get current premiums from api

could dump to csv
could connect up directly?

to make their pm linkable

Make README beautiful for github view with better markdown use.

Add instructions for Azure VM related issues like getting the model working on azure vm as well as adding other users to the vm who can sudo.

I've been trying to ensure that someone who is listed in the premium API as premium is excluded from the weekly suggestions, but putting their AV email as 'email' and their slack email as 'alias_email' does not appear to be working

file is /var/lib/dokku/data/storage/email_aliases.csv with headers "email,alias_email,,,,,"

Currently we have a manual process to assign mentors to reach out to premium upgrade prospects. We use the datamining data post from the bot and spreadsheet from history in order to work out which mentors to assign to which prospects:

post to #datamining data

==> a,b,c,d,e,f,g,h

=====================

history

• previously contacted
  b,c,f,g,h (which mentor reached out)

mentors

• X, Y, Z

assignment process

• posting to private mentors channel

simple improvement - split the predictions

previously predicted - 2 months?:

• b,c,f,g,h
  new
• a,d,e

even better

previously predicted - 2 months?:

• b, contacted by X in - follow up by @y
• c, ...
• f, ...
• g, ...
• h, ...

new

• a, assigned to @x https://www.agileventures.org/user/a
• d,
• e,

good to flag binghamton students - can usually tell from emails

quick fix for production

Right now, we need to document and support in the repo how we are installing a crontab task to automatically run every sunday morning and ping slack with the results.

using dokku and friends

perhaps the current model should be put into its own module or file at least?

We seem to be getting newer premium members in the predictions after we dockerized. Possibly related to the change in the data to be in a folder data and not updating the update_premimum_members script.

The recently introduced forecast bot showed up in the predictions for some reason, even though we are trying to filter out bots.

might be nice

some mentors (e.g. @joaopapereira ) have suggested that along with the suggestions that it might be useful to have information about when a user joined slack for the purpose of informing the way in which the mentor reaches out to the member

there are a lot of them who are rather active at particular times of year, and they seem uniformly disinterested in AgileVentures, beyond what's required for their course - could be helpful to just exclude anyone whose address ends in binghamton.edu

Use the newly available api on WSO for premium signup data to update the data weekly.

*Distinct from updating the legacy data

https://github.com/AgileVentures/AutomatedPremiumModel/blob/master/basic_functionality_so_far.R#L103

this line isnt' needed and the variable probs, which isn't defined elsewhere, makes it trip over itself

...

currently, the functions surrounding this seem to work reasonably well but we need to test this spikey behavior, as well as maybe improve it.

For instance, determine the previous saturday and go back three weeks from there. This is partially implemented in a function finding previous saturday already

Ping #data-mining with the results of the model but no emails.

Ping @tansaku with results of the model including emails

this might be better long term, if for instance, rather than passing in a token at each turn, we just pass it during initialization of "object"

we can probably consolidate the test_token and the api_token into just one bot token with requisite permissions.

...