mirror of
https://github.com/saymrwulf/prophet.git
synced 2026-11-17 08:40:56 +00:00
Fix R warning with extra regressor; disallow constant extra regressors.
This commit is contained in:
parent
d1bf4a1d06
commit
feb7be397b
6 changed files with 21 additions and 8 deletions
|
|
@ -395,9 +395,13 @@ initialize_scales_fn <- function(m, initialize_scales, df) {
|
||||||
m$start <- min(df$ds)
|
m$start <- min(df$ds)
|
||||||
m$t.scale <- time_diff(max(df$ds), m$start, "secs")
|
m$t.scale <- time_diff(max(df$ds), m$start, "secs")
|
||||||
for (name in names(m$extra_regressors)) {
|
for (name in names(m$extra_regressors)) {
|
||||||
|
n.vals <- length(unique(df[[name]]))
|
||||||
|
if (n.vals < 2) {
|
||||||
|
stop('Regressor ', name, ' is constant.')
|
||||||
|
}
|
||||||
standardize <- m$extra_regressors[[name]]$standardize
|
standardize <- m$extra_regressors[[name]]$standardize
|
||||||
if (standardize == 'auto') {
|
if (standardize == 'auto') {
|
||||||
if (all(sort(unique(df[[name]])) == c(0, 1))) {
|
if (n.vals == 2 && all(sort(unique(df[[name]])) == c(0, 1))) {
|
||||||
# Don't standardize binary variables
|
# Don't standardize binary variables
|
||||||
standardize <- FALSE
|
standardize <- FALSE
|
||||||
} else {
|
} else {
|
||||||
|
|
@ -407,9 +411,6 @@ initialize_scales_fn <- function(m, initialize_scales, df) {
|
||||||
if (standardize) {
|
if (standardize) {
|
||||||
mu <- mean(df[[name]])
|
mu <- mean(df[[name]])
|
||||||
std <- stats::sd(df[[name]])
|
std <- stats::sd(df[[name]])
|
||||||
if (std == 0) {
|
|
||||||
std <- mu
|
|
||||||
}
|
|
||||||
m$extra_regressors[[name]]$mu <- mu
|
m$extra_regressors[[name]]$mu <- mu
|
||||||
m$extra_regressors[[name]]$std <- std
|
m$extra_regressors[[name]]$std <- std
|
||||||
}
|
}
|
||||||
|
|
|
||||||
|
|
@ -511,6 +511,11 @@ test_that("added_regressors", {
|
||||||
expect_equal(fcst$seasonal[1],
|
expect_equal(fcst$seasonal[1],
|
||||||
fcst$seasonalities[1] + fcst$extra_regressors[1])
|
fcst$seasonalities[1] + fcst$extra_regressors[1])
|
||||||
expect_equal(fcst$yhat[1], fcst$trend[1] + fcst$seasonal[1])
|
expect_equal(fcst$yhat[1], fcst$trend[1] + fcst$seasonal[1])
|
||||||
|
# Check fails if constant extra regressor
|
||||||
|
df$constant_feature <- 5
|
||||||
|
m <- prophet()
|
||||||
|
m <- add_regressor(m, 'constant_feature')
|
||||||
|
expect_error(fit.prophet(m, df))
|
||||||
})
|
})
|
||||||
|
|
||||||
test_that("copy", {
|
test_that("copy", {
|
||||||
|
|
|
||||||
|
|
@ -362,6 +362,6 @@ m.plot_components(forecast);
|
||||||

|

|
||||||
|
|
||||||
|
|
||||||
NFL Sundays could also have been handled using the "holidays" interface described above, by creating a list of past and future NFL Sundays. The `add_regressor` function provides a more general interface for defining extra linear regressors, and in particular does not require that the regressor be a binary indicator. Another time series could be used as a regressor, although its future values would have to be known.
|
NFL Sundays could also have been handled using the "holidays" interface described above, by creating a list of past and future NFL Sundays. The `add_regressor` function provides a more general interface for defining extra linear regressors, and in particular does not require that the regressor be a binary indicator. Another time series could be used as a regressor, although its future values would have to be known. The regressor cannot be constant in the training data; fitting will exit with an error if it is.
