**161 commits**| Last commit

**≈ 3 months ago**

A Julia package to deconvolve simple moving averages of time series.

2

contributors

Get started

UnrollingAverages is a Julia package aimed at deconvolving simple moving averages of time series to get the original ones back.

UnrollingAverages currently assumes that the moving average is a simple moving average. Further relaxations and extensions may come in the future, see Future Developments section.

Press `]`

in the Julia REPL and then

```
pkg> add UnrollingAverages
```

The package exports a single function called `unroll`

: it returns a `Vector`

whose elements are the possible original time series.

```
unroll(moving_average::Vector{Float64}, window::Int64; initial_conditions::U = nothing, assert_natural::Bool = false) where { U <: Union{ Tuple{Vararg{Union{Int64,Float64}}},Nothing} }
```

`moving_average`

: the time series representing the moving average to unroll ;`window`

: the width of the moving average ;`initial_conditions`

: the initial values of the original time series to be recovered. It may be a`Tuple`

of`window-1`

positive integer values, or`nothing`

if initial conditions are unknown. Currently it is not possible to specify values in the middle of the time series, this may be a feature to be added in the future ;`assert_natural`

default boolean argument. If true, the pipeline will try to recover a time series of natural numbers only. More then one acceptable time series (where "acceptable" means that it reproduces`moving_average`

) may be found and all will be returned.

A few remarks:

- If
`isnothing(initial_conditions)`

:`if assert_natural`

, then an internal`unroll_iterative`

method is called, which tries to exactly recover the whole time series, initial conditions included. Enter`?UnrollingAverages.unroll_iterative`

in a Julia to read further details;`if !assert_natural`

, then an internal`unroll_linear_approximation`

method is called. See this StackExchange post. NB: this is an approximated method, it will generally not return the exact original time series;

- If
`typeof(initial_conditions) <: Ntuple{window-1, <:Union{Int64,Float64}}`

, then an internal`unroll_recursive`

method is called, which exactly recovers the time series. Mathematical details about this function are reported in the documentation, and you may read more by entering`?UnrollingAverages.unroll_recursive`

.

- Modify
`initial_conditions`

argument of`unroll`

so that it accepts known values throughout the series ; - Implement reversing methods for other types of moving averages .

If you wish to change or add some functionality, please file an issue. Some suggestions may be found in the Future Developments section.

If you use this package in your work, please cite this repository using the metadata in `CITATION.bib`

.

Keywords

Data Analysis

Data Science

Deconvolution

Julia Language

Julia Package

Reverse Engineering

Statistics

Time Series

Time Series Analysis

Programming language

License

- MIT

</>Source code

Claudio Moroni

Pietro Monticone

COVID-19 integrated surveillance data provided by the Italian National Institute of Health and processed via UnrollingAverages.jl to deconvolve the weekly simple moving averages.

Updated 3 months ago

Running