This document provides a very brief introduction to the Prophet API. For a detailed guide on using Prophet, please visit the main site at https://facebook.github.io/prophet/.

Prophet uses the normal model fitting API. We provide a prophet function that performs fitting and returns a model object. You can then call predict and plot on this model object.

First we read in the data and create the outcome variable.

library(readr)
df <- read_csv('../tests/testthat/data.csv')
#> Parsed with column specification:
#> cols(
#>   ds = col_date(format = ""),
#>   y = col_double()
#> )

We call the prophet function to fit the model. The first argument is the historical dataframe. Additional arguments control how Prophet fits the data.

m <- prophet(df)
#> Disabling daily seasonality. Run prophet with daily.seasonality=TRUE to override this.

We need to construct a dataframe for prediction. The make_future_dataframe function takes the model object and a number of periods to forecast:

future <- make_future_dataframe(m, periods = 365)
head(future)
#>           ds
#> 1 2012-05-18
#> 2 2012-05-21
#> 3 2012-05-22
#> 4 2012-05-23
#> 5 2012-05-24
#> 6 2012-05-25

As with most modeling procedures in R, we use the generic predict function to get our forecast:

forecast <- predict(m, future)
head(forecast)
#>           ds    trend additive_terms additive_terms_lower additive_terms_upper
#> 1 2012-05-18 40.50193      -4.547887            -4.547887            -4.547887
#> 2 2012-05-21 40.01455      -5.467254            -5.467254            -5.467254
#> 3 2012-05-22 39.85209      -5.609274            -5.609274            -5.609274
#> 4 2012-05-23 39.68963      -5.724989            -5.724989            -5.724989
#> 5 2012-05-24 39.52717      -5.806214            -5.806214            -5.806214
#> 6 2012-05-25 39.36471      -6.155667            -6.155667            -6.155667
#>      weekly weekly_lower weekly_upper    yearly yearly_lower yearly_upper
#> 1 0.5681288    0.5681288    0.5681288 -5.116016    -5.116016    -5.116016
#> 2 0.3000873    0.3000873    0.3000873 -5.767341    -5.767341    -5.767341
#> 3 0.3905757    0.3905757    0.3905757 -5.999850    -5.999850    -5.999850
#> 4 0.5129521    0.5129521    0.5129521 -6.237941    -6.237941    -6.237941
#> 5 0.6736987    0.6736987    0.6736987 -6.479913    -6.479913    -6.479913
#> 6 0.5681288    0.5681288    0.5681288 -6.723796    -6.723796    -6.723796
#>   multiplicative_terms multiplicative_terms_lower multiplicative_terms_upper
#> 1                    0                          0                          0
#> 2                    0                          0                          0
#> 3                    0                          0                          0
#> 4                    0                          0                          0
#> 5                    0                          0                          0
#> 6                    0                          0                          0
#>   yhat_lower yhat_upper trend_lower trend_upper     yhat
#> 1   32.36049   39.19215    40.50193    40.50193 35.95404
#> 2   31.12032   38.10306    40.01455    40.01455 34.54730
#> 3   30.70133   37.79524    39.85209    39.85209 34.24282
#> 4   30.54989   37.46622    39.68963    39.68963 33.96464
#> 5   30.13145   36.89207    39.52717    39.52717 33.72096
#> 6   29.46769   36.58290    39.36471    39.36471 33.20905

You can use the generic plot function to plot the forecast, but you must also pass the model in to be plotted:

plot(m, forecast)

You can plot the components of the forecast using the prophet_plot_components function:

prophet_plot_components(m, forecast)