python - 使用 groupby 对多列进行加权平均，逐列删除 NaN

Question

我有这样的情况
Pandas Group Weighted Average of Multiple Columns但是其中一列的某些值有时是 NaN。

也就是说，我正在执行以下操作:

import pandas as pd
import numpy as np

df=pd.DataFrame({'category':['a','a','b','b'],
 'var1':np.random.randint(0,100,4),
 'var2':np.random.randint(0,100,4),
 'weights':np.random.randint(0,10,4)})
df.loc[1,'var1']=np.nan
df


      category  var1  var2  weights
0        a      74.0    99        9
1        a       NaN     8        4
2        b      13.0    86        2
3        b      49.0    38        7

def weighted(x, cols, w="weights"):
    # Following fails when NaNs might be present:
    #return pd.Series(np.average(x[cols], weights=x[w], axis=0), cols)
    return pd.Series([np.nan if x.dropna(subset=[c]).empty else np.average(x.dropna(subset=[c])[c], weights =x.dropna(subset=[c])[w] ) for c in cols], cols)

df.groupby('category').apply(weighted, ['var1', 'var2'])


          var1       var2
category                 
a         74.0  57.846154
b         23.0   8.000000

我想要一个更好的方法来做到这一点，但 np.nanmean 不允许权重。 np.average 不允许选项来控制 NaN 的处理。

Answer 1

没有比我的建议更清晰的答案，我建议使用下面的函数还不错:

import pandas as pd
import numpy as np

def weighted_means_by_column_ignoring_NaNs(x, cols, w="weights"):
    """ This takes a DataFrame and averages each data column (cols),
        weighting observations by column w, but ignoring individual NaN
        observations within each column.
    """
    return pd.Series([np.nan if x.dropna(subset=[c]).empty else \
                      np.average(x.dropna(subset=[c])[c], 
                      weights =x.dropna(subset=[c])[w] )  \
                      for c in cols], cols)

示例用法如下

df=pd.DataFrame({'category':['a','a','b','b'],
 'var1':np.random.randint(0,100,4),
 'var2':np.random.randint(0,100,4),
 'weights':np.random.randint(0,10,4)})
df.loc[1,'var1']=np.nan
df


      category  var1  var2  weights
0        a      74.0    99        9
1        a       NaN     8        4
2        b      13.0    86        2
3        b      49.0    38        7

df.groupby('category').apply(weighted_means_by_column_ignoring_NaNs), 
        ['var1', 'var2'])


          var1       var2
category                 
a         74.0  57.846154
b         23.0   8.000000