假设我有
bins = np.array([0, 0, 1, 1, 2, 2, 2, 0, 1, 2])
vals = np.array([8, 7, 3, 4, 1, 2, 6, 5, 0, 9])
k = 3
Run Code Online (Sandbox Code Playgroud)
我需要通过唯一bin中的最大值的位置bins.
# Bin == 0
# ? ? ?
# [0 0 1 1 2 2 2 0 1 2]
# [8 7 3 4 1 2 6 5 0 9]
# ? ? ?
# ?
# [0 1 2 3 4 5 6 7 8 9]
# Maximum is 8 and happens at position 0
(vals * (bins == 0)).argmax()
0
Run Code Online (Sandbox Code Playgroud)
# Bin == 1
# ? ? ?
# [0 0 1 1 2 2 2 0 1 2]
# [8 7 3 4 1 2 6 5 0 9]
# ? ? ?
# ?
# [0 1 2 3 4 5 6 7 8 9]
# Maximum is 4 and happens at position 3
(vals * (bins == 1)).argmax()
3
Run Code Online (Sandbox Code Playgroud)
# Bin == 2
# ? ? ? ?
# [0 0 1 1 2 2 2 0 1 2]
# [8 7 3 4 1 2 6 5 0 9]
# ? ? ? ?
# ?
# [0 1 2 3 4 5 6 7 8 9]
# Maximum is 9 and happens at position 9
(vals * (bins == 2)).argmax()
9
Run Code Online (Sandbox Code Playgroud)
这些功能很苛刻,甚至不能用于负值.
如何使用Numpy以最有效的方式获得所有这些值?
def binargmax(bins, vals, k):
out = -np.ones(k, np.int64)
trk = np.empty(k, vals.dtype)
trk.fill(np.nanmin(vals) - 1)
for i in range(len(bins)):
v = vals[i]
b = bins[i]
if v > trk[b]:
trk[b] = v
out[b] = i
return out
binargmax(bins, vals, k)
array([0, 3, 9])
Run Code Online (Sandbox Code Playgroud)
use*_*203 18
numpy_indexed库:我知道这不是技术上的numpy,但是numpy_indexed库有一个矢量化的group_by功能,这是完美的,只是想作为我经常使用的替代方案分享:
>>> import numpy_indexed as npi
>>> npi.group_by(bins).argmax(vals)
(array([0, 1, 2]), array([0, 3, 9], dtype=int64))
Run Code Online (Sandbox Code Playgroud)
pandas groupby和idxmax:df = pd.DataFrame({'bins': bins, 'vals': vals})
df.groupby('bins').vals.idxmax()
Run Code Online (Sandbox Code Playgroud)
sparse.csr_matrix对于非常大的输入,此选项非常快.
sparse.csr_matrix(
(vals, bins, np.arange(vals.shape[0]+1)), (vals.shape[0], k)
).argmax(0)
# matrix([[0, 3, 9]])
Run Code Online (Sandbox Code Playgroud)
功能
def chris(bins, vals, k):
return npi.group_by(bins).argmax(vals)
def chris2(df):
return df.groupby('bins').vals.idxmax()
def chris3(bins, vals, k):
sparse.csr_matrix((vals, bins, np.arange(vals.shape[0] + 1)), (vals.shape[0], k)).argmax(0)
def divakar(bins, vals, k):
mx = vals.max()+1
sidx = bins.argsort()
sb = bins[sidx]
sm = np.r_[sb[:-1] != sb[1:],True]
argmax_out = np.argsort(bins*mx + vals)[sm]
max_out = vals[argmax_out]
return max_out, argmax_out
def divakar2(bins, vals, k):
last_idx = np.bincount(bins).cumsum()-1
scaled_vals = bins*(vals.max()+1) + vals
argmax_out = np.argsort(scaled_vals)[last_idx]
max_out = vals[argmax_out]
return max_out, argmax_out
def user545424(bins, vals, k):
return np.argmax(vals*(bins == np.arange(bins.max()+1)[:,np.newaxis]),axis=-1)
def user2699(bins, vals, k):
res = []
for v in np.unique(bins):
