Numpy：重新编码每个元素所属的五分数的数组

Question

我有一个数字向量a：

import numpy as np

a = np.random.rand(100)

我希望得到矢量（或任何其他矢量）重新编码，以便每个元素是0,1,2,3或4，根据a五分位数（对于任何分位数，可能更为一般，如四分位数，十分位数）等等。）。

这就是我正在做的事情。必须有更优雅的东西，不是吗？

from scipy.stats import percentileofscore

n_quantiles = 5

def get_quantile(i, a, n_quantiles):
    if a[i] >= max(a):
        return n_quantiles - 1
    return int(percentileofscore(a, a[i])/(100/n_quantiles))

a_recoded = np.array([get_quantile(i, a, n_quantiles) for i in range(len(a))])

print(a)
print(a_recoded)

[0.04708996 0.86267278 0.23873192 0.02967989 0.42828385 0.58003015
 0.8996666  0.15359369 0.83094778 0.44272398 0.60211289 0.90286434
 0.40681163 0.91338397 0.3273745  0.00347029 0.37471307 0.72735901
 0.93974808 0.55937197 0.39297097 0.91470761 0.76796271 0.50404401
 0.1817242  0.78244809 0.9548256  0.78097562 0.90934337 0.89914752
 0.82899983 0.44116683 0.50885813 0.2691431  0.11676798 0.84971927
 0.38505195 0.7411976  0.51377242 0.50243197 0.89677377 0.69741088
 0.47880953 0.71116534 0.01717348 0.77641096 0.88127268 0.17925502
 0.53053573 0.16935597 0.65521692 0.19042794 0.21981197 0.01377195
 0.61553814 0.8544525  0.53521604 0.88391848 0.36010949 0.35964882
 0.29721931 0.71257335 0.26350287 0.22821314 0.8951419  0.38416004
 0.19277649 0.67774468 0.27084229 0.46862229 0.3107887  0.28511048
 0.32682302 0.14682896 0.10794566 0.58668243 0.16394183 0.88296862
 0.55442047 0.25508233 0.86670299 0.90549872 0.04897676 0.33042884
 0.4348465  0.62636481 0.48201213 0.49895892 0.36444648 0.01410316
 0.46770595 0.09498391 0.96793139 0.03931124 0.64286295 0.50934846
 0.59088907 0.56368594 0.7820928  0.77172038]

[0 4 1 0 2 3 4 0 4 2 3 4 2 4 1 0 1 3 4 2 1 4 3 2 0 3 4 3 4 4 4 2 2 1 0 4 1 
3 2 2 4 3 2 3 0 3 4 0 2 0 3 0 1 0 3 4 2 4 1 1 1 3 1 1 4 1 0 3 1 2 1 1 1 0 
0 3 0 4 2 1 4 4 0 1 2 3 2 2 1 0 2 0 4 0 3 2 3 2 3 3]

更新：只是想在R：How to get the x which belongs to a quintile?中说这很容易

Answer 1

你可以使用argpartition。例：

>>> a = np.random.random(20)
>>> N = len(a)
>>> nq = 5
>>> o = a.argpartition(np.arange(1, nq) * N // nq)
>>> out = np.empty(N, int)
>>> out[o] = np.arange(N) * nq // N
>>> a
array([0.61238649, 0.37168998, 0.4624829 , 0.28554766, 0.00098016,
       0.41979328, 0.62275886, 0.4254548 , 0.20380679, 0.762435  ,
       0.54054873, 0.68419986, 0.3424479 , 0.54971072, 0.06929464,
       0.51059431, 0.68448674, 0.97009023, 0.16780152, 0.17887862])
>>> out
array([3, 1, 2, 1, 0, 2, 3, 2, 1, 4, 3, 4, 1, 3, 0, 2, 4, 4, 0, 0])

Answer 2

这是使用pd.cut()做到这一点的一种方法

import pandas as pd
import numpy as np

df = pd.DataFrame(np.random.rand(100))
df.columns = ['values']
# Apply the quantiles
gdf = df.groupby(pd.cut(df.loc[:, 'values'], np.arange(0, 1.2, 0.2)))['values'].apply(lambda x: list(x)).to_frame()
# Make use of the automatic indexing to assign quantile numbers
gdf.reset_index(drop=True, inplace=True)
# Re-expand the grouped list of values. Method provided by @Zero at https://stackoverflow.com/questions/32468402/how-to-explode-a-list-inside-a-dataframe-cell-into-separate-rows
gdf['values'].apply(pd.Series).stack().reset_index(level=1, drop=True).to_frame('values').reset_index()