I have this dataset
dat1197=structure(list(Dates = structure(c(18993, 19024, 19052, 19083,
19113, 19144, 19174, 19205, 19236, 19266, 19297, 19327, 19358,
19389, 19417, 19448, 19478, 19509, 19539, 19570, 19601, 19631,
19662, 19692, 19723), class = "Date"), total = c(290107L, 198827L,
369809L, 328653L, 230351L, 319991L, 361509L, 263837L, 423810L,
267680L, 195494L, 236771L, 202171L, 286674L, 313943L, 303044L,
307096L, 170928L, 144136L, 189956L, 232079L, 201174L, 199433L,
150333L, 195069L), conv_count = c(31L, 9414L, 10662L, 10817L,
10544L, 10824L, 11828L, 13365L, 11795L, 12731L, 12961L, 11215L,
16180L, 20123L, 16419L, 16190L, 17597L, 16966L, 18805L, 16072L,
18493L, 17952L, 24781L, 25582L, 712L), unique_id_publishers = c(4270L,
4838L, 4227L, 4628L, 4300L, 5178L, 4297L, 8440L, 7616L, 10328L,
7959L, 6239L, 7429L, 7748L, 7189L, 6837L, 7393L, 6773L, 7028L,
7395L, 7473L, 10730L, 8814L, 64489L, 5464L), median_seconds = c(7881.49604743083,
7881.49604743083, 488.966666666667, 488.966666666667, 531.916666666667,
488.966666666667, 531.916666666667, 595, 574.75, 604.25, 595,
721.25, 595, 1000.75, 1479.5, 1196.5, 2514.5, 2324, 2642.5, 828,
4821, 4344.5, 6468, 3941, 8822), total_forecasted = c(252179.383228222,
211378.341678112, 298854.813540318, 297876.900653167, 298769.06537375,
297419.968269761, 293248.366585249, 282633.709438049, 290279.426901374,
283780.066745602, 284744.759870922, 292012.326293479, 271309.781396652,
249031.822264103, 259416.064075342, 264210.373105608, 241258.234178068,
246833.896200638, 234745.99587691, 268889.359224122, 208522.098966603,
214275.525057851, 159854.631183384, 144778.271030721, 236571.818861993
)), row.names = c(NA, -25L), class = "data.frame")
I want perform time series analysis using predictors. My dependent variable is total.
conv_count, unique_id_publishers, median_seconds are predictors that should explain the total variable.
I try do so . Here my code. This code iterates through the parameters to find those about which the model has the maximum R-squared
library(forecast)
library(zoo)
# Convert the dataset to data.table
dat1197 <- as.data.table(dat1197)
# Convert the Dates column to Date format
dat1197$Dates <- as.Date(paste(dat1197$Dates, "-01", sep=""))
# Create a time series without a Dates column
# Dividing the sample into training and test
train_data <- dat1197[Dates < as.Date("2023-11-01")]
test_data <- dat1197[Dates >= as.Date("2023-11-01") & Dates <= as.Date("2024-01-01")]
ts_data <- zoo(train_data[, c("total")])
# Specifying predictors
xreg <- train_data[, c("conv_count", "unique_id_publishers", "median_seconds")]
# Convert predictors to a numeric matrix
xreg_matrix <- as.matrix(xreg)
best_model <- NULL
best_r_squared <- 0
# Loop for selecting ETS model parameters with maximum R-squared
for (error in c("A", "M")) {
for (trend in c("N", "A", "Ad", "M")) {
for (seasonal in c("N", "A", "Ad", "M")) {
model <- ets(ts_data, model = paste0(error, trend, seasonal), xreg = xreg_matrix)
r_squared <- accuracy(model)$R2
if (r_squared > best_r_squared) {
best_model <- model
best_r_squared <- r_squared
}
}
}
}
# Obtaining forecasts for the test period
forecast_data <- forecast(best_model, xreg = as.matrix(test_data[, c("conv_count", "unique_id_publishers", "median_seconds")]), newdata = as.matrix(test_data[, c("conv_count", "unique_id_publishers ", "median_seconds")]), h = nrow(test_data))
and i get error
Error in ets(ts_data, model = paste0(error, trend, seasonal), xreg = xreg_matrix) :
No model able to be fitted
What did i wrong and how correct perform time series using my predictors? Any help from you is valuable.
ets() does not have an xreg argument. See the help files. The smooth::es() function does allow for covariates.ets() does that internally if you don't specify the model argument.