Converting NLTK chunks to a list of dictionaries

Question

I need to get a list of dictionaries from an example nltk tree below:

   (S
      I/PRP
      'll/MD
      have/VB
      (amount 1/CD)
      (plate pizza/NN)
      and/CC
      (amount 4/CD)
      (plate sandwiches/NNS))

The desired output is as follows

  [{amount: 1, plate: pizza}, {amount: 4, plate: sandwiches}]

I have tried the code below but I only get one dictionary list: [{amount: 4, plate: sandwiches}] It looks like the list does not append new entries, it only updates the same dictionary.

import nltk
from nltk.chunk import *
from nltk.chunk.util import *
from nltk.chunk.regexp import *
from nltk import Tree

training = []
hmm_tagger = HiddenMarkovModelTagger.train(training)
sentence = "I'll have 1 pizza and 4 sandwiches"
gram = r"""
plate:      {<NN|NNS>}                    
amount:    {<CD|DT>}
        """
cp = nltk.RegexpParser(gram)
for sent in sentence:
    tokens = nltk.word_tokenize(sent)
    taggex = hmm_tagger.tag(tokens)
treee = cp.parse(taggex)
iob_ts = tree2conlltags(treee)
tree = conlltags2tree(iob_ts)
def conversion(tree):
    dlist = []
    for leaf in tree:
        if type(leaf) == tuple:
            for leaf in tree:
                key = leaf.label()
                value = leaf[0][0]
                dlist =[dict(zip(key, value)) for leaf in tree]              
    return dlist

Answer 1

The main issue here is that you are not appending after each loop iteration, both inside and outside the conversion function.

from nltk.chunk.regexp import RegexpParser
from nltk import Tree, pos_tag
from nltk.tokenize import word_tokenize, sent_tokenize

gram = r"""
plate:      {<NN|NNS>}                    
amount:    {<CD|DT>}
"""
cp = RegexpParser(gram)

text = "I'll have 1 pizza and 4 sandwiches"

def conversion(tree):
    dlist = []
    d = dict()
    for item in tree:
        if isinstance(item, Tree):
            d[item.label()] = ' '.join([l[0] for l in item.leaves()])
        else:
            dlist.append(d) if len(d)>0 else None
            d = dict()
    dlist.append(d) if len(d)>0 else None
    return dlist

parsed_text = [cp.parse(pos_tag(word_tokenize(sent)))
               for sent in sent_tokenize(text)]

for tree in parsed_text:
    print(conversion(tree))
#[{'amount': '1', 'plate': 'pizza'}, {'amount': '4', 'plate': 'sandwiches'}]