Skip to content

Commit

Permalink
fix all tokenizations for unknown
Browse files Browse the repository at this point in the history
  • Loading branch information
djstrong committed Feb 13, 2024
1 parent 0cbc847 commit 07e7117
Showing 1 changed file with 0 additions and 14 deletions.
14 changes: 0 additions & 14 deletions generator/xgenerator.py
Original file line number Diff line number Diff line change
Expand Up @@ -341,22 +341,8 @@ def is_already_sampled(suggestion: str) -> bool:
only_available_suggestions = self.random_available_name_pipeline.apply(name, None)
grouped_suggestions['other'] = list(islice(only_available_suggestions, other_suggestions_number))

# unique_tokenizations3 = list(uniq([(i.tokenization for i in ints) for ints in name.interpretations.values()]))

for ints in name.interpretations.values():
for i in ints:
print(i.tokenization)
# print((i.tokenization for i in ints))

unique_tokenizations = list(uniq([i.tokenization for ints in name.interpretations.values() for i in ints]))

# unique_tokenizations2 = set(reduce(list.__add__,
# [[i.tokenization for i in ints] for ints in name.interpretations.values()]))

print(unique_tokenizations)
# print(unique_tokenizations2)
# print(unique_tokenizations3)

return all_related_suggestions, grouped_suggestions, unique_tokenizations


0 comments on commit 07e7117

Please sign in to comment.