An open API service indexing awesome lists of open source software.

https://github.com/akai01/ngboostforecast

Probabilistic Time Series Forecasting
https://github.com/akai01/ngboostforecast

forecasting machine-learning ngboost ngboost-forecast probabilistic-forecasts python r sklearn time-series

Last synced: 3 months ago
JSON representation

Probabilistic Time Series Forecasting

Awesome Lists containing this project

README

          

---
output: github_document
---

```{r, include = FALSE}
knitr::opts_chunk$set(
collapse = TRUE,
comment = "#>",
fig.path = "man/figures/README-",
out.width = "100%"
)

```

# ngboostForecast

The goal of ngboostForecast is to provide a tools for probabilistic forecasting by using Python's ngboost for R users.

## Installation

You can install the released version of ngboostForecast from [CRAN](https://CRAN.R-project.org) with:

``` r
install.packages("ngboostForecast")
```

And the development version from [GitHub](https://github.com/) with:

``` r
# install.packages("devtools")
devtools::install_github("Akai01/ngboostForecast")
```
## Example

This is a basic example which shows you how to solve a common problem:

```{r example}

library(ngboostForecast)

train = window(seatbelts, end = c(1983,12))

test = window(seatbelts, start = c(1984,1))

# without external variables with Ridge regression

model <- NGBforecast$new(Dist = Dist("LogNormal"),
Base = sklearner(module = "linear_model",
class = "Ridge"),
Score = Scores("LogScore"),
natural_gradient = TRUE,
n_estimators = 200,
learning_rate = 0.1,
minibatch_frac = 1,
col_sample = 1,
verbose = TRUE,
verbose_eval = 5,
tol = 1e-5)

model$fit(y = train[,2],
seasonal = TRUE,
max_lag = 12,
early_stopping_rounds = 10L)

fc <- model$forecast(h = 12, level = c(99,95,90, 80, 70, 60),
data_frame = FALSE)

autoplot(fc) + autolayer(test[,2])

```

# Tuning

## Set the parameters:

``` {r example2, echo = TRUE}

library(ngboostForecast)

dists <- list(Dist("Normal"))

base_learners <- list(sklearner(module = "tree", class = "DecisionTreeRegressor",
max_depth = 1),
sklearner(module = "tree", class = "DecisionTreeRegressor",
max_depth = 2),
sklearner(module = "tree", class = "DecisionTreeRegressor",
max_depth = 3),
sklearner(module = "tree", class = "DecisionTreeRegressor",
max_depth = 4),
sklearner(module = "tree", class = "DecisionTreeRegressor",
max_depth = 5),
sklearner(module = "tree", class = "DecisionTreeRegressor",
max_depth = 6),
sklearner(module = "tree", class = "DecisionTreeRegressor",
max_depth = 7))

scores <- list(Scores("LogScore"))

model <- NGBforecastCV$new(Dist = dists,
Base = base_learners,
Score = scores,
natural_gradient = TRUE,
n_estimators = list(10, 100),
learning_rate = list(0.1, 0.2),
minibatch_frac = list(0.1, 1),
col_sample = list(0.3),
verbose = FALSE,
verbose_eval = 100,
tol = 1e-5)

```
## Tune the model:
```{r example3, echo=TRUE, warning = FALSE, message = FALSE}

params <- model$tune(y = AirPassengers,
seasonal = TRUE,
max_lag = 12,
xreg = NULL,
early_stopping_rounds = NULL,
n_splits = 4L)

```
## Best parameters:
```{r eample4}

params
```