Commit graph

195 commits

Author SHA1 Message Date
Ben Letham
a519043f1b Fix bug in changepoint handling in prophet_copy (#1529) 2020-08-17 16:24:34 -07:00
Ben Letham
fb6552137c Deduplicate history dates for make_future_dataframe 2020-08-17 14:51:06 -07:00
Ryan Nazareth
f16d9df333
Add mdape performance metric to R (#1472)
* add test and initial function for mdape in R

* Add separate rolling_median_func and tests

* Modify rolling median function

* fix syntax in rolling median function

* sort by h

* R/diagnostics.R

* update .rd docs and notebook

* Add mdape to performance metrics params docstring
2020-05-20 12:28:50 -07:00
Ryan Nazareth
16e632a695
Add custom cutoff option to R (#1484)
* Add test for custom cutoff cv

* implement custom cutoff logic in cv function

* add docstring

* add description in notebook and rebuild .Rd docs

* fix bug and add test case for period is NULL

* replace s.POSIXct set_date
2020-05-15 14:32:54 -07:00
Hadley Wickham
cded5c41b0 Fix failure with dplyr 1.0.0
I'm not sure why a data frame ends up with names and a tibble does not, but it doesn't seem like an important enough problem to investigate in detail, and this is a simple fix.
2020-04-28 17:51:36 -05:00
Mikhail Popov
25e2b88765 {rstantools}-based compilation
+ cleans up Stan model compilation by switching over to the rstantools-based workflow (see https://mc-stan.org/rstantools/articles/minimal-rstan-package.html for more info)
+ minor documentation change: {devtools} -> {remotes}, which is better for end-users
+ adds RStudio project file which makes it easier for community to get started with contributing to the package
2020-04-28 16:06:17 -04:00
Mitchell O'Hara-Wild
578b78a8f3
Use system.file() to obtain package installation path (#1435) 2020-04-23 13:06:36 -07:00
Sean Taylor
3a4539f199 New ignores 2020-03-02 13:20:12 -08:00
Sean Taylor
6bbac0c47b Store compiled model in platform specific location 2020-03-02 13:20:12 -08:00
Sean Taylor
192b9160a7 Dep for building the vignette + ignore libs + rebuild docs 2020-03-02 13:20:12 -08:00
Sean Taylor
83e2479699 Replace deprecated functions 2020-03-02 13:20:12 -08:00
Ben Letham
46e5611983 R defer model compiling to first fit, to remove compiling from onLoad per CRAN 2020-02-19 21:30:08 -08:00
Ben Letham
bb242ea180 R documentation updates 2020-02-09 19:31:44 -08:00
Ben Letham
9413c1141e version bump 2020-02-09 19:16:05 -08:00
Ben Letham
64d54e7748 Fixing some holiday parsing for R csv file 2020-02-04 15:23:11 -08:00
Ben Letham
f640308395 Update holidays csv for R, and fix bad utf-8 parsing 2020-02-04 15:12:28 -08:00
Ben Letham
398d220743 Merge branch 'master' of https://github.com/facebookincubator/prophet 2020-02-04 14:34:05 -08:00
Ben Letham
b372feb31f avoid warning when using tibble (#1128) 2020-02-04 14:33:39 -08:00
Adriano Fantini
187bf06bf7
pass ... from dyplot.prophet to dygraph::dygraph, addresses #1158 (#1177)
* Pass ... from dyplot.prophet to dygraph to be able to set additional parameters

