src/gluonts/dataset/artificial/_base.py [647:845]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        metadata: MetaData,
        max_train_length: int,
        prediction_length: int,
        num_timeseries: int,
        trim_length_fun=lambda x, **kwargs: 0,
        data_start=pd.Timestamp("2014-01-01"),
    ) -> None:
        """

        :param recipe: The recipe to generate from (see class docstring)
        :param metadata: The metadata to be included in the dataset
        :param max_train_length: The maximum length of a training time series.
        :param prediction_length: The length of the prediction range
        :param num_timeseries: Number of time series to generate
        :param trim_length_fun: Callable f(x: int) -> int returning the
               (shortened) training length
        :param data_start: Start date for the data set
        """
        super().__init__(freq=metadata.freq)

        self.recipe = recipe
        self._metadata = metadata
        self.max_train_length = max_train_length
        self.prediction_length = prediction_length
        self.trim_length_fun = trim_length_fun
        self.num_timeseries = num_timeseries
        self.data_start = pd.Timestamp(data_start, freq=self._metadata.freq)

    @property
    def metadata(self) -> MetaData:
        return self._metadata

    def dataset_info(self, train_ds: Dataset, test_ds: Dataset) -> DatasetInfo:
        return DatasetInfo(
            name=f"RecipeDataset({repr(self.recipe)})",
            metadata=self.metadata,
            prediction_length=self.prediction_length,
            train_statistics=calculate_dataset_statistics(train_ds),
            test_statistics=calculate_dataset_statistics(test_ds),
        )

    @staticmethod
    def trim_ts_item_end(x: DataEntry, length: int) -> DataEntry:
        """Trim a DataEntry into a training range, by removing
        the last prediction_length time points from the target and dynamic
        features."""
        y = dict(
            item_id=x[FieldName.ITEM_ID],
            start=x[FieldName.START],
            target=x[FieldName.TARGET][:-length],
        )

        if FieldName.FEAT_DYNAMIC_CAT in x:
            y[FieldName.FEAT_DYNAMIC_CAT] = x[FieldName.FEAT_DYNAMIC_CAT][
                :, :-length
            ]
        if FieldName.FEAT_DYNAMIC_REAL in x:
            y[FieldName.FEAT_DYNAMIC_REAL] = x[FieldName.FEAT_DYNAMIC_REAL][
                :, :-length
            ]
        return y

    @staticmethod
    def trim_ts_item_front(x: DataEntry, length: int) -> DataEntry:
        """Trim a DataEntry into a training range, by removing
        the first offset_front time points from the target and dynamic
        features."""
        assert length <= len(x[FieldName.TARGET])

        y = dict(
            item_id=x[FieldName.ITEM_ID],
            start=x[FieldName.START] + length * x[FieldName.START].freq,
            target=x[FieldName.TARGET][length:],
        )

        if FieldName.FEAT_DYNAMIC_CAT in x:
            y[FieldName.FEAT_DYNAMIC_CAT] = x[FieldName.FEAT_DYNAMIC_CAT][
                :, length:
            ]
        if FieldName.FEAT_DYNAMIC_REAL in x:
            y[FieldName.FEAT_DYNAMIC_REAL] = x[FieldName.FEAT_DYNAMIC_REAL][
                :, length:
            ]
        return y

    def generate(self) -> TrainDatasets:
        metadata = self.metadata
        data_it = generate(
            length=self.max_train_length + self.prediction_length,
            recipe=self.recipe,
            start=self.data_start,
        )
        full_length_data = take_as_list(data_it, self.num_timeseries)

        test_data = [
            RecipeDataset.trim_ts_item_front(
                x, self.trim_length_fun(x, train_length=self.max_train_length)
            )
            for x in full_length_data
        ]
        train_data = [
            RecipeDataset.trim_ts_item_end(x, self.prediction_length)
            for x in test_data
        ]
        return TrainDatasets(
            metadata=metadata,
            train=ListDataset(train_data, metadata.freq),
            test=ListDataset(test_data, metadata.freq),
        )


def default_synthetic() -> Tuple[DatasetInfo, Dataset, Dataset]:

    recipe = [
        (FieldName.TARGET, LinearTrend() + RandomGaussian()),
        (FieldName.FEAT_STATIC_CAT, RandomCat([10])),
        (
            FieldName.FEAT_STATIC_REAL,
            ForEachCat(RandomGaussian(1, (10,)), FieldName.FEAT_STATIC_CAT)
            + RandomGaussian(0.1, (10,)),
        ),
    ]

