mirror/cr-search
1
0
Fork 0
mirror of https://github.com/Findus23/cr-search.git synced 2024-09-19 15:23:44 +02:00
Code Releases Activity

use spacy 3

Browse source
This commit is contained in:
Lukas Winkler 2021-01-18 18:39:40 +01:00
parent f2d9044433
commit 56a52192cd
Signed by: lukas
GPG key ID: 54DE4D798D244853
1 changed files with 3 additions and 3 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
phrases.py
View file

@ -2,10 +2,10 @@ import os
from dataclasses import dataclass from dataclasses import dataclass
from typing import Dict from typing import Dict
import spacy as spacy import en_core_web_md
from alive_progress import alive_bar from alive_progress import alive_bar
from peewee import chunked from peewee import chunked
from spacy.lang.en import English from spacy.lang.en import Language
from spacy.tokens.span import Span from spacy.tokens.span import Span
from spacy.tokens.token import Token from spacy.tokens.token import Token
@ -23,7 +23,7 @@ class Noun:
lemma_cache: Dict[str, str] = {} lemma_cache: Dict[str, str] = {}
nlp: English = spacy.load("en_core_web_sm", disable=["ner", "textcat"]) nlp: Language = en_core_web_md.load(disable=["ner", "textcat"])
nlp.Defaults.stop_words = STOP_WORDS nlp.Defaults.stop_words = STOP_WORDS
for episode in Episode.select().where((Episode.phrases_imported == False) & (Episode.text_imported == True)).order_by( for episode in Episode.select().where((Episode.phrases_imported == False) & (Episode.text_imported == True)).order_by(
Episode.id): Episode.id):