Vidar

Error using certain functions (like RSI from the TTR package) in recursive forecasting

1

``` library(modeltime) library(timetk) library(tidyquant) library(tidyverse) library(tidymodels) horizon % mutate( rsi = TTR::RSI(outcome) # using e.g. mean() from base R works but not SMA() from TTR package ) %>% tk_augment_lags(outcome, .lags...

Feature request - Refit model using X most important variables

4

I just saw [this video](https://www.youtube.com/watch?v=ce1VULptNWQ&ab_channel=%D0%A0%D0%B0%D0%B7%D1%80%D0%B0%D0%B1%D0%BE%D1%82%D0%BA%D0%B0) from the Catboost team regarding using variable importance to eliminate noicy variables (those who are not important) and by doing this, reducing the error. Got...

Wrong prediction interval when going from log to original scale

6

``` library(modeltime) library(tidymodels) library(timetk) library(tidyverse) # Full = Training + Forecast Datasets full_data_tbl % select(id, Date, Weekly_Sales) %>% # Apply Group-wise Time Series Manipulations group_by(id) %>% future_frame( .date_var = Date,...

Feature request: Add data.table backend for timetk

6

Hi Matt. When using functions like `tk_augment_lag()`, `tk_augment_fourier()` and `tk_augment_slidify()`, it can be slow if you have thousands of time series. An example is a data set with 6,000 time...

Feature request. Option to select tune_race_anova in ensemble_model_spec

1

Is it be possible to add tune_race_anova() to ensemble_model_spec() ? Would speed tuning up a lot.

modeltime_fit_resamples does not work with ensemble

2

This code will run but the ensemble is not present when I calculate accuracy: ``` # Create average ensemble and add to the modeltime table ml_mtbl % combine_modeltime_tables( ml_mtbl %>%...

Is there a reason for this? I cannot use `storage_load_rds()` on a VM with 256 GB of RAM but I can download the file and read it in using `read_rds()`....

Add TimeGPT to modeltime

5

Would it be possible to add TimeGPT to modeltime? It's easy to call the API using httr package in R. There also is a Python SDK: https://docs.nixtla.io/reference/timegpt_timegpt_post. The fable team...

Using target encoding in the recipe (step_lencode_mixed or step_lencode_glm) will return an error when calling `modeltime_forecast()`, ``` # 1.0.0 Setup --------------------------------------------------------------------------------- library(modeltime) library(tidymodels) library(tidyverse) library(embed) library(timetk) data_tbl % select(id, Dept,...

Not possible to use ensemble

1

I was going to use an ensemble as a part of my time series cross validation. This did not work. Here is my code. ``` # Create average ensemble and...