Discussion of article "Connecting NeuroSolutions Neuronets" - page 3

[Academic]

I can't say that I'm slow, because I haven't checked it - but when installing the latest NeuroSolutions 6.05 ( downloaded for free but demo http://www.neurosolutions.com/products/ns/ ) I have no way this neurosolutions doesn't want to see GPU and CUDA is missing. Does anyone have positive experience with neurosolutions working with CUDA ? The use of neurosolutions GPU ( CUDA ) can be seen in the About menu.

And without that it seems to be meaningless to use this product.

I searched Google, neurosolutions.com site too - they have no support forum. It doesn't make any sense. I tried both 64 and 32 bit versions.

[Mr.FreeMan]

Why so few deals? I did everything as in the article(((

and what are the messages at the beginning of the training?

[ds2]

Mr.FreeMan:

Why so few trades? I did everything as in the article(((.

and what are the messages at the beginning of the training?

There are probably few trades because of incorrect training. The reason can be guessed from the message about error: NS took "0.00529" as a column name and in general claims that all cells in it are the same. There must be something wrong with this data file. Or, perhaps, regional settings on the computer (comma is used or dot to separate fractional part) may influence.

[Mr.FreeMan]

here are my regional settings, I put a space instead of a comma and saved it.

but when I generate the ns, I get errors like this:

and then this message again:

[ds2]

Mr.FreeMan:

here are my regional settings, I put a space instead of a comma and saved it.

Put a full stop there, not a space. It is the full stop that is used in the data file.

[Mr.FreeMan]

thanks a lot, everything worked :)

[Phil_Forex]

What a great article ! Congratulations

 a few questions :

- Why are you using NeuroSolution t 5.0 instead of the new 6.4 ?

I think that tne new Custom Solution wizard can generate DLL that can re-compute data and i suppose find new pattern !

 and it support now :

New Project Shells for Visual C++ 2008, VB.NET 2008, Visual C++ 2010 and VB.NET 2010

New Visual Studio 2008 and 2010 Support New Project Shells for Excel 2007, Access 2007, Excel 2010 and Access 2010.

 - Why did you choose function Approximation instead of prediction ? 

regards

Philippe 

[NFTrader]

Thanks for the great article.

[Вангелис]

When I try to compile a script for uploading data to a file

#property script_show_inputs
//+------------------------------------------------------------------+
input string    Export_FileName = "NeuroSolutions\\data.csv"; // Export file (in the "MQL5/Files" folder)
input int       Export_Bars     = 260; // Number of rows of data to be exported
//+------------------------------------------------------------------+
void OnStart() 
  {
  
   // Create a file
   int file = FileOpen(Export_FileName, FILE_WRITE|FILE_CSV|FILE_ANSI, ',');
   
   if (file != INVALID_HANDLE)
     {
      // Write the data header
      
      string row="";
      for (int i=0; i<=5; i++)
        {
         if (StringLen(row)) row += ",";
         row += "Open"+i+",High"+i+",Low"+i+",Close"+i;
        }
      FileWrite(file, row);
      
      // Copy all the necessary data from the history
      
      MqlRates rates[], rate;
      int count = Export_Bars + 5;
      if (CopyRates(Symbol(), Period(), 1, count, rates) < count)
        {
         Print("Error! Insufficient history size to export required data.");
         return;
        }
      ArraySetAsSeries(rates, true);
      
      // Let's write the data 
      
      for (int bar=0; bar<Export_Bars; bar++)
        {
         row="";
         double zlevel=0;
         for (int i=0; i<=5; i++)
           {
            if (StringLen(row)) row += ",";
            rate = rates[bar+i];
            if (i==0) zlevel = rate.open; // price reference level
            row += NormalizeDouble(rate.open -zlevel, Digits()) + ","
                 + NormalizeDouble(rate.high -zlevel, Digits()) + ","
                 + NormalizeDouble(rate.low  -zlevel, Digits()) + ","
                 + NormalizeDouble(rate.close-zlevel, Digits());
           }
         FileWrite(file, row);
        }

      FileClose(file);
      Print("Data export completed successfully.");
     }
   else Print("Error! Failed to create a file to export data. ", GetLastError());
  }
//+------------------------------------------------------------------+

I get the following: implicit conversion from 'number' to 'string' WeekPattern-Export.mq5 20 24
implicit conversion from 'number' to 'string' WeekPattern-Export.mq5 20 34 implicit conversion from 'number' to 'string' WeekPattern-Export.mq5 20 43 and a few more of the same with reference to lines 20, 46, 47, 48, 49.

Can you tell me what the reason is - I haven't changed the source code from the article?

.

[Mykola Demko]

Wangelys:
When I try to compile a script for uploading data to a file

I get the following: implicit conversion from 'number' to 'string' WeekPattern-Export.mq5 20 24
implicit conversion from 'number' to 'string' WeekPattern-Export.mq5 20 34 implicit conversion from 'number' to 'string' WeekPattern-Export.mq5 20 43 and a few more of the same with reference to lines 20, 46, 47, 48, 49.

Can you tell me what the reason is - did you change the source code from the article?

.

Change it

NormalizeDouble

to

DoubleToString