python生成时间序列(date_range)

介绍

自己写了一个用python内置模块实现的生成时间序列的函数

支持自动推断字符串到datetime的转换, 但对格式有一定要求, 其它格式可手动指定格式化方式, 格式化方式与python内置格式化格式完全一致

支持输出格式化

以下是方法的源代码(python环境3.5以上, 没做更多版本的支持, 需要的自己稍作调整即可)

源代码

import re
import calendar
import datetime

class FormatError(ValueError):
    pass

class Date(object):
    @classmethod
    def date_range(cls, start=None, end=None, periods=None, freq=None, input_format=None, out_format=None):
        """
        生成时间序列
        :param start: 序列开始时间
        :param end: 序列结束时间, 给定start时, 结束时间不包含end
        :param periods: int, 生成的时间序列长度
        :param freq: 要生成时间序列的时间间隔
        :param out_format: 是否输出格式化后的字符串, 若要输出可指定输出格式. "%Y-%m-%d %H:%M:%S"
        :param input_format: 若start或end是字符串且无法自动推断时间格式则需指定格式
        :return: [date or date_str]
        """
        start = cls.str_to_date(start, input_format)
        end = cls.str_to_date(end, input_format)
        out = []
        if start is None and end and periods:
            for i in range(periods-1):
                old, end = cls.date_replace(end, cls._freq(freq), mod="-")
                if i == 0:
                    out.append(old)
                out = [end] + out
        elif end is None and start and periods:
            for i in range(periods-1):
                old, start = cls.date_replace(start, cls._freq(freq), mod="+")
                if i == 0:
                    out.append(old)
                out.append(start)
        elif periods is None and start and end:
            i = 0
            while True:
                old, start = cls.date_replace(start, cls._freq(freq), mod="+")
                if i == 0:
                    out.append(old)
                    i += 1
                if start < end:
                    out.append(start)
                else:
                    break
        else:
            raise ValueError("start, end, periods 须且只能指定其中两个")
        if out_format is True:
            out = [str(i) for i in out]
        elif out_format is not None:
            out = [i.strftime(out_format) for i in out]
        return out

    @staticmethod
    def date_replace(date, freq=(0, )*6, mod="+"):
        timedelta = datetime.timedelta(days=freq[2], hours=freq[3], minutes=freq[4], seconds=freq[5])
        if mod == "+":
            if sum(freq[:2]) == 0:
                old = date
                date = date + timedelta
            elif sum(freq[2:]) == 0:
                y = date.year + freq[0] + (date.month + freq[1] - 1) // 12
                m = (date.month + freq[1] - 1) % 12 + 1
                old = date.replace(day=calendar.monthrange(date.year, date.month)[1])
                date = date.replace(year=y, month=m, day=calendar.monthrange(y, m)[1])
            else:
                raise ValueError(" '年月' 不能同时和 '日时分秒' 作为间隔")
        elif mod == "-":
            if sum(freq[:2]) == 0:
                old = date
                date = date - timedelta
            elif sum(freq[2:]) == 0:
                y = date.year - freq[0] + (date.month - freq[1] - 1) // 12
                m = (date.month - freq[1] - 1) % 12 + 1
                old = date.replace(day=calendar.monthrange(date.year, date.month)[1])
                date = date.replace(year=y, month=m, day=calendar.monthrange(y, m)[1])
            else:
                raise ValueError(" '年月' 不能同时和 '日时分秒' 作为间隔")
        else:
            raise ValueError("mod值只能是 '+' 或 '-' ")
        return old, date

    @staticmethod
    def _freq(freq=None):
        """
        设置时间间隔
        :param freq: "Y2m3d4H5M6S" 表示间隔 1年2月3日4时5分6秒
        :return: [年, 月, 日, 时, 分, 秒]
        """
        freq_ = [0] * 6
        if freq is None:
            freq_[2] = 1
            return freq_
        for n, i in enumerate(["Y", "m", "d", "H", "M", "S"]):
            r = f'((\d*){i})'
            s = re.search(r, freq)
            if s:
                freq_[n] = int(s.group(2)) if s.group(2) else 1
        return freq_

