如何在数据框的两列的值之间查询

假设我有一个包含以下各列的数据框，

df.head()
    ref_loc ref_chr REF ALT coverage    base
    9532728 21  G   [A] 1   A
    9540473 21  C   [G] 2   G
    9540473 21  CTATT   [C] 2   G
    9540794 21  C   [T] 1   A
    9542965 21  C   [A] 1   T

我想将列ALT与列进行比较，base并查看匹配项和区别。根据匹配和差异，我想生成一个名为的新列cate。

为此，我尝试使用以下功能，

def grouping(row):
    if row['ALT'] == row['base']:
         val = "same_variants"
    elif row['ALT'] != row['base']:
         val = "diff_variants"
    return val

df["cate"] = df.apply(grouping,axis=0)

但是，该函数在尝试应用于数据框时抛出此错误，

    KeyError                                  Traceback (most recent call last)
<ipython-input-13-a265dee72ec1> in <module>
----> 1 df["group"] =df.apply(grouping,axis=0)

~/software/anaconda/lib/python3.7/site-packages/pandas/core/frame.py in apply(self, func, axis, broadcast, raw, reduce, result_type, args, **kwds)
   6911             kwds=kwds,
   6912         )
-> 6913         return op.get_result()
   6914 
   6915     def applymap(self, func):

~/software/anaconda/lib/python3.7/site-packages/pandas/core/apply.py in get_result(self)
    184             return self.apply_raw()
    185 
--> 186         return self.apply_standard()
    187 
    188     def apply_empty_result(self):

~/software/anaconda/lib/python3.7/site-packages/pandas/core/apply.py in apply_standard(self)
    290 
    291         # compute the result using the series generator
--> 292         self.apply_series_generator()
    293 
    294         # wrap results

~/software/anaconda/lib/python3.7/site-packages/pandas/core/apply.py in apply_series_generator(self)
    319             try:
    320                 for i, v in enumerate(series_gen):
--> 321                     results[i] = self.f(v)
    322                     keys.append(v.name)
    323             except Exception as e:

<ipython-input-11-098066170c2f> in grouping(row)
      1 def grouping(row):
----> 2     if row['ALT'] == row['base']:
      3          val = "same_variants"
      4     elif row['ALT'] != row['base']:
      5          val= "diff_variants"

~/software/anaconda/lib/python3.7/site-packages/pandas/core/series.py in __getitem__(self, key)
   1066         key = com.apply_if_callable(key, self)
   1067         try:
-> 1068             result = self.index.get_value(self, key)
   1069 
   1070             if not is_scalar(result):

~/software/anaconda/lib/python3.7/site-packages/pandas/core/indexes/base.py in get_value(self, series, key)
   4728         k = self._convert_scalar_indexer(k, kind="getitem")
   4729         try:
-> 4730             return self._engine.get_value(s, k, tz=getattr(series.dtype, "tz", None))
   4731         except KeyError as e1:
   4732             if len(self) > 0 and (self.holds_integer() or self.is_boolean()):

pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_value()

pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_value()

pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()

pandas/_libs/index_class_helper.pxi in pandas._libs.index.Int64Engine._check_type()

KeyError: ('ALT', 'occurred at index ref_loc')

我想提出一些建议，我可以继续前进。

最后，输出应如下所示：

ref_loc ref_chr REF ALT coverage    base    cate
9532728 21  G   [A]      1         A      same_variants
9540473 21  C   [G]      2         G      same_variants
9540473 21  CTATT   [C]  2         G      diff_variants
9540794 21  C   [T]      1         A      diff_variants
9542965 21  C   [A]      1         T      diff_variants