Python创建不重复词表

Question

为什么最后出现的结果和别人的不一样呢？

Answer 1

用set就能不重复

def loadDataSet():
    postingList = [['my', 'dog', 'has', 'flea', 'problems', 'help', 'please'],
                   ['maybe', 'not', 'take', 'him', 'to', 'dog', 'park', 'stupid'],
                   ['my', 'dalmation', 'is', 'so', 'cute', 'I', 'love', 'him'],
                   ['stop', 'posting', 'stupid', 'worthless', 'garbage'],
                   ['mr', 'licks', 'ate', 'my', 'steak', 'how', 'to', 'stop', 'him'],
                   ['quit', 'buying', 'worthless', 'dog', 'food', 'stupid']]
    return postingList
 
def createVocabList(dataSet):
    vocabSet = set([])  # 创建空集合
    for document in dataSet:
        vocabSet = vocabSet | set(document) # 取并集
    return list(vocabSet)
 
word = loadDataSet()
word_set = createVocabList(word)
print(word_set)