' [0.1] | 'blooms' [0.1]
 V -> 'blooms' [0.8] | 'flower' [0.2]
 """)

# sentence to be parsed
sentence = ['a','flower','blooms']

def question1():
    bu_chart_parser2 = nltk.BottomUpChartParser(cfg_grammar)
    trees = bu_chart_parser2.parse(sentence)
    for item in trees:
        print(item)
        draw_trees(item)

def question2():
    parser = nltk.ViterbiParser(pcfg_grammar)
    trees = parser.parse(sentence)
    for item in trees:
        print(item)
        draw_trees(item)

def question3():
    parser = nltk.InsideChartParser(pcfg_grammar)
    trees = parser.parse(sentence)
    total = 0.0
    for item in trees:
        tree_prob = item.__dict__['_ProbabilisticMixIn__prob']
        print("probability of each tree = {}".format(tree_prob))
        total += item.__dict__['_ProbabilisticMixIn__prob']
        draw_trees(item)
    print("\nTotal probability = {}".format(total))