Label Mapper is a spaCy factory that can receive a mapping dictionary that changes the labels for entities. It should come at the end of the pipeline or after the NER or EntityRuler.
Installation
pip install label-mapper
Usage
nlp = spacy.load("en_core_web_sm")
label_map = {"GPE": "LOC"}
nlp.add_pipe(
"label_fixer",
last=True,
config={"label_map": label_map}
)
doc = nlp("We went into Yellowstone Park in Wyoming.")
for ent in doc.ents:
print(ent.text, ent.label_)
Output:
Yellowstone Park LOC
Wyoming LOC
Metadata
Release files for label-mapper 0.0.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| label_mapper-0.0.1.tar.gz | 1.7 kB | Details |
Release files / label_mapper-0.0.1.tar.gz
| Download URL | label_mapper-0.0.1.tar.gz |
|---|---|
| Size | 1.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
a00904bb4346a0841fcb72d100b93de0d20d4aa2a8efd65cf3513e7fc889f6da
|
|
BLAKE2b-256 checksum How to use checksums |
9e8bc33e5ea4a590fda706dcb35f9c1ac5944434a3594b487b4df8fbb670cba6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/4.0.2 CPython/3.8.5
|