python - 调用 process.extract 时出现 TypeError : ('expected string or bytes-like object' , 'occurred at index 0' )

Question

当我尝试使用 fuzzywuzzy 中的 process.extract 时，收到以下错误消息pandas DataFrame 中的列上的库:

TypeError: ('expected string or bytes-like object', 'occurred at index 0')

背景

我有以下示例df:

from fuzzywuzzy import fuzz 
from fuzzywuzzy import process
import pandas as pd
import nltk 

name_list = ['John D Doe', 'Jane L Doe', 'Jack Doe']
text_list = [' Reason for Visit: John D Doe is a Jon has male pattern baldness',
       'Jane is related to John and Jan L Doe is his sister  ',
            'Jack Doe is thier son and jac is five']
df = pd.DataFrame(
    {'Names': name_list,
     'Text': text_list,
     'P_ID': [1,2,3]

    })
#tokenize
df['Token_Names'] = df.apply(lambda row: nltk.word_tokenize(row['Names']), axis=1)
df['Token_Text'] = df.apply(lambda row: nltk.word_tokenize(row['Text']), axis=1)

#df
    Names        Text                         P_ID  Token_Names     Token_Text
0   John D Doe  Reason for Visit: John D Doe    1   [John, D, Doe]  [Reason, for, Visit, :, John, D, Doe, is, a, J...
1   Jane L Doe  Jane is related to John         2   [Jane, L, Doe]  [Jane, is, related, to, John, and
2   Jack Doe    Jack Doe is thier son           3   [Jack, Doe]     [Jack, Doe, is, thier, son, and, jac, is, five]

问题

我创建了以下函数

def get_alt_names(token_name, token_text):
    if len(token_name) > 1:

          extract = process.extract(token_name,token_text, limit = 3, scorer = fuzz.ratio)
    return extract

我使用lambda和apply

 #use apply with extract
 df['Alt_Names'] = df.apply(lambda x: get_alt_names(x.Token_Names, x.Token_Text) , axis =1)

但我收到以下错误:

TypeError                                 Traceback (most recent call last)
<ipython-input-12-6dcc99fa91b0> in <module>()
      1 #use apply with extract
----> 2 df['Alt_Names'] = df.apply(lambda x: get_alt_names(x.Token_Names, x.Token_Text) , axis =1)

C:\Anaconda\lib\site-packages\pandas\core\frame.py in apply(self, func, axis, broadcast, raw, reduce, result_type, args, **kwds)
   6002                          args=args,
   6003                          kwds=kwds)
-> 6004         return op.get_result()
   6005 
   6006     def applymap(self, func):

C:\Anaconda\lib\site-packages\pandas\core\apply.py in get_result(self)
    140             return self.apply_raw()
    141 
--> 142         return self.apply_standard()
    143 
    144     def apply_empty_result(self):

C:\Anaconda\lib\site-packages\pandas\core\apply.py in apply_standard(self)
    246 
    247         # compute the result using the series generator
--> 248         self.apply_series_generator()
    249 
    250         # wrap results

C:\Anaconda\lib\site-packages\pandas\core\apply.py in apply_series_generator(self)
    275             try:
    276                 for i, v in enumerate(series_gen):
--> 277                     results[i] = self.f(v)
    278                     keys.append(v.name)
    279             except Exception as e:

<ipython-input-12-6dcc99fa91b0> in <lambda>(x)
      1 #use apply with extract
----> 2 df['Alt_Names'] = df.apply(lambda x: get_alt_names(x.Token_Names, x.Token_Text) , axis =1)

<ipython-input-10-360a3b67e5d2> in get_alt_names(token_name, token_text)
      5     #if len(token_name) inside token_names_unlisted > 1:
      6     if len(token_name) > 1:
----> 7         extract = process.extract(token_name,token_text, limit = 3, scorer = fuzz.ratio)
      8         return extract

C:\Anaconda\lib\site-packages\fuzzywuzzy\process.py in extract(query, choices, processor, scorer, limit)
    166     """
    167     sl = extractWithoutOrder(query, choices, processor, scorer)
--> 168     return heapq.nlargest(limit, sl, key=lambda i: i[1]) if limit is not None else \
    169         sorted(sl, key=lambda i: i[1], reverse=True)
    170 

C:\Anaconda\lib\heapq.py in nlargest(n, iterable, key)
    567     # General case, slowest method
    568     it = iter(iterable)
--> 569     result = [(key(elem), i, elem) for i, elem in zip(range(0, -n, -1), it)]
    570     if not result:
    571         return result

C:\Anaconda\lib\heapq.py in <listcomp>(.0)
    567     # General case, slowest method
    568     it = iter(iterable)
--> 569     result = [(key(elem), i, elem) for i, elem in zip(range(0, -n, -1), it)]
    570     if not result:
    571         return result

C:\Anaconda\lib\site-packages\fuzzywuzzy\process.py in extractWithoutOrder(query, choices, processor, scorer, score_cutoff)
     76 
     77     # Run the processor on the input query.
---> 78     processed_query = processor(query)
     79 
     80     if len(processed_query) == 0:

C:\Anaconda\lib\site-packages\fuzzywuzzy\utils.py in full_process(s, force_ascii)
     93         s = asciidammit(s)
     94     # Keep only Letters and Numbers (see Unicode docs).
---> 95     string_out = StringProcessor.replace_non_letters_non_numbers_with_whitespace(s)
     96     # Force into lowercase.
     97     string_out = StringProcessor.to_lower_case(string_out)

C:\Anaconda\lib\site-packages\fuzzywuzzy\string_processing.py in replace_non_letters_non_numbers_with_whitespace(cls, a_string)
     24         numbers with a single white space.
     25         """
---> 26         return cls.regex.sub(" ", a_string)
     27 
     28     strip = staticmethod(string.strip)

TypeError: ('expected string or bytes-like object', 'occurred at index 0')

我认为这是因为我的输入是一个列表

所需输出

我希望输出看起来像下面这样(也许是列表的列表？)

 Other_Columns_Here    Alt_Names
0                 [('John', 100), ('Jon', 86), ('Reason', 40)][('D', 100), ('Doe', 50), ('baldness', 22)][('Doe', 100), ('D', 50), ('baldness', 36)]
1                 [('Jane', 100), ('Jan', 86), ('and', 57)] [('L', 100), ('related', 25), ('Jane', 0)][('Doe', 100), ('to', 40), ('and', 33)]
2                 [('Doe', 100), ('to', 40), ('and', 33)] [('Doe', 100), ('son', 33), ('and', 33)]

问题

如何修复我的错误？

Answer 1

我认为您需要更改 get_alt_names 使其看起来更像以下版本:

from fuzzywuzzy import fuzz
from fuzzywuzzy import process
import pandas as pd
import nltk

name_list = ['John D Doe', 'Jane L Doe', 'Jack Doe']
text_list = [
    'Reason for Visit: John D Doe is a Jon has male pattern baldness',
    'Jane is related to John and Jan L Doe is his sister  ',
    'Jack Doe is their son and jac is five'
]
df = pd.DataFrame({
        'Names': name_list,
        'Text': text_list,
        'P_ID': [1,2,3]
    })

df['Token_Names'] = df.apply(lambda row: nltk.word_tokenize(row['Names']), axis=1)
df['Token_Text'] = df.apply(lambda row: nltk.word_tokenize(row['Text']), axis=1)

def get_alt_names(s):
    token_names = s['Token_Names']
    token_text = s['Token_Text']
    extract = list()
    for name in token_names:
        if len(name) > 1:
            result = process.extract(name, token_text, limit=3, scorer=fuzz.ratio)
            extract.append(result)
    return extract

df['Alt_Names'] = df.apply(get_alt_names, axis=1)

print(df)

输出

0    [[(John, 100), (Jon, 86), (Reason, 40)], [(Doe...
1    [[(Jane, 100), (Jan, 86), (and, 57)], [(Doe, 1...
2    [[(Jack, 100), (jac, 86), (and, 29)], [(Doe, 1...
Name: Alt_Names, dtype: object

此代码可以运行，但您可能仍然需要修改它才能获得您想要的确切结果。具体来说，我不确定您是否希望 'Alt_Names' 成为列表的列表或只是列表。