File size: 4,619 Bytes
6a35a44 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 | from __future__ import annotations
from dataclasses import dataclass
import numpy as np
import pandas as pd
from smc_framework.time._utils import get_datetime_utc
@dataclass(frozen=True)
class HTFResampleParams:
"""
Causal HTF resampling v0.1.
Exemple avec timeframe="1h":
LTF bars:
10:00
10:15
10:30
10:45
HTF candle:
open = 10:00
close = fin de 10:45 candle
Elle devient disponible à:
11:00
La colonne `htf_available_time` représente donc
la première date à laquelle le contenu HTF est causalement connu.
"""
timeframe: str = "1h"
volume_column: str = "volume"
def resample_htf_ohlcv(
df: pd.DataFrame,
params: HTFResampleParams = HTFResampleParams(),
) -> pd.DataFrame:
required = {
"open",
"high",
"low",
"close",
}
missing = required.difference(
df.columns
)
if missing:
raise ValueError(
"resample_htf_ohlcv(): "
f"colonnes manquantes: {sorted(missing)}"
)
dt = get_datetime_utc(
df
)
work = df.copy()
work["_mtf_datetime"] = dt
work = work.set_index(
"_mtf_datetime",
drop=True,
)
aggregation = {
"open":
"first",
"high":
"max",
"low":
"min",
"close":
"last",
}
if (
params.volume_column
in work.columns
):
aggregation[
params.volume_column
] = "sum"
# -------------------------------------------------------------------------
# closed="left", label="right"
#
# [10:00, 11:00) is labelled 11:00.
#
# Therefore the HTF candle appears exactly when it is complete.
# -------------------------------------------------------------------------
htf = (
work
.resample(
params.timeframe,
closed="left",
label="right",
origin="epoch",
)
.agg(
aggregation
)
)
htf = htf.dropna(
subset=[
"open",
"high",
"low",
"close",
]
)
htf = htf.reset_index()
htf = htf.rename(
columns={
"_mtf_datetime":
"datetime",
}
)
htf[
"htf_available_time"
] = htf[
"datetime"
]
htf[
"htf_bar_idx"
] = np.arange(
len(htf),
dtype=np.int64,
)
return htf
def align_completed_htf_to_ltf(
ltf: pd.DataFrame,
htf: pd.DataFrame,
prefix: str = "htf_",
) -> pd.DataFrame:
"""
Forward-align completed HTF data onto LTF.
Uses merge_asof(backward):
LTF 10:45
cannot see HTF candle available at 11:00.
LTF 11:00
can see it.
This is the core causal MTF invariant.
"""
if "htf_available_time" not in htf.columns:
raise ValueError(
"align_completed_htf_to_ltf(): "
"htf_available_time absent"
)
ltf_out = ltf.copy()
ltf_time = get_datetime_utc(
ltf_out
)
ltf_out[
"_mtf_datetime"
] = ltf_time
htf_work = htf.copy()
htf_work[
"_mtf_available"
] = pd.to_datetime(
htf_work[
"htf_available_time"
],
utc=True,
)
protected = {
"datetime",
"htf_available_time",
"_mtf_available",
}
rename = {}
for column in htf_work.columns:
if column in protected:
continue
if column.startswith(
prefix
):
continue
rename[column] = (
f"{prefix}{column}"
)
htf_work = htf_work.rename(
columns=rename
)
ltf_out = ltf_out.sort_values(
"_mtf_datetime"
)
htf_work = htf_work.sort_values(
"_mtf_available"
)
merged = pd.merge_asof(
ltf_out,
htf_work.drop(
columns=[
"datetime",
"htf_available_time",
],
errors="ignore",
),
left_on="_mtf_datetime",
right_on="_mtf_available",
direction="backward",
allow_exact_matches=True,
)
merged = merged.drop(
columns=[
"_mtf_datetime",
"_mtf_available",
],
errors="ignore",
)
merged.index = ltf_out.index
return merged.sort_index()
|