python - 如何解决python中不可散列的错误问题？

Question

我有两个文本数据集，所以我进行了清理过程，然后我想根据name列将它们分成几组，但是在运行代码后我得到了错误unhashable type: 'list'

def cleanDataD(path='data1.csv'):
    
    df = pd.read_csv(path, encoding = "ISO-8859-1")
    
    df['name'] = df['name'].fillna(' ')
    df['name'] = df['name'].apply(lambda x: remove_punct(x) )
    df['name'] = df['name'].apply(lambda x: tokenizer.tokenize(x.lower()) )
    df['name'] = df['name'].apply(lambda x: remove_stopWords(x) )
    df['name_CV'] = df['name'].apply(lambda x: word_lemmatiser(x) )            
    df['name_CV'] = df['name_CV'].apply(lambda x: ['none'] if (len(x)== 0) else x)
    
    df['city'] = df['city'].fillna(' ')
    df['city'] = df['city'].apply(lambda x: remove_punct(x) )
    df['city'] = df['city'].apply(lambda x: tokenizer.tokenize(x.lower()) )
    df['city'] = df['city'].apply(lambda x: remove_stopWords(x) )
    df['city_CV']  = df['city'].apply(lambda x: word_lemmatiser(x) )   
    df['city_CV'] = df['city_CV'].apply(lambda x: ['none'] if (len(x)== 0) else x)
    
    df = df.fillna(0)
    return df 

def cleanDataH(path='data2.csv'):
    
    df = pd.read_csv(path, encoding = "utf_8")
    
    df['name'] = df['name'].fillna(' ')
    df['name'] = df['name'].apply(lambda x: remove_punct(x) )
    df['name'] = df['name'].apply(lambda x: tokenizer.tokenize(x.lower()) )
    df['name'] = df['name'].apply(lambda x: remove_stopWords(x) )
    df['name_CV'] = df['name'].apply(lambda x: word_lemmatiser(x) )            
    df['name_CV'] = df['name_CV'].apply(lambda x: ['none'] if (len(x)== 0) else x)
    
    df['city'] = df['city'].fillna(' ')
    df['city'] = df['city'].apply(lambda x: remove_punct(x) )
    df['city'] = df['city'].apply(lambda x: tokenizer.tokenize(x.lower()) )
    df['city'] = df['city'].apply(lambda x: remove_stopWords(x) )
    df['city_CV']  = df['city'].apply(lambda x: word_lemmatiser(x) )   
    df['city_CV'] = df['city_CV'].apply(lambda x: ['none'] if (len(x)== 0) else x)
    
    df = df.fillna(0)
    return df

df_D = cleanDataD(path='data1.csv')
df_H = cleanDataH(path='data2.csv')

indexer =rl.Index()
indexer.block('name')
ff = indexer.index(df_D, df_H)

TypeError                                 Traceback (most recent call last)
<ipython-input-35-c9ee905d6674> in <module>
----> 1 ff = indexer.index(df_H, df_D)

TypeError: unhashable type: 'list'

如何修复此错误？

标签： pythonpandasrecord-linkage