Automatic Forecasting Procedure
Validates the name of a seasonality, holiday, or regressor.
Validates the inputs to Prophet.
Get layers to overlay significant changepoints on prophet forecast plo...
Add in built-in holidays for the specified country.
Adds a component with given name that contains all of the components i...
Add an additional regressor to be used for fitting and predicting.
Add a seasonal component with specified period, number of Fourier comp...
Construct a dataframe of holiday dates.
Coverage
Cross-validation for time series.
Merge history and forecast for plotting.
Plot the prophet forecast.
Fit the prophet model.
Initialize flat growth.
Evaluate the flat trend function.
Provides Fourier series components with the specified frequency and or...
Generate cutoff dates
Return all possible holiday names of given country
Initialize model scales.
Initialize constant growth.
Initialize logistic growth.
Mean absolute error
Dataframe with seasonality features. Includes seasonality features, ho...
Make dataframe with future dates for forecasting.
Construct a matrix of holiday features.
Make dataframe of holidays for given years and countries
Data frame with seasonality features.
Mean absolute percent error
Median absolute percent error
Mean squared error
Get number of Fourier components for built-in seasonalities.
Compute performance metrics from cross-validation results.
Evaluate the piecewise linear function.
Evaluate the piecewise logistic function.
Plot the prophet forecast.
Plot a performance metric vs. forecast horizon from cross validation. ...
Plot a particular component of the forecast.
Plot a custom seasonal component.
Plot the weekly component of the forecast.
Plot the yearly component of the forecast.
Predict using the prophet model.
Predict seasonality components, holidays, and added regressors.
Predict trend using the prophet model.
Prophet uncertainty intervals for yhat and trend
Sample from the posterior predictive distribution.
Prophet forecaster.
Copy Prophet object.
Plot the components of a prophet forecast. Prints a ggplot2 with which...
Summarise the coefficients of the extra regressors used in the model. ...
Dataframe indicating which columns of the feature matrix correspond to...
Root mean squared error
Compute a rolling mean of x, after first aggregating by h
Compute a rolling median of x, after first aggregating by h
Simulate observations from the extrapolated generative model.
Prophet posterior predictive samples.
Simulate the trend using the extrapolated generative model.
Prepare dataframe for plotting seasonal components.
Set seasonalities that were left on auto.
Set changepoints
Convert date vector
Prepare dataframe for fitting or predicting.
Forecast for a single cutoff. Used in cross_validation function when e...
Symmetric mean absolute percentage error based on Chen and Yang (2004)...
Time difference between datetimes
Implements a procedure for forecasting time series data based on an additive model where non-linear trends are fit with yearly, weekly, and daily seasonality, plus holiday effects. It works best with time series that have strong seasonal effects and several seasons of historical data. Prophet is robust to missing data and shifts in the trend, and typically handles outliers well.