# Fit sigmoid transformation function to  ConfusionMatrixPlot?

**URL:** <https://community.wolfram.com/t/fit-sigmoid-transformation-function-to-confusionmatrixplot/9713>\
**Category:** Questions\
**Tags:** data-science, graphics-and-visualization, statistics-and-probability, machine-learning\
**Created:** [December 4, 2016, 12:19pm UTC](https://community.wolfram.com/t/fit-sigmoid-transformation-function-to-confusionmatrixplot/9713 "2016-12-04T12:19:38Z")\
**Posts on this page:** 4\
**Page:** 1

<div class="post-metadata">

**Author:** ![ghorbani](https://avatars.discourse-cdn.com/v4/letter/g/6a8cbe/32.png) [@ghorbani](https://community.wolfram.com/u/ghorbani)\
**Post date:** [December 4, 2016, 12:19pm UTC](https://community.wolfram.com/t/fit-sigmoid-transformation-function-to-confusionmatrixplot/9713/1 "2016-12-04T12:19:38Z")

</div>

Hi, everybody! In the enclosed file I would like to fit Sigmoid Transformation Function to “ConfusionMatrixPlot”. Can I do that? Thank you!

---

<div class="post-metadata">

**Author:** ![danl](https://yyz1.discourse-cdn.com/wolfram/user_avatar/community.wolfram.com/danl/32/41267_2.png) [@danl](https://community.wolfram.com/u/danl)\
**Post date:** [December 4, 2016, 8:14pm UTC](https://community.wolfram.com/t/fit-sigmoid-transformation-function-to-confusionmatrixplot/9713/2 "2016-12-04T20:14:18Z")

</div>

In your desired function, what is the domain? It looks like it should be four dimensional, corresponding to vectors in `xym` and `xyt`. You seem to have something one dimensional in mind and I do not know what it corresponds to.

---

<div class="post-metadata">

**Author:** ![ghorbani](https://avatars.discourse-cdn.com/v4/letter/g/6a8cbe/32.png) [@ghorbani](https://community.wolfram.com/u/ghorbani)\
**Post date:** [December 5, 2016, 8:17am UTC](https://community.wolfram.com/t/fit-sigmoid-transformation-function-to-confusionmatrixplot/9713/3 "2016-12-05T08:17:35Z")

</div>

Dear Daniel,  
You right! What is your opinion about any function should be fit to Sam function?  
Another question is that :  
Can we see the output of “SaM = Classify[xym → zm, Method → “SupportVectorMachine”]” in traditional from such as y=f(x)?

Many thanks for your help and attention.

---

<div class="post-metadata">

**Author:** ![danl](https://yyz1.discourse-cdn.com/wolfram/user_avatar/community.wolfram.com/danl/32/41267_2.png) [@danl](https://community.wolfram.com/u/danl)\
**Post date:** [December 5, 2016, 3:29pm UTC](https://community.wolfram.com/t/fit-sigmoid-transformation-function-to-confusionmatrixplot/9713/4 "2016-12-05T15:29:55Z")

</div>

You have cases of repeats in the domain, with different values in the range.

```
In[3]:= xym[[1]] === xym[[11]]

Out[3]= True

In[6]:= zm[[1]] === zm[[11]]

Out[6]= False

```

Pretty much any attempt to treat this as a function is going to raise issues that really should be addressed before going any further. My guess is once this is all cleared up, maybe a sum of sigmoids would make sense. Given the relatively small amount of data this could be an overfit.