spaCyで学ぶNatural Language Processing
Azadeh Mobasher
Principal Data Scientist
spaCyはまずテキストをトークン化し、Docオブジェクトを生成Docは複数の段階からなる処理パイプラインで順次処理される
import spacy
nlp = spacy.load("en_core_web_sm")
doc = nlp(example_text)
spaCyのNERパイプライン:print([ent.text for ent in doc.ents])
sentencizer: 文分割用のspaCyパイプラインコンポーネントtext = " ".join(["This is a test sentence."]*10000)en_core_sm_nlp = spacy.load("en_core_web_sm") start_time = time.time() doc = en_core_sm_nlp(text)print(f"Finished processing with en_core_web_sm model in {round((time.time() - start_time)/60.0 , 5)} minutes")
>>> Finished processing with en_core_web_sm model in 0.09332 minutes
sentencizerパイプを追加:blank_nlp = spacy.blank("en")blank_nlp.add_pipe("sentencizer")start_time = time.time() doc = blank_nlp(text) print(f"Finished processing with blank model in {round((time.time() - start_time)/60.0 , 5)} minutes")
>>> Finished processing with blank model in 0.00091 minutes
nlp.analyze_pipes()はspaCyのパイプラインを分析し、次を確認:
prettyをTrueにすると、構造化データの返却に加え、表として出力import spacy
nlp = spacy.load("en_core_web_sm")
analysis = nlp.analyze_pipes(pretty=True)
spaCyで学ぶNatural Language Processing