python python groupby agg獲取lag1

Question

def lag1(x):
    return x[(len(x)-1)]
x=pd.Series([12,3,4,5,6])
lag1(x)
Out[65]: 6
dat.shape
Out[70]: (247619, 33)
d2=dat.groupby('PATID_CD').agg(lag1)
Traceback (most recent call last):

  File "<ipython-input-71-f514757a3da8>", line 1, in <module>
    d2=dat.groupby('PATID_CD').agg(lag1)

  File "D:\Users\shan xu\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py", line 4658, in aggregate
    return super(DataFrameGroupBy, self).aggregate(arg, *args, **kwargs)

  File "D:\Users\shan xu\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py", line 4109, in aggregate
    result = self._aggregate_generic(arg, *args, **kwargs)

  File "D:\Users\shan xu\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py", line 4133, in _aggregate_generic
    return self._aggregate_item_by_item(func, *args, **kwargs)

  File "D:\Users\shan xu\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py", line 4162, in _aggregate_item_by_item
    colg.aggregate(func, *args, **kwargs), data)

  File "D:\Users\shan xu\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py", line 3497, in aggregate
    result = self._aggregate_named(func_or_funcs, *args, **kwargs)

  File "D:\Users\shan xu\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py", line 3627, in _aggregate_named
    output = func(group, *args, **kwargs)

  File "<ipython-input-64-be977293b7b9>", line 2, in lag1
    return x[(len(x)-1)]

  File "D:\Users\shan xu\Anaconda3\lib\site-packages\pandas\core\series.py", line 766, in __getitem__
    result = self.index.get_value(self, key)

  File "D:\Users\shan xu\Anaconda3\lib\site-packages\pandas\core\indexes\base.py", line 3103, in get_value
    tz=getattr(series.dtype, 'tz', None))

  File "pandas\_libs\index.pyx", line 106, in pandas._libs.index.IndexEngine.get_value

  File "pandas\_libs\index.pyx", line 114, in pandas._libs.index.IndexEngine.get_value

  File "pandas\_libs\index.pyx", line 162, in pandas._libs.index.IndexEngine.get_loc

  File "pandas\_libs\hashtable_class_helper.pxi", line 958, in pandas._libs.hashtable.Int64HashTable.get_item

  File "pandas\_libs\hashtable_class_helper.pxi", line 964, in pandas._libs.hashtable.Int64HashTable.get_item
KeyError: 23

我不知道為什么我的函數不能正常工作，它給了我一個密鑰錯誤，提示該名稱不存在。 這有點令人困惑。 我是在做正確的方法，還是有其他解決方案？

dat.groupby('PATID_CD').agg('mean')
Out[73]: 
           MONTH_LOOKBACK_NR      CCYYMM_CD    ...     ENG_SPOKEN  EVENT_FL
PATID_CD                                       ...                         
584                     12.0  201556.500000    ...            1.0       0.0
4277                    12.0  201556.500000    ...            1.0       0.0

我也嘗試過：

dat.groupby('PATID_CD').agg(lambda x : x.iloc[-1,:])

這個很好，但是我不能把這個函數放到一個可以和其他函數一起計算的列表中：

def lag1(x):
    return x.iloc[-1,:]
d2=dat.groupby(dat['PATID_CD']).agg({'mean','max','min','std','skew', lambda x:len(x),kurtosis,lag1})
Traceback (most recent call last):

  File "<ipython-input-86-ac95a8297b5c>", line 1, in <module>

    d2=dat.groupby(dat['PATID_CD']).agg({'mean','max','min','std','skew', lambda x:len(x),kurtosis,lag1})

  File "D:\Users\shan xu\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py", line 4658, in aggregate
    return super(DataFrameGroupBy, self).aggregate(arg, *args, **kwargs)

  File "D:\Users\shan xu\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py", line 4089, in aggregate
    result, how = self._aggregate(arg, _level=_level, *args, **kwargs)

  File "D:\Users\shan xu\Anaconda3\lib\site-packages\pandas\core\base.py", line 551, in _aggregate
    _axis=_axis), None

  File "D:\Users\shan xu\Anaconda3\lib\site-packages\pandas\core\base.py", line 596, in _aggregate_multiple_funcs
    results.append(colg.aggregate(arg))

  File "D:\Users\shan xu\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py", line 3485, in aggregate
    (_level or 0) + 1)

  File "D:\Users\shan xu\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py", line 3558, in _aggregate_multiple_funcs
    results[name] = obj.aggregate(func)

  File "D:\Users\shan xu\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py", line 3497, in aggregate
    result = self._aggregate_named(func_or_funcs, *args, **kwargs)

  File "D:\Users\shan xu\Anaconda3\lib\site-packages\pandas\core\groupby\groupby.py", line 3627, in _aggregate_named
    output = func(group, *args, **kwargs)

  File "<ipython-input-85-6bbffa1ca952>", line 2, in lag1
    return x.iloc[-1,:]

  File "D:\Users\shan xu\Anaconda3\lib\site-packages\pandas\core\indexing.py", line 1472, in __getitem__
    return self._getitem_tuple(key)

  File "D:\Users\shan xu\Anaconda3\lib\site-packages\pandas\core\indexing.py", line 2013, in _getitem_tuple
    self._has_valid_tuple(tup)

  File "D:\Users\shan xu\Anaconda3\lib\site-packages\pandas\core\indexing.py", line 220, in _has_valid_tuple
    raise IndexingError('Too many indexers')  

IndexingError：索引器過多與此相同：

x=pd.Series([12,3,4,5,6])
lag1(x)
Traceback (most recent call last):

  File "<ipython-input-85-6bbffa1ca952>", line 5, in <module>
    lag1(x)

  File "<ipython-input-85-6bbffa1ca952>", line 2, in lag1
    return x.iloc[-1,:]

  File "D:\Users\shan xu\Anaconda3\lib\site-packages\pandas\core\indexing.py", line 1472, in __getitem__
    return self._getitem_tuple(key)

  File "D:\Users\shan xu\Anaconda3\lib\site-packages\pandas\core\indexing.py", line 2013, in _getitem_tuple
    self._has_valid_tuple(tup)

  File "D:\Users\shan xu\Anaconda3\lib\site-packages\pandas\core\indexing.py", line 220, in _has_valid_tuple
    raise IndexingError('Too many indexers')

IndexingError: Too many indexers

Answer 1

您尚未解釋您要完成的工作，並且代碼中也不清楚。 我在這里的代表不足，無法將此添加為評論，因此請考慮：

1）您的第一個示例是在隱式使用RangeIndex的Series上執行的，因此x[(5-1)] == 6 。 您的第二個示例似乎是一個以PATID_CD為索引的PATID_CD 。 如果PATID_CD.dtype是如object ，你會得到一個KeyError例外，只是因為你已經通過了錯誤的參數類型（ int ）為大熊貓索引表達式DataFrame[label] 文檔 。

2）如果您只想提取組的最后一行，請編寫groupby調用，例如

dat.groupby('PATID_CD').apply(lambda x: x.iloc[-1, :])