informer辅助笔记：utils/timefeatures.py
定义了一套与时间特征相关的类和函数，旨在从时间序列数据中提取有用的时间特征，以支持各种时间序列分析和预测任务
from typing import List
import numpy as np
import pandas as pd
from pandas.tseries import offsets
from pandas.tseries.frequencies import to_offset1 TimeFeature 类
- 这是一个基础类，其他与时间特征相关的类都继承自它。
- 它提供了一个基本框架，但没有实现具体的功能。
class TimeFeature:
def __init__(self):
pass
def __call__(self, index: pd.DatetimeIndex) -> np.ndarray:
pass
def __repr__(self):
return self.__class__.__name__ + "()"2 时间特征类
SecondOfMinute、MinuteOfHour、HourOfDay、DayOfWeek、DayOfMonth、DayOfYear、MonthOfYear、WeekOfYear：这些类都继承自TimeFeature，每个类都实现了一个特定的时间特征提取方法。例如，HourOfDay类提取一天中的小时数并进行规范化处理，使得值在[-0.5, 0.5]之间。
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 - 0.5
class 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 - 0.5
class 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 - 0.5
class 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 - 0.5
class 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 - 0.5
class 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 - 0.5
class 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 - 0.5
class 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 - 0.53 time_features_from_frwquency_str
def time_features_from_frequency_str(freq_str: str) -> List[TimeFeature]:
"""
根据给定的频率字符串（如"12H", "5min", "1D"等）返回一组适当的时间特征类实例
"""
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:
这个字典将pandas的时间偏移类（如YearEnd、QuarterEnd、MonthEnd等）映射到对应的时间特征类列表。
例如，对于每月的数据（MonthEnd），它映射到MonthOfYear类；
对于每小时的数据（Hour），它映射到HourOfDay、DayOfWeek、DayOfMonth和DayOfYear类。
'''
offset = to_offset(freq_str)
#使用pandas的to_offset函数将频率字符串（如"12H"）转换为相应的pandas时间偏移对象。
for offset_type, feature_classes in features_by_offsets.items():
if isinstance(offset, offset_type):
return [cls() for cls in feature_classes]
'''
遍历映射字典，检查提供的偏移对象是否属于字典中的某个偏移类型。
如果找到匹配，为每个相关的特征类创建一个实例，并将这些实例作为列表返回。
'''
supported_freq_msg = f"""
Unsupported frequency {freq_str}
The following frequencies are supported:
Y - yearly
alias: A
M - monthly
W - weekly
D - daily
B - business days
H - hourly
T - minutely
alias: min
S - secondly
"""
raise RuntimeError(supported_freq_msg)4 time_features
'''
从日期数据中提取有用的时间特征
'''
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，函数直接从日期中提取特定的时间特征，如月份、日期、星期几、小时和分钟。
freq参数指定要提取的时间特征的精度。例如，如果freq为'd'，则提取月、日和星期几。
对于分钟，它被转换为一个从0到3的数字，表示15分钟的时间段。
'''
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，函数使用time_features_from_frequency_str函数来获取一组特征提取器，并应用它们来转换时间数据。
这些特征提取器提取的特征被编码在[-0.5, 0.5]的范围内，以提供规范化的时间特征。
freq参数在这种情况下也指定了提取的时间特征的类型和精度。
'''