mdl_time_forecast

Used for low-level forecasting of modeltime, parnsip and workflow models.
These functions are not intended for user use.

internal

The time series forecasting framework for use with the 'tidymodels' ecosystem.
Models include ARIMA, Exponential Smoothing, and additional time series models
from the 'forecast' and 'prophet' packages. Refer to "Forecasting Principles & Practice, Second edition"
(<https://otexts.com/fpp2/>).
Refer to "Prophet: forecasting at scale"
(<https://research.facebook.com/blog/2017/02/prophet-forecasting-at-scale/>.).

Matt Dancho

modeltime

The Tidymodels Extension for Time Series Modeling

Business Science 

mdl_time_forecast function

<dl><dt>object</dt>
<dd>A Modeltime Table</dd>
<dt>calibration_data</dt>
<dd>Data that has been calibrated from a testing set</dd>
<dt>new_data</dt>
<dd>A <code>tibble</code> containing future information to forecast.
If <code>NULL</code>, forecasts the calibration data.</dd>
<dt>h</dt>
<dd>The forecast horizon (can be used instead of <code>new_data</code> for
time series with no exogenous regressors).
Extends the calibration data <code>h</code> periods into the future.</dd>
<dt>actual_data</dt>
<dd>Reference data that is combined with the output tibble and given a <code>.key = "actual"</code></dd>
<dt>bind_actual</dt>
<dd>Logical. Whether or not to skip rowwise binding of `actual_data``</dd>
<dt>keep_data</dt>
<dd>Whether or not to keep the <code>new_data</code> and <code>actual_data</code> as extra columns in the results.
This can be useful if there is an important feature in the <code>new_data</code> and <code>actual_data</code> needed
when forecasting.
Default: <code>FALSE</code>.</dd>
<dt>arrange_index</dt>
<dd>Whether or not to sort the index in rowwise chronological order (oldest to newest) or to
keep the original order of the data.
Default: <code>FALSE</code>.</dd>
<dt>...</dt>
<dd>Not currently used</dd></dl>

Arguments

Modeltime Forecast Helpers — mdl_time_forecast

<dl>

<dt>object</dt>
<dd>A Modeltime Table</dd>


<dt>calibration_data</dt>
<dd>Data that has been calibrated from a testing set</dd>


<dt>new_data</dt>
<dd>A <code>tibble</code> containing future information to forecast.
If <code>NULL</code>, forecasts the calibration data.</dd>


<dt>h</dt>
<dd>The forecast horizon (can be used instead of <code>new_data</code> for
time series with no exogenous regressors).
Extends the calibration data <code>h</code> periods into the future.</dd>


<dt>actual_data</dt>
<dd>Reference data that is combined with the output tibble and given a <code>.key = "actual"</code></dd>


<dt>bind_actual</dt>
<dd>Logical. Whether or not to skip rowwise binding of `actual_data``</dd>


<dt>keep_data</dt>
<dd>Whether or not to keep the <code>new_data</code> and <code>actual_data</code> as extra columns in the results.
This can be useful if there is an important feature in the <code>new_data</code> and <code>actual_data</code> needed
when forecasting.
Default: <code>FALSE</code>.</dd>


<dt>arrange_index</dt>
<dd>Whether or not to sort the index in rowwise chronological order (oldest to newest) or to
keep the original order of the data.
Default: <code>FALSE</code>.</dd>


<dt>...</dt>
<dd>Not currently used</dd>

</dl>

mdl_time_forecast: Modeltime Forecast Helpers

Description

Usage

Value

Arguments