Do you mean something like [**this plot**][1]? :

[![diabolical plot][2]][2]  
<sup>(Generated by SEDE: [/query/201360?ShowScore=0&Tag1=excel&Tag2=python&Tag3=NA&Tag4=NA#graph][1])</sup>

Use the data explorer (SEDE) for that.

To do this with the API, is *possible* but not pretty.  
For example, to replicate the above plot you would need to make 111<sup>(Age of SO in months)</sup> API calls for `python` like [**this call**][3], a then make 111 API calls for `excel` with the same time parameters. (Then piece the results all together and plot it.)

Due to [rate limiting][4], those 222 calls would take *at least* 8 seconds.  More tags, or finer time slices, increases the time proportionally. 

Also, you are allowed 10,000 API calls a day, max.  So that means, at most, 90 such runs per day -- including tests and development.


----------
**UPDATE:**

For comparing compound tags, EG [excel]+[python] vs [excel]+[php], this would become even more problematic in the API.

But, I forked the SEDE query into [**something that compares tag set A versus tag set B**][5]:

[![plot 2][6]][6]

Right now it does 1 by 1, 1 by 2, 2 by 1, and 2 by 2 tag combos. But it should be obvious how to extend it for more tags on each side.


  [1]: https://data.stackexchange.com/stackoverflow/query/201360?ShowScore=0&Tag1=excel&Tag2=python&Tag3=NA&Tag4=NA#graph
  [2]: https://i.sstatic.net/kbYp4.png
  [3]: https://api.stackexchange.com/docs/questions#fromdate=2016-08-01&todate=2016-08-08&order=desc&sort=creation&tagged=python&filter=!.UE8F0_CXHtXg77C&site=stackoverflow&run=true
  [4]: https://api.stackexchange.com/docs/throttle
  [5]: https://data.stackexchange.com/stackoverflow/query/767104/tag-set-a-versus-tag-set-b-growth-comparison?ShowScore=1&LeftTag1=excel&LeftTag2=python&RightTag1=excel&RightTag2=php#graph
  [6]: https://i.sstatic.net/3sDJj.png