我有一个DataFrame：
>>> df = pd.DataFrame({'row1' : [1,2,np.nan,4,5], 'row2' : [11,12,13,14,np.nan], 'row3':[22,22,23,24,25]}, index = 'a b c d e'.split()).T
>>> df
a b c d e
row1 1.0 2.0 NaN 4.0 5.0
row2 11.0 12.0 13.0 14.0 NaN
row3 22.0 22.0 23.0 24.0 25.0
和一个系列，它指定每行所需的前N个值
>>> n_max = pd.Series([2,3,4])
Panda使用df和n_max查找每个元素的最大N元素的方式是什么（与随机选择断开关系，就像.nlargest()那样）？
所需的输出是
a b c d e
row1 NaN NaN NaN 4.0 5.0
row2 NaN 12.0 13.0 14.0 NaN
row3 22.0 NaN 23.0 24.0 25.0
我知道如何在所有行中使用统一/固定N（例如，N = 4）。请注意第3行中的打破平局：
>>> df.stack().groupby(level=0).nlargest(4).unstack().reset_index(level=1, drop=True).reindex(columns=df.columns)
a b c d e
row1 1.0 2.0 NaN 4.0 5.0
row2 11.0 12.0 13.0 14.0 NaN
row3 22.0 NaN 23.0 24.0 25.0
但目标再次是具有行特定N。循环显示每行显然不计算（出于性能原因）。而且我尝试使用带掩码的.rank()但是在那里打破平局......
答案 0 :(得分：1)
根据@ ScottBoston对OP的评论，可以使用以下基于排名的掩码来解决这个问题：
>>> n_max.index = df.index
>>> df_rank = df.stack(dropna=False).groupby(level=0).rank(ascending=False, method='first').unstack()
>>> selected = df_rank.le(n_max, axis=0)
>>> df[selected]
a b c d e
row1 NaN NaN NaN 4.0 5.0
row2 NaN 12.0 13.0 14.0 NaN
row3 22.0 NaN 23.0 24.0 25.0
答案 1 :(得分：0)
为表现，我会建议NumPy -
def mask_variable_largest_per_row(df, n_max):
a = df.values
m,n = a.shape
nan_row_count = np.isnan(a).sum(1)
n_reset = n-n_max.values-nan_row_count
n_reset.clip(min=0, max=n-1, out = n_reset)
sidx = a.argsort(1)
mask = n_reset[:,None] > np.arange(n)
c = sidx[mask]
r = np.repeat(np.arange(m), n_reset)
a[r,c] = np.nan
return df
示例运行 -
In [182]: df
Out[182]:
a b c d e
row1 1.0 2.0 NaN 4.0 5.0
row2 11.0 12.0 13.0 14.0 NaN
row3 22.0 22.0 5.0 24.0 25.0
In [183]: n_max = pd.Series([2,3,2])
In [184]: mask_variable_largest_per_row(df, n_max)
Out[184]:
a b c d e
row1 NaN NaN NaN 4.0 5.0
row2 NaN 12.0 13.0 14.0 NaN
row3 NaN NaN NaN 24.0 25.0
进一步提升：引入numpy.argpartition替换numpy.argsort应该有所帮助，因为我们并不关心要重置为{{的指数的顺序1}}。因此，基于NaNs的将是 -
numpy.argpartition运行时测试
其他方法 -
def mask_variable_largest_per_row_v2(df, n_max):
a = df.values
m,n = a.shape
nan_row_count = np.isnan(a).sum(1)
n_reset = n-n_max.values-nan_row_count
n_reset.clip(min=0, max=n-1, out = n_reset)
N = (n-n_max.values).max()
N = np.clip(N, a_min=0, a_max=n-1)
sidx = a.argpartition(N, axis=1) #sidx = a.argsort(1)
mask = n_reset[:,None] > np.arange(n)
c = sidx[mask]
r = np.repeat(np.arange(m), n_reset)
a[r,c] = np.nan
return df
验证和时间安排 -
def pandas_rank_based(df, n_max):
n_max.index = df.index
df_rank = df.stack(dropna=False).groupby(level=0).rank\
(ascending=False, method='first').unstack()
selected = df_rank.le(n_max, axis=0)
return df[selected]
内置大熊猫的 In [387]: arr = np.random.rand(1000,1000)
...: arr.ravel()[np.random.choice(arr.size, 10000, replace=0)] = np.nan
...: df1 = pd.DataFrame(arr)
...: df2 = df1.copy()
...: df3 = df1.copy()
...: n_max = pd.Series(np.random.randint(0,1000,(1000)))
...:
...: out1 = pandas_rank_based(df1, n_max)
...: out2 = mask_variable_largest_per_row(df2, n_max)
...: out3 = mask_variable_largest_per_row_v2(df3, n_max)
...: print np.nansum(out1-out2)==0 # Verify
...: print np.nansum(out1-out3)==0 # Verify
...:
True
True
In [388]: arr = np.random.rand(1000,1000)
...: arr.ravel()[np.random.choice(arr.size, 10000, replace=0)] = np.nan
...: df1 = pd.DataFrame(arr)
...: df2 = df1.copy()
...: df3 = df1.copy()
...: n_max = pd.Series(np.random.randint(0,1000,(1000)))
...:
In [389]: %timeit pandas_rank_based(df1, n_max)
1 loops, best of 3: 559 ms per loop
In [390]: %timeit mask_variable_largest_per_row(df2, n_max)
10 loops, best of 3: 34.1 ms per loop
In [391]: %timeit mask_variable_largest_per_row_v2(df3, n_max)
100 loops, best of 3: 5.92 ms per loop
相当不错！