Python：如何从日期列表中计算日期范围？

Question

我有一个日期列表，例如：

['2011-02-27', '2011-02-28', '2011-03-01', '2011-04-12', '2011-04-13', '2011-06-08']

如何找到这些日期中包含的连续日期范围？在上面的例子中，范围应该是：

[{"start_date": '2011-02-27', "end_date": '2011-03-01'},
 {"start_date": '2011-04-12', "end_date": '2011-04-13'},
 {"start_date": '2011-06-08', "end_date": '2011-06-08'}
]

谢谢。

Answer 1

这行得通，但我对此不满意，将使用更清洁的解决方案并编辑答案。完成，这是一个干净、有效的解决方案：

import datetime
import pprint

def parse(date):
    return datetime.date(*[int(i) for i in date.split('-')])

def get_ranges(dates):
    while dates:
        end = 1
        try:
            while dates[end] - dates[end - 1] == datetime.timedelta(days=1):
                end += 1
        except IndexError:
            pass

        yield {
            'start-date': dates[0],
            'end-date': dates[end-1]
        }
        dates = dates[end:]

dates = [
    '2011-02-27', '2011-02-28', '2011-03-01',
    '2011-04-12', '2011-04-13',
    '2011-06-08'
]

# Parse each date and convert it to a date object. Also ensure the dates
# are sorted, you can remove 'sorted' if you don't need it
dates = sorted([parse(d) for d in dates]) 

pprint.pprint(list(get_ranges(dates)))

以及相对输出：

[{'end-date': datetime.date(2011, 3, 1),
  'start-date': datetime.date(2011, 2, 27)},
 {'end-date': datetime.date(2011, 4, 13),
  'start-date': datetime.date(2011, 4, 12)},
 {'end-date': datetime.date(2011, 6, 8),
  'start-date': datetime.date(2011, 6, 8)}]

Answer 2

正在尝试忍者 GaretJax 的编辑：;)

def date_to_number(date):
  return datetime.date(*[int(i) for i in date.split('-')]).toordinal()

def number_to_date(number):
  return datetime.date.fromordinal(number).strftime('%Y-%m-%d')

def day_ranges(dates):
  day_numbers = set(date_to_number(d) for d in dates)
  start = None
  # We loop including one element guaranteed not to be in the set, to force the
  # closing of any range that's currently open.
  for n in xrange(min(day_numbers), max(day_numbers) + 2):
    if start == None:
      if n in day_numbers: start = n
    else:
      if n not in day_numbers: 
        yield {
          'start_date': number_to_date(start),
          'end_date': number_to_date(n - 1)
        }
        start = None

list(
  day_ranges([
    '2011-02-27', '2011-02-28', '2011-03-01',
    '2011-04-12', '2011-04-13', '2011-06-08'
  ])
)

Answer 3

from datetime import datetime, timedelta

dates = ['2011-02-27', '2011-02-28', '2011-03-01', '2011-04-12', '2011-04-13', '2011-06-08']
d = [datetime.strptime(date, '%Y-%m-%d') for date in dates]
test = lambda x: x[1] - x[0] != timedelta(1)
slices = [0] + [i+1 for i, x in enumerate(zip(d, d[1:])) if test(x)] + [len(dates)]
ranges = [{"start_date": dates[s], "end_date": dates[e-1]} for s, e in zip(slices, slices[1:])]

结果如下：

>>> pprint.pprint(ranges)
[{'end_date': '2011-03-01', 'start_date': '2011-02-27'},
 {'end_date': '2011-04-13', 'start_date': '2011-04-12'},
 {'end_date': '2011-06-08', 'start_date': '2011-06-08'}]

slices 列表解析获取上一个日期不是当前日期前一天的所有索引。在前面加上0，在最后加上len(dates)，每个日期范围都可以描述为dates[slices[i]:slices[i+1]-1]。

Answer 4

我对主题的细微改动（我最初构建了开始/结束列表并将它们压缩以返回元组，但我更喜欢@Karl Knechtel 的生成器方法）：

from datetime import date, timedelta

ONE_DAY = timedelta(days=1)

def find_date_windows(dates):
    # guard against getting empty list
    if not dates:
        return

    # convert strings to sorted list of datetime.dates
    dates = sorted(date(*map(int,d.split('-'))) for d in dates)

    # build list of window starts and matching ends
    lastStart = lastEnd = dates[0]
    for d in dates[1:]:
        if d-lastEnd > ONE_DAY:
            yield {'start_date':lastStart, 'end_date':lastEnd}
            lastStart = d
        lastEnd = d
    yield {'start_date':lastStart, 'end_date':lastEnd}

这里是测试用例：

tests = [
    ['2011-02-27', '2011-02-28', '2011-03-01', '2011-04-12', '2011-04-13', '2011-06-08'],
    ['2011-06-08'],
    [],
    ['2011-02-27', '2011-02-28', '2011-03-01', '2011-04-12', '2011-04-13', '2011-06-08', '2011-06-10'],
]
for dates in tests:
    print dates
    for window in find_date_windows(dates):
        print window
    print

打印：

['2011-02-27', '2011-02-28', '2011-03-01', '2011-04-12', '2011-04-13', '2011-06-08']
{'start_date': datetime.date(2011, 2, 27), 'end_date': datetime.date(2011, 3, 1)}
{'start_date': datetime.date(2011, 4, 12), 'end_date': datetime.date(2011, 4, 13)}
{'start_date': datetime.date(2011, 6, 8), 'end_date': datetime.date(2011, 6, 8)}

['2011-06-08']
{'start_date': datetime.date(2011, 6, 8), 'end_date': datetime.date(2011, 6, 8)}

[]

['2011-02-27', '2011-02-28', '2011-03-01', '2011-04-12', '2011-04-13', '2011-06-08', '2011-06-10']
{'start_date': datetime.date(2011, 2, 27), 'end_date': datetime.date(2011, 3, 1)}
{'start_date': datetime.date(2011, 4, 12), 'end_date': datetime.date(2011, 4, 13)}
{'start_date': datetime.date(2011, 6, 8), 'end_date': datetime.date(2011, 6, 8)}
{'start_date': datetime.date(2011, 6, 10), 'end_date': datetime.date(2011, 6, 10)}

Answer 5

这是一个替代解决方案：它返回一个 (start,finish) 的列表元组，因为这正是我所需要的 ;)。

这会改变列表，所以我需要复制一份。显然，这会增加内存使用量。我怀疑 list.pop() 效率不是很高，但这可能取决于 python 中 list 的实现。

def collapse_dates(date_list):
    if not date_list:
        return date_list
    result = []
    # We are going to alter the list, so create a (sorted) copy.
    date_list = sorted(date_list)
    while len(date_list):
        # Grab the first item: this is both the start and end of the range.
        start = current = date_list.pop(0)
        # While the first item in the list is the next day, pop that and
        # set it to the end of the range.
        while len(date_list) and date_list[0] == current + datetime.timedelta(1):
            current = date_list.pop(0)
        # That's a completed range.
        result.append((start,current))

    return result

您可以轻松更改附加行以附加 dict，或 yield 而不是附加到列表。

哦，我假设它们已经是约会对象了。