作为一个简单的例子，考虑 numpy 数组
arrimport numpy as np
arr = np.array([[5, np.nan, np.nan, 7, 2],
[3, np.nan, 1, 8, np.nan],
[4, 9, 6, np.nan, np.nan]])
其中
arrarray([[ 5., nan, nan, 7., 2.],
[ 3., nan, 1., 8., nan],
[ 4., 9., 6., nan, nan]])
我现在想按行“向前填充”数组
nanarrnanarray([[ 5., 5., 5., 7., 2.],
[ 3., 3., 1., 8., 8.],
[ 4., 9., 6., 6., 6.]])
我尝试过使用for循环：
for row_idx in range(arr.shape[0]):
for col_idx in range(arr.shape[1]):
if np.isnan(arr[row_idx][col_idx]):
arr[row_idx][col_idx] = arr[row_idx][col_idx - 1]
我还尝试使用 pandas 数据框作为中间步骤（因为 pandas 数据框有一个非常简洁的内置前向填充方法）：
import pandas as pd
df = pd.DataFrame(arr)
df.fillna(method='ffill', axis=1, inplace=True)
arr = df.as_matrix()
上述两种策略都产生了期望的结果，但我一直想知道：仅使用 numpy 向量化运算的策略不是最有效的策略吗？
是否有另一种更有效的方法来“前向填充”numpy 数组中的
nan到目前为止，我已尝试计算所有解决方案的时间。这是我的设置脚本：
import numba as nb
import numpy as np
import pandas as pd
def random_array():
choices = [1, 2, 3, 4, 5, 6, 7, 8, 9, np.nan]
out = np.random.choice(choices, size=(1000, 10))
return out
def loops_fill(arr):
out = arr.copy()
for row_idx in range(out.shape[0]):
for col_idx in range(1, out.shape[1]):
if np.isnan(out[row_idx, col_idx]):
out[row_idx, col_idx] = out[row_idx, col_idx - 1]
return out
@nb.jit
def numba_loops_fill(arr):
'''Numba decorator solution provided by shx2.'''
out = arr.copy()
for row_idx in range(out.shape[0]):
for col_idx in range(1, out.shape[1]):
if np.isnan(out[row_idx, col_idx]):
out[row_idx, col_idx] = out[row_idx, col_idx - 1]
return out
def pandas_fill(arr):
df = pd.DataFrame(arr)
df.fillna(method='ffill', axis=1, inplace=True)
out = df.as_matrix()
return out
def numpy_fill(arr):
'''Solution provided by Divakar.'''
mask = np.isnan(arr)
idx = np.where(~mask,np.arange(mask.shape[1]),0)
np.maximum.accumulate(idx,axis=1, out=idx)
out = arr[np.arange(idx.shape[0])[:,None], idx]
return out
随后是此控制台输入：
%timeit -n 1000 loops_fill(random_array())
%timeit -n 1000 numba_loops_fill(random_array())
%timeit -n 1000 pandas_fill(random_array())
%timeit -n 1000 numpy_fill(random_array())
导致控制台输出：
1000 loops, best of 3: 9.64 ms per loop
1000 loops, best of 3: 377 µs per loop
1000 loops, best of 3: 455 µs per loop
1000 loops, best of 3: 351 µs per loop
这是一种方法 -
mask = np.isnan(arr)
idx = np.where(~mask,np.arange(mask.shape[1]),0)
np.maximum.accumulate(idx,axis=1, out=idx)
out = arr[np.arange(idx.shape[0])[:,None], idx]
如果您不想创建另一个数组而只想在
arrarr[mask] = arr[np.nonzero(mask)[0], idx[mask]]
样本输入、输出-
In [179]: arr
Out[179]:
array([[ 5., nan, nan, 7., 2., 6., 5.],
[ 3., nan, 1., 8., nan, 5., nan],
[ 4., 9., 6., nan, nan, nan, 7.]])
In [180]: out
Out[180]:
array([[ 5., 5., 5., 7., 2., 6., 5.],
[ 3., 3., 1., 8., 8., 5., 5.],
[ 4., 9., 6., 6., 6., 6., 7.]])
