From 0eec74e1a4a8393fe5b7a4c3e46724653886fe68 Mon Sep 17 00:00:00 2001
From: Lukasz Pszenny <lpszenny@hotmail.com>
Date: Thu, 11 May 2023 11:37:17 +0200
Subject: [PATCH] Change of lambo.py name to lambo_tokenizer.py
---
combo/predict.py | 6 +++---
combo/utils/{lambo.py => lambo_tokenizer.py} | 0
docs/prediction.md | 4 ++--
3 files changed, 5 insertions(+), 5 deletions(-)
rename combo/utils/{lambo.py => lambo_tokenizer.py} (100%)
diff --git a/combo/predict.py b/combo/predict.py
index 0423437..9d0b4a6 100644
--- a/combo/predict.py
+++ b/combo/predict.py
@@ -12,7 +12,7 @@ from overrides import overrides
from combo import data
from combo.data import sentence2conllu, tokens2conllu, conllu2sentence
-from combo.utils import download, graph, lambo
+from combo.utils import download, graph, lambo_tokenizer
logger = logging.getLogger(__name__)
@@ -59,7 +59,7 @@ class COMBO(predictor.Predictor):
def predict(self, sentence: Union[str, List[str], List[List[str]], List[data.Sentence]]):
if isinstance(sentence, str):
- if isinstance(self._tokenizer,lambo.LamboTokenizer):
+ if isinstance(self._tokenizer,lambo_tokenizer.LamboTokenizer):
segmented = self._tokenizer.segment(sentence)
return self.predict(segmented)
else:
@@ -239,7 +239,7 @@ class COMBO(predictor.Predictor):
@classmethod
def with_lambo_tokenizer(cls, model: models.Model,
dataset_reader: allen_data.DatasetReader, lambo_model_name : str = 'en'):
- return cls(model, dataset_reader, lambo.LamboTokenizer(lambo_model_name))
+ return cls(model, dataset_reader, lambo_tokenizer.LamboTokenizer(lambo_model_name))
@classmethod
def from_pretrained(cls, path: str, tokenizer=tokenizers.SpacyTokenizer(),
diff --git a/combo/utils/lambo.py b/combo/utils/lambo_tokenizer.py
similarity index 100%
rename from combo/utils/lambo.py
rename to combo/utils/lambo_tokenizer.py
diff --git a/docs/prediction.md b/docs/prediction.md
index 25b7df1..f6fe5ef 100644
--- a/docs/prediction.md
+++ b/docs/prediction.md
@@ -34,10 +34,10 @@ You can use COMBO with the [LAMBO](https://gitlab.clarin-pl.eu/syntactic-tools/l
```python
# Import COMBO and lambo
from combo.predict import COMBO
-from combo.utils import lambo
+from combo.utils import lambo_tokenizer
# Download models
-nlp = COMBO.from_pretrained("english-bert-base-ud29",tokenizer=lambo.LamboTokenizer("en"))
+nlp = COMBO.from_pretrained("english-bert-base-ud29",tokenizer=lambo_tokenizer.LamboTokenizer("en"))
sentences = nlp("This is the first sentence. This is the second sentence to parse.")
```
--
GitLab