pip3 install -U spacy -i http://pypi.douban.com/simple --trusted-host pypi.douban.com
python3 -m spacy download en
在终端里输一下就完事了
# import stanfordnlp # nlp = stanfordnlp.Pipeline() # doc = nlp("Barack Obama was born in Hawaii. He was elected president in 2008.") # doc.sentences[0].print_dependencies() import spacy s="Everything will be OK in the end,if it's not OK,it's not the end." nlp=spacy.load("en_core_web_sm") doc=nlp(s) # 利用空格分开 print(doc.text.split()) # 利用token的.orth_方法，可以识别标点符号 print([token.orth_ for token in doc]) # 带下划线的方法返回字符、不带下划线的方法返回数字 print([(token, token.orth_, token.orth) for token in doc]) # 分词，去除标点和空格 print([token.orth_ for token in doc if not token.is_punct | token.is_space]) # 标准化到基本形式 #practice = "practice practiced practicing" #nlp_practice = nlp(practice) #print([word.lemma_ for word in nlp_practice])