这是在向量数组中找到最近向量的扩展。

import numpy as np

def find_nearest_vector(array, value):
  idx = np.array([np.linalg.norm(x+y) for (x,y) in array-value]).argmin()
  return array[idx]

A = np.random.random((10,2))*100
""" A = array([[ 34.19762933,  43.14534123],
   [ 48.79558706,  47.79243283],
   [ 38.42774411,  84.87155478],
   [ 63.64371943,  50.7722317 ],
   [ 73.56362857,  27.87895698],
   [ 96.67790593,  77.76150486],
   [ 68.86202147,  21.38735169],
   [  5.21796467,  59.17051276],
   [ 82.92389467,  99.90387851],
   [  6.76626539,  30.50661753]])"""
pt = [6, 30]  
print find_nearest_vector(A,pt)
# array([  6.76626539,  30.50661753])

所有的答案都有助于收集信息来编写高效的代码。但是，我已经编写了一个小的Python脚本来针对各种情况进行优化。如果提供的数组已排序，则将是最佳情况。如果搜索一个指定值的最近点的索引，那么对半模块是最省时的。当一个索引对应一个数组时，numpy searchsorted是最有效的。

import numpy as np
import bisect
xarr = np.random.rand(int(1e7))

srt_ind = xarr.argsort()
xar = xarr.copy()[srt_ind]
xlist = xar.tolist()
bisect.bisect_left(xlist, 0.3)

In[63]: %时间平分。bisect_left (xlist, 0.3) CPU次数:user 0ns, sys: 0ns, total: 0ns 壁时间:22.2µs

np.searchsorted(xar, 0.3, side="left")

In [64]: %time np。Searchsorted (xar, 0.3, side="left") CPU次数:user 0ns, sys: 0ns, total: 0ns 壁时间:98.9µs

randpts = np.random.rand(1000)
np.searchsorted(xar, randpts, side="left")

%的时间np。Searchsorted (xar, randpts, side="left") CPU次数:用户4ms, sys: 0ns, total: 4ms 壁时间:1.2 ms

如果我们遵循乘法规则，那么numpy应该花费~100 ms，这意味着快了~83倍。

下面是一个使用2D数组的版本，如果用户拥有scipy的cdist函数，则使用它，如果用户没有，则使用更简单的距离计算。

默认情况下，输出是最接近输入值的索引，但您可以使用output关键字将其更改为'index'， 'value'或'both'之一，其中'value'输出数组[index]， 'both'输出索引，数组[index]。

对于非常大的数组，您可能需要使用kind='euclidean'，因为默认的scipy cdist函数可能会耗尽内存。

这可能不是绝对最快的解决方案，但已经很接近了。

def find_nearest_2d(array, value, kind='cdist', output='index'):
    # 'array' must be a 2D array
    # 'value' must be a 1D array with 2 elements
    # 'kind' defines what method to use to calculate the distances. Can choose one
    #    of 'cdist' (default) or 'euclidean'. Choose 'euclidean' for very large
    #    arrays. Otherwise, cdist is much faster.
    # 'output' defines what the output should be. Can be 'index' (default) to return
    #    the index of the array that is closest to the value, 'value' to return the
    #    value that is closest, or 'both' to return index,value
    import numpy as np
    if kind == 'cdist':
        try: from scipy.spatial.distance import cdist
        except ImportError:
            print("Warning (find_nearest_2d): Could not import cdist. Reverting to simpler distance calculation")
            kind = 'euclidean'
    index = np.where(array == value)[0] # Make sure the value isn't in the array
    if index.size == 0:
        if kind == 'cdist': index = np.argmin(cdist([value],array)[0])
        elif kind == 'euclidean': index = np.argmin(np.sum((np.array(array)-np.array(value))**2.,axis=1))
        else: raise ValueError("Keyword 'kind' must be one of 'cdist' or 'euclidean'")
    if output == 'index': return index
    elif output == 'value': return array[index]
    elif output == 'both': return index,array[index]
    else: raise ValueError("Keyword 'output' must be one of 'index', 'value', or 'both'")

如果你有很多值需要搜索(值可以是多维数组)，下面是@Dimitri的快速向量化解决方案:

# `values` should be sorted
def get_closest(array, values):
    # make sure array is a numpy array
    array = np.array(array)

    # get insert positions
    idxs = np.searchsorted(array, values, side="left")
    
    # find indexes where previous index is closer
    prev_idx_is_less = ((idxs == len(array))|(np.fabs(values - array[np.maximum(idxs-1, 0)]) < np.fabs(values - array[np.minimum(idxs, len(array)-1)])))
    idxs[prev_idx_is_less] -= 1
    
    return array[idxs]

基准

>使用@Demitri的解决方案比使用for循环快100倍”

>>> %timeit ar=get_closest(np.linspace(1, 1000, 100), np.random.randint(0, 1050, (1000, 1000)))
139 ms ± 4.04 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)

>>> %timeit ar=[find_nearest(np.linspace(1, 1000, 100), value) for value in np.random.randint(0, 1050, 1000*1000)]
took 21.4 seconds

也许对ndarray有帮助:

def find_nearest(X, value):
    return X[np.unravel_index(np.argmin(np.abs(X - value)), X.shape)]

下面是一个处理非标量“values”数组的版本:

import numpy as np

def find_nearest(array, values):
    indices = np.abs(np.subtract.outer(array, values)).argmin(0)
    return array[indices]

如果输入是标量，则返回数字类型(例如int, float)的版本:

def find_nearest(array, values):
    values = np.atleast_1d(values)
    indices = np.abs(np.subtract.outer(array, values)).argmin(0)
    out = array[indices]
    return out if len(out) > 1 else out[0]