Spaces:
Running
Running
File size: 5,570 Bytes
e317359 | 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 | from __future__ import annotations
import math
import os
from enum import Enum
from functools import cached_property
from pathlib import Path
from typing import Iterable, Iterator
from dotenv import load_dotenv
from gluonts.dataset import DataEntry
from gluonts.dataset.common import ProcessDataEntry
from gluonts.dataset.split import TestData, TrainingDataset, split
from gluonts.itertools import Map
from gluonts.time_feature import norm_freq_str
from gluonts.transform import Transformation
from pandas.tseries.frequencies import to_offset
from toolz import compose
from tsfm_bench.data.interface import TimeSeriesDataSource, TimeSeriesRecord
from tsfm_bench.data.registry import load_data_source
TEST_SPLIT = 0.1
MAX_WINDOW = 20
M4_PRED_LENGTH_MAP = {
"A": 6,
"Q": 8,
"M": 18,
"W": 13,
"D": 14,
"H": 48,
}
PRED_LENGTH_MAP = {
"M": 12,
"W": 8,
"D": 30,
"H": 48,
"T": 48,
"S": 60,
}
class Term(Enum):
SHORT = "short"
MEDIUM = "medium"
LONG = "long"
@property
def multiplier(self) -> int:
if self == Term.SHORT:
return 1
if self == Term.MEDIUM:
return 10
return 15
def itemize_start(data_entry: DataEntry) -> DataEntry:
start = data_entry["start"]
if hasattr(start, "item"):
data_entry["start"] = start.item()
return data_entry
def maybe_reconvert_freq(freq: str) -> str:
deprecated_map = {
"Y": "A",
"YE": "A",
"QE": "Q",
"ME": "M",
"h": "H",
"min": "T",
"s": "S",
"us": "U",
}
return deprecated_map.get(freq, freq)
class MultivariateToUnivariate(Transformation):
def __init__(self, field: str):
self.field = field
def __call__(
self, data_it: Iterable[DataEntry], is_train: bool = False
) -> Iterator[DataEntry]:
for data_entry in data_it:
item_id = data_entry["item_id"]
val_ls = list(data_entry[self.field])
for dim_id, val in enumerate(val_ls):
univariate_entry = data_entry.copy()
univariate_entry[self.field] = val
univariate_entry["item_id"] = f"{item_id}_dim{dim_id}"
yield univariate_entry
def _record_to_entry(record: TimeSeriesRecord) -> dict:
import pandas as pd
return {
"item_id": record.item_id,
"start": pd.Period(record.start),
"target": record.target,
"freq": record.freq,
}
class Dataset:
"""GluonTS-compatible dataset backed by a streaming data source."""
def __init__(
self,
name: str,
term: Term | str = Term.SHORT,
to_univariate: bool = False,
source: TimeSeriesDataSource | None = None,
config_path: str | Path | None = None,
):
load_dotenv()
if source is None:
env_config = os.getenv("TSFM_BENCH_CONFIG")
source = load_data_source(config_path or env_config)
self.source = source
self.metadata = source.get_metadata(name)
self.name = name
self.term = Term(term)
records = list(source.stream(name))
self._raw_entries = [_record_to_entry(record) for record in records]
first_target = self._raw_entries[0]["target"]
target_dim = first_target.shape[0] if getattr(first_target, "ndim", 1) > 1 else 1
process = ProcessDataEntry(
self.freq,
one_dim_target=target_dim == 1,
)
self.gluonts_dataset = Map(compose(process, itemize_start), self._raw_entries)
if to_univariate:
self.gluonts_dataset = MultivariateToUnivariate("target").apply(
self.gluonts_dataset
)
@cached_property
def prediction_length(self) -> int:
freq = norm_freq_str(to_offset(self.freq).name)
freq = maybe_reconvert_freq(freq)
pred_len = PRED_LENGTH_MAP.get(freq, 48)
return self.term.multiplier * pred_len
@cached_property
def freq(self) -> str:
return self.metadata.frequency
@cached_property
def target_dim(self) -> int:
target = self._raw_entries[0]["target"]
return target.shape[0] if getattr(target, "ndim", 1) > 1 else 1
@cached_property
def windows(self) -> int:
w = math.ceil(TEST_SPLIT * self._min_series_length / self.prediction_length)
return min(max(1, w), MAX_WINDOW)
@cached_property
def _min_series_length(self) -> int:
lengths = []
for entry in self._raw_entries:
target = entry["target"]
lengths.append(target.shape[-1] if getattr(target, "ndim", 1) > 1 else len(target))
return min(lengths)
@property
def training_dataset(self) -> TrainingDataset:
training_dataset, _ = split(
self.gluonts_dataset, offset=-self.prediction_length * (self.windows + 1)
)
return training_dataset
@property
def validation_dataset(self) -> TrainingDataset:
validation_dataset, _ = split(
self.gluonts_dataset, offset=-self.prediction_length * self.windows
)
return validation_dataset
@property
def test_data(self) -> TestData:
_, test_template = split(
self.gluonts_dataset, offset=-self.prediction_length * self.windows
)
return test_template.generate_instances(
prediction_length=self.prediction_length,
windows=self.windows,
distance=self.prediction_length,
)
|