我正在使用数据集进行以下测试
df = pandas.DataFrame({'A' : ['foo', 'bar', 'foo','bar','foo', 'bar','foo', 'foo'],'B' : ['one', 'one', 'two','three','two', 'two', 'one', 'three'],'C' : np.random.randn(8),'D' : np.random.randn(8)})
df = pandas.concat([df, df])
df.reset_index(inplace= True, drop = True)
df['dates'] = pandas.date_range('1/1/2000', periods = df.shape[0])
grouped = df.groupby(['A','B'], as_index = False)
现在我写了一个像
这样的自定义函数def knowType(x):
print(type(x))
并应用于像这样的“分组”组对象
grouped.agg(knowType)
我得到了这样的标准：
<class 'pandas.core.series.Series'>
<class 'pandas.core.series.Series'>
<class 'pandas.core.series.Series'>
<class 'pandas.core.series.Series'>
<class 'pandas.core.series.Series'>
<class 'pandas.core.series.Series'>
<class 'pandas.core.series.Series'>
<class 'pandas.core.series.Series'>
<class 'pandas.core.series.Series'>
<class 'pandas.core.series.Series'>
<class 'pandas.core.series.Series'>
<class 'pandas.core.series.Series'>
<class 'pandas.core.series.Series'>
<class 'pandas.core.series.Series'>
<class 'pandas.core.series.Series'>
<class 'pandas.core.series.Series'>
<class 'pandas.core.series.Series'>
<class 'pandas.core.series.Series'>
但是当我改变这个功能时
def knowType(x):
print(type(x))
uniq = x.unique()
print(",".join(uniq))
并将此类似地称为
grouped.agg(knowType)
我收到以下错误：
<class 'pandas.core.series.Series'>
<class 'pandas.core.series.Series'>
<class 'pandas.core.series.Series'>
<class 'pandas.core.frame.DataFrame'>
<class 'pandas.core.frame.DataFrame'>
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-41-5e12be303545> in <module>()
----> 1 grouped.agg(knowType)
/home/srinath/anaconda3/lib/python3.5/site-packages/pandas/core/groupby.py in aggregate(self, arg, *args, **kwargs)
3595 @Appender(SelectionMixin._agg_doc)
3596 def aggregate(self, arg, *args, **kwargs):
-> 3597 return super(DataFrameGroupBy, self).aggregate(arg, *args, **kwargs)
3598
3599 agg = aggregate
/home/srinath/anaconda3/lib/python3.5/site-packages/pandas/core/groupby.py in aggregate(self, arg, *args, **kwargs)
3120 # grouper specific aggregations
3121 if self.grouper.nkeys > 1:
-> 3122 return self._python_agg_general(arg, *args, **kwargs)
3123 else:
3124
/home/srinath/anaconda3/lib/python3.5/site-packages/pandas/core/groupby.py in _python_agg_general(self, func, *args, **kwargs)
781
782 if len(output) == 0:
--> 783 return self._python_apply_general(f)
784
785 if self.grouper._filter_empty_groups:
/home/srinath/anaconda3/lib/python3.5/site-packages/pandas/core/groupby.py in _python_apply_general(self, f)
653 def _python_apply_general(self, f):
654 keys, values, mutated = self.grouper.apply(f, self._selected_obj,
--> 655 self.axis)
656
657 return self._wrap_applied_output(
/home/srinath/anaconda3/lib/python3.5/site-packages/pandas/core/groupby.py in apply(self, f, data, axis)
1525 # group might be modified
1526 group_axes = _get_axes(group)
-> 1527 res = f(group)
1528 if not _is_indexed_like(res, group_axes):
1529 mutated = True
/home/srinath/anaconda3/lib/python3.5/site-packages/pandas/core/groupby.py in <lambda>(x)
769 def _python_agg_general(self, func, *args, **kwargs):
770 func = self._is_builtin_func(func)
--> 771 f = lambda x: func(x, *args, **kwargs)
772
773 # iterate through "columns" ex exclusions to populate output dict
<ipython-input-40-e3b0c59fb896> in knowType(x)
16 def knowType(x):
17 print(type(x))
---> 18 uniq = x.unique()
19 print(",".join(uniq))
/home/srinath/anaconda3/lib/python3.5/site-packages/pandas/core/generic.py in __getattr__(self, name)
2670 if name in self._info_axis:
2671 return self[name]
-> 2672 return object.__getattribute__(self, name)
2673
2674 def __setattr__(self, name, value):
AttributeError: 'DataFrame' object has no attribute 'unique'
有趣的是stdout说类型是DataFrame。这是为什么？ 我经历了this但是无法得到那里发生的事情。有谁能够帮我？ 谢谢