Speed ​​up comparison of floats between lists

Question

I have a block of code that does the following:

• take the float from the list b_lstbelow the indexindx
• check if this float is between the floating point of the index iand the next (index i+1) in the lista_lst
• if it is, then save it indxin a sub-list of the third list ( c_lst), where the index of the sub-list is an index of the left in the float a_lst(ie: i)
• repeat for all floats in b_lst

Here is a MWE, which shows what the code is doing:

import numpy as np
import timeit

def random_data(N):
    # Generate some random data.
    return np.random.uniform(0., 10., N).tolist()

# Data lists.
# Note that a_lst is sorted.
a_lst = np.sort(random_data(1000))
b_lst = random_data(5000)
# Fixed index value (int)
c = 25

def func():
    # Create empty list with as many sub-lists as elements present
    # in a_lst beyond the 'c' index.
    c_lst = [[] for _ in range(len(a_lst[c:])-1)]

    # For each element in b_lst.
    for indx,elem in enumerate(b_lst):

        # For elements in a_lst beyond the 'c' index.
        for i in range(len(a_lst[c:])-1):

            # Check if 'elem' is between this a_lst element
            # and the next.
            if a_lst[c+i] < elem <= a_lst[c+(i+1)]:

                # If it is then store the index of 'elem' ('indx')
                # in the 'i' sub-list of c_lst.
                c_lst[i].append(indx)

    return c_lst

print func()
# time function.
func_time = timeit.timeit(func, number=10)
print func_time

This code works as it should, but I really need to improve its performance, as it slows down the rest of my code.

---

Add

, . , .

def func_opt():
    c_lst = [[] for _ in range(len(a_lst[c:])-1)]
    c_opt = np.searchsorted(a_lst[c:], b_lst, side='left')
    for elem in c_opt:
        if 0<elem<len(a_lst[c:]):
            c_lst[elem-1] = np.where(c_opt==elem)[0].tolist()
    return c_lst

~ 7 , .

---

2

np.where:

def func_opt2():
    c_lst = [[] for _ in range(len(a_lst[c:])-1)]
    c_opt = np.searchsorted(a_lst[c:], b_lst, side='left')
    for indx,elem in enumerate(c_opt):
        if 0<elem<len(a_lst[c:]):
            c_lst[elem-1].append(indx)
    return c_lst

130 , .

---

3

jtaylor, np.searchsorted .tolist():

def func_opt3():
    c_lst = [[] for _ in range(len(a_lst[c:])-1)]
    c_opt = np.searchsorted(a_lst[c:], b_lst, side='left').tolist()
    for indx,elem in enumerate(c_opt):
        if 0<elem<len(a_lst[c:]):
            c_lst[elem-1].append(indx)
    return c_lst

~ 470x , .

Answer 1

numpy searchsorted.

np.searchsorted(a_lst, b_lst, side='right')

, , b_lst, , a_lst . , , C. , :

>>> a = np.arange(1, 10)
>>> b = np.random.rand(100) * 10
>>> c = np.searchsorted(a, b, side='right')
>>> b[c == 0]
array([ 0.54620226,  0.40043875,  0.62398925,  0.40097674,  0.58765603,
        0.14045264,  0.16990249,  0.78264088,  0.51507254,  0.31808327,
        0.03895417,  0.92130027])
>>> b[c == 1]
array([ 1.34599709,  1.42645778,  1.13025996,  1.20096723,  1.75724448,
        1.87447058,  1.23422399,  1.37807553,  1.64118058,  1.53740299])