Return a 2-D array of shape (time, component), containing the series' values for one `sample`. Parameters ---------- copy

Can be used to replace "raise" when throwing an exception to ensure the logging of the exception. After logging it, the exception is raised.

End time of the series. Returns ------- pandas.Timestamp | int A timestamp containing the last time of the TimeSe

Return a 3-D array of dimension (time, component, sample) containing the series' values for all samples. Parameters ----------

Return a new series with the `other` series appended to this series along the time axis (added to the end). Parameters ----------

Creates a univariate TimeSeries with a starting value of `start_value` that increases linearly such that it takes on the value `end_value` at

Start time of the series. Returns ------- pandas.Timestamp | int A timestamp containing the first time of the Tim

Create a ``TimeSeries`` from a time index and value array. Parameters ---------- times A pandas DateTimeIndex, Ra

Return a new series with the `other` series stacked to this series along the component axis. The resulting TimeSeries will have the same name

Generates calibrated historical forecasts by simulating predictions at various points in time throughout the history of the provided (potentia

Create an ``TimeSeries`` from an array of values. The series will have an integer time index (RangeIndex). Parameters ------

Return a new series with added static covariates. Static covariates hold information / data about the time series which does not vary over ti

Return a new series where this series is concatenated with the `other` series along a given `axis`. Parameters ---------- oth

Creates a constant univariate TimeSeries with the given value, length (or end date), start date and frequency. Parameters ----------

Create a copy of the series. Returns ------- TimeSeries A copy of the series.

Internally calls the logging.getLogger function with the `name` argument to create or retrieve a logger object. It is recommended to pass __n

Get the current option value.

Return a new series with the values have been converted to the desired `dtype`. Parameters ---------- dtype A Num

Returns an index with a given start point and length. Either a pandas DatetimeIndex with given frequency or a pandas RangeIndex. The index starts

If possible, converts `ts` into the desired sequence type `seq_type_out`. Otherwise, returns the original `ts`. Parameters ----------

Return a new series with the mean computed over the specified `axis`. If we reduce over time (``axis=0``), the series will have length one an

For each data transformer in the pipeline, first fit the data if transformer is fittable then transform data using fitted transformer

Checks provided boolean condition and raises a ValueError if it evaluates to False. It logs the error to the provided logger before raising i

r"""Compute error values that the model produced for historical forecasts on (potentially multiple) `series`. If `historical_forecasts` are p

Create a ``TimeSeries`` from a selection of columns of a `DataFrame`. One column (or the DataFrame index) has to represent the time, and a li

Return a new series with the sum computed over the specified `axis`. If we reduce over time (``axis=0``), the series will have length one and

Concatenates multiple series along a given axis. ``axis`` can be an integer in (0, 1, 2) to denote (time, component, sample) or, alternatively, a

Score the results against true anomalies. Parameters ---------- anomalies The (sequence of) ground truth binary a

Returns one or multiple explanations based on some input parameters.

Create a ``TimeSeries`` from a `Series`. The series must contain an index that is either a pandas DatetimeIndex, a pandas RangeIndex, or a pa

Checks provided boolean condition and raises a ValueError if it evaluates to True. It logs the error to the provided logger before raising it

Return a DataFrame representation of the series in a given `backend`. Each of the series components will appear as a column in the DataFrame.

Computes the anomaly score on the two (sequence of) series. If a pair of sequences is given, they must contain the same number of ser

Return a `Series` representation of the series in a given `backend`. Works only for univariate series that are deterministic (i.e., made of 1

Return a deterministic series with the desired quantile(s) `q` of each component computed over the samples of the stochastic series.

static cov or metadata must be identical

Load the dataset in memory, as a TimeSeries. Downloads the dataset if it is not present already Raises ------

Returns one or several ``TimeSeries`` representing the feature values for a given horizon and component. Parameters

Return a 1-D Numpy array of shape (time,) containing the univariate series' values for one `sample`. Parameters ---------- co

Returns the underlying ``shap.Explanation`` object for a given horizon and component. Parameters ---------- horizon

Return a new series with the specified window transformations applied. Supports moving/rolling, expanding or exponentially weighted window tr

Split the series in two, after a provided `split_point`. Parameters ---------- split_point A timestamp, float or

Compute the residuals that the model produced for historical forecasts on (potentially multiple) `series`. This function computes the differe