    data = RecipeDataset(
        recipe=recipe,
        metadata=MetaData(
            freq="D",
            feat_static_real=[
                BasicFeatureInfo(name=FieldName.FEAT_STATIC_REAL)
            ],
            feat_static_cat=[
                CategoricalFeatureInfo(
                    name=FieldName.FEAT_STATIC_CAT, cardinality=10
                )
            ],
            feat_dynamic_real=[
                BasicFeatureInfo(name=FieldName.FEAT_DYNAMIC_REAL)
            ],
        ),
        max_train_length=20,
        prediction_length=10,
        num_timeseries=10,
        trim_length_fun=lambda x, **kwargs: np.minimum(
            int(np.random.geometric(1 / (kwargs["train_length"] / 2))),
            kwargs["train_length"],
        ),
    )

    generated = data.generate()
    assert generated.test is not None
    info = data.dataset_info(generated.train, generated.test)

    return info, generated.train, generated.test


def constant_dataset() -> Tuple[DatasetInfo, Dataset, Dataset]:
    metadata = MetaData(
        freq="1H",
        feat_static_cat=[
            CategoricalFeatureInfo(
                name="feat_static_cat_000", cardinality="10"
            )
        ],
        feat_static_real=[BasicFeatureInfo(name="feat_static_real_000")],
    )

    start_date = "2000-01-01 00:00:00"

    train_ds = ListDataset(
        data_iter=[
            {
                FieldName.ITEM_ID: str(i),
                FieldName.START: start_date,
                FieldName.TARGET: [float(i)] * 24,
                FieldName.FEAT_STATIC_CAT: [i],
                FieldName.FEAT_STATIC_REAL: [float(i)],
            }
            for i in range(10)
        ],
        freq=metadata.freq,
    )

    test_ds = ListDataset(
        data_iter=[
            {
                FieldName.ITEM_ID: str(i),
                FieldName.START: start_date,
                FieldName.TARGET: [float(i)] * 30,
                FieldName.FEAT_STATIC_CAT: [i],
                FieldName.FEAT_STATIC_REAL: [float(i)],
            }
            for i in range(10)
        ],
        freq=metadata.freq,
    )

    info = DatasetInfo(
        name="constant_dataset",
        metadata=metadata,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/gluonts/nursery/SCott/pts/dataset/artificial.py [643:841]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        metadata: MetaData,
        max_train_length: int,
        prediction_length: int,
        num_timeseries: int,
        trim_length_fun=lambda x, **kwargs: 0,
        data_start=pd.Timestamp("2014-01-01"),
    ) -> None:
        """

        :param recipe: The recipe to generate from (see class docstring)
        :param metadata: The metadata to be included in the dataset
        :param max_train_length: The maximum length of a training time series.
        :param prediction_length: The length of the prediction range
        :param num_timeseries: Number of time series to generate
        :param trim_length_fun: Callable f(x: int) -> int returning the
               (shortened) training length
        :param data_start: Start date for the data set
        """
        super().__init__(freq=metadata.freq)

        self.recipe = recipe
        self._metadata = metadata
        self.max_train_length = max_train_length
        self.prediction_length = prediction_length
        self.trim_length_fun = trim_length_fun
        self.num_timeseries = num_timeseries
        self.data_start = pd.Timestamp(data_start, freq=self._metadata.freq)

    @property
    def metadata(self) -> MetaData:
        return self._metadata

    def dataset_info(self, train_ds: Dataset, test_ds: Dataset) -> DatasetInfo:
        return DatasetInfo(
            name=f"RecipeDataset({repr(self.recipe)})",
            metadata=self.metadata,
            prediction_length=self.prediction_length,
            train_statistics=calculate_dataset_statistics(train_ds),
            test_statistics=calculate_dataset_statistics(test_ds),
        )

    @staticmethod
    def trim_ts_item_end(x: DataEntry, length: int) -> DataEntry:
        """Trim a TimeSeriesItem into a training range, by removing
        the last prediction_length time points from the target and dynamic
        features."""
        y = dict(
            item_id=x[FieldName.ITEM_ID],
            start=x[FieldName.START],
            target=x[FieldName.TARGET][:-length],
        )

        if FieldName.FEAT_DYNAMIC_CAT in x:
            y[FieldName.FEAT_DYNAMIC_CAT] = x[FieldName.FEAT_DYNAMIC_CAT][
                :, :-length
            ]
        if FieldName.FEAT_DYNAMIC_REAL in x:
            y[FieldName.FEAT_DYNAMIC_REAL] = x[FieldName.FEAT_DYNAMIC_REAL][
                :, :-length
            ]
        return y

