java合并不连续的时间段_基于时间戳不完全匹配的pandas合并

考虑以下迷你版本的问题：

from io import StringIO

from pandas import read_csv, to_datetime

# how close do sessions have to be to be considered equal? (in minutes)

threshold = 5

# datetime column (combination of date + start_time)

dtc = [['date', 'start_time']]

# index column (above combination)

ixc = 'date_start_time'

df1 = read_csv(StringIO(u'''

date,start_time,employee_id,session_id

01/01/2016,02:03:00,7261824,871631182

01/01/2016,06:03:00,7261824,871631183

01/01/2016,11:01:00,7261824,871631184

01/01/2016,14:01:00,7261824,871631185

'''), parse_dates=dtc)

df2 = read_csv(StringIO(u'''

date,start_time,employee_id,session_id

01/01/2016,02:03:00,7261824,871631182

01/01/2016,06:05:00,7261824,871631183