我喜欢 Divakar 关于 pure numpy 的回答。 这是 n 维数组的广义函数：
def np_ffill(arr, axis):
idx_shape = tuple([slice(None)] + [np.newaxis] * (len(arr.shape) - axis - 1))
idx = np.where(~np.isnan(arr), np.arange(arr.shape[axis])[idx_shape], 0)
np.maximum.accumulate(idx, axis=axis, out=idx)
slc = [np.arange(k)[tuple([slice(None) if dim==i else np.newaxis
for dim in range(len(arr.shape))])]
for i, k in enumerate(arr.shape)]
slc[axis] = idx
return arr[tuple(slc)]
AFIK pandas 只能处理二维，尽管有多索引来弥补。实现此目的的唯一方法是展平 DataFrame、取消堆叠所需级别、重新堆叠，最后重新整形为原始形状。这种拆栈/重新堆叠/重塑（涉及 pandas 排序）只是实现相同结果的不必要的开销。
测试：
def random_array(shape):
choices = [1, 2, 3, 4, np.nan]
out = np.random.choice(choices, size=shape)
return out
ra = random_array((2, 4, 8))
print('arr')
print(ra)
print('\nffull')
print(np_ffill(ra, 1))
raise SystemExit
输出：
arr
[[[ 3. nan 4. 1. 4. 2. 2. 3.]
[ 2. nan 1. 3. nan 4. 4. 3.]
[ 3. 2. nan 4. nan nan 3. 4.]
[ 2. 2. 2. nan 1. 1. nan 2.]]
[[ 2. 3. 2. nan 3. 3. 3. 3.]
[ 3. 3. 1. 4. 1. 4. 1. nan]
[ 4. 2. nan 4. 4. 3. nan 4.]
[ 2. 4. 2. 1. 4. 1. 3. nan]]]
ffull
[[[ 3. nan 4. 1. 4. 2. 2. 3.]
[ 2. nan 1. 3. 4. 4. 4. 3.]
[ 3. 2. 1. 4. 4. 4. 3. 4.]
[ 2. 2. 2. 4. 1. 1. 3. 2.]]
[[ 2. 3. 2. nan 3. 3. 3. 3.]
[ 3. 3. 1. 4. 1. 4. 1. 3.]
[ 4. 2. 1. 4. 4. 3. 1. 4.]
[ 2. 4. 2. 1. 4. 1. 3. 4.]]]
更新：正如financial_practician在评论中指出的，我最初提出的解决方案可以简单地与反转数组上的
ffill%timeit对于那些来这里寻找 NaN 值向后填充的人，我修改了 上面 Divakar 提供的解决方案来做到这一点。技巧是你必须使用除最大值之外的最小值对反转数组进行累加。
这是代码：
# ffill along axis 1, as provided in the answer by Divakar
def ffill(arr):
mask = np.isnan(arr)
idx = np.where(~mask, np.arange(mask.shape[1]), 0)
np.maximum.accumulate(idx, axis=1, out=idx)
out = arr[np.arange(idx.shape[0])[:,None], idx]
return out
# Simple solution for bfill provided by financial_physician in comment below
def bfill(arr):
return ffill(arr[:, ::-1])[:, ::-1]
# My outdated modification of Divakar's answer to do a backward-fill
def bfill_old(arr):
mask = np.isnan(arr)
idx = np.where(~mask, np.arange(mask.shape[1]), mask.shape[1] - 1)
idx = np.minimum.accumulate(idx[:, ::-1], axis=1)[:, ::-1]
out = arr[np.arange(idx.shape[0])[:,None], idx]
return out
# Test both functions
arr = np.array([[5, np.nan, np.nan, 7, 2],
[3, np.nan, 1, 8, np.nan],
[4, 9, 6, np.nan, np.nan]])
print('Array:')
print(arr)
print('\nffill')
print(ffill(arr))
print('\nbfill')
print(bfill(arr))
输出：
Array:
[[ 5. nan nan 7. 2.]
[ 3. nan 1. 8. nan]
[ 4. 9. 6. nan nan]]
ffill
[[5. 5. 5. 7. 2.]
[3. 3. 1. 8. 8.]
[4. 9. 6. 6. 6.]]
bfill
[[ 5. 7. 7. 7. 2.]
[ 3. 1. 1. 8. nan]
[ 4. 9. 6. nan nan]]
编辑：根据MS_的评论更新
使用Numba。这应该会显着加速：
import numba
@numba.jit
def loops_fill(arr):
...
我喜欢 Divakar 的答案，但它不适用于行以 np.nan 开头的边缘情况，如下面的
arrarr = np.array([[9, np.nan, 4, np.nan, 6, 6, 7, 2, 3, np.nan],
[ np.nan, 5, 5, 6, 5, 3, 2, 1, np.nan, 10]])
使用 Divakar 代码的输出将是：
[[ 9. 9. 4. 4. 6. 6. 7. 2. 3. 3.]
