jeffmv / lofea Goto Github PK

so i have a pretty firm belief that a lottery from where i am is affected by universe over 10, even though its a 649 lottery. each number in the draw has a "likely follower from a list of 18 or 21 numbers between 1 and 49" i was able to prove this by building a python script.
and i discovered it was effectively making each of the 6 numbers drawn an embedded 1/49 lottery similiar to youre 1/10 lottery triomagic.

upon testing your software Lofea, i have been able to correctly predict 2/6 number in the past 6 draws by manually reading a classification report generated by lofea. and i believe this because ussually the first 2 numbers of every draw are a number between 1 and 10 or 1 and 20. in order to predict numbers in the higher range i feel i'd need to modify your code. but i'm having trouble understanding your code.

i was wondering if you'd be willing to provide guidance on where in your code i should make edits to ensure it works for a 1/49 lottery.

I don't know if you're still working on magic3?
But it seems like there are some issues with your code, causing it not to run properly.
Could you simplify your process? It only needs two parts:
First, reading data, training the model, and saving the model.
Second, calling the model to make predictions.
Also, historical data only needs to include 3 winning numbers, nothing else.
I'm a beginner in Python, could you provide assistance? Thank you very much.

Some computations use a bad index for indexing current and past draws.
It uses the informations of the current draw (the one to coming at the current day id) to compute measurements for that day id.

What this issue does is that it shifts the correspondance.
Instead of having on day N (when draw results of day N are not out): the computation using data up to N-1.

It does instead the following (wrong way to do): on day N: the computation using data up to N