    @staticmethod
    def str_to_date(string, format_=None):
        """
        字符串转时间, 默认自动推断格式
        :param string: 时间字符串
        :param format_: 格式
        :return: 对应的时间类型, 输入非字符串则原值输出
        """
        if not isinstance(string, str):
            return string
        if format_:
            return datetime.datetime.strptime(string, format_)
        s = re.match(r'(\d{4})\D+(\d{1,2})\D+(\d{1,2})(?:\D+(\d{1,2}))?(?:\D+(\d{1,2}))?(?:\D+(\d{1,2}))?\D*$', string)
        if s:
            result = [int(i) for i in s.groups() if i]
            return datetime.datetime(*result)
        s = re.match(r'(\d{4})\D*(\d{2})\D*(\d{2})\D*(\d{2})?\D*(\d{2})?\D*(\d{2})?\D*$', string)
        if s:
            result = [int(i) for i in s.groups() if i]
            return datetime.datetime(*result)
        else:
            raise FormatError("自动推断失败, 请指定format_")

使用方式

print(Date.date_range(datetime.datetime(2018, 9, 18), periods=10))
print()
print(Date.date_range('20180918', '2018-09-28'))
print()
print(Date.date_range(end='20180927', periods=10))
print()
print(Date.date_range('20180918', '2018-09-28', out_format=True))
print()
print(Date.date_range('2018/09/18', '2018-09-28', out_format="%Y-%m-%d"))
print()
print(Date.date_range('2018年9月18日', '2019-09-28', freq="m", out_format="%Y-%m-%d"))
print()
print(Date.date_range('2018/9/18', '2018-9-19', freq="3H", out_format=True))

对应结果

[datetime.datetime(2018, 9, 18, 0, 0), datetime.datetime(2018, 9, 19, 0, 0), datetime.datetime(2018, 9, 20, 0, 0), datetime.datetime(2018, 9, 21, 0, 0), datetime.datetime(2018, 9, 22, 0, 0), datetime.datetime(2018, 9, 23, 0, 0), datetime.datetime(2018, 9, 24, 0, 0), datetime.datetime(2018, 9, 25, 0, 0), datetime.datetime(2018, 9, 26, 0, 0), datetime.datetime(2018, 9, 27, 0, 0)]

[datetime.datetime(2018, 9, 18, 0, 0), datetime.datetime(2018, 9, 19, 0, 0), datetime.datetime(2018, 9, 20, 0, 0), datetime.datetime(2018, 9, 21, 0, 0), datetime.datetime(2018, 9, 22, 0, 0), datetime.datetime(2018, 9, 23, 0, 0), datetime.datetime(2018, 9, 24, 0, 0), datetime.datetime(2018, 9, 25, 0, 0), datetime.datetime(2018, 9, 26, 0, 0), datetime.datetime(2018, 9, 27, 0, 0)]

[datetime.datetime(2018, 9, 18, 0, 0), datetime.datetime(2018, 9, 19, 0, 0), datetime.datetime(2018, 9, 20, 0, 0), datetime.datetime(2018, 9, 21, 0, 0), datetime.datetime(2018, 9, 22, 0, 0), datetime.datetime(2018, 9, 23, 0, 0), datetime.datetime(2018, 9, 24, 0, 0), datetime.datetime(2018, 9, 25, 0, 0), datetime.datetime(2018, 9, 26, 0, 0), datetime.datetime(2018, 9, 27, 0, 0)]

['2018-09-18 00:00:00', '2018-09-19 00:00:00', '2018-09-20 00:00:00', '2018-09-21 00:00:00', '2018-09-22 00:00:00', '2018-09-23 00:00:00', '2018-09-24 00:00:00', '2018-09-25 00:00:00', '2018-09-26 00:00:00', '2018-09-27 00:00:00']

['2018-09-18', '2018-09-19', '2018-09-20', '2018-09-21', '2018-09-22', '2018-09-23', '2018-09-24', '2018-09-25', '2018-09-26', '2018-09-27']

['2018-09-30', '2018-10-31', '2018-11-30', '2018-12-31', '2019-01-31', '2019-02-28', '2019-03-31', '2019-04-30', '2019-05-31', '2019-06-30', '2019-07-31', '2019-08-31']

['2018-09-18 00:00:00', '2018-09-18 03:00:00', '2018-09-18 06:00:00', '2018-09-18 09:00:00', '2018-09-18 12:00:00', '2018-09-18 15:00:00', '2018-09-18 18:00:00', '2018-09-18 21:00:00']