[nan 4. 5. 6. 5. 3. 2. 1. 1. 10.]]
Divakar的代码可以简化一点，简化版同时解决了这个问题：
arr[np.isnan(arr)] = arr[np.nonzero(np.isnan(arr))[0], np.nonzero(np.isnan(arr))[1]-1]
如果连续出现多个
np.nannp.nannp.nanfor i in range(0, 5):
value[np.isnan(value)] = value[np.nonzero(np.isnan(value))[0], np.nonzero(np.isnan(value))[1]-1]
使用bottleneck模块，它与pandas或numpy模块一起提供，因此无需单独安装。
下面的代码应该会给你想要的结果。
import bottleneck as bn
bn.push(arr,axis=1)
对于那些对前向填充后有领先
np.nanmask = np.isnan(arr)
first_non_zero_idx = (~mask!=0).argmax(axis=1) #Get indices of first non-zero values
arr = [ np.hstack([
[arr[i,first_nonzero]]*(first_nonzero),
arr[i,first_nonzero:]])
for i, first_nonzero in enumerate(first_non_zero_idx) ]
如果你愿意使用 Pandas/ xarray: 让 axis 为你想要填充/b填充的方向，如下所示，
xr.DataArray(arr).ffill(f'dim_{axis}').values
xr.DataArray(arr).bfill(f'dim_{axis}').values
更多信息： http://xarray.pydata.org/en/stable/ generated/xarray.DataArray.ffill.html https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.ffill.html
除非我错过了什么，否则这些解决方案不适用于任何示例：
arr = np.array([[ 3.],
[ 8.],
[np.nan],
[ 7.],
[np.nan],
[ 1.],
[np.nan],
[ 3.],
[ 8.],
[ 8.]])
print("A:::: \n", arr)
print("numpy_fill::: \n ", numpy_fill(arr))
print("loop_fill", loops_fill(arr))
A::::
[[ 3.]
[ 8.]
[nan]
[ 7.]
[nan]
[ 1.]
[nan]
[ 3.]
[ 8.]
[ 8.]]
numpy_fill:::
[[ 3.]
[ 8.]
[nan]
[ 7.]
[nan]
[ 1.]
[nan]
[ 3.]
[ 8.]
[ 8.]]
loop_fill [[ 3.]
[ 8.]
[nan]
[ 7.]
[nan]
[ 1.]
[nan]
[ 3.]
[ 8.]
[ 8.]]
Comments ??
对 RichieV 广义纯 numpy 解决方案 的微小改进，具有轴选择和“向后”支持
def _np_fill_(arr, axis=-1, fill_dir='f'):
"""Base function for np_fill, np_ffill, np_bfill."""
if axis < 0:
axis = len(arr.shape) + axis
if fill_dir.lower() in ['b', 'backward']:
dir_change = tuple([*[slice(None)]*axis, slice(None, None, -1)])
return np_ffill(arr[dir_change])[dir_change]
elif fill_dir.lower() not in ['f', 'forward']:
raise KeyError(f"fill_dir must be one of: 'b', 'backward', 'f', 'forward'. Got: {fill_dir}")
idx_shape = tuple([slice(None)] + [np.newaxis] * (len(arr.shape) - axis - 1))
idx = np.where(~np.isnan(arr), np.arange(arr.shape[axis])[idx_shape], 0)
np.maximum.accumulate(idx, axis=axis, out=idx)
slc = [np.arange(k)[tuple([slice(None) if dim==i else np.newaxis
for dim in range(len(arr.shape))])]
for i, k in enumerate(arr.shape)]
slc[axis] = idx
return arr[tuple(slc)]
def np_fill(arr, axis=-1, fill_dir='f'):
"""General fill function which supports multiple filling steps. I.e.:
fill_dir=['f', 'b'] or fill_dir=['b', 'f']"""
if isinstance(fill_dir, (tuple, list, np.ndarray)):
for i in fill_dir:
arr = _np_fill_(arr, axis=axis, fill_dir=i)
else:
arr = _np_fill_(arr, axis=axis, fill_dir=fill_dir)
return arr
def np_ffill(arr, axis=-1):
return np_fill(arr, axis=axis, fill_dir='forward')
def np_bfill(arr, axis=-1):
return np_fill(arr, axis=axis, fill_dir='backward')
如果，通过
efficienthttps://github.com/DomTomCat/signalProcessing/blob/main/interpolateNonFiniteValues.py