Computes attributes given the tree structure in ``levels``. Parameters ---------- levels : `list` [`list` [`int]] or None

Right addition.

Right multiplication.

Right division.

Division of objects or an object with a number.

Call estimator with method and args and kwargs. This code is private in scikit-learn 0.24, so it is copied here.

Class directly implements `split` instead of providing this function

Select the column of the positive label in `y_pred` when probabilities are provided. Parameters ---------- y_pred : nd

Holiday constants used by the estimator.

Adds features to one joined dataframe. This will be used to add features to all joined dataframes. Parameters ----------

SilverkiteTemplate does not allow `config.model_components_param` to be a list.

SilverkiteTemplate allows `config.model_components_param` to be a list.

AutoArimaTemplate does not allow `config.model_components_param` to be a list.

LagBasedTemplate does not allow `config.model_components_param` to be a list.

Whether the template accepts a list for `config.model_components_param` (bool)

ProphetTemplate does not allow `config.model_components_param` to be a list.

SilverkiteTemplate does not allow `config.model_template` to be a list.

SimpleSilverkiteTemplate allows config.model_template to be a list.

AutoArimaTemplate does not allow `config.model_template` to be a list.

LagBasedTemplate does not allow `config.model_template` to be a list.

Whether the template accepts a list for `config.model_template` (bool)

ProphetTemplate does not allow `config.model_template` to be a list.

Overwrites ``fit_params`` with those specified by ``fit_params["method"]``. Calls ``fit_func`` with those params. Parameters

Decorator for ``apply_template_for_pipeline_params`` function. Overrides the method in `~greykite.framework.templates.base_template.BaseTempl

Decorator for ``apply_template_for_pipeline_params`` function. Overrides the method in `~greykite.framework.templates.base_template.BaseTempl

Decorator for ``apply_template_for_pipeline_params`` function. Overrides the method in `~greykite.framework.templates.base_template.BaseTempl

Decorator for ``apply_template_for_pipeline_params`` function. By default, this applies ``apply_forecast_config_defaults`` to ``config``.

Decorator for ``apply_template_for_pipeline_params`` function. Overrides the method in `~greykite.framework.templates.base_template.BaseTempl

Explicitly calls the method in `~greykite.framework.templates.base_template.BaseTemplate` to make use of the decorator in this class.

Converts forecast config to pipeline params. Takes input data and optional configuration parameters to customize the model. Returns a

A function which generates a lagged dataframe for a given dataframe with potentially multiple value columns to be lagged. Note `df` an

This is the calculation step with ``param`` and ``data``. In this simple example, this does not depend on ``data.``

Predicts anomalies assuming the parameters: - ``volatility_features`` - ``coverage`` are passed. This will enable op

Constants used by the template class. Includes the model templates and their default values.

Root mean absolute error

Generates data for testing `GreykiteDetector`.

Generates data for testing `GreykiteDetector`.

Generates daily data with regressors for tests. Returns ------- df : pd.DataFrame with columns of type: datetime, number, number,

A sample holiday configuration.

Generates dataset for test cases :return: pd.DataFrame with columns of type: datetime, number, number, boolean, object, category

Generates test dataframe for outlier detection

Generates test dataframe for null imputation

Generates iris dataset for test cases :return:

Generates test dataframe for outlier detection

Generates data for testing.

Sample data for regression.

Generate data for tests

Training data with weights

Default holidays by country params

Training data in design matrix form

The logic of outlier detection, after `fit` is done. This method uses the fit information to decide which points are outliers and what

The logic of outlier detection, after `fit` is done. This method uses the fit information to decide which points are outliers and what

8 months of daily data