>>> alist = ['foo', 'spam', 'egg', 'foo']
>>> foo_indexes = [n for n,x in enumerate(alist) if x=='foo']
>>> foo_indexes
[0, 3]
>>>
让我们把函数命名为findindex
这个函数以项目和列表作为参数，并返回项目在列表中的位置，就像我们前面看到的那样。
def indexlist(item2find, list_or_string):
"Returns all indexes of an item in a list or a string"
return [n for n,item in enumerate(list_or_string) if item==item2find]
print(indexlist("1", "010101010"))
输出
[1, 3, 5, 7]
简单的
for n, i in enumerate([1, 2, 3, 4, 1]):
if i == 1:
print(n)
def get_indices(x: list, value: int) -> list:
indices = list()
i = 0
while True:
try:
# find an occurrence of value and update i to that index
i = x.index(value, i)
# add i to the list
indices.append(i)
# advance i by 1
i += 1
except ValueError as e:
break
return indices
print(get_indices(n, -60))
>>> [4, 8, 9]
# np.where
start_times = []
end_times = []
for i in range(10000):
start = time.time()
start_times.append(start)
temp_list = np.array([1,2,3,3,5])
ixs = np.where(temp_list==3)[0].tolist()
end = time.time()
end_times.append(end)
print("Took on average {} seconds".format(
np.mean(end_times)-np.mean(start_times)))
Took on average 3.81469726562e-06 seconds
# list_comprehension
start_times = []
end_times = []
for i in range(10000):
start = time.time()
start_times.append(start)
temp_list = np.array([1,2,3,3,5])
ixs = [i for i in range(len(temp_list)) if temp_list[i]==3]
end = time.time()
end_times.append(end)
print("Took on average {} seconds".format(
np.mean(end_times)-np.mean(start_times)))
import numpy as np
import random # to create test list
# create sample list
random.seed(365)
l = [random.choice(['s1', 's2', 's3', 's4']) for _ in range(20)]
# convert the list to an array for use with these numpy methods
a = np.array(l)
# create a dict of each unique entry and the associated indices
idx = {v: np.where(a == v)[0].tolist() for v in np.unique(a)}
# print(idx)
{'s1': [7, 9, 10, 11, 17],
's2': [1, 3, 6, 8, 14, 18, 19],
's3': [0, 2, 13, 16],
's4': [4, 5, 12, 15]}
%timeit在2M元素列表中，有4个唯一的str元素
# create 2M element list
random.seed(365)
l = [random.choice(['s1', 's2', 's3', 's4']) for _ in range(2000000)]
功能
def test1():
# np.where: convert list to array and find indices of a single element
a = np.array(l)
return np.where(a == 's1')
def test2():
# list-comprehension: on list l and find indices of a single element
return [i for i, x in enumerate(l) if x == "s1"]
def test3():
# filter: on list l and find indices of a single element
return list(filter(lambda i: l[i]=="s1", range(len(l))))
def test4():
# use np.where and np.unique to find indices of all unique elements: convert list to array
a = np.array(l)
return {v: np.where(a == v)[0].tolist() for v in np.unique(a)}
def test5():
# list comprehension inside dict comprehension: on list l and find indices of all unique elements
return {req_word: [idx for idx, word in enumerate(l) if word == req_word] for req_word in set(l)}
214 ms ± 19.9 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
85.1 ms ± 1.48 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)
146 ms ± 1.65 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)
365 ms ± 11.4 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
360 ms ± 5.82 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
结果# EYZ0
209 ms ± 15.7 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
70.4 ms ± 1.86 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)
132 ms ± 4.65 ms per loop (mean ± std. dev. of 7 runs, 10 loops each)
371 ms ± 20.1 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
314 ms ± 15.9 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
def indices(iter, val):
"""Generator: Returns all indices of val in iter
Raises a ValueError if no val does not occur in iter
Passes on the AttributeError if iter does not have an index method (e.g. is a set)
"""
i = -1
NotFound = False
while not NotFound:
try:
i = iter.index(val, i+1)
except ValueError:
NotFound = True
else:
yield i
if i == -1:
raise ValueError("No occurrences of {v} in {i}".format(v = val, i = iter))
上面的代码可以用来创建索引列表:list(indices(input,value));使用它们作为字典键:dict(indices(input,value));求和:sum(indices(input,value));在for循环中for index_ in indices(input,value):;等……没有创建临时列表/元组或类似的。
@version("WhileTrueBreak", versions)
def indices2(iter, val):
i = -1
while True:
try:
i = iter.index(val, i+1)
except ValueError:
break
else:
yield i
@version("WhileErrFalse", versions)
def indices5(iter, val):
i = -1
err = False
while not err:
try:
i = iter.index(val, i+1)
except ValueError:
err = True
else:
yield i
@version("RemainingSlice", versions)
def indices1(iter, val):
i = 0
while val in iter[i:]:
i = iter.index(val, i)
yield i
i += 1
@version("LastOccurrence", versions)
def indices4(iter,val):
i = 0
last = len(iter) - tuple(reversed(iter)).index(val)
while i < last:
i = iter.index(val, i)
yield i
i += 1
