|
PureBytes Links
Trading Reference Links
|
Hi all,
I have been spending some time trying to use ADK to integrate an
Aussie Dollar NN into Amibroker.
The code i have written so far is below.
Everything up to the AmiVar function works fine, however i am having
difficulty reading in the input values for the function.
Can anyne help here? cheers..J
include "stdafx.h"
#include "Plugin.h"
#include <stdio.h>
#include <math.h>
#include <stdlib.h>
////////////////////////////////////
// Network Calculation functions
////////////////////////////////////
double input_hidden_weights[4][6]=
{
{-9.41493586282049e-001, -8.27678659948781e-001,
5.33357172027228e+000, -8.81433105395710e+000, -
5.62990822935282e+000, 3.33188108288555e+000 },
{-7.21310882837554e-001, 2.66136821466042e+000, -
1.30616133275411e+000, 2.22745742211765e+000, 1.48166162052262e+000, -
5.02573921885824e-001 },
{-1.19975838533084e+000, -1.02273814209505e+000,
6.26326878536705e+000, -8.73585783044836e+000, -
3.61252492344994e+000, 5.07994479550933e+000 },
{-1.36613217835628e-001, 4.64156076188643e+000, -
1.75930666708638e+000, 3.81695078259574e+000, 1.60987267382251e+000, -
2.16079221557054e+000 }
};
double hidden_bias[4]={ 2.80708720868898e+000, -
2.38093875656134e+000, 9.60983501333011e-001, -
3.43286402530261e+000 };
double hidden_output_wts[1][4]=
{
{1.17956836551340e+000, 3.04046922300849e+000, -
1.33236764769559e+000, -2.40961518644655e+000 }
};
double output_bias[1]={ 1.05931141496123e+000 };
double max_input[6]={ 8.38014000000000e+001, 1.91800000000000e-001,
3.13800000000000e-001, 3.80900000000000e-001, 2.07700000000000e-001,
4.27100000000000e-001 };
double min_input[6]={ 1.71557000000000e+001, -2.14400000000000e-001, -
4.08600000000000e-001, -2.51700000000000e-001, -2.17500000000000e-
001, -1.99800000000000e-001 };
double max_target[1]={ 1.62800000000000e-001 };
double min_target[1]={ -1.88900000000000e-001 };
double input[6];
double hidden[4];
double output[1];
void FindMax(double* vec, double* max, long* maxIndex,int len)
{
long i;
*max = vec[0];
*maxIndex = 0;
for(i=1; i<len; i++)
{
if(vec[i]>*max)
{
*max = vec[i];
*maxIndex = i;
}
}
}
void FindMin(double* vec, double* min, long* minIndex,int len)
{
long i;
*min = vec[0];
*minIndex = 0;
for(i=1; i<len; i++)
{
if(vec[i]<*min)
{
*min = vec[i];
*minIndex = i;
}
}
}
void ScaleInputs(double* input, double min, double max, int size)
{
double delta;
long i;
for(i=0; i<size; i++)
{
delta = (max-min)/(max_input[i]-min_input[i]);
input[i] = min - delta*min_input[i]+ delta*input[i];
}
}
void UnscaleTargets(double* output, double min, double max, int size)
{
double delta;
long i;
for(i=0; i<size; i++)
{
delta = (max-min)/(max_target[i]-min_target[i]);
output[i] = (output[i] - min + delta*min_target[i])/delta;
}
}
double logistic(double x)
{
if(x > 100.0) x = 1.0;
else if (x < -100.0) x = 0.0;
else x = 1.0/(1.0+exp(-x));
return x;
}
void ComputeFeedForwardSignals(double* MAT_INOUT,double* V_IN,double*
V_OUT, double* V_BIAS,int size1,int size2,int layer)
{
int row,col;
for(row=0;row < size2; row++)
{
V_OUT[row]=0.0;
for(col=0;col<size1;col++)V_OUT[row]+=(*(MAT_INOUT+(row*size1)
+col)*V_IN[col]);
V_OUT[row]+=V_BIAS[row];
if(layer==0) V_OUT[row] = tanh(V_OUT[row]);
if(layer==1) V_OUT[row] = logistic(V_OUT[row]);
}
}
void RunNeuralNet_Regression ()
{
ComputeFeedForwardSignals((double*)
input_hidden_weights,input,hidden,hidden_bias,6, 4,0);
ComputeFeedForwardSignals((double*)
hidden_output_wts,hidden,output,output_bias,4, 1,1);
}
// Helper function
int SkipEmptyValues( int nSize, float *Src, float *Dst )
{
int i;
for( i = 0; i < nSize && IS_EMPTY( Src[ i ] ); i++ )
{
Dst[ i ] = EMPTY_VAL;
}
return i;
}
// Neural Network Function
AmiVar VNeuralNetAD( int NumArgs, AmiVar *ArgsTable )
{
int i;
int nSize = gSite.GetArraySize();
for (i=250; i<nSize; ++i)
{
input[0] = 45; // dummy value - i need to read in the
values of the 14 bar RSI here
input[1] = -0.023; // dummy value - i need to read in
the values of the 50 bar ROC of the Dollar Index here
input[2] = 0.014; // dummy value - i need to read in the
values of the 50 bar ROC of the S&P here
input[3] = 0.0076; // dummy value - i need to read in
the values of the 50 bar RSI of Feeder Cattle here
input[4] = -0.054; // dummay value - i need to read in
the values of the 50 bar LOG return of the Swiss Franc here
input[5] = 0.0005; // dummy value - i need to read in
the values of the 50 bar log return of Gold here
ScaleInputs(input,0,1,6);
RunNeuralNet_Regression();
UnscaleTargets(output,0,1,1);
AmiVar result = gSite.GetVariable("Close"); //the result
needs to be set to the network output.. i've just used the close so
that i can compile and test back in AB
return result;
}
}
/////////////////////////////////////////////
// Function table
/////////////////////////////////////////////
FunctionTag gFunctionTable[] = {
"NeuralNetAD", { VNeuralNetAD, 0, 0, 0, 0, NULL }
};
int gFunctionTableSize = sizeof( gFunctionTable )/sizeof(
FunctionTag );
Please note that this group is for discussion between users only.
To get support from AmiBroker please send an e-mail directly to
SUPPORT {at} amibroker.com
For NEW RELEASE ANNOUNCEMENTS and other news always check DEVLOG:
http://www.amibroker.com/devlog/
For other support material please check also:
http://www.amibroker.com/support.html
Yahoo! Groups Links
<*> To visit your group on the web, go to:
http://groups.yahoo.com/group/amibroker/
<*> Your email settings:
Individual Email | Traditional
<*> To change settings online go to:
http://groups.yahoo.com/group/amibroker/join
(Yahoo! ID required)
<*> To change settings via email:
mailto:amibroker-digest@xxxxxxxxxxxxxxx
mailto:amibroker-fullfeatured@xxxxxxxxxxxxxxx
<*> To unsubscribe from this group, send an email to:
amibroker-unsubscribe@xxxxxxxxxxxxxxx
<*> Your use of Yahoo! Groups is subject to:
http://docs.yahoo.com/info/terms/
|