# install.packages("remotes")
remotes::install_github("bearloga/maltese")
The included dataset is a tidy time series of pageviews for R's article on English Wikipedia from 2015-10-01 to 2017-01-30.
library(maltese)
head(r_enwiki)
|date | pageviews| |:----------|---------:| |2015-10-01 | 3072| |2015-10-02 | 2575| |2015-10-03 | 1431| |2015-10-04 | 1540| |2015-10-05 | 3041| |2015-10-06 | 3695|
We can use mlts_transform
to convert the data into a machine learning-friendly format with a 7-day lag:
mlts <- mlts_transform(
r_enwiki, date, pageviews,
p = 7, # how many previous points of data to use as features
granularity = "day", # optional, can be automatically detected,
extras = TRUE, extrasAsFactors = TRUE # FALSE by default :D
)
head(mlts)
|dt | y|mlts_extras_monthday |mlts_extras_weekday |mlts_extras_week |mlts_extras_month |mlts_extras_year | mlts_lag_1| mlts_lag_2| mlts_lag_3| mlts_lag_4| mlts_lag_5| mlts_lag_6| mlts_lag_7| |:----------|----:|:--------------------|:-------------------|:----------------|:-----------------|:----------------|----------:|----------:|----------:|----------:|----------:|----------:|----------:| |2015-10-08 | 3278|8 |Thursday |41 |October |2015 | 3385| 3695| 3041| 1540| 1431| 2575| 3072| |2015-10-09 | 2886|9 |Friday |41 |October |2015 | 3278| 3385| 3695| 3041| 1540| 1431| 2575| |2015-10-10 | 1692|10 |Saturday |41 |October |2015 | 2886| 3278| 3385| 3695| 3041| 1540| 1431| |2015-10-11 | 1902|11 |Sunday |41 |October |2015 | 1692| 2886| 3278| 3385| 3695| 3041| 1540| |2015-10-12 | 3030|12 |Monday |41 |October |2015 | 1902| 1692| 2886| 3278| 3385| 3695| 3041| |2015-10-13 | 3245|13 |Tuesday |41 |October |2015 | 3030| 1902| 1692| 2886| 3278| 3385| 3695|
See the vignette for a detailed walkthrough.
Users of maltese may also be interested in timetk (available on CRAN) which provides several utility functions for working with and manipulating time series data into a ML-friendly form.
Please note that this project is released with a Contributor Code of Conduct. By participating in this project you agree to abide by its terms.
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.