File size: 5,908 Bytes
093b0a5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 | from typing import List
import numpy as np
import pandas as pd
from pandas.tseries import offsets
from pandas.tseries.frequencies import to_offset
class TimeFeature:
def __init__(self):
pass
def __call__(self, index: pd.DatetimeIndex) -> np.ndarray:
pass
def __repr__(self):
return self.__class__.__name__ + "()"
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 - 0.5
def time_features_from_frequency_str(freq_str: str) -> List[TimeFeature]:
"""
Returns a list of time features that will be appropriate for the given frequency string.
Parameters
----------
freq_str
Frequency string of the form [multiple][granularity] such as "12H", "5min", "1D" etc.
"""
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,
],
}
offset = to_offset(freq_str)
for offset_type, feature_classes in features_by_offsets.items():
if isinstance(offset, offset_type):
return [cls() for cls in feature_classes]
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)
def time_features(dates, timeenc=1, 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
elif 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)
elif timeenc == 2:
# Time2Vec
dates = pd.to_datetime(dates.date.values)
return np.vstack(
[feat(dates) for feat in time_features_from_frequency_str(freq)]
).transpose(1, 0)
|