Learn R Programming
⚠️There's a newer version (1.0) of this package.Take me there.

prophet (version 0.6.1)

Automatic Forecasting Procedure

Description

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.

Copy Link

Version

Install

install.packages('prophet')

Monthly Downloads

12,649

Version

0.6.1

License

MIT + file LICENSE

Issues

414

Pull Requests

14

Stars

18,283

Forks

4,511

Maintainer

Sean Taylor

Last Published

April 29th, 2020

Functions in prophet (0.6.1)

add_group_component

Adds a component with given name that contains all of the components in group.
add_seasonality

Add a seasonal component with specified period, number of Fourier components, and prior scale.
make_seasonality_features

Data frame with seasonality features.
plot_forecast_component

Plot a particular component of the forecast.
logistic_growth_init

Initialize logistic growth.
make_holidays_df

Make dataframe of holidays for given years and countries
plot_seasonality

Plot a custom seasonal component.
construct_holiday_dataframe

Construct a dataframe of holiday dates.
predictive_samples

Sample from the posterior predictive distribution.
get_holiday_names

Return all possible holiday names of given country
prophet

Prophet forecaster.
linear_growth_init

Initialize linear growth.
generated_holidays

holidays table
plot.prophet

Plot the prophet forecast.
add_changepoints_to_plot

Get layers to overlay significant changepoints on prophet forecast plot.
mse

Mean squared error
add_country_holidays

Add in built-in holidays for the specified country.
cross_validation

Cross-validation for time series.
plot_cross_validation_metric

Plot a performance metric vs. forecast horizon from cross validation. Cross validation produces a collection of out-of-sample model predictions that can be compared to actual values, at a range of different horizons (distance from the cutoff). This computes a specified performance metric for each prediction, and aggregated over a rolling window with horizon.
predict.prophet

Predict using the prophet model.
initialize_scales_fn

Initialize model scales.
mape

Mean absolute percent error
fit.prophet

Fit the prophet model.
piecewise_logistic

Evaluate the piecewise logistic function.
prophet_plot_components

Plot the components of a prophet forecast. Prints a ggplot2 with whichever are available of: trend, holidays, weekly seasonality, yearly seasonality, and additive and multiplicative extra regressors.
coverage

Coverage
piecewise_linear

Evaluate the piecewise linear function.
performance_metrics

Compute performance metrics from cross-validation results.
mae

Mean absolute error
sample_posterior_predictive

Prophet posterior predictive samples.
predict_trend

Predict trend using the prophet model.
setup_dataframe

Prepare dataframe for fitting or predicting.
predict_seasonal_components

Predict seasonality components, holidays, and added regressors.
prophet_copy

Copy Prophet object.
fourier_series

Provides Fourier series components with the specified frequency and order.
predict_uncertainty

Prophet uncertainty intervals for yhat and trend
make_future_dataframe

Make dataframe with future dates for forecasting.
regressor_column_matrix

Dataframe indicating which columns of the feature matrix correspond to which seasonality/regressor components.
make_all_seasonality_features

Dataframe with seasonality features. Includes seasonality features, holiday features, and added regressors.
parse_seasonality_args

Get number of Fourier components for built-in seasonalities.
set_changepoints

Set changepoints
seasonality_plot_df

Prepare dataframe for plotting seasonal components.
set_auto_seasonalities

Set seasonalities that were left on auto.
time_diff

Time difference between datetimes
sample_predictive_trend

Simulate the trend using the extrapolated generative model.
rolling_mean_by_h

Compute a rolling mean of x, after first aggregating by h
rmse

Root mean squared error
set_date

Convert date vector
make_holiday_features

Construct a matrix of holiday features.
plot_weekly

Plot the weekly component of the forecast.
validate_inputs

Validates the inputs to Prophet.
sample_model

Simulate observations from the extrapolated generative model.
validate_column_name

Validates the name of a seasonality, holiday, or regressor.
plot_yearly

Plot the yearly component of the forecast.
df_for_plotting

Merge history and forecast for plotting.
add_regressor

Add an additional regressor to be used for fitting and predicting.
dyplot.prophet

Plot the prophet forecast.
generate_cutoffs

Generate cutoff dates