[BlindMath] Exploratory Data Analysis And Sonification

[Robin Williams]

Hi,

As Jonathan says, if you have some basic familiarity with R you might want to check out our sonify package. The package allows you to plot 'tick marks' on the x-axis, which are played when that point is passed in the soundscape. You can also overlay white noise if you want to know when the value of the curve on the y axis is contained within a certain interval. For other sonification options there is the SAS Graphics Accelerator, and I believe there is at least one implementation in Python, although I'm unsure on the details. I recall a thread on the program-l list some time ago, so it could be worth searching the archives and asking there.
Something I do often is to fit a Loess curve to the data and have the sonify package play the curve. I've included my wrapper function below by way of an example. 
One  thing you miss with our current sonification package is the amount of spread in the points throughout the time series. To get a handle on this you could break the time series in to bins, and calculate the standard deviation of the points in each bin.
You also might  miss changes in the density of data throughout the time series. You could get a handle on this with a histogram of the x values. I believe Jonathan's BrailleR package has some exciting developments in the works, which sadly I'm yet to check out.

Here's my, very simple, Loess wrapper function. Note that if you try to fit it on too much data it will take for ever, so you might want to randomly cut down the dataset.
audioLoess = function(x,y,degree=2L,span=0.5,...) {
    require(sonify)
    mod = loess(y~x,span=span,degree=degree)
    sonify(sort(x),mod$fitted[order(x)],...)
}

HTH,
Robin

-----Original Message-----
From: BlindMath <blindmath-bounces at nfbnet.org> On Behalf Of Peter Rayner via BlindMath
Sent: Wednesday, March 22, 2023 12:14 AM
To: Blind Math list for those interested in mathematics <blindmath at nfbnet.org>
Cc: peter.julien.rayner at gmail.com
Subject: [BlindMath] Exploratory Data Analysis And Sonification

A colleague and I wrote a sonification function for python but it does have two requirements:
1) it's only been tested on Linux
2) it makes heavy use of a touchscreen or similar.
Hence it's probably not useful for you but get in touch if it might be.
regards
Peter
Bhavya shah via BlindMath writes:
>Dear all,
>
>I am tasked with some exploratory data analysis for some large 
>time-seried data sets. My sense is that graphing a variable in terms of 
>value of the variable on the y axis and time on the x axis, i.e.
>data visualization, would be a good first step to get a feel for 
>general trends before conducting more specific analyses. While I cannot 
>see such a graph, I know that audio graphing technologies generally 
>exist. What tools or libraries could I use to sonify plots that I 
>generate in the process of analysing a .csv file in Python?
>Other strategies for exploratory data analysis are also welcome.
>
>I would appreciate any thoughts and inputs!
>
>Kind Regards,
>Bhavya Shah
>B.S. in Mathematical and Computational Science | Stanford '24
>LinkedIn: https://www.linkedin.com/in/bhavyashah125/
>
>_______________________________________________
>BlindMath mailing list
>BlindMath at nfbnet.org
>http://nfbnet.org/mailman/listinfo/blindmath_nfbnet.org
>To unsubscribe, change your list options or get your account info for BlindMath:
>http://nfbnet.org/mailman/options/blindmath_nfbnet.org/peter.julien.ray
>ner%40gmail.com BlindMath Gems can be found at 
><http://www.blindscience.org/blindmath-gems-home>

--
Peter Rayner (he/him)
the Inversion Lab
mobile +61 402 752 379
zoom id 4431343191, join at  <https://unimelb.zoom.us/j/4431343191?pwd=a1E5Z3JEOTRVQUJsaVdRbVUvR1QyZz09>
mail-to: peter.julien.rayner at gmail.com
google scholar: <https://scholar.google.com.au/citations?user=H3up71wAAAAJ&hl=en>
I acknowledge the Traditional Custodians of the land on which I work, the Wurundjeri people of the Kulin nation, and pay my respect to their Elders, past and present I am sending this email when convenient for me, please only respond when convenient for you

_______________________________________________
BlindMath mailing list
BlindMath at nfbnet.org
http://nfbnet.org/mailman/listinfo/blindmath_nfbnet.org
To unsubscribe, change your list options or get your account info for BlindMath:
http://nfbnet.org/mailman/options/blindmath_nfbnet.org/robin.williams%40atass-sports.co.uk
BlindMath Gems can be found at <http://www.blindscience.org/blindmath-gems-home>