idx = (bins==v)
r = np.where(idx)[0][np.argmax(vals[idx])]
res.append(r)
return np.array(res)
def sacul(bins, vals, k):
return np.lexsort((vals, bins))[np.append(np.diff(np.sort(bins)), 1).astype(bool)]
@njit
def piRSquared(bins, vals, k):
out = -np.ones(k, np.int64)
trk = np.empty(k, vals.dtype)
trk.fill(np.nanmin(vals))
for i in range(len(bins)):
v = vals[i]
b = bins[i]
if v > trk[b]:
trk[b] = v
out[b] = i
return out
Run Code Online (Sandbox Code Playgroud)
建立
import numpy_indexed as npi
import numpy as np
import pandas as pd
from timeit import timeit
import matplotlib.pyplot as plt
from numba import njit
from scipy import sparse
res = pd.DataFrame(
index=['chris', 'chris2', 'chris3', 'divakar', 'divakar2', 'user545424', 'user2699', 'sacul', 'piRSquared'],
columns=[10, 50, 100, 500, 1000, 5000, 10000, 50000, 100000, 500000],
dtype=float
)
k = 5
for f in res.index:
for c in res.columns:
bins = np.random.randint(0, k, c)
k = 5
vals = np.random.rand(c)
df = pd.DataFrame({'bins': bins, 'vals': vals})
stmt = '{}(df)'.format(f) if f in {'chris2'} else '{}(bins, vals, k)'.format(f)
setp = 'from __main__ import bins, vals, k, df, {}'.format(f)
res.at[f, c] = timeit(stmt, setp, number=50)
ax = res.div(res.min()).T.plot(loglog=True)
ax.set_xlabel("N");
ax.set_ylabel("time (relative)");
plt.show()
Run Code Online (Sandbox Code Playgroud)
结果
结果大得多k(这是广播受到重创的地方):
res = pd.DataFrame(
index=['chris', 'chris2', 'chris3', 'divakar', 'divakar2', 'user545424', 'user2699', 'sacul', 'piRSquared'],
columns=[10, 50, 100, 500, 1000, 5000, 10000, 50000, 100000, 500000],
dtype=float
)
k = 500
for f in res.index:
for c in res.columns:
bins = np.random.randint(0, k, c)
vals = np.random.rand(c)
df = pd.DataFrame({'bins': bins, 'vals': vals})
stmt = '{}(df)'.format(f) if f in {'chris2'} else '{}(bins, vals, k)'.format(f)
setp = 'from __main__ import bins, vals, df, k, {}'.format(f)
res.at[f, c] = timeit(stmt, setp, number=50)
ax = res.div(res.min()).T.plot(loglog=True)
ax.set_xlabel("N");
ax.set_ylabel("time (relative)");
plt.show()
Run Code Online (Sandbox Code Playgroud)
从图中可以明显看出,当组的数量很少时,广播是一个很好的技巧,但是广播的时间复杂度/存储器在较高k值时增加得太快以使其具有高性能.
Div*_*kar 18
这是通过抵消每个组数据的一种方式,以便我们可以argsort一次性使用整个数据 -
def binargmax_scale_sort(bins, vals):
w = np.bincount(bins)
valid_mask = w!=0
last_idx = w[valid_mask].cumsum()-1
scaled_vals = bins*(vals.max()+1) + vals
#unique_bins = np.flatnonzero(valid_mask) # if needed
return len(bins) -1 -np.argsort(scaled_vals[::-1], kind='mergesort')[last_idx]
Run Code Online (Sandbox Code Playgroud)
DSM*_*DSM 11
好的,这是我的线性时间条目,仅使用索引和np.(max|min)inum.at.它假设垃圾箱从0上升到最大(垃圾箱).