    @staticmethod
    def trim_ts_item_front(x: DataEntry, length: int) -> DataEntry:
        """Trim a TimeSeriesItem into a training range, by removing
        the first offset_front time points from the target and dynamic
        features."""
        assert length <= len(x[FieldName.TARGET])

        y = dict(
            item_id=x[FieldName.ITEM_ID],
            start=x[FieldName.START] + length * x[FieldName.START].freq,
            target=x[FieldName.TARGET][length:],
        )

        if FieldName.FEAT_DYNAMIC_CAT in x:
            y[FieldName.FEAT_DYNAMIC_CAT] = x[FieldName.FEAT_DYNAMIC_CAT][
                :, length:
            ]
        if FieldName.FEAT_DYNAMIC_REAL in x:
            y[FieldName.FEAT_DYNAMIC_REAL] = x[FieldName.FEAT_DYNAMIC_REAL][
                :, length:
            ]
        return y

    def generate(self) -> TrainDatasets:
        metadata = self.metadata
        data_it = generate(
            length=self.max_train_length + self.prediction_length,
            recipe=self.recipe,
            start=self.data_start,
        )
        full_length_data = take_as_list(data_it, self.num_timeseries)

        test_data = [
            RecipeDataset.trim_ts_item_front(
                x, self.trim_length_fun(x, train_length=self.max_train_length)
            )
            for x in full_length_data
        ]
        train_data = [
            RecipeDataset.trim_ts_item_end(x, self.prediction_length)
            for x in test_data
        ]
        return TrainDatasets(
            metadata=metadata,
            train=ListDataset(train_data, metadata.freq),
            test=ListDataset(test_data, metadata.freq),
        )


def default_synthetic() -> Tuple[DatasetInfo, Dataset, Dataset]:

    recipe = [
        (FieldName.TARGET, LinearTrend() + RandomGaussian()),
        (FieldName.FEAT_STATIC_CAT, RandomCat([10])),
        (
            FieldName.FEAT_STATIC_REAL,
            ForEachCat(RandomGaussian(1, (10,)), FieldName.FEAT_STATIC_CAT)
            + RandomGaussian(0.1, (10,)),
        ),
    ]

    data = RecipeDataset(
        recipe=recipe,
        metadata=MetaData(
            freq="D",
            feat_static_real=[
                BasicFeatureInfo(name=FieldName.FEAT_STATIC_REAL)
            ],
            feat_static_cat=[
                CategoricalFeatureInfo(
                    name=FieldName.FEAT_STATIC_CAT, cardinality=10
                )
            ],
            feat_dynamic_real=[
                BasicFeatureInfo(name=FieldName.FEAT_DYNAMIC_REAL)
            ],
        ),
        max_train_length=20,
        prediction_length=10,
        num_timeseries=10,
        trim_length_fun=lambda x, **kwargs: np.minimum(
            int(np.random.geometric(1 / (kwargs["train_length"] / 2))),
            kwargs["train_length"],
        ),
    )

    generated = data.generate()
    assert generated.test is not None
    info = data.dataset_info(generated.train, generated.test)

    return info, generated.train, generated.test


def constant_dataset() -> Tuple[DatasetInfo, Dataset, Dataset]:
    metadata = MetaData(
        freq="1H",
        feat_static_cat=[
            CategoricalFeatureInfo(
                name="feat_static_cat_000", cardinality="10"
            )
        ],
        feat_static_real=[BasicFeatureInfo(name="feat_static_real_000")],
    )

    start_date = "2000-01-01 00:00:00"

    train_ds = ListDataset(
        data_iter=[
            {
                FieldName.ITEM_ID: str(i),
                FieldName.START: start_date,
                FieldName.TARGET: [float(i)] * 24,
                FieldName.FEAT_STATIC_CAT: [i],
                FieldName.FEAT_STATIC_REAL: [float(i)],
            }
            for i in range(10)
        ],
        freq=metadata.freq,
    )

    test_ds = ListDataset(
        data_iter=[
            {
                FieldName.ITEM_ID: str(i),
                FieldName.START: start_date,
                FieldName.TARGET: [float(i)] * 30,
                FieldName.FEAT_STATIC_CAT: [i],
                FieldName.FEAT_STATIC_REAL: [float(i)],
            }
            for i in range(10)
        ],
        freq=metadata.freq,
    )

    info = DatasetInfo(
        name="constant_dataset",
        metadata=metadata,
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -