Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/spsanderson/healthyr.ts
A time-series companion package to healthyR
https://github.com/spsanderson/healthyr.ts
ai arima-forecasting arima-model ets forecasting ggplot2 machine-learning modeling prophet r r-package r-stats rstats time-series time-series-analysis workflows
Last synced: 2 days ago
JSON representation
A time-series companion package to healthyR
- Host: GitHub
- URL: https://github.com/spsanderson/healthyr.ts
- Owner: spsanderson
- License: other
- Created: 2020-12-05T02:49:29.000Z (almost 4 years ago)
- Default Branch: master
- Last Pushed: 2024-09-11T01:28:01.000Z (about 2 months ago)
- Last Synced: 2024-09-11T06:04:06.130Z (about 2 months ago)
- Topics: ai, arima-forecasting, arima-model, ets, forecasting, ggplot2, machine-learning, modeling, prophet, r, r-package, r-stats, rstats, time-series, time-series-analysis, workflows
- Language: R
- Homepage: https://www.spsanderson.com/healthyR.ts/
- Size: 308 MB
- Stars: 18
- Watchers: 6
- Forks: 3
- Open Issues: 4
-
Metadata Files:
- Readme: README.Rmd
- Changelog: NEWS.md
- License: LICENSE
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%",
message = FALSE,
warning = FALSE
)
```
# healthyR.ts 
[](https://cran.r-project.org/package=healthyR.ts)
[](https://lifecycle.r-lib.org/articles/stages.html#experimental)
[](https://makeapullrequest.com/)
The goal of `healthyR.ts` is to provide a consistent verb framework for performing
time series analysis and forecasting on both administrative and clinical hospital
data.
## Installation
You can install the released version of healthyR.ts from [CRAN](https://CRAN.R-project.org) with:
``` r
install.packages("healthyR.ts")
```
And the development version from [GitHub](https://github.com/) with:
``` r
# install.packages("devtools")
devtools::install_github("spsanderson/healthyR.ts")
```
## Example
This is a basic example which shows you how to generate random walk data.
```{r ts_random_walk, message=FALSE, warning=FALSE}
library(healthyR.ts)
library(ggplot2)
df <- ts_random_walk()
head(df)
```
Now that the data has been generated, lets take a look at it.
```{r ts_random_walk_ggplot_layers}
df %>%
ggplot(
mapping = aes(
x = x
, y = cum_y
, color = factor(run)
, group = factor(run)
)
) +
geom_line(alpha = 0.8) +
ts_random_walk_ggplot_layers(df)
```
That is still pretty noisy, so lets see this in a different way. Lets clear this up a bit
to make it easier to see the full range of the possible volatility of the random walks.
```{r message=FALSE, warning=FALSE}
library(dplyr)
library(ggplot2)
df %>%
group_by(x) %>%
summarise(
min_y = min(cum_y),
max_y = max(cum_y)
) %>%
ggplot(
aes(x = x)
) +
geom_line(aes(y = max_y), color = "steelblue") +
geom_line(aes(y = min_y), color = "firebrick") +
geom_ribbon(aes(ymin = min_y, ymax = max_y), alpha = 0.2) +
ts_random_walk_ggplot_layers(df)
```
This package comes with a wide variety of functions from Data Generators to Statistics
functions. The function `ts_random_walk()` in the above example is a Data Generator.
Let's take a look at a plotting function.
```{r}
data_tbl <- data.frame(
date_col = seq.Date(
from = as.Date("2020-01-01"),
to = as.Date("2022-06-01"),
length.out = 365*2 + 180
),
value = rnorm(365*2+180, mean = 100)
)
ts_calendar_heatmap_plot(
.data = data_tbl
, .date_col = date_col
, .value_col = value
, .interactive = FALSE
)
```
Time Series Clustering via Features:
```{r warning=TRUE, message=FALSE}
data_tbl <- ts_to_tbl(AirPassengers) %>%
mutate(group_id = rep(1:12, 12))
output <- ts_feature_cluster(
.data = data_tbl,
.date_col = date_col,
.value_col = value,
group_id,
.features = c("acf_features","entropy"),
.scale = TRUE,
.prefix = "ts_",
.centers = 3
)
ts_feature_cluster_plot(
.data = output,
.date_col = date_col,
.value_col = value,
.center = 2,
group_id
)
```
Time to/from Event Analysis
```{r warning=FALSE, message=FALSE}
library(dplyr)
df <- ts_to_tbl(AirPassengers) %>% select(-index)
ts_time_event_analysis_tbl(
.data = df,
.horizon = 6,
.date_col = date_col,
.value_col = value,
.direction = "both"
) %>%
ts_event_analysis_plot()
ts_time_event_analysis_tbl(
.data = df,
.horizon = 6,
.date_col = date_col,
.value_col = value,
.direction = "both"
) %>%
ts_event_analysis_plot(.plot_type = "individual")
```
ARIMA Simulators
```{r message=FALSE, warning=FALSE}
output <- ts_arima_simulator()
output$plots$static_plot
```
Automatic Workflows which can be thought of as Boiler Plate Time Series modeling. This
is in it's infancy in this package.
| Auto Workflows | Boilerplate Workflow |
|---------------------------|------------------------|
| ts_auto_arima() | Boilerplate Workflow |
| ts_auto_arima_xgboost() | Boilerplate Workflow |
| ts_auto_croston() | Boilerplate Workflow |
| ts_auto_exp_smoothing() | Boilerplate Workflow |
| ts_auto_glmnet() | Boilerplate Workflow |
| ts_auto_lm() | Boilerplate Workflow |
| ts_auto_mars() | Boilerplate Workflow |
| ts_auto_nnetar() | Boilerplate Workflow |
| ts_auto_prophet_boost() | Boilerplate Workflow |
| ts_auto_prophet_reg() | Boilerplate Workflow |
| ts_auto_smooth_es() | Boilerplate Workflow |
| ts_auto_svm_poly() | Boilerplate Workflow |
| ts_auto_svm_rbf() | Boilerplate Workflow |
| ts_auto_theta() | Boilerplate Workflow |
| ts_auto_xgboost() | Boilerplate Workflow |
This is just a start of what is in this package!