def via_at(bins, vals):
max_vals = np.full(bins.max()+1, -np.inf)
np.maximum.at(max_vals, bins, vals)
expanded = max_vals[bins]
max_idx = np.full_like(max_vals, np.inf)
np.minimum.at(max_idx, bins, np.where(vals == expanded, np.arange(len(bins)), np.inf))
return max_vals, max_idx
Run Code Online (Sandbox Code Playgroud)
这个怎么样:
>>> import numpy as np
>>> bins = np.array([0, 0, 1, 1, 2, 2, 2, 0, 1, 2])
>>> vals = np.array([8, 7, 3, 4, 1, 2, 6, 5, 0, 9])
>>> k = 3
>>> np.argmax(vals*(bins == np.arange(k)[:,np.newaxis]),axis=-1)
array([0, 3, 9])
Run Code Online (Sandbox Code Playgroud)
如果你想要阅读,这可能不是最好的解决方案,但我认为它有效
def binargsort(bins,vals):
s = np.lexsort((vals,bins))
s2 = np.sort(bins)
msk = np.roll(s2,-1) != s2
# or use this for msk, but not noticeably better for performance:
# msk = np.append(np.diff(np.sort(bins)),1).astype(bool)
return s[msk]
array([0, 3, 9])
Run Code Online (Sandbox Code Playgroud)
说明:
lexsortvals根据排序顺序对索引进行排序bins,然后按以下顺序排序vals:
>>> np.lexsort((vals,bins))
array([7, 1, 0, 8, 2, 3, 4, 5, 6, 9])
Run Code Online (Sandbox Code Playgroud)
那么你可以通过排序bins从一个索引到下一个索引的不同来掩盖:
>>> np.sort(bins)
array([0, 0, 0, 1, 1, 1, 2, 2, 2, 2])
# Find where sorted bins end, use that as your mask on the `lexsort`
>>> np.append(np.diff(np.sort(bins)),1)
array([0, 0, 1, 0, 0, 1, 0, 0, 0, 1])
>>> np.lexsort((vals,bins))[np.append(np.diff(np.sort(bins)),1).astype(bool)]
array([0, 3, 9])
Run Code Online (Sandbox Code Playgroud)
这是一个有趣的小问题需要解决.我的方法是vals根据中的值获取索引bins.使用where得到其中指数是点True结合argmax在丘壑这些点给出结果值.
def binargmaxA(bins, vals):
res = []
for v in unique(bins):
idx = (bins==v)
r = where(idx)[0][argmax(vals[idx])]
res.append(r)
return array(res)
Run Code Online (Sandbox Code Playgroud)
可以unique通过使用range(k)获取可能的bin值来删除调用.这会加快速度,但随着k的大小增加,性能也会下降.
def binargmaxA2(bins, vals, k):
res = []
for v in range(k):
idx = (bins==v)
r = where(idx)[0][argmax(vals[idx])]
res.append(r)
return array(res)
Run Code Online (Sandbox Code Playgroud)
最后一次尝试,比较每个值会大大减慢速度.此版本计算排序的值数组,而不是对每个唯一值进行比较.好吧,它实际上计算排序的索引,只在需要时获取排序值,因为这样可以避免一次将val加载到内存中.性能仍然随着垃圾箱的数量而扩展,但比之前慢得多.
def binargmaxB(bins, vals):
idx = argsort(bins) # Find sorted indices
split = r_[0, where(diff(bins[idx]))[0]+1, len(bins)] # Compute where values start in sorted array
newmax = [argmax(vals[idx[i1:i2]]) for i1, i2 in zip(split, split[1:])] # Find max for each value in sorted array
return idx[newmax +split[:-1]] # Convert to indices in unsorted array
Run Code Online (Sandbox Code Playgroud)
这是其他答案的一些基准.
使用更大的数据集(bins = randint(0, 30, 3000); vals = randn(3000); k = 30;)
还有一个更大的数据集(bins = randint(0, 30, 30000); vals = randn(30000); k = 30).令人惊讶的是,这并未改变解决方案之间的相对性能.
编辑我没有k随着可能的bin值的增加而改变,现在我已经修复了基准更均匀.
增加唯一bin值的数量也可能会对性能产生影响.Divakar和sacul的解决方案大多不受影响,而其他解决方案则具有相当大的影响力.
bins = randint(0, 1000, 30000); vals = randn(30000); k = 1000
编辑包括问题中参考代码的基准,它具有惊人的竞争力,尤其是更多的箱子.