定義了一套與時(shí)間特征相關(guān)的類(lèi)和函數(shù)，旨在從時(shí)間序列數(shù)據(jù)中提取有用的時(shí)間特征，以支持各種時(shí)間序列分析和預(yù)測(cè)任務(wù)?

from typing import Listimport numpy as np
import pandas as pd
from pandas.tseries import offsets
from pandas.tseries.frequencies import to_offset

1 TimeFeature 類(lèi)

• 這是一個(gè)基礎(chǔ)類(lèi)，其他與時(shí)間特征相關(guān)的類(lèi)都繼承自它。
• 它提供了一個(gè)基本框架，但沒(méi)有實(shí)現(xiàn)具體的功能。

class TimeFeature:def __init__(self):passdef __call__(self, index: pd.DatetimeIndex) -> np.ndarray:passdef __repr__(self):return self.__class__.__name__ + "()"

?2 時(shí)間特征類(lèi)

SecondOfMinute、MinuteOfHour、HourOfDay、DayOfWeek、DayOfMonth、DayOfYear、MonthOfYear、WeekOfYear：這些類(lèi)都繼承自TimeFeature，每個(gè)類(lèi)都實(shí)現(xiàn)了一個(gè)特定的時(shí)間特征提取方法。例如，HourOfDay類(lèi)提取一天中的小時(shí)數(shù)并進(jìn)行規(guī)范化處理，使得值在[-0.5, 0.5]之間。

class SecondOfMinute(TimeFeature):"""Minute of hour encoded as value between [-0.5, 0.5]"""def __call__(self, index: pd.DatetimeIndex) -> np.ndarray:return index.second / 59.0 - 0.5class MinuteOfHour(TimeFeature):"""Minute of hour encoded as value between [-0.5, 0.5]"""def __call__(self, index: pd.DatetimeIndex) -> np.ndarray:return index.minute / 59.0 - 0.5class HourOfDay(TimeFeature):"""Hour of day encoded as value between [-0.5, 0.5]"""def __call__(self, index: pd.DatetimeIndex) -> np.ndarray:return index.hour / 23.0 - 0.5class DayOfWeek(TimeFeature):"""Hour of day encoded as value between [-0.5, 0.5]"""def __call__(self, index: pd.DatetimeIndex) -> np.ndarray:return index.dayofweek / 6.0 - 0.5class DayOfMonth(TimeFeature):"""Day of month encoded as value between [-0.5, 0.5]"""def __call__(self, index: pd.DatetimeIndex) -> np.ndarray:return (index.day - 1) / 30.0 - 0.5class DayOfYear(TimeFeature):"""Day of year encoded as value between [-0.5, 0.5]"""def __call__(self, index: pd.DatetimeIndex) -> np.ndarray:return (index.dayofyear - 1) / 365.0 - 0.5class MonthOfYear(TimeFeature):"""Month of year encoded as value between [-0.5, 0.5]"""def __call__(self, index: pd.DatetimeIndex) -> np.ndarray:return (index.month - 1) / 11.0 - 0.5class WeekOfYear(TimeFeature):"""Week of year encoded as value between [-0.5, 0.5]"""def __call__(self, index: pd.DatetimeIndex) -> np.ndarray:return (index.week - 1) / 52.0 - 0.5

