Machine learning in trading: theory, models, practice and algo-trading - page 3451

You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
After that, it would be hard to switch to a C-like language.
Thanks for the clarification, a human is still more useful than a machine when it comes to learning!
There is a book "Python for Complex Problems", you can download it. It's well written about nampai and pandas.
There is a book "Python for Complex Problems", you can download it. It has good information about nampai and pandas.
Yes, the book can be useful for understanding the nuances, I have read a bit, thanks.
I personally lack a handy help like in MQL5, but in Russian!
Funny dialogue
Shows a good understanding of context from someone as illiterate on the subject as me - amazing next to it.
I came up with a beautiful algo on MO. It is when 2 or more models exchange errors with each other, each trying to minimise their own. The goal is to minimise the total error.
Such a ping-pong of errors. That's basically what it was going for :)
The first results will outperform all other models, but not everything is fully understood yet.Who can tell me ?
How does python get data from MT5 ?
1) It writes to a file and then python reads it.
2) or is there some kind of direct data transfer?
If the second, how long will it take to load into python say 20 instruments with all timeframes from m1 to d1.
2) Or is there some kind of direct data transfer?
If the second, how long will it take to load into python, say 20 instruments with all timeframes from m1 to d1?
1. The idea is to transfer without files.
2. Yes.
Depends on the history size and hardware.
1- The idea is to transfer without files.
2. Yes.
Depends on the size of the story and the hardware.
I understand correctly about python:
If this is the case, where is it described?
I understand correctly about the python:
If this is the case, where is it described?
Advisor is unnecessary. All queries are from python, including trade queries.
Here, you can read the documentation on the language.
1- The idea is to transfer without files.
2. Yes.
Depends on the size of the story and the hardware.
For example, one week for 20 instruments, all TFs.
How much +-? Half a second, a minute?
Well, one week, for example, on 20 instruments, all TFs.
How much +-? Half a second, a minute?
in no time, if the quotes are loaded in the terminal.