Python：导入 csv 忽略单个逗号

Question

我在下面有一个 csv 文件，它可以正常工作：

Test Case ID,summary

TC-16610,“verify that user is able to u_pdate 'active' attribute  'false ' on adding “new category records” using 'v3/definition/categories' PUT API on specifying the 'active' attribute 'true'”
TC-16609,“verify that user is able to u_pdate 'active' attribute  'true ' on adding “new category records” using 'v3/definition/categories' PUT API on specifying the 'active' attribute 'false'”

但如果我添加单个逗号，则无法解析：

Test Case ID,summary
,
TC-16610,“verify that user is able to u_pdate 'active' attribute  'false ' on adding “new category records” using 'v3/definition/categories' PUT API on specifying the 'active' attribute 'true'”
TC-16609,“verify that user is able to u_pdate 'active' attribute  'true ' on adding “new category records” using 'v3/definition/categories' PUT API on specifying the 'active' attribute 'false'”

即使只有一个逗号，我也想解析 csv 文件。它应该跳过并解析或验证解析。谁能帮我解决这个问题。

我的代码...我在 django 中使用它：

class CsvUpload(forms.Form):
    csv_file = forms.FileField()

    def clean_csv_file(self):
        # Probably worth doing this check first anyway
        value = self.cleaned_data['csv_file']
        if not value.name.endswith('.csv'):
            raise forms.ValidationError('Invalid file type')

        try:
            data = pd.read_csv(value.file, encoding = 'ISO-8859-1', engine='python')

            data.columns= data.columns.str.strip().str.lower()
            data=data.rename(columns = {'test case id':'Test Case ID'})

            def transform(df):
                my_new_string = re.sub('[^a-zA-Z0-9"''-_“” \n\.]', '', df)
                return my_new_string

            data['summary'] = data['summary'].apply(transform)
        
        except KeyError:
            raise forms.ValidationError(
                    'CSV file must have "summary" column and "Issue Key" column')
       
        except Exception as e:
            print('Error while parsing CSV file=> %s', e)
            raise forms.ValidationError('Failed to parse the CSV file')

        return data

编辑：解析文件后会导致异常“无法解析 CSV 文件”，如果我删除最后一个异常，则会导致

Traceback (most recent call last):
  File "C:\Users\ssuri\Envs\elixir\lib\site-packages\django\core\handlers\exception.py", line 34, in inner
    response = get_response(request)
  File "C:\Users\ssuri\Envs\elixir\lib\site-packages\django\core\handlers\base.py", line 115, in _get_response
    response = self.process_exception_by_middleware(e, request)
  File "C:\Users\ssuri\Envs\elixir\lib\site-packages\django\core\handlers\base.py", line 113, in _get_response
    response = wrapped_callback(request, *callback_args, **callback_kwargs)
  File "C:\Users\ssuri\Envs\elixir\lib\site-packages\django\utils\decorators.py", line 130, in _wrapped_view
    response = view_func(request, *args, **kwargs)
  File "C:\Users\ssuri\Envs\elixir\lib\site-packages\django\views\decorators\cache.py", line 44, in _wrapped_view_func
    response = view_func(request, *args, **kwargs)
  File "C:\Users\ssuri\Envs\elixir\lib\site-packages\django\contrib\admin\sites.py", line 231, in inner
    return view(request, *args, **kwargs)
  File "C:\Users\ssuri\myproject\elixirdev\test_suite_optimizer\admin.py", line 282, in process_csv
    if form.is_valid():
  File "C:\Users\ssuri\Envs\elixir\lib\site-packages\django\forms\forms.py", line 180, in is_valid
    return self.is_bound and not self.errors
  File "C:\Users\ssuri\Envs\elixir\lib\site-packages\django\forms\forms.py", line 175, in errors
    self.full_clean()
  File "C:\Users\ssuri\Envs\elixir\lib\site-packages\django\forms\forms.py", line 376, in full_clean
    self._clean_fields()
  File "C:\Users\ssuri\Envs\elixir\lib\site-packages\django\forms\forms.py", line 397, in _clean_fields
    value = getattr(self, 'clean_%s' % name)()
  File "C:\Users\ssuri\myproject\elixirdev\test_suite_optimizer\forms.py", line 78, in clean_csv_file
    data['summary'] = data['summary'].apply(transform)
  File "C:\Users\ssuri\Envs\elixir\lib\site-packages\pandas\core\series.py", line 4045, in apply
    mapped = lib.map_infer(values, f, convert=convert_dtype)
  File "pandas/_libs/lib.pyx", line 2228, in pandas._libs.lib.map_infer
  File "C:\Users\ssuri\myproject\elixirdev\test_suite_optimizer\forms.py", line 74, in transform
    my_new_string = re.sub('[^a-zA-Z0-9"''-_“” \n\.]', '', df)
  File "c:\users\ssuri\appdata\local\programs\python\python38\lib\re.py", line 210, in sub
    return _compile(pattern, flags).sub(repl, string, count)
TypeError: expected string or bytes-like object

使用后：

data = data.dropna()

它导致：

Traceback (most recent call last):
  File "C:\Users\ssuri\Envs\elixir\lib\site-packages\pandas\core\indexes\base.py", line 2897, in get_loc
    return self._engine.get_loc(key)
  File "pandas/_libs/index.pyx", line 107, in pandas._libs.index.IndexEngine.get_loc
  File "pandas/_libs/index.pyx", line 131, in pandas._libs.index.IndexEngine.get_loc
  File "pandas/_libs/hashtable_class_helper.pxi", line 992, in pandas._libs.hashtable.Int64HashTable.get_item
  File "pandas/_libs/hashtable_class_helper.pxi", line 998, in pandas._libs.hashtable.Int64HashTable.get_item
KeyError: 0

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "C:\Users\ssuri\Envs\elixir\lib\site-packages\django\core\handlers\exception.py", line 34, in inner
    response = get_response(request)
  File "C:\Users\ssuri\Envs\elixir\lib\site-packages\django\core\handlers\base.py", line 115, in _get_response
    response = self.process_exception_by_middleware(e, request)
  File "C:\Users\ssuri\Envs\elixir\lib\site-packages\django\core\handlers\base.py", line 113, in _get_response
    response = wrapped_callback(request, *callback_args, **callback_kwargs)
  File "C:\Users\ssuri\Envs\elixir\lib\site-packages\django\utils\decorators.py", line 130, in _wrapped_view
    response = view_func(request, *args, **kwargs)
  File "C:\Users\ssuri\Envs\elixir\lib\site-packages\django\views\decorators\cache.py", line 44, in _wrapped_view_func
    response = view_func(request, *args, **kwargs)
  File "C:\Users\ssuri\Envs\elixir\lib\site-packages\django\contrib\admin\sites.py", line 231, in inner
    return view(request, *args, **kwargs)
  File "C:\Users\ssuri\myproject\elixirdev\test_suite_optimizer\admin.py", line 287, in process_csv
    data = handle_demo_ai(csv_data)
  File "C:\Users\ssuri\myproject\elixirdev\test_suite_optimizer\ai\web_demo_test_suite_optimization.py", line 108, in handle_json_ai
    X = df_tcs.loc[X_row, "Summary_lemmatized"]
  File "C:\Users\ssuri\Envs\elixir\lib\site-packages\pandas\core\indexing.py", line 1418, in __getitem__
    return self._getitem_tuple(key)
  File "C:\Users\ssuri\Envs\elixir\lib\site-packages\pandas\core\indexing.py", line 805, in _getitem_tuple
    return self._getitem_lowerdim(tup)
  File "C:\Users\ssuri\Envs\elixir\lib\site-packages\pandas\core\indexing.py", line 929, in _getitem_lowerdim
    section = self._getitem_axis(key, axis=i)
  File "C:\Users\ssuri\Envs\elixir\lib\site-packages\pandas\core\indexing.py", line 1850, in _getitem_axis
    return self._get_label(key, axis=axis)
  File "C:\Users\ssuri\Envs\elixir\lib\site-packages\pandas\core\indexing.py", line 160, in _get_label
    return self.obj._xs(label, axis=axis)
  File "C:\Users\ssuri\Envs\elixir\lib\site-packages\pandas\core\generic.py", line 3737, in xs
    loc = self.index.get_loc(key)
  File "C:\Users\ssuri\Envs\elixir\lib\site-packages\pandas\core\indexes\base.py", line 2899, in get_loc
    return self._engine.get_loc(self._maybe_cast_indexer(key))
  File "pandas/_libs/index.pyx", line 107, in pandas._libs.index.IndexEngine.get_loc
  File "pandas/_libs/index.pyx", line 131, in pandas._libs.index.IndexEngine.get_loc
  File "pandas/_libs/hashtable_class_helper.pxi", line 992, in pandas._libs.hashtable.Int64HashTable.get_item
  File "pandas/_libs/hashtable_class_helper.pxi", line 998, in pandas._libs.hashtable.Int64HashTable.get_item
KeyError: 0

Answer 1

当您读取带有逗号的文件时，第一行有NAN 值。 在尝试应用 transform() 之前，您需要删除 NAN 值 使用

data = data.dropna()