def __init__(self):
self.binary_q = {}
self.unary_q = {}
self.counter = Counts()
self.counter_n = Counts()
self.pi = []
self.bp = []
self.parser = {}
self.use_vert = False
#0.95 curr best
self.beta = 0
self.vm = "\^\<[A-Z]+[+A-Z]*\>"
self.vocab = {}
def __init__(self, parse_file):
counter = Counts()
for l in open(parse_file):
tree = json.loads(l)
counter.count(tree)
#N is 'Non-terminal'=> N[symbol] = count
self.N = counter.nonterm
#binary_R is 'binary Rule' binary_R[symbol, y1, y2] = count
self.binary_R = counter.binary
#unary will be on this form=> unary[symbol, word] = count
self.unary_R = counter.unary
#V is 'vocabulary' and there are 245 words in it.
self.V = counter.vocabulary #245
# pi[i, i, x] = probability
#'pi' is a dictionary, 'i' is the index of the word in the sentence, 'x' is the non-terminal symbol
#'pi[i, i, x]' = 0.03 where 0.03 is the probability of the word at 'i' being assigned to 'x'
self.pi = {}
#'bp' stands for 'back pointer' and it's a dictionary that maps the best rule and best_split to
#the binary table
#'bp[i, i, x]' = [(x,word),i]
self.bp = {}
#binary_table is a dictionary that collects the binary rules derived from one symbol
#binary_table['S'] = [ ('NP', 'VP'), ('NP', 'VP+VERB'), ...]
self.binary_table = defaultdict(set)
self.initialize_binary_table()
def __init__(self):
self.binary_q = {}
self.unary_q = {}
self.counter = Counts()
self.pi = []
self.bp = []
self.parser = {}
self.use_vert = False
import json
from count_cfg_freq import Counts
counter = Counts()
vocab = {}
def loadData(corpus_file):
l = corpus_file.readline()
while (l):
t = json.loads(l)
counter.count(t)
wordList = [y for x, y in extract_tag(t)]
for word in wordList:
if word not in vocab:
vocab[word] = 0
vocab[word] += 1
#for tag in tagList
l = corpus_file.readline()
def extract_tag(t):
if len(t) == 3:
return extract_tag(t[1]) + extract_tag(t[2])
if len(t) == 2:
return [(t[0], t[1])]
def tagRareWord(corpus_file, new_corpus_file):
l = corpus_file.readline()
while (l):