Created
January 30, 2021 12:48
-
-
Save gidgid/c24e9efdaf4713cfc98da5213dd7757b to your computer and use it in GitHub Desktop.
we use more_itertools flatten to do a much better job
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from typing import Dict, Set | |
from more_itertools import flatten | |
def flatten_multivalues(key_to_values: Dict[str, Set[int]]) -> Set[int]: | |
return set(flatten(key_to_values.values())) | |
def test_flattens_multivalue_dicts(): | |
# shamelessly taken from: https://www.elastic.co/blog/found-elasticsearch-from-the-bottom-up | |
term_to_document_indices = { | |
"choice": {3}, | |
"coming": {1}, | |
"fury": {2}, | |
"is": {1, 2, 3}, | |
"the": {2, 3}, | |
} | |
all_document_indices = flatten_multivalues(term_to_document_indices) | |
assert all_document_indices == {1, 2, 3} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment