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([])  # 建立空集合
    for document in dataSet:
        vocabSet = vocabSet | set(document) # 取並集
    return list(vocabSet)

word = loadDataSet()
word_set = createVocabList(word)
print(word_set)
 

輸出：（可以看到輸出沒有重複詞彙）

['stop', 'not', 'stupid', 'how', 'food', 'him', 'posting', 'worthless', 'I', 'has', 'please', 'dalmation', 'licks', 'problems', 'help', 'garbage', 'buying', 'maybe', 'my', 'to', 'quit', 'flea', 'so', 'mr', 'dog', 'park', 'is', 'love', 'steak', 'ate', 'take', 'cute']