Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

modify DatasetWalker to be subscriptable #5

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

modify DatasetWalker to be subscriptable #5

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
61 changes: 38 additions & 23 deletions scripts/dataset_walker.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,12 +1,13 @@
import os
import json
import os

from scripts.knowledge_reader import KnowledgeReader


class DatasetWalker(object):
def __init__(self, dataset, dataroot, labels=False, labels_file=None, incl_knowledge=False):
path = os.path.join(os.path.abspath(dataroot))

if dataset not in ['train', 'val']:
raise ValueError('Wrong dataset name: %s' % (dataset))

Expand All @@ -31,29 +32,43 @@ def __iter__(self):
if self.labels is not None:
for log, label in zip(self.logs, self.labels):
if self._incl_knowledge is True and label['target'] is True:
for idx, snippet in enumerate(label['knowledge']):
domain = snippet['domain']
entity_id = snippet['entity_id']
doc_type = snippet['doc_type']
doc_id = snippet['doc_id']

if doc_type == 'review':
sent_id = snippet['sent_id']
sent = self._knowledge.get_review_sent(domain, entity_id, doc_id, sent_id)
label['knowledge'][idx]['sent'] = sent

elif doc_type == 'faq':
doc = self._knowledge.get_faq_doc(domain, entity_id, doc_id)
question = doc['question']
answer = doc['answer']

label['knowledge'][idx]['question'] = question
label['knowledge'][idx]['answer'] = answer

yield(log, label)
label = self.resolve_knowledge(label)
yield (log, label)
else:
for log in self.logs:
yield(log, None)
yield (log, None)

def __len__(self, ):
return len(self.logs)

def __getitem__(self, item):
if self.labels is not None:
log = self.logs[item]
label = self.labels[item]
if self._incl_knowledge is True and label['target'] is True:
label = self.resolve_knowledge(label)
return (log, label)
else:
return (self.logs[item], None)

def resolve_knowledge(self, label):
for idx, snippet in enumerate(label['knowledge']):
domain = snippet['domain']
entity_id = snippet['entity_id']
doc_type = snippet['doc_type']
doc_id = snippet['doc_id']

if doc_type == 'review':
sent_id = snippet['sent_id']
sent = self._knowledge.get_review_sent(domain, entity_id, doc_id, sent_id)
label['knowledge'][idx]['sent'] = sent

elif doc_type == 'faq':
doc = self._knowledge.get_faq_doc(domain, entity_id, doc_id)
question = doc['question']
answer = doc['answer']

label['knowledge'][idx]['question'] = question
label['knowledge'][idx]['answer'] = answer

return label