1、基于 nltk 包

  1. from nltk.stem.porter import PorterStemmer
  2. from nltk.stem.lancaster import LancasterStemmer
  3. from nltk.stem import SnowballStemmer
  6. # jy: 基于 Porter 词干提取算法 =========================
  7. porter_stemmer = PorterStemmer()
  9. word_stem = porter_stemmer.stem("multiply")
  10. # jy: "multipli"
  11. print(word_stem)
  14. # jy: 基于 Lancaster 词干提取算法 ======================
  15. lancaster_stemmer = LancasterStemmer()
  16. word_stem = lancaster_stemmer.stem("multiply")
  17. # jy: "multiply"
  18. print(word_stem)
  21. # jy: 基于 Snowball 词干提取算法 ======================
  22. snowball_stemmer = SnowballStemmer("english")
  23. word_stem = snowball_stemmer.stem("multiply")
  24. # jy: "multipli"
  25. print(word_stem)

2、基于 spacy 包（非严格意义上的词干提取）

  1. import spacy
  3. nlp = spacy.load("en_core_web_sm")
  5. str_words = "multiply successfully others leaf leaves"
  6. doc = nlp(str_words)
  7. ls_lemma = [i.lemma_ for i in doc]
  9. # jy: ['multiply', 'successfully', 'other', 'leaf', 'leave']
  10. print(ls_lemma)