fix: use spacy-download (#8)

acryldata · Nov 15, 2022 · e9ab334 · e9ab334
1 parent f253f62
commit e9ab334
Show file tree

Hide file tree

Showing 3 changed files with 3 additions and 3,391 deletions.
diff --git a/datahub-classify/setup.py b/datahub-classify/setup.py
@@ -17,7 +17,7 @@ def get_long_description():
     "spacy==3.4.1",
     "phonenumbers==8.12.56",
     "pandas==1.5.0",
-    "en_core_web_sm @ https://github.com/explosion/spacy-models/releases/download/en_core_web_sm-3.4.1/en_core_web_sm-3.4.1.tar.gz",
+    "spacy-download==1.0.0"
 }
 
 dev_requirements = {

diff --git a/datahub-classify/src/datahub_classify/infotype_helper.py b/datahub-classify/src/datahub_classify/infotype_helper.py
@@ -5,7 +5,7 @@
 import numpy as np
 import pandas as pd
 import phonenumbers
-import spacy
+from spacy_download import load_spacy
 
 from datahub_classify.constants import (
     DATATYPE,
@@ -24,9 +24,8 @@
     match_regex_for_values,
 )
 
-# logging.basicConfig(filename='logs.log', encoding='utf-8', level=logging.DEBUG)
 logger = logging.getLogger(__name__)
-nlp_english = spacy.load("en_core_web_sm")
+nlp_english = load_spacy("en_core_web_sm")
 spacy_models_list = [nlp_english]