Group timestamps at 20 second intervals
from datetime import datetime, timedelta
d = datetime.now()
data = [d + timedelta(minutes=i) for i in range(100)]
# prepare and group the data
from itertools import groupby
def get_key(d):
# group by 30 minutes
k = d + timedelta(minutes=-(d.minute % 20))
return datetime(k.year, k.month, k.day, k.hour, k.minute, 0)
g = groupby(sorted(data), key=get_key)
# print data
for key, items in g:
print(key)
for item in items:
print('-', item)
I have a large set of timestamps and I want to group them into 20 second windows. The above code works really well, grouping it in minutes, but I can't get it to work for grouping in 20 seconds.
+3
source to share
1 answer
The group must have a seconds field:
Code:
import datetime as dt
def get_key(d):
# group by 20 seconds
k = d - dt.timedelta(seconds=d.second % 20)
return dt.datetime(k.year, k.month, k.day, k.hour, k.minute, k.second)
Test code:
d = dt.datetime.now()
data = [d + dt.timedelta(seconds=i*5) for i in range(20)]
# prepare and group the data
import itertools as it
g = it.groupby(sorted(data), key=get_key)
# print data
for key, items in g:
print(key)
for item in items:
print('-', item)
Results:
2017-04-07 17:51:00
- 2017-04-07 17:51:16.372000
2017-04-07 17:51:20
- 2017-04-07 17:51:21.372000
- 2017-04-07 17:51:26.372000
- 2017-04-07 17:51:31.372000
- 2017-04-07 17:51:36.372000
2017-04-07 17:51:40
- 2017-04-07 17:51:41.372000
- 2017-04-07 17:51:46.372000
- 2017-04-07 17:51:51.372000
- 2017-04-07 17:51:56.372000
2017-04-07 17:52:00
- 2017-04-07 17:52:01.372000
- 2017-04-07 17:52:06.372000
- 2017-04-07 17:52:11.372000
- 2017-04-07 17:52:16.372000
2017-04-07 17:52:20
- 2017-04-07 17:52:21.372000
- 2017-04-07 17:52:26.372000
- 2017-04-07 17:52:31.372000
- 2017-04-07 17:52:36.372000
2017-04-07 17:52:40
- 2017-04-07 17:52:41.372000
- 2017-04-07 17:52:46.372000
- 2017-04-07 17:52:51.372000
+3
source to share