Machine learning in trading: theory, models, practice and algo-trading - page 2000

[mytarmailS]

Maxim Dmitrievsky:
There are no libraries in python, so I don't understand what you need

google lies ! I knew it, the pindos )))

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

When you run pandas or any other library, you don't need to have 10 open scripts with functions for it in the IDE.

[Evgeniy Chumakov]

.

[mytarmailS]

Evgeniy Chumakov:

Where are X[,3], etc.?

there aren't any, because there's no need for them.

Evgeniy Chumakov :

I don't understand X[,1] == X[,1] meaning?

you have to, it takes a long time to explain.

Evgeniy Chumakov :

You have to go through the last 10 values to make a prediction.

Yes

[[Deleted]]

mytarmailS:

google is lying ! i knew it, pindos ))))

When you run pandas or any other bible, you don't need to have 10 open scripts with functions for it in the IDE, that's what I need

these are packages

create an empty __init__.py file in the folder and enjoy

[Evgeniy Chumakov]

[16,] "X[,8]>-0.03370967745 & X[,9]<=-0.00120967745 & X[,10]>-0.00596774195 & X[,10]<=0.0229032258"

I see, in general if array[x3] > - 0.03370967745 and array[x4] <= -0.00120967745 then [16] etc.

[mytarmailS]

Maxim Dmitrievsky:

these are the packages

create an empty __init__.py file in the folder and enjoy

Ok, I'll try it

[mytarmailS]

Evgeniy Chumakov:

I see, in general if array[x3] > - 0.03370967745 and array[x4] <= -0.00120967745 then [16] etc.

i don't know the mt4 syntax, i'm not sure i understand what you wrote.

[mytarmailS]

mytarmailS:

I don't know mt4 syntax, I'm not sure I understand what you wrote

let's say if your array of values is called "x" and you're predicting the i-th element

then X[,10] is x[i-1] for you

and X[,1] is x[i-10]

and we predict x[i ]

here are the statistics on the rules and their error

      len freq                  err                 
 [1,] "2" "0.258200032315398"   "0"                 
 [2,] "3" "0.168363225076749"   "0"                 
 [3,] "1" "0.0980772338019066"  "0"                 
 [4,] "1" "0.0929067700759412"  "0"                 
 [5,] "3" "0.0575214089513653"  "0"                 
 [6,] "4" "0.0571982549684925"  "0"                 
 [7,] "3" "0.0542898691226369"  "0"                 
 [8,] "2" "0.0525125222168363"  "0"                 
 [9,] "2" "0.0313459363386654"  "0"                 
[10,] "3" "0.0274680885441913"  "0"                 
[11,] "2" "0.025044433672645"   "0"                 
[12,] "3" "0.015026660203587"   "0"                 
[13,] "2" "0.0124414283406043"  "0"                 
[14,] "3" "0.010017773469058"   "0"                 
[15,] "5" "0.0122798513491679"  "0.0131578947368421"
[16,] "4" "0.0103409274519308"  "0.1875"            
[17,] "1" "0.0122798513491679"  "0.236842105263158" 
[18,] "1" "0.00468573275165616" "0.482758620689655" 

in principle you can try to ignore 16, 17, 18 rules

[Evgeniy Chumakov]

mytarmailS:

let's say that if your array with values is called "x" and you are predicting the i-th element

then X[,10] is x[i-1] for you

and X[,1] is x[i-10]

and we predict x[i ]

x[i], x[1], x[2],x[3] is such a sequence.

so X[,10] is most likely x[i+1] , if minus, then into the future .

[mytarmailS]

Evgeniy Chumakov:

x[i], x[1], x[2],x[3] is such a sequence.

so X[,10] is most likely x[i+1] , if minus then to the future.

Ah, then forget what I wrote, in my language i+1 is the future

Just look at this picture.

#19988