DESCRIPTION 1.0 KB

123456789101112131415161718192021222324252627282930313233343536373839
  1. Package: prophet
  2. Title: Automatic Forecasting Procedure
  3. Version: 0.3.0.1
  4. Date: 2018-06-13
  5. Authors@R: c(
  6. person("Sean", "Taylor", email = "sjt@fb.com", role = c("cre", "aut")),
  7. person("Ben", "Letham", email = "bletham@fb.com", role = "aut")
  8. )
  9. Description: Implements a procedure for forecasting time series data based on
  10. an additive model where non-linear trends are fit with yearly, weekly, and
  11. daily seasonality, plus holiday effects. It works best with time series
  12. that have strong seasonal effects and several seasons of historical data.
  13. Prophet is robust to missing data and shifts in the trend, and typically
  14. handles outliers well.
  15. Depends:
  16. R (>= 3.2.3),
  17. Rcpp (>= 0.12.0)
  18. Imports:
  19. dplyr (>= 0.5.0),
  20. dygraphs (>= 1.1.1.4),
  21. extraDistr,
  22. ggplot2,
  23. grid,
  24. rstan (>= 2.14.0),
  25. scales,
  26. stats,
  27. tidyr (>= 0.6.1),
  28. xts
  29. Suggests:
  30. knitr,
  31. testthat,
  32. readr
  33. License: BSD_3_clause + file LICENSE
  34. LazyData: true
  35. RoxygenNote: 6.1.1
  36. VignetteBuilder: knitr
  37. SystemRequirements: C++11
  38. Encoding: UTF-8