gluonts.dataset.artificial 包

class gluonts.dataset.artificial.ArtificialDataset(freq)

基类: object

可以从代码生成的数据集的父类。

generate() → gluonts.dataset.common.TrainDatasets

abstract property metadata: gluonts.dataset.common.MetaData

abstract property test: List[Dict[str, Any]]

abstract property train: List[Dict[str, Any]]

class gluonts.dataset.artificial.ComplexSeasonalTimeSeries(num_series: int = 100, prediction_length: int = 20, freq_str: str = 'D', length_low: int = 30, length_high: int = 200, min_val: float = - 10000, max_val: float = 10000, is_integer: bool = False, proportion_missing_values: float = 0, is_noise: bool = True, is_scale: bool = True, percentage_unique_timestamps: float = 0.07, is_out_of_bounds_date: bool = False, seasonality: Optional[int] = None, clip_values: bool = False)

基类: gluonts.dataset.artificial._base.ArtificialDataset

生成正弦时间序列，该序列逐渐增加并达到一定振幅和水平，并在每个周日有额外的峰值。

TODO: 可以将其转换为 RecipeDataset 以避免代码重复。

make_timeseries(seed: int = 1) → List[Dict[str, Any]]

property metadata: gluonts.dataset.common.MetaData

property test: List[Dict[str, Any]]

property train: List[Dict[str, Any]]

class gluonts.dataset.artificial.ConstantDataset(num_timeseries: int = 10, num_steps: int = 30, freq: str = '1h', start: str ='2000-01-01 00:00:00', is_nan: bool = False, is_random_constant: bool = False, is_different_scales: bool = False, is_piecewise: bool = False, is_noise: bool = False, is_long: bool = False, is_short: bool = False, is_trend: bool = False, num_missing_middle: int = 0, is_promotions: bool = False, holidays: Optional[List[pandas._libs.tslibs.timestamps.Timestamp]] = None)

基类: gluonts.dataset.artificial._base.ArtificialDataset

compute_data_from_recipe(num_steps: int, constant: Optional[float] = None, one_to_zero: float = 0.1, zero_to_one: float = 0.1, scale_features: float = 200) → gluonts.dataset.common.TrainDatasets

determine_constant(index: int, constant: Optional[float] = None, seed: int = 1) → Optional[float]

generate_ts(num_ts_steps: int, is_train: bool = False) → List[Dict[str, Any]]

get_num_steps(index: int, num_steps_max: int = 10000, long_freq: int = 4, num_steps_min: int = 2, short_freq: int = 4) → int#

insert_missing_vals_middle(ts_len: int, constant: Optional[float]) → List[Optional[float]]

static insert_nans_and_zeros(ts_len: int) → List

property metadata: gluonts.dataset.common.MetaData

piecewise_constant(index: int, num_steps: int) → List

property test: List[Dict[str, Any]]

property train: List[Dict[str, Any]]

class gluonts.dataset.artificial.RecipeDataset(recipe: typing.Union[typing.Callable, typing.Dict[str, typing.Callable], typing.List[typing.Tuple[str, typing.Callable]]], metadata: gluonts.dataset.common.MetaData, max_train_length: int, prediction_length: int, num_timeseries: int, trim_length_fun=<function RecipeDataset.<lambda>>, data_start=Timestamp('2014-01-01 00:00:00'))

基类: gluonts.dataset.artificial._base.ArtificialDataset

通过提供 Recipe 生成的合成数据集。

Recipe 可以是一个（非确定性）函数

f(length: int, global_state: dict) -> dict

或形如 (field, function) 的元组列表

(field: str, f(data: dict, length: int, global_state: dict) -> dict)

它们按顺序处理，初始时 data 为 {}，每个条目将 data[field] 更新为函数调用的输出。

dataset_info(train_ds: gluonts.dataset.Dataset, test_ds: gluonts.dataset.Dataset) → gluonts.dataset.artificial._base.DatasetInfo

generate() → gluonts.dataset.common.TrainDatasets

property metadata: gluonts.dataset.common.MetaData

property test

property train

static trim_ts_item_end(x: Dict[str, Any], length: int) → Dict[str, Any]

通过移除 target 和动态特征的最后 prediction_length 个时间点，将 DataEntry 修剪到训练范围。

static trim_ts_item_front(x: Dict[str, Any], length: int) → Dict[str, Any]

通过移除 target 和动态特征的开头 offset_front 个时间点，将 DataEntry 修剪到训练范围。

gluonts.dataset.artificial.constant_dataset() → Tuple[gluonts.dataset.artificial._base.DatasetInfo, gluonts.dataset.Dataset, gluonts.dataset.Dataset]

gluonts.dataset.artificial.default_synthetic() → Tuple[gluonts.dataset.artificial._base.DatasetInfo, gluonts.dataset.Dataset, gluonts.dataset.Dataset]

子模块

• gluonts.dataset.artificial.ar_p 模块
• gluonts.dataset.artificial.recipe 模块