Welcome to mirror list, hosted at ThFree Co, Russian Federation.

github.com/MaartenGr/KeyBERT.git - Unnamed repository; edit this file 'description' to name the repository.
summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorMaartenGr <maarten_grootendorst@hotmail.com>2022-08-02 08:46:06 +0300
committerMaartenGr <maarten_grootendorst@hotmail.com>2022-08-02 08:46:06 +0300
commit74c4797436369b52cb9e6d030f2741ef2027449c (patch)
tree52d0edfc9e0327874315df2e14485a0b620c427f
parent9dd7b591cd113a712c4eae7621aa1900c17afa47 (diff)
Fix #122
-rw-r--r--keybert/_model.py2
1 files changed, 2 insertions, 0 deletions
diff --git a/keybert/_model.py b/keybert/_model.py
index 904fcec..8a38660 100644
--- a/keybert/_model.py
+++ b/keybert/_model.py
@@ -74,6 +74,7 @@ class KeyBERT:
Arguments:
docs: The document(s) for which to extract keywords/keyphrases
candidates: Candidate keywords/keyphrases to use instead of extracting them from the document(s)
+ NOTE: This is not used if you passed a `vectorizer`.
keyphrase_ngram_range: Length, in words, of the extracted keywords/keyphrases.
NOTE: This is not used if you passed a `vectorizer`.
stop_words: Stopwords to remove from the document.
@@ -138,6 +139,7 @@ class KeyBERT:
ngram_range=keyphrase_ngram_range,
stop_words=stop_words,
min_df=min_df,
+ vocabulary=candidates,
).fit(docs)
except ValueError:
return []