# python - structures - 给定一百万个数字的字符串,返回所有重复的3位数字

## python leetcode (9)

- 从C.的角度讲 - 你可以有一个int 3-d数组结果[10] [10] [10]; - 从第0位到第4位，其中n是字符串数组的大小。 - 在每个位置，检查当前，下一个和下一个下一个。 - 将cntr增加为resutls [current] [next] [next's next] ++; - 打印的价值

``````results[1][2][3]
results[2][3][4]
results[3][4][5]
results[4][5][6]
results[5][6][7]
results[6][7][8]
results[7][8][9]``````

- 这是O（n）时间，没有涉及比较。 - 你可以通过分区数组和计算分区周围的匹配来运行一些并行的东西。

``````123 - 3 times
234 - 3 times
345 - 2 times``````

000 - > 999

``````from collections import Counter

def triple_counter(s):
c = Counter(s[n-3: n] for n in range(3, len(s)))
for tri, n in c.most_common():
if n > 1:
print('%s - %i times.' % (tri, n))
else:
break

if __name__ == '__main__':
import random

s = ''.join(random.choice('0123456789') for _ in range(1_000_000))
triple_counter(s)``````

# 并行执行版本

``````def calc_repeating_digits(number):

hash = {}

for i in range(len(str(number))-2):

current_three_digits = number[i:i+3]
if current_three_digits in hash.keys():
hash[current_three_digits] += 1

else:
hash[current_three_digits] = 1

return hash``````

``````def setup_data(n):
import random
digits = "0123456789"
return dict(text = ''.join(random.choice(digits) for i in range(n)))

def f_np(text):
# Get the data into NumPy
import numpy as np
a = np.frombuffer(bytes(text, 'utf8'), dtype=np.uint8) - ord('0')
# Rolling triplets
a3 = np.lib.stride_tricks.as_strided(a, (3, a.size-2), 2*a.strides)

bins = np.zeros((10, 10, 10), dtype=int)
# Next line performs O(n) binning
np.add.at(bins, tuple(a3), 1)
# Filtering is left as an exercise
return bins.ravel()

def f_py(text):
counts = [0] * 1000
for idx in range(len(text)-2):
counts[int(text[idx:idx+3])] += 1
return counts

import numpy as np
import types
from timeit import timeit
for n in (10, 1000, 1000000):
data = setup_data(n)
ref = f_np(**data)
print(f'n = {n}')
for name, func in list(globals().items()):
if not name.startswith('f_') or not isinstance(func, types.FunctionType):
continue
try:
assert np.all(ref == func(**data))
print("{:16s}{:16.8f} ms".format(name[2:], timeit(
'f(**data)', globals={'f':func, 'data':data}, number=10)*100))
except:
print("{:16s} apparently crashed".format(name[2:]))``````

``````# n = 10
# np                    0.03481400 ms
# py                    0.00669330 ms
# n = 1000
# np                    0.11215360 ms
# py                    0.34836530 ms
# n = 1000000
# np                   82.46765980 ms
# py                  360.51235450 ms``````

``````from timeit import timeit
from collections import Counter
import types
import random

def setup_data(n):
digits = "0123456789"
return dict(text = ''.join(random.choice(digits) for i in range(n)))

def f_counter(text):
c = Counter()
for i in range(len(text)-2):
ss = text[i:i+3]
c.update([ss])
return (i for i in c.items() if i[1] > 1)

def f_dict(text):
d = {}
for i in range(len(text)-2):
ss = text[i:i+3]
if ss not in d:
d[ss] = 0
d[ss] += 1
return ((i, d[i]) for i in d if d[i] > 1)

def f_array(text):
a = [[[0 for _ in range(10)] for _ in range(10)] for _ in range(10)]
for n in range(len(text)-2):
i, j, k = (int(ss) for ss in text[n:n+3])
a[i][j][k] += 1
for i, b in enumerate(a):
for j, c in enumerate(b):
for k, d in enumerate(c):
if d > 1: yield (f'{i}{j}{k}', d)

for n in (1E1, 1E3, 1E6):
n = int(n)
data = setup_data(n)
print(f'n = {n}')
results = {}
for name, func in list(globals().items()):
if not name.startswith('f_') or not isinstance(func, types.FunctionType):
continue
print("{:16s}{:16.8f} ms".format(name[2:], timeit(
'results[name] = f(**data)', globals={'f':func, 'data':data, 'results':results, 'name':name}, number=10)*100))
for r in results:
print('{:10}: {}'.format(r, sorted(list(results[r]))[:5]))``````

``````n = 10
counter               0.10595780 ms
dict                  0.01070654 ms
array                 0.00135370 ms
f_counter : []
f_dict    : []
f_array   : []
n = 1000
counter               2.89462101 ms
dict                  0.40434612 ms
array                 0.00073838 ms
f_counter : [('008', 2), ('009', 3), ('010', 2), ('016', 2), ('017', 2)]
f_dict    : [('008', 2), ('009', 3), ('010', 2), ('016', 2), ('017', 2)]
f_array   : [('008', 2), ('009', 3), ('010', 2), ('016', 2), ('017', 2)]
n = 1000000
counter            2849.00500992 ms
dict                438.44007806 ms
array                 0.00135370 ms
f_counter : [('000', 1058), ('001', 943), ('002', 1030), ('003', 982), ('004', 1042)]
f_dict    : [('000', 1058), ('001', 943), ('002', 1030), ('003', 982), ('004', 1042)]
f_array   : [('000', 1058), ('001', 943), ('002', 1030), ('003', 982), ('004', 1042)]``````

``````inputStr = '123456123138276237284287434628736482376487234682734682736487263482736487236482634'

count = {}
for i in range(len(inputStr) - 2):
subNum = int(inputStr[i:i+3])
if subNum not in count:
count[subNum] = 1
else:
count[subNum] += 1

print count``````