3 time_features_from_frwquency_str

def time_features_from_frequency_str(freq_str: str) -> List[TimeFeature]:"""根據(jù)給定的頻率字符串（如"12H", "5min", "1D"等）返回一組適當(dāng)?shù)臅r(shí)間特征類(lèi)實(shí)例"""features_by_offsets = {offsets.YearEnd: [],offsets.QuarterEnd: [MonthOfYear],offsets.MonthEnd: [MonthOfYear],offsets.Week: [DayOfMonth, WeekOfYear],offsets.Day: [DayOfWeek, DayOfMonth, DayOfYear],offsets.BusinessDay: [DayOfWeek, DayOfMonth, DayOfYear],offsets.Hour: [HourOfDay, DayOfWeek, DayOfMonth, DayOfYear],offsets.Minute: [MinuteOfHour,HourOfDay,DayOfWeek,DayOfMonth,DayOfYear,],offsets.Second: [SecondOfMinute,MinuteOfHour,HourOfDay,DayOfWeek,DayOfMonth,DayOfYear,],}'''特征映射字典 features_by_offsets:這個(gè)字典將pandas的時(shí)間偏移類(lèi)（如YearEnd、QuarterEnd、MonthEnd等）映射到對(duì)應(yīng)的時(shí)間特征類(lèi)列表。例如，對(duì)于每月的數(shù)據(jù)（MonthEnd），它映射到MonthOfYear類(lèi)；對(duì)于每小時(shí)的數(shù)據(jù)（Hour），它映射到HourOfDay、DayOfWeek、DayOfMonth和DayOfYear類(lèi)。'''offset = to_offset(freq_str)#使用pandas的to_offset函數(shù)將頻率字符串（如"12H"）轉(zhuǎn)換為相應(yīng)的pandas時(shí)間偏移對(duì)象。for offset_type, feature_classes in features_by_offsets.items():if isinstance(offset, offset_type):return [cls() for cls in feature_classes]'''遍歷映射字典，檢查提供的偏移對(duì)象是否屬于字典中的某個(gè)偏移類(lèi)型。如果找到匹配，為每個(gè)相關(guān)的特征類(lèi)創(chuàng)建一個(gè)實(shí)例，并將這些實(shí)例作為列表返回。'''supported_freq_msg = f"""Unsupported frequency {freq_str}The following frequencies are supported:Y   - yearlyalias: AM   - monthlyW   - weeklyD   - dailyB   - business daysH   - hourlyT   - minutelyalias: minS   - secondly"""raise RuntimeError(supported_freq_msg)

4?time_features

'''
從日期數(shù)據(jù)中提取有用的時(shí)間特征
'''
def time_features(dates, timeenc=0, freq='h'):"""> `time_features` takes in a `dates` dataframe with a 'dates' column and extracts the date down to `freq` where freq can be any of the following if `timeenc` is 0:> * m - [month]> * w - [month]> * d - [month, day, weekday]> * b - [month, day, weekday]> * h - [month, day, weekday, hour]> * t - [month, day, weekday, hour, *minute]>> If `timeenc` is 1, a similar, but different list of `freq` values are supported (all encoded between [-0.5 and 0.5]):> * Q - [month]> * M - [month]> * W - [Day of month, week of year]> * D - [Day of week, day of month, day of year]> * B - [Day of week, day of month, day of year]> * H - [Hour of day, day of week, day of month, day of year]> * T - [Minute of hour*, hour of day, day of week, day of month, day of year]> * S - [Second of minute, minute of hour, hour of day, day of week, day of month, day of year]*minute returns a number from 0-3 corresponding to the 15 minute period it falls into."""if timeenc==0:dates['month'] = dates.date.apply(lambda row:row.month,1)dates['day'] = dates.date.apply(lambda row:row.day,1)dates['weekday'] = dates.date.apply(lambda row:row.weekday(),1)dates['hour'] = dates.date.apply(lambda row:row.hour,1)dates['minute'] = dates.date.apply(lambda row:row.minute,1)dates['minute'] = dates.minute.map(lambda x:x//15)freq_map = {'y':[],'m':['month'],'w':['month'],'d':['month','day','weekday'],'b':['month','day','weekday'],'h':['month','day','weekday','hour'],'t':['month','day','weekday','hour','minute'],}return dates[freq_map[freq.lower()]].values'''此模式下，函數(shù)直接從日期中提取特定的時(shí)間特征，如月份、日期、星期幾、小時(shí)和分鐘。freq參數(shù)指定要提取的時(shí)間特征的精度。例如，如果freq為'd'，則提取月、日和星期幾。對(duì)于分鐘，它被轉(zhuǎn)換為一個(gè)從0到3的數(shù)字，表示15分鐘的時(shí)間段。'''if timeenc==1:dates = pd.to_datetime(dates.date.values)return np.vstack([feat(dates) for feat in time_features_from_frequency_str(freq)]).transpose(1,0)'''此模式下，函數(shù)使用time_features_from_frequency_str函數(shù)來(lái)獲取一組特征提取器，并應(yīng)用它們來(lái)轉(zhuǎn)換時(shí)間數(shù)據(jù)。這些特征提取器提取的特征被編碼在[-0.5, 0.5]的范圍內(nèi)，以提供規(guī)范化的時(shí)間特征。
freq參數(shù)在這種情況下也指定了提取的時(shí)間特征的類(lèi)型和精度。'''