Fits the forecasting models with the entire series except the last `regression_train_n_points` values, which are used to train the re

Return a new series with `values` appended to this series along the time axis (added to the end). This adds time steps to the end of the new

Returns a single (first) TimeSeries or `None` from `ts`. Returns `ts` if `ts` is a TimeSeries, `ts[0]` if `ts` is a `Sequence[TimeSeries]`, and `

Returns a tuple containing the times in `target_series`, the times in `past_covariates`, and the times in `future_covariates` that *could* be

Returns the times shared by all specified `TimeSeries` or time indexes (i.e. the intersection of all these times). If `sort = True`, then the

Split the series in two, before a provided `split_point`. Parameters ---------- split_point A timestamp, float or

Saves the ensemble model under a given path or file handle. Additionally, two files are stored for each `TorchForecastingModel` unde

Explains all possible foreground series forecasts (or background, if foreground is not provided) and returns a :class:`ShapExplainabi

Retrieves the value of the specified option. Available Options: - display.[max_rows, max_cols] - plotting.use_darts_style Para

Computes the anomaly score on the given series. If a sequence of series is given, the scorer will score each series independently and

Return a 2-D array of dimension (component, static variable) containing the series' static covariate values. Parameters ----------

Detect anomalies on given time series. Parameters ---------- series The (sequence of) series on which to detect a

Helper function to call the `create_lagged_training_data()` method with lags argument either in the list format or the dictionary format (auto

Return a slice of the series where the time index was intersected with the `other` series. This method is in general *not* symmetric.

Return a new series with the function `fn` applied to the values of this series. If `fn` takes 1 argument it is simply applied on the values

Return a new series where the time index and values were resampled with a given frequency. The provided `method` is used to aggregate/fill ho

Plot the series using Matplotlib. Parameters ---------- new_plot Whether to spawn a new axis to plot on. See also

Creates the features array `X` and labels array `y` to train a lagged-variables `SKLearnModel` (e.g. an `sklearn` model); the time index valu

Return a new series with the maximum computed over the specified `axis`. If we reduce over time (``axis=0``), the series will have length one

Creates the features array `X` to produce a series of prediction from an already-trained `SKLearnModel`; the time index values of each observ

Creates a gaussian univariate TimeSeries by sampling all the series values independently, from a gaussian distribution with mean `mean` and s

Returns the sequence type of `ts`. - SeriesType.SINGLE: `TimeSeries` (e.g. a single series) - SeriesType.SEQ: sequence of `TimeSeries` (e.g.

Return a new series with the minimum computed over the specified `axis`. If we reduce over time (``axis=0``), the series will have length one

Return a new series with differenced values. This is often used to make a time series stationary. Parameters ----------

Generates formatted likelihood parameter names for components and parameter names. The order of the returned names is: `[comp1_param_1, ... comp1

Plot the series using Plotly. Parameters ---------- fig Optionally, a Plotly `go.Figure` object to plot on. If pr

Return the schema of the series as a dictionary. Can be used to create new `TimeSeries` with the same schema. The keys and values ar

Creates a univariate TimeSeries with a sinusoidal value progression with a given frequency, amplitude, phase and y offset. Parameters

Build an iterable, possibly using tqdm (either in notebook or regular mode) Parameters ---------- iterable verbose total

Input `series` checks used for Aggregators, Detectors, ... - `series` must be (sequence of) series with length (`num_series_expected`) where

Returns the processed numpy values of two time series. Processing can be customized with arguments `intersect, q, remove_nan_union, is_classificat

Helper function that creates a `linear_timeseries` with a specified number of components. To help distinguish each component from one another

Loads the weights from a manually saved model (saved with :meth:`save() <TorchForecastingModel.save()>`). Note: This method needs to

Splits the provided series into training and test series. Supports splitting along the sample axis or time axis. If the input type is si

Return a new series with new columns/components names. It also adapts the names in the hierarchy, if any. Parameters -------

Returns the latest `start_time` and the earliest `end_time` among all non-`None` `series_or_times`; these are (non-tight) lower and upper `bo

Generates formatted quantile names, optionally added to a component name. Parameters ---------- q A float or list of floats with

Return a new series where the time index was shifted by `n` steps. If :math:`n > 0`, shifts into the future. If :math:`n < 0`, shifts into th

Return a slice of the series starting at `start_ts` and ending before `end_ts`. For series having DatetimeIndex, this is inclusive on both en