Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/business-science/modeltime.gluonts
GluonTS Deep Learning with Modeltime
https://github.com/business-science/modeltime.gluonts
deep-learning forecasting gluonts gluonts-deep-learning modeltime r-package tidymodels time-series
Last synced: 2 months ago
JSON representation
GluonTS Deep Learning with Modeltime
- Host: GitHub
- URL: https://github.com/business-science/modeltime.gluonts
- Owner: business-science
- License: other
- Created: 2020-11-15T12:09:32.000Z (about 4 years ago)
- Default Branch: master
- Last Pushed: 2024-01-04T22:31:45.000Z (about 1 year ago)
- Last Synced: 2024-01-29T16:27:07.682Z (12 months ago)
- Topics: deep-learning, forecasting, gluonts, gluonts-deep-learning, modeltime, r-package, tidymodels, time-series
- Language: R
- Homepage: https://business-science.github.io/modeltime.gluonts/
- Size: 13.6 MB
- Stars: 37
- Watchers: 6
- Forks: 10
- Open Issues: 32
-
Metadata Files:
- Readme: README.Rmd
- License: LICENSE
Awesome Lists containing this project
README
---
output: github_document
---
```{r, include = FALSE}
knitr::opts_chunk$set(
collapse = TRUE,
message = F,
warning = F,
comment = "#>",
fig.path = "man/figures/README-",
out.width = "90%",
fig.align = "center"
)
```
# modeltime.gluonts 
[](https://cran.r-project.org/package=modeltime)
[](https://codecov.io/gh/business-science/modeltime.gluonts?branch=master)
[](https://github.com/business-science/modeltime.gluonts/actions)
> GluonTS Deep Learning in R.
## GluonTS Deep Learning in R
Modeltime GluonTS integrates the __Python GluonTS Deep Learning Library__, making it easy to develop forecasts using Deep Learning for those that are comfortable with the [Modeltime Forecasting Workflow](https://business-science.github.io/modeltime/).
```{r, echo=F}
knitr::include_graphics("man/figures/m4_hourly_forecast.jpg")
```
## Installation Requirements
__Important: This package is being maintained on GitHub (not CRAN). Please install the GitHub version, which is updated with the latest features:__
```
# Install GitHub Version
remotes::install_github("business-science/modeltime.gluonts")
# Install Python Dependencies
modeltime.gluonts::install_gluonts()
```
For more detailed installation instructions and troubleshooting guidance, visit our [Installation Guide](https://business-science.github.io/modeltime.gluonts/articles/managing-envs.html).
## Make Your First DeepAR Model
Make your first `deep_ar()` model, which connects to the GluonTS `DeepAREstimator()`. For a more detailed walkthough, visit our [Getting Started Guide](https://business-science.github.io/modeltime.gluonts/articles/getting-started.html).
```{r example, eval = F}
library(modeltime.gluonts)
library(tidymodels)
library(tidyverse)
# Fit a GluonTS DeepAR Model
model_fit_deepar <- deep_ar(
id = "id",
freq = "M",
prediction_length = 24,
lookback_length = 48,
epochs = 5
) %>%
set_engine("gluonts_deepar") %>%
fit(value ~ ., training(m750_splits))
# Forecast with 95% Confidence Interval
modeltime_table(
model_fit_deepar
) %>%
modeltime_calibrate(new_data = testing(m750_splits)) %>%
modeltime_forecast(
new_data = testing(m750_splits),
actual_data = m750,
conf_interval = 0.95
) %>%
plot_modeltime_forecast(.interactive = FALSE)
```
```{r, echo = F}
knitr::include_graphics("man/figures/deepar_example_1.png")
```
## Meet the modeltime ecosystem
> Learn a growing ecosystem of forecasting packages
```{r, echo=F, out.width='100%', fig.align='center', fig.cap="The modeltime ecosystem is growing"}
knitr::include_graphics("man/figures/modeltime_ecosystem.jpg")
```
Modeltime is part of a __growing ecosystem__ of Modeltime forecasting packages.
- [Modeltime (Machine Learning)](https://business-science.github.io/modeltime/)
- [Modeltime H2O (AutoML)](https://business-science.github.io/modeltime.h2o/)
- [Modeltime GluonTS (Deep Learning)](https://business-science.github.io/modeltime.gluonts/)
- [Modeltime Ensemble (Blending Forecasts)](https://business-science.github.io/modeltime.ensemble/)
- [Modeltime Resample (Backtesting)](https://business-science.github.io/modeltime.resample/)
- [Timetk (Feature Engineering, Data Wrangling, Time Series Visualization)](https://business-science.github.io/timetk/)
## Take the High-Performance Forecasting Course
> Become the forecasting expert for your organization
[_High-Performance Time Series Course_](https://university.business-science.io/p/ds4b-203-r-high-performance-time-series-forecasting/)
### Time Series is Changing
Time series is changing. __Businesses now need 10,000+ time series forecasts every day.__ This is what I call a _High-Performance Time Series Forecasting System (HPTSF)_ - Accurate, Robust, and Scalable Forecasting.
__High-Performance Forecasting Systems will save companies by improving accuracy and scalability.__ Imagine what will happen to your career if you can provide your organization a "High-Performance Time Series Forecasting System" (HPTSF System).
### How to Learn High-Performance Time Series Forecasting
I teach how to build a HPTFS System in my [__High-Performance Time Series Forecasting Course__](https://university.business-science.io/p/ds4b-203-r-high-performance-time-series-forecasting). You will learn:
- __Time Series Machine Learning__ (cutting-edge) with `Modeltime` - 30+ Models (Prophet, ARIMA, XGBoost, Random Forest, & many more)
- __Deep Learning__ with `GluonTS` (Competition Winners)
- __Time Series Preprocessing__, Noise Reduction, & Anomaly Detection
- __Feature engineering__ using lagged variables & external regressors
- __Hyperparameter Tuning__
- __Time series cross-validation__
- __Ensembling__ Multiple Machine Learning & Univariate Modeling Techniques (Competition Winner)
- __Scalable Forecasting__ - Forecast 1000+ time series in parallel
- and more.
Become the Time Series Expert for your organization.