|
||||||
|
|
||||||
The `add_regressor` function has optional arguments for specifying the prior scale (holiday prior scale is used by default) and whether or not the regressor is standardized - see the docstring with `help(Prophet.add_regressor)` in Python and `?add_regressor` in R.
|
The `add_regressor` function has optional arguments for specifying the prior scale (holiday prior scale is used by default) and whether or not the regressor is standardized - see the docstring with `help(Prophet.add_regressor)` in Python and `?add_regressor` in R.
|
||||||
|
|
|
||||||
|
|
@ -728,7 +728,7 @@
|
||||||
"cell_type": "markdown",
|
"cell_type": "markdown",
|
||||||
"metadata": {},
|
"metadata": {},
|
||||||
"source": [
|
"source": [
|
||||||
"NFL Sundays could also have been handled using the \"holidays\" interface described above, by creating a list of past and future NFL Sundays. The `add_regressor` function provides a more general interface for defining extra linear regressors, and in particular does not require that the regressor be a binary indicator. Another time series could be used as a regressor, although its future values would have to be known.\n",
|
"NFL Sundays could also have been handled using the \"holidays\" interface described above, by creating a list of past and future NFL Sundays. The `add_regressor` function provides a more general interface for defining extra linear regressors, and in particular does not require that the regressor be a binary indicator. Another time series could be used as a regressor, although its future values would have to be known. The regressor cannot be constant in the training data; fitting will exit with an error if it is.\n",
|
||||||
"\n",
|
"\n",
|
||||||
"The `add_regressor` function has optional arguments for specifying the prior scale (holiday prior scale is used by default) and whether or not the regressor is standardized - see the docstring with `help(Prophet.add_regressor)` in Python and `?add_regressor` in R."
|
"The `add_regressor` function has optional arguments for specifying the prior scale (holiday prior scale is used by default) and whether or not the regressor is standardized - see the docstring with `help(Prophet.add_regressor)` in Python and `?add_regressor` in R."
|
||||||
]
|
]
|
||||||
|
|
|
||||||
|
|
@ -278,6 +278,9 @@ class Prophet(object):
|
||||||
self.t_scale = df['ds'].max() - self.start
|
self.t_scale = df['ds'].max() - self.start
|
||||||
for name, props in self.extra_regressors.items():
|
for name, props in self.extra_regressors.items():
|
||||||
standardize = props['standardize']
|
standardize = props['standardize']
|
||||||
|
n_vals = len(df[name].unique())
|
||||||
|
if n_vals < 2:
|
||||||
|
raise ValueError('Regressor {} is constant.'.format(name))
|
||||||
if standardize == 'auto':
|
if standardize == 'auto':
|
||||||
if set(df[name].unique()) == set([1, 0]):
|
if set(df[name].unique()) == set([1, 0]):
|
||||||
# Don't standardize binary variables.
|
# Don't standardize binary variables.
|
||||||
|
|
@ -287,8 +290,6 @@ class Prophet(object):
|
||||||
if standardize:
|
if standardize:
|
||||||
mu = df[name].mean()
|
mu = df[name].mean()
|
||||||
std = df[name].std()
|
std = df[name].std()
|
||||||
if std == 0:
|
|
||||||
std = mu
|
|
||||||
self.extra_regressors[name]['mu'] = mu
|
self.extra_regressors[name]['mu'] = mu
|
||||||
self.extra_regressors[name]['std'] = std
|
self.extra_regressors[name]['std'] = std
|
||||||
|
|
||||||
|
|
|
||||||
|
|
@ -548,6 +548,12 @@ class TestProphet(TestCase):
|
||||||
fcst['yhat'][0],
|
fcst['yhat'][0],
|
||||||
fcst['trend'][0] + fcst['seasonal'][0],
|
fcst['trend'][0] + fcst['seasonal'][0],
|
||||||
)
|
)
|
||||||
|
# Check fails if constant extra regressor
|
||||||
|
df['constant_feature'] = 5
|
||||||
|
m = Prophet()
|
||||||
|
m.add_regressor('constant_feature')
|
||||||
|
with self.assertRaises(ValueError):
|
||||||
|
m.fit(df.copy())
|
||||||
|
|
||||||
def test_copy(self):
|
def test_copy(self):
|
||||||
# These values are created except for its default values
|
# These values are created except for its default values
|
||||||
|
|
|
||||||
Loading…
Reference in a new issue