* Add documentation for ... in dyplot.prophet

Co-authored-by: Ben Letham <bletham@gmail.com>
2020-02-04 13:39:17 -08:00
Ben Letham
9320ed1fb5 Add test for MCMC with 0 changepoints (R) 2020-02-04 13:32:26 -08:00
Ben Letham
be25372090 improvements in docstrings and testing for disabling uncertainty 2020-02-04 13:22:08 -08:00
Ben Letham
8d0f23f8be Add unit tests for disabling uncertainty estimation in R 2020-02-04 13:05:28 -08:00
Ben Letham
6e51130f28 Use fit kwargs in cross validation (#1040) 2020-02-03 17:02:23 -08:00
Ben Letham
4fcecdb3df Fix bugs that were introduced into R cross validation 2020-02-03 16:18:46 -08:00
ben-schwen
bbadf65e3b added test case for valid_metrics 2020-01-27 13:53:11 -08:00
ben-schwen
5b58ad13cb fix output of valid metrics in performance_metrics 2020-01-27 13:53:11 -08:00
Ben Letham
83f66dadfd Typo fix 2019-11-06 15:34:14 -08:00
Maxim Grishin
a3ae4715bb Make Python version consistent with R 2019-10-22 17:28:27 -07:00
bl
c7a150312a Bugfix for R uncertainty sample handling 2019-10-18 17:06:58 -07:00
Mitchell
f4d997e0ac Fix usage of uncertainty.samples 2019-10-16 16:48:49 -07:00
Ryan Nazareth
a2a0df904e Disabling plotting uncertainties if m.samples is False or 0 2019-10-07 14:17:54 -07:00
Ryan Nazareth
36f3ddc436 Correct syntax issues 2019-10-07 14:17:54 -07:00
Ryan Nazareth
c95eb0dcd9 Disabling calculation of uncertainties if uncertainty.samples is not True 2019-10-07 14:17:54 -07:00
Ryan Nazareth
eb797eefaa Adapt model cv with 0 uncertainty samples and fix performance metrics 2019-10-07 14:17:54 -07:00
Jireh Tan
e8ddded4fe [BUG] Ensure regressor/seasonality names are valid; fixes #996
Ensures that `add_regressor` and `add_seasonality` are valid column names
to R, to ensure that the generated columns are then used downstream to fit
the model.

Why not put it in `validate_column_names`? Because `validate_column_names` is
also used to validate if holiday names (which can be scalar values in columns) are
valid. We want to allow `c('seans-bday', 'Xmas')` as a valid holiday input, so we
cannot then put it there.

Tested these changes by using devtools::testthat().

Resolves: #996
2019-06-25 09:39:14 -07:00
Jireh Tan
a554873a38 [BUG/TST] Add validation to prevent fourier.order <= 0; addresses #980
In reverse order of importance, this change addresses:
  - #980, by adding validation to ensure that `fourier.order` > 0
  - changes all the tests that `expect_error` using the argument
    `fourier_order`, as the argument is named `fourier.order`, so
    the intent of the test is to validate the holiday names rather
    than to check the use of the correct argument name

Resolves: #980
2019-06-21 15:27:31 -07:00
Ben Letham
7ff33137eb Change to MIT license 2019-05-21 11:40:04 -07:00
Sean J. Taylor
39e356ddbe Readying for 0.5 release 2019-05-13 23:00:12 -07:00
Ben Letham
f09ad61c26 R documentation updates 2019-05-13 15:47:28 -07:00
Ben Letham
28cd55241f Verify that cap > floor (#807) 2019-05-13 13:11:07 -07:00
Ben Letham
269133c133 Change cross validation performance metrics to first aggregate over horizon before computing rolling average (#839, #863) 2019-05-08 10:47:26 -07:00
Ben Letham
e9c017ba01 Default to Newton optimizer if less than 100 datapoints (#842, #870, #888) 2019-05-07 11:47:36 -07:00
Ben Letham
16b0166518 Bump dplyr requirement to 0.7.7 (#781) 2019-05-06 16:44:48 -07:00
Ben Letham
ec7689f03e R fallback to Newton if non-zero return code from optimization, to match existing Py behavior (#654) 2019-05-06 09:49:29 -07:00
Ben Letham
c8f2e8f847 Warn in cross validation if initial period is less than seasonality (#557), and fix bug that can produce error if period > initial 2019-05-03 08:40:20 -07:00
Ben Letham
35d470cbff Meaningful error message if predict is called before fit (for #462) 2019-05-02 14:53:57 -07:00
Ben Letham
921b604022 Update R documentation 2019-03-22 11:08:09 -07:00
Ben Letham
c5db6f8619 Update R tests with condition.name 2019-03-22 10:52:53 -07:00
Olof Höjvall
0092638abe Added conditional seasonality for R (#894) 2019-03-22 10:43:52 -07:00
Sean J. Taylor
703c0731f6 Supress warning messages while building model 2018-12-20 17:04:03 -08:00