Creates an HTML paragraph with optional bold text and margin.

Return a new series with the `other` series prepended to this series along the time axis (added to the beginning). Parameters

Double test on stationarity using both Kwiatkowski-Phillips-Schmidt-Shin and Augmented Dickey-Fuller statistical tests. WARNING Beca

Converts a sequence of `TimeSeries` into a long DataFrame representation. It converts each series into individual DataFrames and then concatenate

Export model to ONNX format for optimized inference, wrapping around PyTorch Lightning's :func:`torch.onnx.export` method (`official documenta

Return a deterministic series with the variance of each component computed over the samples of the stochastic series. This works only

Return a new series similar to this one but with new `times` and `values`. Parameters ---------- times A pandas D

Regression Model Can be used to fit any scikit-learn-like regressor class to predict the target time series from lagged values. Param

Transform each series using the corresponding Pipeline. If the Pipeline is fittable and `fit_transformers=True`, the series are sliced to corresp

If a preprocessing pipeline is registered under ``"series"`` and can be reversed, convert ``forecasts`` from preprocessed form back to the or

Checks if the two sequences contain the same number of TimeSeries.

Checks if given input is of type Darts TimeSeries

Builds a forecast time series starting after the end of an input time series, with the correct time index (or after the end of the input seri

Builds a forecast time series from predicted values and `TimeSeries` schema starting at `pred_start`. Parameters ---------- values

Every `stride`-th values in a dataset with stride=1 should be identical to the dataset stridden with `stride

Find options matching a pattern (supports both exact match and prefix match).

Finds pd.Timestamp attributes relevant for seasonality. Analyzes the given TimeSeries instance for relevant pd.Timestamp attributes in terms

Generates an Encoder or Decoder with one of Darts' Feed-forward Network variants. Parameters ---------- coder_cls Either `torch.nn

Returns the lower and upper bound values from `vals` for all quantile intervals in `q_interval`. Parameters ---------- vals A num

Returns the matrix S for a series, as defined `here <https://otexts.com/fpp3/reconciliation.html>`__. The dimension of the matrix is `(n, m)

If (actual) covariates are given, merge the encoded index with the covariates Parameters ---------- encoded The e

For SKLearnModels we create the lagged prediction data once per series using a moving window. With this, we can avoid having to recre

Internal function called by `show_anomalies_from_scores()` Plot the series on the given axes ax_id. Parameters ---------- series

Sort `times` and `values` by ascending dates. Only performed if `times` is not already monotonically increasing.

Internal function called by WindowedAnomalyScorer `fit()` and `score()` functions. Transforms a sequence of series into tabular data of size

Converts a time series Tensor to a feature Tensor.

Return a new series with an added holiday component. The holiday component is binary where `1` corresponds to a time step falling on a holida

Adds a custom seasonality to the model that repeats after every n `seasonal_periods` timesteps. An example for `seasonal_periods`: If you have

Fits the Gaussian Process on the observations and returns samples from the Gaussian Process, or its mean values if `num_samples` is s

Fit all fittable transformers in pipeline. Parameters ---------- data (`Sequence` of) `TimeSeries` to fi

Fit the underlying filtering model (if applicable) and the fittable scorers, if any. Train the filter (if not already fitted and `allow_model

Formats a list as a string, showing at most `max_items` items. Pass `render_html=True` to escape '<' and '>' characters. Parameters -----

Generates the covariate encodings that were used/generated for fitting the model and returns a tuple of past, and future covariates series wit

Returns the time-dependent decoder importances as a pd.DataFrames. If multiple series were used in :func:`TFTExplainer.explain()

Returns the time-dependent encoder importances as a pd.DataFrames. If multiple series were used in :func:`TFTExplainer.explain()

Returns the numeric and categorical static covariates importances as a pd.DataFrames. If multiple series were used in :func:`TFTExpla

Evaluate model on given series, for all 4 supported metric functions

test comparisons for `SequentialEncoder.encode_inference()

Test cases for both `PastCyclicEncoder` and `FutureCyclicEncoder`

Test `SingleEncoder.encode_inference()`

For prediction (`n` is given) with past covariates we have to distinguish between two cases: 1) if past covariates are given, we can

If covariates are given, the index generators should return the covariate series' index. If covariates are not given, the index gener

test the index type of generated index

checks whether prediction has same number of variable as input series and whether prediction has correct length

values of static cov or metadata must match but not row index (component names). I.e. series.quantile() adds "_quantiles" to component names

Forecasts values for `n` time steps after the end of the training series. Parameters ---------- n Forecast horizo

Removes the TimeSeries `other` from the TimeSeries `ts` as specified by `model`. Use e.g. to remove an additive or multiplicative trend from

Adjusts the TimeSeries `ts` for a seasonality of order `frequency` using the `model` decomposition. Parameters ---------- ts

Adjusts the TimeSeries `ts` for a trend using the `model` decomposition. Parameters ---------- ts The TimeSeries to adjust.

Generates `num_samples` samples from quantile predictions using linear interpolation. The generated samples should have quantile values close to t

Computes SHAP explanations for the given foreground data, horizons, and target components. It returns a nested dictionary of SHAP Exp

Return a slice of the series starting at `start_ts` (inclusive) and having at most `n` points. Parameters ---------- start_ts

Return a slice of the series ending at `end_ts` (inclusive) and having at most `n` points. Parameters ---------- end_ts

Provides Augmented Dickey-Fuller unit root test for a time series, using :func:`statsmodels.tsa.stattools.adfuller`. See [1]_. Paramete

Provides Kwiatkowski-Phillips-Schmidt-Shin test for stationarity for a time series, using :func:`statsmodels.tsa.stattools.kpss`. See [1]_.

Splits all provided TimeSeries instances into train and test sets according to the provided timestamp. Parameters ---------- feature

Abstract class for all training datasets that can be used with Darts' `TorchForecastingModel`. Each sample drawn from this dataset m

Reversible Instance Normalization based on [1]_ Parameters ---------- input_dim The dimension of the input axis b

PyTorch module implementing the basic building block of the N-HiTS architecture. The blocks produce outputs of size (target_length, nr_params

Naive Mean Model This model has no parameter, and always predicts the mean value of the training series. Examples --

returns the name of the aggregator

Checks if series is a binary timeseries (1 and 0)" Parameters ---------- series series to check for. name name of the

Utility function to create pseudo *_exog_list inputs expected by NeuralForecast

Builds the SHAP explainer based on the specified SHAP method. Parameters ---------- func The function wr

Models can override this method to return a custom `TorchInferenceDataset`.

Computes a score on the confusion matrix of two np.arrays `y_true` and `y_pred`. Parameters ---------- y_true The true labels.

Returns a torch distribution built with the specified params