在Python中使用NLTK库实现对词干的提取的教程

sudo pip install nltk

sudo pip install pandas

sudo pip install ipython

mkdir Codes
cd Codes
ipython notebook

from pandas import DataFrame
import pandas as pd
d = ['pets insurance','pets insure','pet insurance','pet insur','pet insurance"','pet insu']
df = DataFrame(d)
df.columns = ['Words']
df

import nltk
tokenizer = nltk.RegexpTokenizer(r'w+')

df["Stemming Words"] = ""
df["Count"] = 1

j = 0
while (j <= 5):
  for word in tokenizer.tokenize(df["Words"][j]):
    df["Stemming Words"][j] = df["Stemming Words"][j] + " " + nltk.PorterStemmer().stem_word(word)
  j += 1
df

uniqueWords = df.groupby(['Stemming Words'], as_index = False).sum().sort(['Count'])
uniqueWords

sudo pip install enchant

import enchant
from nltk.metrics import edit_distance
class SpellingReplacer(object):
  def __init__(self, dict_name='en', max_dist=2):
    self.spell_dict = enchant.Dict(dict_name)
    self.max_dist = 2
  def replace(self, word):
    if self.spell_dict.check(word):
      return word
    suggestions = self.spell_dict.suggest(word)
    if suggestions and edit_distance(word, suggestions[0]) <=
      self.max_dist:
      return suggestions[0]
    else:
      return word

from replacers import SpellingReplacer
replacer = SpellingReplacer()
replacer.replace('insu')

'insu'

import Levenshtein
minDistance = 0.8
distance = -1
lastWord = ""
j = 0
while (j < 1):
   lastWord = uniqueWords["Stemming Words"][j]
   distance = Levenshtein.ratio(uniqueWords["Stemming Words"][j], uniqueWords["Stemming Words"][j + 1])
   if (distance > minDistance):
    uniqueWords["Stemming Words"][j] = uniqueWords["Stemming Words"][j + 1]
  j += 1
uniqueWords

uniqueWords = uniqueWords.groupby(['Stemming Words'], as_index = False).sum()
uniqueWords